Authors: Theo Demessance, Chongke Bi, Sonia Djebali, Guillaume Guerard
Abstract: Nowadays, social networks are becoming a popular way of analyzing tourist behavior, thanks to the digital traces left by travelers during their stays on these networks. The massive amount of data generated; by the propensity of tourists to share comments and photos during their trip; makes it possible to model their journeys and analyze their behavior. Predicting the next movement of tourists plays a key role in tourism marketing to understand demand and improve decision support. In this paper, we propose a method to understand and to learn tourists' movements based on social network data analysis to predict future movements. The method relies on a machine learning grammatical inference algorithm. A major contribution in this paper is to adapt the grammatical inference algorithm to the context of big data. Our method produces a hidden Markov model representing the movements of a group of tourists. The hidden Markov model is flexible and editable with new data. The capital city of France, Paris is selected to demonstrate the efficiency of the proposed methodology.
Authors: Padegal Amit, Omkar Mahesh Kashyap, Namitha Rayasam, Nidhi Shekhar, Surabhi Narayan
Abstract: Quantifying modality contributions in multimodal models remains a challenge, as existing approaches conflate the notion of contribution itself. Prior work relies on accuracy-based approaches, interpreting performance drops after removing a modality as indicative of its influence. However, such outcome-driven metrics fail to distinguish whether a modality is inherently informative or whether its value arises only through interaction with other modalities. This distinction is particularly important in cross-attention architectures, where modalities influence each other's representations. In this work, we propose a framework based on Partial Information Decomposition (PID) that quantifies modality contributions by decomposing predictive information in internal embeddings into unique, redundant, and synergistic components. To enable scalable, inference-only analysis, we develop an algorithm based on the Iterative Proportional Fitting Procedure (IPFP) that computes layer and dataset-level contributions without retraining. This provides a principled, representation-level view of multimodal behavior, offering clearer and more interpretable insights than outcome-based metrics.
Authors: Ruogu Ding, Xin Ning, Ulf Schlichtmann, Weikang Qian
Abstract: Prefix adders are widely used in compute-intensive applications for their high speed. However, designing optimized prefix adders is challenging due to strict design rules and an exponentially large design space. We introduce PrefixGPT, a generative pre-trained Transformer (GPT) that directly generates optimized prefix adders from scratch. Our approach represents an adder's topology as a two-dimensional coordinate sequence and applies a legality mask during generation, ensuring every design is valid by construction. PrefixGPT features a customized decoder-only Transformer architecture. The model is first pre-trained on a corpus of randomly synthesized valid prefix adders to learn design rules and then fine-tuned to navigate the design space for optimized design quality. Compared with existing works, PrefixGPT not only finds a new optimal design with a 7.7% improved area-delay product (ADP) but exhibits superior exploration quality, lowering the average ADP by up to 79.1%. This demonstrates the potential of GPT-style models to first master complex hardware design principles and then apply them for more efficient design optimization.
Authors: Haojin Yang, Rui Hu, Zequn Sun, Rui Zhou, Yujun Cai, Yiwei Wang
Abstract: Diffusion Language Models (DLMs) have shown strong potential for text generation and are becoming a competitive alternative to autoregressive models. The denoising strategy plays an important role in determining the quality of their outputs. Mainstream denoising strategies include Standard Diffusion and BlockDiffusion. Standard Diffusion performs global denoising without restricting the update range, often finalizing incomplete context and causing premature end-of-sequence predictions. BlockDiffusion updates fixed-size blocks in a preset order, but its rigid structure can break apart coherent semantic units and disrupt reasoning. We present WavefrontDiffusion, a dynamic decoding approach that expands a wavefront of active tokens outward from finalized positions. This adaptive process follows the natural flow of semantic structure while keeping computational cost equal to block-based methods. Across four benchmarks in reasoning and code generation, WavefrontDiffusion achieves state-of-the-art performance while producing outputs with higher semantic fidelity, showing the value of adaptive scheduling for more coherent and efficient generation.
Authors: Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Dheeraj Kulshrestha, Rajiv Ramnath
Abstract: Mixture-of-Experts (MoE) architectures are increasingly adopted in large language models (LLMs) for their scalability and efficiency. However, their modular structure introduces a unique vulnerability: adversaries can attempt to compress or repurpose models by pruning experts and cheaply fine-tuning the remainder, effectively bypassing licensing and security constraints. In this paper, we systematically study the prunability of MoE-LLMs under task-specific usage. We first develop an expert attribution framework that identifies the subset of experts most responsible for a given task, then evaluate the performance trade-offs of pruning and re-aligning these experts using active learning-driven fine-tuning. Our findings reveal a critical knowledge loss--recovery trade-off: while certain experts can be isolated to retain task accuracy, significant degradation occurs without targeted re-alignment. Based on this analysis, we propose defense strategies that aim to make MoE models harder to compress and fine-tune without authorization, including entangled expert training and selective fine-tuning protocols that resist unauthorized adaptation. By positioning expert pruning as both a threat vector and a defense target, this work highlights the dual-use nature of MoE modularity and provides the first systematic evaluation framework for secure specialization of MoE-LLMs.
Authors: Ruoxin Zhang, Zhizhao Wen, Chao Wang, Chenchen Tang, Puyang Xu, Yifan Jiang
Abstract: With the rapid evolution of large language models, retrieval enhanced generation technology has been widely used due to its ability to integrate external knowledge to improve output accuracy. However, the performance of the system is highly dependent on the quality of the retrieval module. If the retrieval results have low relevance to user needs or contain noisy information, it will directly lead to distortion of the generated content. In response to the performance bottleneck of existing models in processing tabular features, this paper proposes an XGBoost machine learning regression model based on feature engineering and particle swarm optimization. Correlation analysis shows that answer_quality is positively correlated with doc_delevance by 0.66, indicating that document relevance has a significant positive effect on answer quality, and improving document relevance may enhance answer quality; The strong negative correlations between semantic similarity, redundancy, and diversity were -0.89 and -0.88, respectively, indicating a trade- off between semantic similarity, redundancy, and diversity. In other words, as the former two increased, diversity significantly decreased. The experimental results comparing decision trees, AdaBoost, etc. show that the VMD PSO BiLSTM model is superior in all evaluation indicators, with significantly lower MSE, RMSE, MAE, and MAPE compared to the comparison model. The R2 value is higher, indicating that its prediction accuracy, stability, and data interpretation ability are more outstanding. This achievement provides an effective path for optimizing the retrieval quality and improving the generation effect of RAG system, and has important value in promoting the implementation and application of related technologies.
Authors: Wanzhe Xu, Yutong Dai, Yitao Yang, Martin Loza, Weihang Zhang, Yang Cui, Xin Zeng, Sung Joon Park, Kenta Nakai
Abstract: Accurate multivariate time-series prediction of vital signs and laboratory results is crucial for early intervention and precision medicine in intensive care units (ICUs). However, vital signs are often noisy and exhibit rapid fluctuations, while laboratory tests suffer from missing values, measurement lags, and device-specific bias, making integrative forecasting highly challenging. To address these issues, we propose OmniTFT, a deep learning framework that jointly learns and forecasts high-frequency vital signs and sparsely sampled laboratory results based on the Temporal Fusion Transformer (TFT). Specifically, OmniTFT implements four novel strategies to enhance performance: sliding window equalized sampling to balance physiological states, frequency-aware embedding shrinkage to stabilize rare-class representations, hierarchical variable selection to guide model attention toward informative feature clusters, and influence-aligned attention calibration to enhance robustness during abrupt physiological changes. By reducing the reliance on target-specific architectures and extensive feature engineering, OmniTFT enables unified modeling of multiple heterogeneous clinical targets while preserving cross-institutional generalizability. Across forecasting tasks, OmniTFT achieves substantial performance improvement for both vital signs and laboratory results on the MIMIC-III, MIMIC-IV, and eICU datasets. Its attention patterns are interpretable and consistent with known pathophysiology, underscoring its potential utility for quantitative decision support in clinical care.
Authors: Lei Wang, Zikun Ye, Jinglong Zhao
Abstract: Driven by recent advances in artificial intelligence (AI), a growing body of work demonstrates the potential of using large language models (LLMs) to generate human-like responses in market research and social science applications. Two primary approaches can be applied to improve the performance of LLMs: fine-tuning, which aligns LLM predictions more closely with human responses, and rectification, which corrects biases in LLM outputs. In this paper, we develop a framework that combines fine-tuning and rectification, and optimally allocates limited labeled samples across the two stages. Unlike the conventional objective that minimizes the mean squared prediction errors, we propose to minimize the variance of the prediction errors as the fine-tuning objective, which is optimal for the downstream rectification stage. Building on this insight, we leverage empirical scaling laws to develop a data-driven method for optimally splitting samples between the fine-tuning and rectification stages. Empirical analysis validates our framework, demonstrating improved estimation and inference performance compared to using either fine-tuning or rectification alone.
Authors: Ben Shaw, Adam Rustad, Sofia Pelagalli Maia, Jake S. Rhodes, Kevin R. Moon
Abstract: Recent work has demonstrated the utility of Random Forest (RF) proximities for various supervised machine learning tasks, including outlier detection, missing data imputation, and visualization. However, the utility of the RF proximities depends upon the success of the RF model, which itself is not the ideal model in all contexts. RF proximities have recently been extended to time series by means of the distance-based Proximity Forest (PF) model, among others, affording time series analysis with the benefits of RF proximities. In this work, we introduce the generalized PF model, thereby extending RF proximities to all contexts in which supervised distance-based machine learning can occur. Additionally, we introduce a variant of the PF model for regression tasks. We also introduce the notion of using the generalized PF model as a meta-learning framework, extending supervised imputation capability to any pre-trained classifier. We experimentally demonstrate the unique advantages of the generalized PF model compared with both the RF model and the $k$-nearest neighbors model.
Authors: Guijun Liu, Yuwen Cao, Tomoaki Ohtsuki, Jiguang He, Shahid Mumtaz
Abstract: Deep autoencoder (DAE) frameworks have demonstrated their effectiveness in reducing channel state information (CSI) feedback overhead in massive multiple-input multiple-output (mMIMO) orthogonal frequency division multiplexing (OFDM) systems. However, existing CSI feedback models struggle to adapt to dynamic environments caused by user mobility, requiring retraining when encountering new CSI distributions. Moreover, returning to previously encountered environments often leads to performance degradation due to catastrophic forgetting. Continual learning involves enabling models to incorporate new information while maintaining performance on previously learned tasks. To address these challenges, we propose a generative adversarial network (GAN)-based learning approach for CSI feedback. By using a GAN generator as a memory unit, our method preserves knowledge from past environments and ensures consistently high performance across diverse scenarios without forgetting. Simulation results show that the proposed approach enhances the generalization capability of the DAE framework while maintaining low memory overhead. Furthermore, it can be seamlessly integrated with other advanced CSI feedback models, highlighting its robustness and adaptability.
Authors: Jitendra Parmar, Praveen Singh Thakur
Abstract: Open-world machine learning is an emerging technique in artificial intelligence, where conventional machine learning models often follow closed-world assumptions, which can hinder their ability to retain previously learned knowledge for future tasks. However, automated intelligence systems must learn about novel classes and previously known tasks. The proposed model offers novel learning classes in an open and continuous learning environment. It consists of two different but connected tasks. First, it discovers unknown classes in the data and creates novel classes; next, it learns how to perform class incrementally for each new class. Together, they enable continual learning, allowing the system to expand its understanding of the data and improve over time. The proposed model also outperformed existing approaches in open-world learning. Furthermore, it demonstrated strong performance in continuous learning, achieving a highest average accuracy of 82.54% over four iterations and a minimum accuracy of 65.87%.
Authors: Chris Kuchar
Abstract: RFX (Random Forests X), where X stands for compression or quantization, presents a production-ready implementation of Breiman and Cutler's Random Forest classification methodology in Python. RFX v1.0 provides complete classification: out-of-bag error estimation, overall and local importance measures, proximity matrices with QLORA compression, case-wise analysis, and interactive visualization (rfviz)--all with CPU and GPU acceleration. Regression, unsupervised learning, CLIQUE importance, and RF-GAP proximity are planned for v2.0. This work introduces four solutions addressing the proximity matrix memory bottleneck limiting Random Forest analysis to ~60,000 samples: (1) QLORA (Quantized Low-Rank Adaptation) compression for GPU proximity matrices, reducing memory from 80GB to 6.4MB for 100k samples (12,500x compression with INT8 quantization) while maintaining 99% geometric structure preservation, (2) CPU TriBlock proximity--combining upper-triangle storage with block-sparse thresholding--achieving 2.7x memory reduction with lossless quality, (3) SM-aware GPU batch sizing achieving 95% GPU utilization, and (4) GPU-accelerated 3D MDS visualization computing embeddings directly from low-rank factors using power iteration. Validation across four implementation modes (GPU/CPU x case-wise/non-case-wise) demonstrates correct implementation. GPU achieves 1.4x speedup over CPU for overall importance with 500+ trees. Proximity computation scales from 1,000 to 200,000+ samples (requiring GPU QLORA), with CPU TriBlock filling the gap for medium-scale datasets (10K-50K samples). RFX v1.0 eliminates the proximity memory bottleneck, enabling proximity-based Random Forest analysis on datasets orders of magnitude larger than previously feasible. Open-source production-ready classification following Breiman and Cutler's original methodology.
Authors: Shivansh Chhawri, Rahul Mahadik, Suparna Rooj
Abstract: Large Language Models (LLMs) require substantial computational resources, making model compression essential for efficient deployment in constrained environments. Among the dominant compression techniques: knowledge distillation, structured pruning, and low-bit quantization, their individual effects are well studied, but their interactions and optimal sequencing remain unclear. This work systematically examines how these techniques perform both independently and in combination when applied to the Qwen2.5 3B model. We evaluate multiple compression pipelines, including single, and proposed three-technique sequences, using perplexity, G-Eval, clarity, prompt alignment, and compression ratio as metrics. Our experiments show that quantization provides the greatest standalone compression, while pruning introduces moderate quality degradation. Critically, the ordering of techniques significantly affects the final model quality: the sequence Pruning, Knowledge Distillation, Quantization (P-KD-Q) yields the best balance, achieving a 3.68x compression ratio while preserving strong instruction-following and language understanding capabilities. Conversely, pipelines applying quantization early suffer severe performance degradation due to irreversible information loss that impairs subsequent training. Overall, this study offers practical insight into designing effective, ordering-aware compression pipelines for deploying LLMs in resource-limited settings.
Authors: Yang Liu, Xiaolong Zhong, Ling Jiang
Abstract: Large language models deliver strong reasoning and tool-use skills, yet their computational demands make them impractical for edge or cost-sensitive deployments. We present \textbf{Xmodel-2.5}, a 1.3-billion-parameter small language model designed as a \emph{drop-in agent core}. Training with maximal-update parameterization ($\mu$P) allows hyper-parameters tuned on a 20M-parameter proxy to transfer directly to the full model, even under the parameter-tied \emph{tie-word-embedding} architecture. A 1.4T-token Warmup--Stable--Decay curriculum is used, and we further show that \textbf{switching from AdamW to Muon during the decay phase} improves the 13-task reasoning average by 4.58\,\% while keeping every other hyper-parameter fixed, verifying that early AdamW stability can be paired with late Muon sharpening for better downstream performance. FP8-mixed-precision training balances accuracy and throughput. All checkpoints, recipes, and evaluation code are released under the Apache-2.0 license.\footnote{https://huggingface.co/XiaoduoAILab/Xmodel-2.5 and https://huggingface.co/XiaoduoAILab/Xmodel-2.5-history (training checkpoints).} Training code and evaluation harness: https://github.com/XiaoduoAILab/Xmodel-2.5.
URLs: https://huggingface.co/XiaoduoAILab/Xmodel-2.5, https://huggingface.co/XiaoduoAILab/Xmodel-2.5-history, https://github.com/XiaoduoAILab/Xmodel-2.5.
Authors: Bowen Zhao, Huanlai Xing, Zhiwen Xiao, Jincheng Peng, Li Feng, Xinhan Wang, Rong Qu, Hui Li
Abstract: The attention mechanism has demonstrated remarkable potential in sequence modeling, exemplified by its successful application in natural language processing with models such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pre-trained Transformer (GPT). Despite these advancements, its utilization in time series forecasting (TSF) has yet to meet expectations. Exploring a better network structure for attention in TSF holds immense significance across various domains. In this paper, we present PeriodNet with a brand new structure to forecast univariate and multivariate time series. PeriodNet incorporates period attention and sparse period attention mechanism for analyzing adjacent periods. It enhances the mining of local characteristics, periodic patterns, and global dependencies. For efficient cross-variable modeling, we introduce an iterative grouping mechanism which can directly reduce the cross-variable redundancy. To fully leverage the extracted features on the encoder side, we redesign the entire architecture of the vanilla Transformer and propose a period diffuser for precise multi-period prediction. Through comprehensive experiments conducted on eight datasets, we demonstrate that PeriodNet outperforms six state-of-the-art models in both univariate and multivariate TSF scenarios in terms of mean square error and mean absolute error. In particular, PeriodNet achieves a relative improvement of 22% when forecasting time series with a length of 720, in comparison to other models based on the conventional encoder-decoder Transformer architecture.
Authors: Yi Zhang, Tianxiang Xu, Zijian Li, Chao Zhang, Kunyu Zhang, Zhan Gao, Meinuo Li, Xiaohan Zhang, Qichao Qi, Bing Chen
Abstract: Large language models (LLMs) exhibit exceptional performance but pose substantial privacy risks due to training data memorization, particularly within healthcare contexts involving imperfect or privacy-sensitive patient information. We present a hierarchical dual-strategy framework for selective knowledge unlearning that precisely removes specialized knowledge while preserving fundamental medical competencies. Our approach synergistically integrates geometric-constrained gradient updates to selectively modulate target parameters with concept-aware token-level interventions that distinguish between preservation-critical and unlearning-targeted tokens via a unified four-level medical concept hierarchy. Comprehensive evaluations on the MedMCQA (surgical) and MHQA (anxiety, depression, trauma) datasets demonstrate superior performance, achieving an 82.7% forgetting rate and 88.5% knowledge preservation. Notably, our framework maintains robust privacy guarantees while requiring modification of only 0.1% of parameters, addressing critical needs for regulatory compliance, auditability, and ethical standards in clinical research.
Authors: Hong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen, Nhien-An Le-Khac
Abstract: The rapid advancement of generators (e.g., StyleGAN, Midjourney, DALL-E) has produced highly realistic synthetic images, posing significant challenges to digital media authenticity. These generators are typically based on a few core architectural families, primarily Generative Adversarial Networks (GANs) and Diffusion Models (DMs). A critical vulnerability in current forensics is the failure of detectors to achieve cross-generator generalization, especially when crossing architectural boundaries (e.g., from GANs to DMs). We hypothesize that this gap stems from fundamental differences in the artifacts produced by these \textbf{distinct architectures}. In this work, we provide a theoretical analysis explaining how the distinct optimization objectives of the GAN and DM architectures lead to different manifold coverage behaviors. We demonstrate that GANs permit partial coverage, often leading to boundary artifacts, while DMs enforce complete coverage, resulting in over-smoothing patterns. Motivated by this analysis, we propose the \textbf{Tri}archy \textbf{Detect}or (TriDetect), a semi-supervised approach that enhances binary classification by discovering latent architectural patterns within the "fake" class. TriDetect employs balanced cluster assignment via the Sinkhorn-Knopp algorithm and a cross-view consistency mechanism, encouraging the model to learn fundamental architectural distincts. We evaluate our approach on two standard benchmarks and three in-the-wild datasets against 13 baselines to demonstrate its generalization capability to unseen generators.
Authors: Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary
Abstract: Reinforcement Learning from Human Feedback (RLHF) is widely used for aligning large language models, yet practitioners face a persistent puzzle: improving safety often reduces fairness, scaling to diverse populations becomes computationally intractable, and making systems robust often amplifies majority biases. We formalize this tension as the Alignment Trilemma: no RLHF system can simultaneously achieve (i) epsilon-representativeness across diverse human values, (ii) polynomial tractability in sample and compute complexity, and (iii) delta-robustness against adversarial perturbations and distribution shift. Through a complexity-theoretic analysis integrating statistical learning theory and robust optimization, we prove that achieving both representativeness (epsilon <= 0.01) and robustness (delta <= 0.001) for global-scale populations requires Omega(2^{d_context}) operations, which is super-polynomial in the context dimensionality. We show that current RLHF implementations resolve this trilemma by sacrificing representativeness: they collect only 10^3--10^4 samples from homogeneous annotator pools while 10^7--10^8 samples are needed for true global representation. Our framework provides a unified explanation for documented RLHF pathologies including preference collapse, sycophancy, and systematic bias amplification. We conclude with concrete directions for navigating these fundamental trade-offs through strategic relaxations of alignment requirements.
Authors: Raoul H. Kutil, Georg Zimmermann, Barbara Strasser-Kirchweger, Christian Borgelt
Abstract: Mental health disorders, particularly cognitive disorders defined by deficits in cognitive abilities, are described in detail in the DSM-5, which includes definitions and examples of signs and symptoms. A simplified, machine-actionable representation was developed to assess the similarity and separability of these disorders, but it is not suited for the most complex cases. Generating or applying a full binary matrix for similarity calculations is infeasible due to the vast number of symptom combinations. This research develops an alternative representation that links the narrative form of the DSM-5 with the binary matrix representation and enables automated generation of valid symptom combinations. Using a strict pre-defined format of lists, sets, and numbers with slight variations, complex diagnostic pathways involving numerous symptom combinations can be represented. This format, called the symptom profile generator (or simply generator), provides a readable, adaptable, and comprehensive alternative to a binary matrix while enabling easy generation of symptom combinations (profiles). Cognitive disorders, which typically involve multiple diagnostic criteria with several symptoms, can thus be expressed as lists of generators. Representing several psychotic disorders in generator form and generating all symptom combinations showed that matrix representations of complex disorders become too large to manage. The MPCS (maximum pairwise cosine similarity) algorithm cannot handle matrices of this size, prompting the development of a profile reduction method using targeted generator manipulation to find specific MPCS values between disorders. The generators allow easier creation of binary representations for large matrices and make it possible to calculate specific MPCS cases between complex disorders through conditional generators.
Authors: Kailin Lyu, Long Xiao, Jianing Zeng, Junhao Dong, Xuexin Liu, Zhuojun Zou, Haoyue Yang, Lin Shu, Jie Hao
Abstract: Traditional vision-based material perception methods often experience substantial performance degradation under visually impaired conditions, thereby motivating the shift toward non-visual multimodal material perception. Despite this, existing approaches frequently perform naive fusion of multimodal inputs, overlooking key challenges such as modality-specific noise, missing modalities common in real-world scenarios, and the dynamically varying importance of each modality depending on the task. These limitations lead to suboptimal performance across several benchmark tasks. In this paper, we propose a robust multimodal fusion framework, TouchFormer. Specifically, we employ a Modality-Adaptive Gating (MAG) mechanism and intra- and inter-modality attention mechanisms to adaptively integrate cross-modal features, enhancing model robustness. Additionally, we introduce a Cross-Instance Embedding Regularization(CER) strategy, which significantly improves classification accuracy in fine-grained subcategory material recognition tasks. Experimental results demonstrate that, compared to existing non-visual methods, the proposed TouchFormer framework achieves classification accuracy improvements of 2.48% and 6.83% on SSMC and USMC tasks, respectively. Furthermore, real-world robotic experiments validate TouchFormer's effectiveness in enabling robots to better perceive and interpret their environment, paving the way for its deployment in safety-critical applications such as emergency response and industrial automation. The code and datasets will be open-source, and the videos are available in the supplementary materials.
Authors: Bing Liu, Boao Kong, Limin Lu, Kun Yuan, Chengcheng Zhao
Abstract: Decentralized learning often involves a weighted global loss with heterogeneous node weights $\lambda$. We revisit two natural strategies for incorporating these weights: (i) embedding them into the local losses to retain a uniform weight (and thus a doubly stochastic matrix), and (ii) keeping the original losses while employing a $\lambda$-induced row-stochastic matrix. Although prior work shows that both strategies yield the same expected descent direction for the global loss, it remains unclear whether the Euclidean-space guarantees are tight and what fundamentally differentiates their behaviors. To clarify this, we develop a weighted Hilbert-space framework $L^2(\lambda;\mathbb{R}^d)$ and obtain convergence rates that are strictly tighter than those from Euclidean analysis. In this geometry, the row-stochastic matrix becomes self-adjoint whereas the doubly stochastic one does not, creating additional penalty terms that amplify consensus error, thereby slowing convergence. Consequently, the difference in convergence arises not only from spectral gaps but also from these penalty terms. We then derive sufficient conditions under which the row-stochastic design converges faster even with a smaller spectral gap. Finally, by using a Rayleigh-quotient and Loewner-order eigenvalue comparison, we further obtain topology conditions that guarantee this advantage and yield practical topology-design guidelines.
Authors: Adarsh Kumarappan, Ananya Mujoo
Abstract: Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way for a more significant one, to bypass safety alignments, pose a persistent threat to Large Language Models (LLMs). Progress in defending against these attacks is hindered by a reliance on manual, hard-to-scale dataset creation. This paper introduces a novel, automated pipeline for generating large-scale, psychologically-grounded multi-turn jailbreak datasets. We systematically operationalize FITD techniques into reproducible templates, creating a benchmark of 1,500 scenarios across illegal activities and offensive content. We evaluate seven models from three major LLM families under both multi-turn (with history) and single-turn (without history) conditions. Our results reveal stark differences in contextual robustness: models in the GPT family demonstrate a significant vulnerability to conversational history, with Attack Success Rates (ASR) increasing by as much as 32 percentage points. In contrast, Google's Gemini 2.5 Flash exhibits exceptional resilience, proving nearly immune to these attacks, while Anthropic's Claude 3 Haiku shows strong but imperfect resistance. These findings highlight a critical divergence in how current safety architectures handle conversational context and underscore the need for defenses that can resist narrative-based manipulation.
Authors: Shivam Pal, Sakshi Varshney, Piyush Rai
Abstract: Deep neural networks are prone to learning shortcuts, spurious and easily learned correlations in training data that cause severe failures in out-of-distribution (OOD) generalization. A dominant line of work seeks robustness by learning a robust representation, often explicitly partitioning the latent space into core and spurious components; this approach can be complex, brittle, and difficult to scale. We take a different approach, instead of a robust representation, we learn a robust function. We present a simple and effective training method that renders the classifier functionally invariant to shortcut signals. Our method operates within a disentangled latent space, which is essential as it isolates spurious and core features into distinct dimensions. This separation enables the identification of candidate shortcut features by their strong correlation with the label, used as a proxy for semantic simplicity. The classifier is then desensitized to these features by injecting targeted, anisotropic latent noise during training. We analyze this as targeted Jacobian regularization, which forces the classifier to ignore spurious features and rely on more complex, core semantic signals. The result is state-of-the-art OOD performance on established shortcut learning benchmarks.
Authors: Kaidi Wan, Minghao Liu, Yong Lai
Abstract: Wepropose SplitGNN, a graph neural network (GNN)-based approach that learns to solve weighted maximum satisfiabil ity (MaxSAT) problem. SplitGNN incorporates a co-training architecture consisting of supervised message passing mech anism and unsupervised solution boosting layer. A new graph representation called edge-splitting factor graph is proposed to provide more structural information for learning, which is based on spanning tree generation and edge classification. To improve the solutions on challenging and weighted instances, we implement a GPU-accelerated layer applying efficient score calculation and relaxation-based optimization. Exper iments show that SplitGNN achieves 3* faster convergence and better predictions compared with other GNN-based ar chitectures. More notably, SplitGNN successfully finds solu tions that outperform modern heuristic MaxSAT solvers on much larger and harder weighted MaxSAT benchmarks, and demonstrates exceptional generalization abilities on diverse structural instances.
Authors: Yiven (Louis), Zhu
Abstract: Neuroeconomics promises to ground welfare analysis in neural and computational evidence about how people value outcomes, learn from experience and exercise self-control. At the same time, policy and commercial actors increasingly invoke neural data to justify paternalistic regulation, "brain-based" interventions and new welfare measures. This paper asks under what conditions neural data can legitimately inform welfare judgements for policy rather than merely describing behaviour. I develop a non-empirical, model-based framework that links three levels: neural signals, computational decision models and normative welfare criteria. Within an actor-critic reinforcement-learning model, I formalise the inference path from neural activity to latent values and prediction errors and then to welfare claims. I show that neural evidence constrains welfare judgements only when the neural-computational mapping is well validated, the decision model identifies "true" interests versus context-dependent mistakes, and the welfare criterion is explicitly specified and defended. Applying the framework to addiction, neuromarketing and environmental policy, I derive a Neuroeconomic Welfare Inference Checklist for regulators and for designers of NeuroAI systems. The analysis treats brains and artificial agents as value-learning systems while showing that internal reward signals, whether biological or artificial, are computational quantities and cannot be treated as welfare measures without an explicit normative model.
Authors: Ruiyang Xu
Abstract: The processing of high-dimensional streaming data commonly utilizes online streaming feature selection (OSFS) techniques. However, practical implementations often face challenges with data incompleteness due to equipment failures and technical constraints. Online Sparse Streaming Feature Selection (OS2FS) tackles this issue through latent factor analysis-based missing data imputation. Despite this advancement, existing OS2FS approaches exhibit substantial limitations in feature evaluation, resulting in performance deterioration. To address these shortcomings, this paper introduces a novel Online Differential Evolution for Sparse Feature Selection (ODESFS) in data streams, incorporating two key innovations: (1) missing value imputation using a latent factor analysis model, and (2) feature importance evaluation through differential evolution. Comprehensive experiments conducted on six real-world datasets demonstrate that ODESFS consistently outperforms state-of-the-art OSFS and OS2FS methods by selecting optimal feature subsets and achieving superior accuracy.
Authors: Zecheng Pan, Zhikang Chen, Ding Li, Min Zhang, Sen Cui, Hongshuo Jin, Luqi Tao, Yi Yang, Deheng Ye, Yu Zhang, Tingting Zhu, Tianling Ren
Abstract: Merging models fine-tuned for different tasks into a single unified model has become an increasingly important direction for building versatile, efficient multi-task systems. Existing approaches predominantly rely on parameter interpolation in weight space, which we show introduces significant distribution shift in the feature space and undermines task-specific knowledge. In this paper, we propose OTMF (Optimal Transport-based Masked Fusion), a novel model merging framework rooted in optimal transport theory to address the distribution shift that arises from naive parameter interpolation. Instead of directly aggregating features or weights, OTMF aligns the semantic geometry of task-specific models by discovering common masks applied to task vectors through optimal transport plans. These masks selectively extract transferable and task-agnostic components while preserving the unique structural identities of each task. To ensure scalability in real-world settings, OTMF further supports a continual fusion paradigm that incrementally integrates each new task vector without revisiting previous ones, maintaining a bounded memory footprint and enabling efficient fusion across a growing number of tasks. We conduct comprehensive experiments on multiple vision and language benchmarks, and results show that OTMF achieves state-of-the-art performance in terms of both accuracy and efficiency. These findings highlight the practical and theoretical value of our approach to model merging.
Authors: Dhruva Kashyap, Chaitanya Murti, Pranav K Nayak, Tanay Narshana, Chiranjib Bhattacharyya
Abstract: Open weight models, which are ubiquitous, rarely provide access to their training data or loss function. This makes modifying such models for tasks such as pruning or unlearning constrained by this unavailability an active area of research. Existing techniques typically require gradients or ground-truth labels, rendering them infeasible in settings with limited computational resources. In this work, we investigate the fundamental question of identifying components that are critical to the model's predictive performance, without access to either gradients or the loss function, and with only distributional access such as synthetic data. We theoretically demonstrate that the global reconstruction error is linearly bounded by local reconstruction errors for Lipschitz-continuous networks such as CNNs and well-trained Transformers (which, contrary to existing literature, we find exhibit Lipschitz continuity). This motivates using the locally reconstructive behavior of component subsets to quantify their global importance, via a metric that we term Subset Fidelity. In the uncorrelated features setting, selecting individual components via their Subset Fidelity scores is optimal, which we use to propose ModHiFi, an algorithm for model modification that requires no training data or loss function access. ModHiFi-P, for structured pruning, achieves an 11% speedup over the current state of the art on ImageNet models and competitive performance on language models. ModHiFi-U, for classwise unlearning, achieves complete unlearning on CIFAR-10 without fine-tuning and demonstrates competitive performance on Swin Transformers.
Authors: Wentao Ye, Jiaqi Hu, Haobo Wang, Xinpeng Ti, Zhiqing Xiao, Hao Chen, Liyao Li, Lei Feng, Sai Wu, Junbo Zhao
Abstract: Language model inversion (LMI), i.e., recovering hidden prompts from outputs, emerges as a concrete threat to user privacy and system security. We recast LMI as reusing the LLM's own latent space and propose the Invariant Latent Space Hypothesis (ILSH): (1) diverse outputs from the same source prompt should preserve consistent semantics (source invariance), and (2) input<->output cyclic mappings should be self-consistent within a shared latent space (cyclic invariance). Accordingly, we present Inv^2A, which treats the LLM as an invariant decoder and learns only a lightweight inverse encoder that maps outputs to a denoised pseudo-representation. When multiple outputs are available, they are sparsely concatenated at the representation layer to increase information density. Training proceeds in two stages: contrastive alignment (source invariance) and supervised reinforcement (cyclic invariance). An optional training-free neighborhood search can refine local performance. Across 9 datasets covering user and system prompt scenarios, Inv^2A outperforms baselines by an average of 4.77% BLEU score while reducing dependence on large inverse corpora. Our analysis further shows that prevalent defenses provide limited protection, underscoring the need for stronger strategies. The source code and data involved in this paper can be found in https://github.com/yyy01/Invariant_Attacker.
Authors: Jialiang Li, Weitong Chen, Mingyu Guo
Abstract: Neural models have shown promise in solving NP-hard graph combinatorial optimization (CO) problems. Once trained, they offer fast inference and reasonably high-quality solutions for in-distribution testing instances, but they generally fall short in terms of absolute solution quality compared to classical search-based algorithms that are admittedly slower but offer optimality guarantee once search finishes. We propose a novel framework that combines the inference efficiency and exploratory power of neural models with the solution quality guarantee of search-based algorithms. In particular, we use parameterized algorithms (PAs) as the search component. PAs are dedicated to identifying easy instances of generally NP-hard problems, and allow for practically efficient search by exploiting structural simplicity (of the identified easy instances). Under our framework, we use parameterized analysis to identify the structurally hard parts of a CO instance. The neural model handles the hard parts by generating advisory signals based on its data-driven understanding. The PA-based search component then integrates the advisory signals to systematically and efficiently searches through the remaining structurally easy parts. Notably, our framework is agnostic to the choice of neural model and produces strictly better solutions than neural solvers alone. We examine our framework on multiple CO tasks. Empirical results show that it achieves superior solution quality, competitive with that of commercial solvers. Furthermore, by using the neural model only for exploratory advisory signals, our framework exhibits improved out-of-distribution generalization, addressing a key limitation of existing neural CO solvers.
Authors: Nicklas Hansen, Hao Su, Xiaolong Wang
Abstract: General-purpose control demands agents that act across many tasks and embodiments, yet research on reinforcement learning (RL) for continuous control remains dominated by single-task or offline regimes, reinforcing a view that online RL does not scale. Inspired by the foundation model recipe (large-scale pretraining followed by light RL) we ask whether a single agent can be trained on hundreds of tasks with online interaction. To accelerate research in this direction, we introduce a new benchmark with 200 diverse tasks spanning many domains and embodiments, each with language instructions, demonstrations, and optionally image observations. We then present \emph{Newt}, a language-conditioned multitask world model that is first pretrained on demonstrations to acquire task-aware representations and action priors, and then jointly optimized with online interaction across all tasks. Experiments show that Newt yields better multitask performance and data-efficiency than a set of strong baselines, exhibits strong open-loop control, and enables rapid adaptation to unseen tasks. We release our environments, demonstrations, code for training and evaluation, as well as 200+ checkpoints.
Authors: Shihan Feng, Cheng Zhang, Michael Xi, Ethan Hsu, Lesia Semenova, Chudi Zhong
Abstract: Modern neural networks rarely have a single way to be right. For many tasks, multiple models can achieve identical performance while relying on different features or reasoning patterns, a property known as the Rashomon Effect. However, uncovering this diversity in deep architectures is challenging as their continuous parameter spaces contain countless near-optimal solutions that are numerically distinct but often behaviorally similar. We introduce Rashomon Concept Bottleneck Models, a framework that learns multiple neural networks which are all accurate yet reason through distinct human-understandable concepts. By combining lightweight adapter modules with a diversity-regularized training objective, our method constructs a diverse set of deep concept-based models efficiently without retraining from scratch. The resulting networks provide fundamentally different reasoning processes for the same predictions, revealing how concept reliance and decision making vary across equally performing solutions. Our framework enables systematic exploration of data-driven reasoning diversity in deep models, offering a new mechanism for auditing, comparison, and alignment across equally accurate solutions.
Authors: Kaiyi Ji
Abstract: Although upper bound guarantees for bilevel optimization have been widely studied, progress on lower bounds has been limited due to the complexity of the bilevel structure. In this work, we focus on the smooth nonconvex-strongly-convex setting and develop new hard instances that yield nontrivial lower bounds under deterministic and stochastic first-order oracle models. In the deterministic case, we prove that any first-order zero-respecting algorithm requires at least $\Omega(\kappa^{3/2}\epsilon^{-2})$ oracle calls to find an $\epsilon$-accurate stationary point, improving the optimal lower bounds known for single-level nonconvex optimization and for nonconvex-strongly-convex min-max problems. In the stochastic case, we show that at least $\Omega(\kappa^{5/2}\epsilon^{-4})$ stochastic oracle calls are necessary, again strengthening the best known bounds in related settings. Our results expose substantial gaps between current upper and lower bounds for bilevel optimization and suggest that even simplified regimes, such as those with quadratic lower-level objectives, warrant further investigation toward understanding the optimal complexity of bilevel optimization under standard first-order oracles.
Authors: Sepideh Koohfar
Abstract: Time-series forecasting remains difficult in real-world settings because temporal patterns operate at multiple scales, from broad contextual trends to fast, fine-grained fluctuations that drive critical decisions. Existing neural models often struggle to represent these interacting dynamics, leading to unstable predictions and reduced reliability in downstream applications. This work introduces a forecast-blur-denoise framework that improves temporal fidelity through structured noise modeling. The approach incorporates a learnable Gaussian Process module that generates smooth, correlated perturbations, encouraging the forecasting backbone to capture long-range structure while a dedicated refinement model restores high-resolution temporal detail. Training the components jointly enables natural competence division and avoids the artifacts commonly produced by isotropic corruption methods. Experiments across electricity, traffic, and solar datasets show consistent gains in multi-horizon accuracy and stability. The modular design also allows the blur-denoise layer to operate as a lightweight enhancement for pretrained models, supporting efficient adaptation in limited-data scenarios. By strengthening the reliability and interpretability of fine-scale temporal predictions, this framework contributes to more trustworthy AI systems used in forecasting-driven decision support across energy, infrastructure, and other time-critical domains.
Authors: Jiaxin Shi, Michalis K. Titsias
Abstract: We derive a new theoretical interpretation of the reweighted losses that are widely used for training diffusion models. Our method is based on constructing a cascade of time-dependent variational lower bounds on the data log-likelihood, that provably improves upon the standard evidence lower bound and results in reduced data-model KL-divergences. Combining such bounds gives rise to reweighted objectives that can be applied to any generative diffusion model including both continuous Gaussian diffusion and masked (discrete) diffusion models. Then, we showcase this framework in masked diffusion and report significant improvements over previous training losses in pixel-space image modeling, approaching sample quality comparable to continuous diffusion models. Our results also provide a theoretical justification for the simple weighting scheme widely used in masked image models.
Authors: Chin-Chia Michael Yeh, Uday Singh Saini, Xin Dai, Xiran Fan, Shubham Jain, Yujie Fan, Jiarui Sun, Junpeng Wang, Menghai Pan, Yingtong Dou, Yuzhong Chen, Vineeth Rakesh, Liang Wang, Yan Zheng, Mahashweta Das
Abstract: Payment networks form the backbone of modern commerce, generating high volumes of transaction records from daily activities. Properly modeling this data can enable applications such as abnormal behavior detection and consumer-level insights for hyper-personalized experiences, ultimately improving people's lives. In this paper, we present TREASURE, TRansformer Engine As Scalable Universal transaction Representation Encoder, a multipurpose transformer-based foundation model specifically designed for transaction data. The model simultaneously captures both consumer behavior and payment network signals (such as response codes and system flags), providing comprehensive information necessary for applications like accurate recommendation systems and abnormal behavior detection. Verified with industry-grade datasets, TREASURE features three key capabilities: 1) an input module with dedicated sub-modules for static and dynamic attributes, enabling more efficient training and inference; 2) an efficient and effective training paradigm for predicting high-cardinality categorical attributes; and 3) demonstrated effectiveness as both a standalone model that increases abnormal behavior detection performance by 111% over production systems and an embedding provider that enhances recommendation models by 104%. We present key insights from extensive ablation studies, benchmarks against production models, and case studies, highlighting valuable knowledge gained from developing TREASURE.
Authors: Chin-Chia Michael Yeh, Uday Singh Saini, Junpeng Wang, Xin Dai, Xiran Fan, Jiarui Sun, Yujie Fan, Yan Zheng
Abstract: The ubiquity of time series data creates a strong demand for general-purpose foundation models, yet developing them for classification remains a significant challenge, largely due to the high cost of labeled data. Foundation models capable of in-context learning (ICL) offer a powerful solution, adapting to new tasks with minimal examples and reducing the need for extensive retraining. However, prior work on large-scale time series models has predominantly focused on forecasting, leaving a critical gap for versatile, fine-tuning-free classification. To address this, we introduce TiCT (Time-series in-Context Transformer), a transformer-based model pre-trained exclusively on synthetic data to perform in-context classification. We make two primary technical contributions: 1) a novel architecture featuring a scalable bit-based label encoding and a special output attention mechanism to handle an arbitrary number of classes; and 2) a synthetic pre-training framework that combines a Mixup-inspired process with data augmentation to foster generalization and noise invariance. Extensive evaluations on the UCR Archive show that TiCT achieves competitive performance against state-of-the-art supervised methods. Crucially, this is accomplished using only in-context examples at inference time, without updating a single model weight.
Authors: Ziteng Sun, Adrian Benton, Samuel Kushnir, Asher Trockman, Vikas Singh, Suhas Diggavi, Ananda Theertha Suresh
Abstract: Post-training quantization is an effective method for reducing the serving cost of large language models, where the standard approach is to use a round-to-nearest quantization level scheme. However, this often introduces large errors due to outliers in the weights. Proposed mitigation mechanisms include applying adaptive rounding, random rotation transformations or committing to a post-training target using calibration data. Unfortunately, this reliance on calibration data can be severely limiting in some real-world scenarios as such data may be unavailable or subject to privacy regulations. In this paper, we propose algorithms to optimize transformations and adaptive rounding without access to any calibration data. The optimization is achieved by designing a suitable proxy function for the quantization loss without calibration data. To maintain inference efficiency, we perform structured matrix transformations for single matrices. For paired weights that interact directly in the computation graph, we use dual matrix transformations and adaptive rounding methods. We conduct experiments on Gemma 2 models, and observe consistent improvement over the baselines. For Gemma 2 9B quantization, our method improves the average benchmark score from 61.9 to 62.4 for 4-bit quantization and from 52.0 to 60.6 for 3-bit quantization, while adding less than 3% of computation overhead. Furthermore, our method achieves performance comparable to the commonly used GPTQ method, which requires calibration data.
Authors: Hongchen Wang, Rafael Espinosa Casta\~neda, Jay R. Werber, Yao Fehlis, Edward Kim, Jason Hattrick-Simpers
Abstract: Active learning (AL) accelerates scientific discovery by prioritizing the most informative experiments, but traditional machine learning (ML) models used in AL suffer from cold-start limitations and domain-specific feature engineering, restricting their generalizability. Large language models (LLMs) offer a new paradigm by leveraging their pretrained knowledge and universal token-based representations to propose experiments directly from text-based descriptions. Here, we introduce an LLM-based active learning framework (LLM-AL) that operates in an iterative few-shot setting and benchmark it against conventional ML models across four diverse materials science datasets. We explored two prompting strategies: one using concise numerical inputs suited for datasets with more compositional and structured features, and another using expanded descriptive text suited for datasets with more experimental and procedural features to provide additional context. Across all datasets, LLM-AL could reduce the number of experiments needed to reach top-performing candidates by over 70% and consistently outperformed traditional ML models. We found that LLM-AL performs broader and more exploratory searches while still reaching the optima with fewer iterations. We further examined the stability boundaries of LLM-AL given the inherent non-determinism of LLMs and found its performance to be broadly consistent across runs, within the variability range typically observed for traditional ML approaches. These results demonstrate that LLM-AL can serve as a generalizable alternative to conventional AL pipelines for more efficient and interpretable experiment selection and potential LLM-driven autonomous discovery.
Authors: Julien T. T. Vignoud, Val\'erian Rousset, Hugo El Guedj, Ignacio Aleman, Walid Bennaceur, Batuhan Faik Derinbay, Eduard \v{D}urech, Damien Gengler, Lucas Giordano, Felix Grimberg, Franziska Lippoldt, Christina Kopidaki, Jiafan Liu, Lauris Lopata, Nathan Maire, Paul Mansat, Martin Milenkoski, Emmanuel Omont, G\"une\c{s} \"Ozg\"un, Mina Petrovi\'c, Francesco Posa, Morgan Ridel, Giorgio Savini, Marcel Torne, Lucas Trognon, Alyssa Unell, Olena Zavertiaieva, Sai Praneeth Karimireddy, Tahseen Rabbani, Mary-Anne Hartley, Martin Jaggi
Abstract: Data is often impractical to share for a range of well considered reasons, such as concerns over privacy, intellectual property, and legal constraints. This not only fragments the statistical power of predictive models, but creates an accessibility bias, where accuracy becomes inequitably distributed to those who have the resources to overcome these concerns. We present DISCO: an open-source DIStributed COllaborative learning platform accessible to non-technical users, offering a means to collaboratively build machine learning models without sharing any original data or requiring any programming knowledge. DISCO's web application trains models locally directly in the browser, making our tool cross-platform out-of-the-box, including smartphones. The modular design of \disco offers choices between federated and decentralized paradigms, various levels of privacy guarantees and several approaches to weight aggregation strategies that allow for model personalization and bias resilience in the collaborative training. Code repository is available at https://github.com/epfml/disco and a showcase web interface at https://discolab.ai
Authors: Wenzhang Du
Abstract: Recent machine learning papers often report 1-2 percentage point improvements from a single run on a benchmark. These gains are highly sensitive to random seeds, data ordering, and implementation details, yet are rarely accompanied by uncertainty estimates or significance tests. It is therefore unclear when a reported +1-2% reflects a real algorithmic advance versus noise. We revisit this problem under realistic compute budgets, where only a few runs are affordable. We propose a simple, PC-friendly evaluation protocol based on paired multi-seed runs, bias-corrected and accelerated (BCa) bootstrap confidence intervals, and a sign-flip permutation test on per-seed deltas. The protocol is intentionally conservative and is meant as a guardrail against over-claiming. We instantiate it on CIFAR-10, CIFAR-10N, and AG News using synthetic no-improvement, small-gain, and medium-gain scenarios. Single runs and unpaired t-tests often suggest significant gains for 0.6-2.0 point improvements, especially on text. With only three seeds, our paired protocol never declares significance in these settings. We argue that such conservative evaluation is a safer default for small gains under tight budgets.
Authors: Linqi Zhou, Mathias Parger, Ayaan Haque, Jiaming Song
Abstract: We propose Terminal Velocity Matching (TVM), a generalization of flow matching that enables high-fidelity one- and few-step generative modeling. TVM models the transition between any two diffusion timesteps and regularizes its behavior at its terminal time rather than at the initial time. We prove that TVM provides an upper bound on the $2$-Wasserstein distance between data and model distributions when the model is Lipschitz continuous. However, since Diffusion Transformers lack this property, we introduce minimal architectural changes that achieve stable, single-stage training. To make TVM efficient in practice, we develop a fused attention kernel that supports backward passes on Jacobian-Vector Products, which scale well with transformer architectures. On ImageNet-256x256, TVM achieves 3.29 FID with a single function evaluation (NFE) and 1.99 FID with 4 NFEs. It similarly achieves 4.32 1-NFE FID and 2.94 4-NFE FID on ImageNet-512x512, representing state-of-the-art performance for one/few-step models from scratch.
Authors: Sibo Ma, Julian Nyarko
Abstract: Data attribution seeks to trace model behavior back to the training examples that shaped it, enabling debugging, auditing, and data valuation at scale. Classical influence-function methods offer a principled foundation but remain impractical for modern networks because they require expensive backpropagation or Hessian inversion at inference. We propose a data attribution method that preserves the same first-order counterfactual target while eliminating per-query backward passes. Our approach simulates each training example's parameter influence through short-horizon gradient propagation during training and later reads out attributions for any query using only forward evaluations. This design shifts computation from inference to simulation, reflecting real deployment regimes where a model may serve billions of user queries but originate from a fixed, finite set of data sources (for example, a large language model trained on diverse corpora while compensating a specific publisher such as the New York Times). Empirically, on standard MLP benchmarks, our estimator matches or surpasses state-of-the-art baselines such as TRAK on standard attribution metrics (LOO and LDS) while offering orders-of-magnitude lower inference cost. By combining influence-function fidelity with first-order scalability, our method provides a theoretical framework for practical, real-time data attribution in large pretrained models.
Authors: Marzi Heidari, Hanping Zhang, Yuhong Guo
Abstract: The challenge of learning with noisy labels is significant in machine learning, as it can severely degrade the performance of prediction models if not addressed properly. This paper introduces a novel framework that conceptualizes noisy label correction as a reinforcement learning (RL) problem. The proposed approach, Reinforcement Learning for Noisy Label Correction (RLNLC), defines a comprehensive state space representing data and their associated labels, an action space that indicates possible label corrections, and a reward mechanism that evaluates the efficacy of label corrections. RLNLC learns a deep feature representation based policy network to perform label correction through reinforcement learning, utilizing an actor-critic method. The learned policy is subsequently deployed to iteratively correct noisy training labels and facilitate the training of the prediction model. The effectiveness of RLNLC is demonstrated through extensive experiments on multiple benchmark datasets, where it consistently outperforms existing state-of-the-art techniques for learning with noisy labels.
Authors: Divyansh Chaurasia, Manoj Daram, Roshan Kumar, Nihal Thukarama Rao, Vipul Sangode, Pranjal Srivastava, Avnish Tripathi, Shoubhik Chakraborty, Akanksha, Ambasht Kumar, Davender Sethi, Sachchida Nand Tripathi, Purushottam Kar
Abstract: We present a case study for the calibration of Low-cost air-quality (LCAQ) CO sensors from one of the largest multi-site-multi-season-multi-sensor-multi-pollutant mobile air-quality monitoring network deployments in India. LCAQ sensors have been shown to play a critical role in the establishment of dense, expansive air-quality monitoring networks and combating elevated pollution levels. The calibration of LCAQ sensors against regulatory-grade monitors is an expensive, laborious and time-consuming process, especially when a large number of sensors are to be deployed in a geographically diverse layout. In this work, we present the RESPIRE technique to calibrate LCAQ sensors to detect ambient CO (Carbon Monoxide) levels. RESPIRE offers specific advantages over baseline calibration methods popular in literature, such as improved prediction in cross-site, cross-season, and cross-sensor settings. RESPIRE offers a training algorithm that is provably resistant to outliers and an explainable model with the ability to flag instances of model overfitting. Empirical results are presented based on data collected during an extensive deployment spanning four sites, two seasons and six sensor packages. RESPIRE code is available at https://github.com/purushottamkar/respire.
Authors: Wentao Hu, Mingkuan Zhao, Shuangyong Song, Xiaoyan Zhu, Xin Lai, Jiayin Wang
Abstract: Sparse Mixture-of-Experts (SMoE) architectures have enabled a new frontier in scaling Large Language Models (LLMs), offering superior performance by activating only a fraction of their total parameters during inference. However, their practical deployment is severely hampered by substantial static memory overhead, as all experts must be loaded into memory. Existing post-training pruning methods, while reducing model size, often derive their pruning criteria from a single, general-purpose corpus. This leads to a critical limitation: a catastrophic performance degradation when the pruned model is applied to other domains, necessitating a costly re-pruning for each new domain. To address this generalization gap, we introduce Mosaic Pruning (MoP). The core idea of MoP is to construct a functionally comprehensive set of experts through a structured ``cluster-then-select" process. This process leverages a similarity metric that captures expert performance across different task domains to functionally cluster the experts, and subsequently selects the most representative expert from each cluster based on our proposed Activation Variability Score. Unlike methods that optimize for a single corpus, our proposed Mosaic Pruning ensures that the pruned model retains a functionally complementary set of experts, much like the tiles of a mosaic that together form a complete picture of the original model's capabilities, enabling it to handle diverse downstream tasks.Extensive experiments on various MoE models demonstrate the superiority of our approach. MoP significantly outperforms prior work, achieving a 7.24\% gain on general tasks and 8.92\% on specialized tasks like math reasoning and code generation.
Authors: Zhentao Zhan, Xiaoliang Xu, Jingjing Wang, Junmei Wang
Abstract: Graph Similarity Computation (GSC) is a fundamental graph related task where Graph Edit Distance (GED) serves as a prevalent metric. GED is determined by an optimal alignment between a pair of graphs that partitions each into aligned (zero-cost) and unaligned (cost-incurring) substructures. Due to NP-hard nature of exact GED computation, GED approximations based on Graph Neural Network(GNN) have emerged. Existing GNN-based GED approaches typically learn node embeddings for each graph and then aggregate pairwise node similarities to estimate the final similarity. Despite their effectiveness, we identify a mismatch between this prevalent node-centric matching paradigm and the core principles of GED. This discrepancy leads to two critical limitations: (1) a failure to capture the global structural correspondence for optimal alignment, and (2) a misattribution of edit costs driven by spurious node level signals. To address these limitations, we propose GCGSim, a GED-consistent graph similarity learning framework centering on graph-level matching and substructure-level edit costs. Specifically, we make three core technical contributions. Extensive experiments on four benchmark datasets show that GCGSim achieves state-of-the-art performance. Our comprehensive analyses further validate that the framework effectively learns disentangled and semantically meaningful substructure representations.
Authors: Liang Gou (Ellen), Archit Khare (Ellen), Praneet Pabolu (Ellen), Prachi Patel (Ellen), Joseph Ross (Ellen), Hercy Shen (Ellen), Yuhan (Ellen), Song, Jingze Sun, Kristal Curtis, Vedant Dharnidharka, Abhinav Mathur, Hao Yang
Abstract: We introduce the Cisco Time Series Model, a univariate zero-shot forecaster. This time series foundation model is the result of a general architectural innovation to a time series model enabling it to accept multiresolution input, applied to a popular decoder-only time series model (TimesFM). The resulting multiresolution decoder-only model is trained on over 300B unique data points, with more than half coming from the observability domain. Quantitative and qualitative evaluations demonstrate that the resulting model achieves superior performance on observability datasets while retaining very similar performance on a standard general-purpose forecasting benchmark (GIFT-Eval), and suggest that the multiresolution structure enables the model to make more accurate predictions on long context input.
Authors: Chaogui Kang, Lijian Luo, Qingfeng Guan, Yu Liu
Abstract: Decision trees remain central for tabular prediction but struggle with (i) capturing spatial dependence and (ii) producing locally stable (robust) explanations. We present SX-GeoTree, a self-explaining geospatial regression tree that integrates three coupled objectives during recursive splitting: impurity reduction (MSE), spatial residual control (global Moran's I), and explanation robustness via modularity maximization on a consensus similarity network formed from (a) geographically weighted regression (GWR) coefficient distances (stimulus-response similarity) and (b) SHAP attribution distances (explanatory similarity). We recast local Lipschitz continuity of feature attributions as a network community preservation problem, enabling scalable enforcement of spatially coherent explanations without per-sample neighborhood searches. Experiments on two exemplar tasks (county-level GDP in Fujian, n=83; point-wise housing prices in Seattle, n=21,613) show SX-GeoTree maintains competitive predictive accuracy (within 0.01 $R^{2}$ of decision trees) while improving residual spatial evenness and doubling attribution consensus (modularity: Fujian 0.19 vs 0.09; Seattle 0.10 vs 0.05). Ablation confirms Moran's I and modularity terms are complementary; removing either degrades both spatial residual structure and explanation stability. The framework demonstrates how spatial similarity - extended beyond geometric proximity through GWR-derived local relationships - can be embedded in interpretable models, advancing trustworthy geospatial machine learning and offering a transferable template for domain-aware explainability.
Authors: Kun Guo, Xuefei Li, Xijun Wang, Howard H. Yang, Wei Feng, Tony Q. S. Quek
Abstract: Federated learning (FL) and split learning (SL) are two effective distributed learning paradigms in wireless networks, enabling collaborative model training across mobile devices without sharing raw data. While FL supports low-latency parallel training, it may converge to less accurate model. In contrast, SL achieves higher accuracy through sequential training but suffers from increased delay. To leverage the advantages of both, hybrid split and federated learning (HSFL) allows some devices to operate in FL mode and others in SL mode. This paper aims to accelerate HSFL by addressing three key questions: 1) How does learning mode selection affect overall learning performance? 2) How does it interact with batch size? 3) How can these hyperparameters be jointly optimized alongside communication and computational resources to reduce overall learning delay? We first analyze convergence, revealing the interplay between learning mode and batch size. Next, we formulate a delay minimization problem and propose a two-stage solution: a block coordinate descent method for a relaxed problem to obtain a locally optimal solution, followed by a rounding algorithm to recover integer batch sizes with near-optimal performance. Experimental results demonstrate that our approach significantly accelerates convergence to the target accuracy compared to existing methods.
Authors: Shuoyan Xu, Yu Zhang, Eric J. Miller
Abstract: Ride-hailing platforms are characterized by high-frequency, behavior-driven environments. Although survival analysis has been applied to recurrent events in other domains, its use in modeling ride-hailing driver behavior remains largely unexplored. This study formulates idle behavior as a recurrent survival process using large-scale platform data and proposes a Transformer-based framework that captures long-term temporal dependencies with causal masking and incorporates driver-specific embeddings to model latent heterogeneity. Results on Toronto ride-hailing data demonstrate that the proposed Frailty-Aware Cox Transformer (FACT) achieves the highest time-dependent C-indices and lowest Brier Scores, outperforming classical and deep learning survival models. This approach enables more accurate risk estimation, supports platform retention strategies, and provides policy-relevant insights.
Authors: Songlin Zhao, Michael Pitts, Zhuwei Qin
Abstract: The rapid advancement of large language models (LLMs) has increased the demand for domain-specialized variants in areas such as law, healthcare, and finance. However, their large size remains a barrier to deployment in resource-constrained environments, and existing compression methods either generalize poorly across domains or incur high overhead. In this work, we propose \textbf{EfficientXpert}, a lightweight domain-pruning framework that combines a propagation-aware pruning criterion (Foresight Mask) with an efficient adapter-update algorithm (Partial Brain Surgeon). Integrated into the LoRA fine-tuning process, EfficientXpert enables a one-step transformation of general pretrained models into sparse, domain-adapted experts. Across health and legal tasks, it retains up to 98% of dense-model performance at 40% sparsity, outperforming state-of-the-art methods. Further analysis reveals substantial domain-dependent structural shifts that degrade the effectiveness of general pruning masks, underscoring the need for adaptive, domain-aware pruning strategies tailored to each domain.
Authors: Peng Zhao, Yu-Hu Yan, Hang Yu, Zhi-Hua Zhou
Abstract: Universal online learning aims to achieve optimal regret guarantees without requiring prior knowledge of the curvature of online functions. Existing methods have established minimax-optimal regret bounds for universal online learning, where a single algorithm can simultaneously attain $\mathcal{O}(\sqrt{T})$ regret for convex functions, $\mathcal{O}(d \log T)$ for exp-concave functions, and $\mathcal{O}(\log T)$ for strongly convex functions, where $T$ is the number of rounds and $d$ is the dimension of the feasible domain. However, these methods still lack problem-dependent adaptivity. In particular, no universal method provides regret bounds that scale with the gradient variation $V_T$, a key quantity that plays a crucial role in applications such as stochastic optimization and fast-rate convergence in games. In this work, we introduce UniGrad, a novel approach that achieves both universality and adaptivity, with two distinct realizations: UniGrad.Correct and UniGrad.Bregman. Both methods achieve universal regret guarantees that adapt to gradient variation, simultaneously attaining $\mathcal{O}(\log V_T)$ regret for strongly convex functions and $\mathcal{O}(d \log V_T)$ regret for exp-concave functions. For convex functions, the regret bounds differ: UniGrad.Correct achieves an $\mathcal{O}(\sqrt{V_T \log V_T})$ bound while preserving the RVU property that is crucial for fast convergence in online games, whereas UniGrad.Bregman achieves the optimal $\mathcal{O}(\sqrt{V_T})$ regret bound through a novel design. Both methods employ a meta algorithm with $\mathcal{O}(\log T)$ base learners, which naturally requires $\mathcal{O}(\log T)$ gradient queries per round. To enhance computational efficiency, we introduce UniGrad++, which retains the regret while reducing the gradient query to just $1$ per round via surrogate optimization. We further provide various implications.
Authors: Shenjun Zhong, Zhifeng Chen, Zhaolin Chen
Abstract: Magnetic Resonance Fingerprinting (MRF) leverages transient-state signal dynamics generated by the tunable acquisition parameters, making the design of an optimal, robust sequence a complex, high-dimensional sequential decision problem, such as optimizing one of the key parameters, flip angle. Reinforcement learning (RL) offers a promising approach to automate parameter selection, to optimize pulse sequences that maximize the distinguishability of fingerprints across the parameter space. In this work, we introduce an RL framework for optimizing the flip-angle schedule in MRF and demonstrate a learned schedule exhibiting non-periodic patterns that enhances fingerprint separability. Additionally, an interesting observation is that the RL-optimized schedule may enable a reduction in the number of repetition time, potentially accelerate MRF acquisitions.
Authors: Jingchu Gai, Guanning Zeng, Huaqing Zhang, Aditi Raghunathan
Abstract: It is widely recognized that reinforcement learning (RL) fine-tuning of large language models often leads to \textit{diversity collapse}, where outputs lack variety. Prior work has proposed a range of heuristics to counteract this effect, but these methods are ad hoc: they frequently trade off correctness for diversity, their effectiveness varies across tasks, and in some cases they even contradict one another. In this work, we place these observations on a rigorous foundation. We first provide a formal proof of why RL fine-tuning exhibits diversity collapse via a selection and reinforcement bias. Next, we make a key observation that any reward modification to address diversity collapse only needs to be applied on the correct trajectories. Building directly on this analysis, we introduce a principled method -- \textit{differential smoothing} -- that provably improves both correctness and diversity, outperforming vanilla RL as well as widely used entropy-based heuristics. Our theory precisely characterizes when existing heuristics help and why they fail, while showing that differential smoothing is universally superior. Extensive experiments with models from 1B to 7B parameters, across domains including CountDown and real-world mathematical reasoning, demonstrate consistent gains. Differential smoothing improves both Pass@1 and Pass@k, with up to 6.7\% improvements on AIME24 dataset.
Authors: Haoran Hu, Junren Shi, Shuo Jiang, Kun Cheng, Xia Yang, Changhao Piao
Abstract: Forward Collision Warning systems are crucial for vehicle safety and autonomous driving, yet current methods often fail to balance precise multi-agent interaction modeling with real-time decision adaptability, evidenced by the high computational cost for edge deployment and the unreliability stemming from simplified interaction models.To overcome these dual challenges-computational complexity and modeling insufficiency-along with the high false alarm rates of traditional static-threshold warnings, this paper introduces an integrated FCW framework that pairs a Hierarchical Spatio-Temporal Attention Network with a Dynamic Risk Threshold Adjustment algorithm. HSTAN employs a decoupled architecture (Graph Attention Network for spatial, cascaded GRU with self-attention for temporal) to achieve superior performance and efficiency, requiring only 12.3 ms inference time (73% faster than Transformer methods) and reducing the Average Displacement Error (ADE) to 0.73m (42.2% better than Social_LSTM) on the NGSIM dataset. Furthermore, Conformalized Quantile Regression enhances reliability by generating prediction intervals (91.3% coverage at 90% confidence), which the DTRA module then converts into timely warnings via a physics-informed risk potential function and an adaptive threshold mechanism inspired by statistical process control.Tested across multi-scenario datasets, the complete system demonstrates high efficacy, achieving an F1 score of 0.912, a low false alarm rate of 8.2%, and an ample warning lead time of 2.8 seconds, validating the framework's superior performance and practical deployment feasibility in complex environments.
Authors: Meiyu Zhong, Noel Teku, Ravi Tandon
Abstract: Large Language Models (LLMs), though shown to be effective in many applications, can vary significantly in their response quality. In this paper, we investigate this problem of prompt fairness: specifically, the phrasing of a prompt by different users/styles, despite the same question being asked in principle, may elicit different responses from an LLM. To quantify this disparity, we propose to use information-theoretic metrics that can capture two dimensions of bias: subgroup sensitivity, the variability of responses within a subgroup and cross group consistency, the variability of responses across subgroups. Our analysis reveals that certain subgroups exhibit both higher internal variability and greater divergence from others. Our empirical analysis reveals that certain demographic sub groups experience both higher internal variability and greater divergence from others, indicating structural inequities in model behavior. To mitigate these disparities, we propose practical interventions, including majority voting across multiple generations and prompt neutralization, which together improve response stability and enhance fairness across user populations. In the experiments, we observe clear prompt sensitivity disparities across demographic subgroups: before mitigation, cross-group divergence values reach 0.28 and typically fall in the from 0.14 to 0.22 range. After applying our neutralization and multi generation strategy, these divergences consistently decrease, with the largest gap reduced to 0.22 and many distances falling to 0.17 or below, indicating more stable and consistent outputs across subgroups.
Authors: Yujia Wang, Yuanpu Cao, Jinghui Chen
Abstract: Federated learning (FL) has been extensively studied as a privacy-preserving training paradigm. Recently, federated block coordinate descent scheme has become a popular option in training large-scale models, as it allows clients to train only a subset of the model locally instead of the entire model. However, in the era of large language models (LLMs), even a single block can contain a significant number of parameters, posing substantial communication latency, particularly for resource-constrained clients. To address this challenge in federated training/fine-tuning LLMs, we propose ParaBlock, a novel approach that establishes two parallel threads for communication and computation to enhance communication efficiency. We theoretically prove that the proposed ParaBlock achieves the same convergence rate as the standard federated block coordinate descent methods. Empirical evaluations on fine-tuning LLMs on general instruction following and mathematical reasoning confirm that ParaBlock not only maintains strong performance but also significantly improves communication efficiency.
Authors: Yujia Wang, Fenglong Ma, Jinghui Chen
Abstract: Asynchronous federated learning (FL) has recently gained attention for its enhanced efficiency and scalability, enabling local clients to send model updates to the server at their own pace without waiting for slower participants. However, such a design encounters significant challenges, such as the risk of outdated updates from straggler clients degrading the overall model performance and the potential bias introduced by faster clients dominating the learning process, especially under heterogeneous data distributions. Existing methods typically address only one of these issues, creating a conflict where mitigating the impact of outdated updates can exacerbate the bias created by faster clients, and vice versa. To address these challenges, we propose FedEcho, a novel framework that incorporates uncertainty-aware distillation to enhance the asynchronous FL performances under large asynchronous delays and data heterogeneity. Specifically, uncertainty-aware distillation enables the server to assess the reliability of predictions made by straggler clients, dynamically adjusting the influence of these predictions based on their estimated uncertainty. By prioritizing more certain predictions while still leveraging the diverse information from all clients, FedEcho effectively mitigates the negative impacts of outdated updates and data heterogeneity. Through extensive experiments, we demonstrate that FedEcho consistently outperforms existing asynchronous federated learning baselines, achieving robust performance without requiring access to private client data.
Authors: Songbo Wang, Renchi Yang, Yurui Lai, Xiaoyang Lin, Tsz Nam Chan
Abstract: The emergence of graph neural networks (GNNs) has offered a powerful tool for semi-supervised node classification tasks. Subsequent studies have achieved further improvements through refining the message passing schemes in GNN models or exploiting various data augmentation techniques to mitigate limited supervision. In real graphs, nodes often tend to form tightly-knit communities/clusters, which embody abundant signals for compensating label scarcity in semi-supervised node classification but are not explored in prior methods. Inspired by this, this paper presents NCGC that integrates self-supervised graph clustering and semi-supervised classification into a unified framework. Firstly, we theoretically unify the optimization objectives of GNNs and spectral graph clustering, and based on that, develop soft orthogonal GNNs (SOGNs) that leverage a refined message passing paradigm to generate node representations for both classification and clustering. On top of that, NCGC includes a self-supervised graph clustering module that enables the training of SOGNs for learning representations of unlabeled nodes in a self-supervised manner. Particularly, this component comprises two non-trivial clustering objectives and a Sinkhorn-Knopp normalization that transforms predicted cluster assignments into balanced soft pseudo-labels. Through combining the foregoing clustering module with the classification model using a multi-task objective containing the supervised classification loss on labeled data and self-supervised clustering loss on unlabeled data, NCGC promotes synergy between them and achieves enhanced model capacity. Our extensive experiments showcase that the proposed NCGC framework consistently and considerably outperforms popular GNN models and recent baselines for semi-supervised node classification on seven real graphs, when working with various classic GNN backbones.
Authors: Aras Bacho, Aleksei G. Sorokin, Xianjin Yang, Th\'eo Bourdais, Edoardo Calvello, Matthieu Darcy, Alexander Hsu, Bamdad Hosseini, Houman Owhadi
Abstract: Neural operator learning methods have garnered significant attention in scientific computing for their ability to approximate infinite-dimensional operators. However, increasing their complexity often fails to substantially improve their accuracy, leaving them on par with much simpler approaches such as kernel methods and more traditional reduced-order models. In this article, we set out to address this shortcoming and introduce CHONKNORIS (Cholesky Newton--Kantorovich Neural Operator Residual Iterative System), an operator learning paradigm that can achieve machine precision. CHONKNORIS draws on numerical analysis: many nonlinear forward and inverse PDE problems are solvable by Newton-type methods. Rather than regressing the solution operator itself, our method regresses the Cholesky factors of the elliptic operator associated with Tikhonov-regularized Newton--Kantorovich updates. The resulting unrolled iteration yields a neural architecture whose machine-precision behavior follows from achieving a contractive map, requiring far lower accuracy than end-to-end approximation of the solution operator. We benchmark CHONKNORIS on a range of nonlinear forward and inverse problems, including a nonlinear elliptic equation, Burgers' equation, a nonlinear Darcy flow problem, the Calder\'{o}n problem, an inverse wave scattering problem, and a problem from seismic imaging. We also present theoretical guarantees for the convergence of CHONKNORIS in terms of the accuracy of the emulated Cholesky factors. Additionally, we introduce a foundation model variant, FONKNORIS (Foundation Newton--Kantorovich Neural Operator Residual Iterative System), which aggregates multiple pre-trained CHONKNORIS experts for diverse PDEs to emulate the solution map of a novel nonlinear PDE. Our FONKNORIS model is able to accurately solve unseen nonlinear PDEs such as the Klein--Gordon and Sine--Gordon equations.
Authors: Haoran Zheng, Renchi Yang, Yubo Zhou, Jianliang Xu
Abstract: Message passing neural networks (MPNNs) have emerged as go-to models for learning on graph-structured data in the past decade. Despite their effectiveness, most of such models still incur severe issues such as over-smoothing and -correlation, due to their underlying objective of minimizing the Dirichlet energy and the derived neighborhood aggregation operations. In this paper, we propose the DDSM, a new MPNN model built on an optimization framework that includes the stress majorization and orthogonal regularization for overcoming the above issues. Further, we introduce the diffusion distances for nodes into the framework to guide the new message passing operations and develop efficient algorithms for distance approximations, both backed by rigorous theoretical analyses. Our comprehensive experiments showcase that DDSM consistently and considerably outperforms 15 strong baselines on both homophilic and heterophilic graphs.
Authors: Lianming Huang, Haibo Hu, Qiao Li, Nan Guan, Chun Jason Xue
Abstract: Sparsity is essential for deploying large models on resource constrained edge platforms. However, optimizing sparsity patterns for individual tasks in isolation ignores the significant I/O overhead incurred during frequent task switching. We introduce an on-demand multi-task sparsity framework specifically designed to minimize switching costs by maximizing parameter reuse. Unlike monolithic approaches, we decompose weights into reusable block-granular units and align sparse structures across tasks to maximize overlap. By dynamically loading only the small differential set of blocks required for the next task, our method effectively mitigates the cold-start latency inherent in traditional monolithic approaches.Experiments on a real-world autonomous driving platform demonstrate that our framework achieves superior switching efficiency, accelerating task switching by over 6.6X on average compared to existing sparsity methods.
Authors: Dishanika Denipitiyage, Naveen Karunanayake, Suranga Seneviratne, Sanjay Chawla
Abstract: We propose RankOOD, a rank-based Out-of-Distribution (OOD) detection approach based on training a model with the Placket-Luce loss, which is now extensively used for preference alignment tasks in foundational models. Our approach is based on the insight that with a deep learning model trained using the Cross Entropy Loss, in-distribution (ID) class prediction induces a ranking pattern for each ID class prediction. The RankOOD framework formalizes the insight by first extracting a rank list for each class using an initial classifier and then uses another round of training with the Plackett-Luce loss, where the class rank, a fixed permutation for each class, is the predicted variable. An OOD example may get assigned with high probability to an ID example, but the probability of it respecting the ranking classification is likely to be small. RankOOD, achieves SOTA performance on the near-ODD TinyImageNet evaluation benchmark, reducing FPR95 by 4.3%.
Authors: Nikit Phadke
Abstract: REWA introduces a general theory of similarity based on witness-overlap structures. We show that whenever similarity between concepts can be expressed as monotone witness overlap -- whether arising from graph neighborhoods, causal relations, temporal structure, topological features, symbolic patterns, or embedding-based neighborhoods -- it admits a reduction to compact encodings with provable ranking preservation guarantees. REWA systems consist of: (1) finite witness sets $W(v)$, (2) semi-random bit assignments generated from each witness, and (3) monotonicity of expected similarity in the overlap $\Delta(u, v) = |W(u) \cap W(v)|$. We prove that under an overlap-gap condition on the final witness sets -- independent of how they were constructed -- top-$k$ rankings are preserved using $m = O(\log(|V|/\delta))$ bits. The witness-set formulation is compositional: any sequence of structural, temporal, causal, topological, information-theoretic, or learned transformations can be combined into pipelines that terminate in discrete witness sets. The theory applies to the final witness overlap, enabling modular construction of similarity systems from reusable primitives. This yields a vast design space: millions of composable similarity definitions inherit logarithmic encoding complexity. REWA subsumes and unifies Bloom filters, minhash, LSH bitmaps, random projections, sketches, and hierarchical filters as special cases. It provides a principled foundation for similarity systems whose behavior is governed by witness overlap rather than hash-function engineering. This manuscript presents the axioms, the main reducibility theorem, complete proofs with explicit constants, and a detailed discussion of compositional design, limitations, and future extensions including multi-bit encodings, weighted witnesses, and non-set representations.
Authors: Peining Zhang, Hongchen Qin, Haochen Zhang, Ziqi Guo, Guiling Wang, Jinbo Bi
Abstract: This work investigates the zero-shot forecasting capability of time-series foundation models for Leaf Area Index (LAI) forecasting in agricultural monitoring. Using the HiQ dataset (U.S., 2000-2022), we systematically compare statistical baselines, a fully supervised LSTM, and the Sundial foundation model under multiple evaluation protocols. We find that Sundial, in the zero-shot setting, can outperform a fully trained LSTM provided that the input context window is sufficiently long-specifically, when covering more than one or two full seasonal cycles. This demonstrates, for the first time, that a general-purpose foundation model can surpass specialized supervised models on remote-sensing time series prediction without any task-specific tuning. These results highlight the strong potential of pretrained time-series foundation models to serve as effective plug-and-play forecasters in agricultural and environmental applications.
Authors: Xiucheng Wang, Tingwei Yuan, Yang Cao, Nan Cheng, Ruijin Sun, Weihua Zhuang
Abstract: Radio maps (RMs) serve as environment-aware electromagnetic (EM) representations that connect scenario geometry and material properties to the spatial distribution of signal strength, enabling localization without costly in-situ measurements. However, constructing high-fidelity indoor RMs remains challenging due to the prohibitive latency of EM solvers and the limitations of learning-based methods, which often rely on sparse measurements or assumptions of homogeneous material, which are misaligned with the heterogeneous and multipath-rich nature of indoor environments. To overcome these challenges, we propose iRadioDiff, a sampling-free diffusion-based framework for indoor RM construction. iRadioDiff is conditioned on access point (AP) positions, and physics-informed prompt encoded by material reflection and transmission coefficients. It further incorporates multipath-critical priors, including diffraction points, strong transmission boundaries, and line-of-sight (LoS) contours, to guide the generative process via conditional channels and boundary-weighted objectives. This design enables accurate modeling of nonstationary field discontinuities and efficient construction of physically consistent RMs. Experiments demonstrate that iRadioDiff achieves state-of-the-art performance in indoor RM construction and received signal strength based indoor localization, which offers effective generalization across layouts and material configurations. Code is available at https://github.com/UNIC-Lab/iRadioDiff.
Authors: Haoran Zheng, Renchi Yang, Hongtao Wang, Jianliang Xu
Abstract: Multimodal Attributed Graphs (MMAGs) are an expressive data model for representing the complex interconnections among entities that associate attributes from multiple data modalities (text, images, etc.). Clustering over such data finds numerous practical applications in real scenarios, including social community detection, medical data analytics, etc. However, as revealed by our empirical studies, existing multi-view clustering solutions largely rely on the high correlation between attributes across various views and overlook the unique characteristics (e.g., low modality-wise correlation and intense feature-wise noise) of multimodal attributes output by large pre-trained language and vision models in MMAGs, leading to suboptimal clustering performance. Inspired by foregoing empirical observations and our theoretical analyses with graph signal processing, we propose the Dual Graph Filtering (DGF) scheme, which innovatively incorporates a feature-wise denoising component into node representation learning, thereby effectively overcoming the limitations of traditional graph filters adopted in the extant multi-view graph clustering approaches. On top of that, DGF includes a tri-cross contrastive training strategy that employs instance-level contrastive learning across modalities, neighborhoods, and communities for learning robust and discriminative node representations. Our comprehensive experiments on eight benchmark MMAG datasets exhibit that DGF is able to outperform a wide range of state-of-the-art baselines consistently and significantly in terms of clustering quality measured against ground-truth labels.
Authors: PengYu Chen, Xiaohou Shi, Yuan Chang, Yan Sun, Sajal K. Das
Abstract: The proactive prediction of anomalies (AP) in mul- tivariate time series (MTS) is a critical challenge to ensure system dependability. The difficulty lies in identifying subtle anomaly precursors concealed within normal signals. However, existing unsupervised methods, trained exclusively on normal data, demonstrate a fundamental propensity to reconstruct normal patterns. Consequently, when confronted with weak precursors, their predictions are dominated by the normal pattern, submerging the very signal required for prediction. To contend with the limitation, we propose RED-F, a Reconstruction- Elimination based Dual-stream Contrastive Forecasting frame- work, comprising the Reconstruction-Elimination Model (REM) and the Dual-stream Contrastive Forecasting Model (DFM). The REM utilizes a hybrid time-frequency mechanism to mitigate the precursor, generating a purified, normal-pattern baseline. The DFM then receives this purified baseline and the original sequence which retains the precursor as parallel inputs. At the core of our framework, RED-F employs a contrastive forecast that transforms the difficult task of absolute signal detection into a simpler, more robust task of relative trajectory comparison by computing the divergence between these two predictive streams. This contrastive mechanism serves to amplify the faint precursor signal. Furthermore, the DFM is trained with a novel Multi-Series Prediction (MSP) objective, which leverages distant future con- text to enhance its predictive sensitivity. Extensive experiments on six real-world datasets demonstrate the superior capability of RED-F in anomaly prediction tasks.
Authors: Bhavya Sukhija, Lenart Treven, Carmelo Sferrazza, Florian D\"orfler, Pieter Abbeel, Andreas Krause
Abstract: We address the challenge of efficient exploration in model-based reinforcement learning (MBRL), where the system dynamics are unknown and the RL agent must learn directly from online interactions. We propose Scalable and Optimistic MBRL (SOMBRL), an approach based on the principle of optimism in the face of uncertainty. SOMBRL learns an uncertainty-aware dynamics model and greedily maximizes a weighted sum of the extrinsic reward and the agent's epistemic uncertainty. SOMBRL is compatible with any policy optimizers or planners, and under common regularity assumptions on the system, we show that SOMBRL has sublinear regret for nonlinear dynamics in the (i) finite-horizon, (ii) discounted infinite-horizon, and (iii) non-episodic settings. Additionally, SOMBRL offers a flexible and scalable solution for principled exploration. We evaluate SOMBRL on state-based and visual-control environments, where it displays strong performance across all tasks and baselines. We also evaluate SOMBRL on a dynamic RC car hardware and show SOMBRL outperforms the state-of-the-art, illustrating the benefits of principled exploration for MBRL.
Authors: Lei Huang, Rui Zhang, Jiaming Guo, Yang Zhang, Di Huang, Shuyao Cheng, Pengwei Jin, Chongxiao Li, Zidong Du, Xing Hu, Qi Guo, Yunji Chen
Abstract: Large language models (LLMs) have shown promising capabilities in hardware description language (HDL) generation. However, existing approaches often rely on free-form natural language descriptions that are often ambiguous, redundant, and unstructured, which poses significant challenges for downstream Verilog code generation. We treat hardware code generation as a complex transformation from an open-ended natural language space to a domain-specific, highly constrained target space. To bridge this gap, we introduce Core Refined Understanding eXpression (CRUX), a structured intermediate space that captures the essential semantics of user intent while organizing the expression for precise Verilog code generation. We further design a two-stage training framework, comprising Joint Expression Modeling and Dual-Space Optimization, to enhance the quality of both CRUX and Verilog code. Experiments across multiple Verilog generation benchmarks demonstrate that our model, CRUX-V, achieves state-of-the-art performance among general models, particularly under challenging design tasks. Furthermore, the CRUX space proves transferable and beneficial when used as input prompts for other code models, highlighting its effectiveness in narrowing the gap between free-form natural language descriptions and precise Verilog generation.
Authors: Craig Dickson
Abstract: Prior work has shown that fine-tuning models on a narrow domain with misaligned data can lead to broad misalignment - a phenomenon termed "emergent misalignment" (Betley et al. 2025). While all tested models were susceptible to emergent misalignment, some models showed more resistance than others. Specifically the Qwen-2.5 family proved to be relatively resistant, while GPT-4o exhibited the strongest misalignment. In this paper we evaluate if current-generation open-weights models exhibit similar resistance to the Qwen-2.5 family and measure misalignment robustness over a range of model architectures and scales. We replicate the effect across nine modern open-weights models (Gemma 3 and Qwen 3 families, 1B-32B parameters). Models fine-tuned on insecure code generation show a 0.68% misalignment rate (compared to 0.07% for base models), matching the lower end of prior open-model results but dramatically lower than GPT-4o's 20%. We identify a critical format-dependent vulnerability: requiring JSON output doubles misalignment rates compared to natural language prompts (0.96% vs 0.42%). This suggests that structural constraints may bypass safety training by reducing the model's 'degrees of freedom' to refuse. These findings confirm emergent misalignment as a reproducible phenomenon in modern open-weights models, with rates substantially lower than observed in proprietary systems.
Authors: Grzegorz Dudek, Mateusz Kasprzyk, Pawe{\l} Pe{\l}ka
Abstract: This study investigates the application of the Light Gradient Boosting Machine (LGBM) model for both deterministic and probabilistic forecasting of Bitcoin realized volatility. Utilizing a comprehensive set of 69 predictors -- encompassing market, behavioral, and macroeconomic indicators -- we evaluate the performance of LGBM-based models and compare them with both econometric and machine learning baselines. For probabilistic forecasting, we explore two quantile-based approaches: direct quantile regression using the pinball loss function, and a residual simulation method that transforms point forecasts into predictive distributions. To identify the main drivers of volatility, we employ gain-based and permutation feature importance techniques, consistently highlighting the significance of trading volume, lagged volatility measures, investor attention, and market capitalization. The results demonstrate that LGBM models effectively capture the nonlinear and high-variance characteristics of cryptocurrency markets while providing interpretable insights into the underlying volatility dynamics.
Authors: Hyeonjae Kim, Chenyue Li, Wen Deng, Mengxi Jin, Wen Huang, Mengqian Lu, Binhang Yuan
Abstract: Climate science demands automated workflows to transform comprehensive questions into data-driven statements across massive, heterogeneous datasets. However, generic LLM agents and static scripting pipelines lack climate-specific context and flexibility, thus, perform poorly in practice. We present ClimateAgent, an autonomous multi-agent framework that orchestrates end-to-end climate data analytic workflows. ClimateAgent decomposes user questions into executable sub-tasks coordinated by an Orchestrate-Agent and a Plan-Agent; acquires data via specialized Data-Agents that dynamically introspect APIs to synthesize robust download scripts; and completes analysis and reporting with a Coding-Agent that generates Python code, visualizations, and a final report with a built-in self-correction loop. To enable systematic evaluation, we introduce Climate-Agent-Bench-85, a benchmark of 85 real-world tasks spanning atmospheric rivers, drought, extreme precipitation, heat waves, sea surface temperature, and tropical cyclones. On Climate-Agent-Bench-85, ClimateAgent achieves 100% task completion and a report quality score of 8.32, outperforming GitHub-Copilot (6.27) and a GPT-5 baseline (3.26). These results demonstrate that our multi-agent orchestration with dynamic API awareness and self-correcting execution substantially advances reliable, end-to-end automation for climate science analytic tasks.
Authors: Aleksei Samarin, Artem Nazarenko, Egor Kotenko, Valentin Malykh, Alexander Savelev, Aleksei Toropov
Abstract: This paper presents a novel approach to neural network compression that addresses redundancy at both the filter and architectural levels through a unified framework grounded in information flow analysis. Building on the concept of tensor flow divergence, which quantifies how information is transformed across network layers, we develop a two-stage optimization process. The first stage employs iterative divergence-aware pruning to identify and remove redundant filters while preserving critical information pathways. The second stage extends this principle to higher-level architecture optimization by analyzing layer-wise contributions to information propagation and selectively eliminating entire layers that demonstrate minimal impact on network performance. The proposed method naturally adapts to diverse architectures, including convolutional networks, transformers, and hybrid designs, providing a consistent metric for comparing the structural importance across different layer types. Experimental validation across multiple modern architectures and datasets reveals that this combined approach achieves substantial model compression while maintaining competitive accuracy. The presented approach achieves parameter reduction results that are globally comparable to those of state-of-the-art solutions and outperforms them across a wide range of modern neural network architectures, from convolutional models to transformers. The results demonstrate how flow divergence serves as an effective guiding principle for both filter-level and layer-level optimization, offering practical benefits for deployment in resource-constrained environments.
Authors: Riccardo Zaccone, Sai Praneeth Karimireddy, Carlo Masone
Abstract: Recent works have explored the use of momentum in local methods to enhance distributed SGD. This is particularly appealing in Federated Learning (FL), where momentum intuitively appears as a solution to mitigate the effects of statistical heterogeneity. Despite recent progress in this direction, it is still unclear if momentum can guarantee convergence under unbounded heterogeneity in decentralized scenarios, where only some workers participate at each round. In this work we analyze momentum under cyclic client participation, and theoretically prove that it remains inevitably affected by statistical heterogeneity. Similarly to SGD, we prove that decreasing step-sizes do not help either: in fact, any schedule decreasing faster than $\Theta\left(1/t\right)$ leads to convergence to a constant value that depends on the initialization and the heterogeneity bound. Numerical results corroborate the theory, and deep learning experiments confirm its relevance for realistic settings.
Authors: Bruno Belucci, Karim Lounici, Katia Meziani
Abstract: Neural networks struggle on small tabular datasets, where tree-based models remain dominant. We introduce Adaptive Contrastive Approach (AdaCap), a training scheme that combines a permutation-based contrastive loss with a Tikhonov-based closed-form output mapping. Across 85 real-world regression datasets and multiple architectures, AdaCap yields consistent and statistically significant improvements in the small-sample regime, particularly for residual models. A meta-predictor trained on dataset characteristics (size, skewness, noise) accurately anticipates when AdaCap is beneficial. These results show that AdaCap acts as a targeted regularization mechanism, strengthening neural networks precisely where they are most fragile. All results and code are publicly available at https://github.com/BrunoBelucci/adacap.
Authors: Lincen Yang, Zhong Li, Matthijs van Leeuwen, Saber Salehkaleybar
Abstract: Discovering subgroups with the maximum average treatment effect is crucial for targeted decision making in domains such as precision medicine, public policy, and education. While most prior work is formulated in the potential outcome framework, the corresponding structural causal model (SCM) for this task has been largely overlooked. In practice, two approaches dominate. The first estimates pointwise conditional treatment effects and then fits a tree on those estimates, effectively turning subgroup estimation into the harder problem of accurate pointwise estimation. The second constructs decision trees or rule sets with ad-hoc 'causal' heuristics, typically without rigorous justification for why a given heuristic may be used or whether such heuristics are necessary at all. We address these issues by studying the problem directly under the SCM framework. Under the assumption of a partition-based model, we show that optimal subgroup discovery reduces to recovering the data-generating models and hence a standard supervised learning problem (regression or classification). This allows us to adopt any partition-based methods to learn the subgroup from data. We instantiate the approach with CART, arguably one of the most widely used tree-based methods, to learn the subgroup with maximum treatment effect. Finally, on a large collection of synthetic and semi-synthetic datasets, we compare our method against a wide range of baselines and find that our approach, which avoids such causal heuristics, more accurately identifies subgroups with maximum treatment effect. Our source code is available at https://github.com/ylincen/causal-subgroup.
Authors: Wei Chen, Jingxi Yu, Zichen Miao, Qiang Qiu
Abstract: Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target problems by inferring compositional rules from context examples, which are composed of basic components structured by underlying rules. However, some of these tasks remain challenging for Transformers, which are not inherently designed to handle compositional tasks and offer limited structural inductive bias. In this work, inspired by the principle of sparse coding, we propose a reformulation of the attention to enhance its capability for compositional tasks. In sparse coding, data are represented as sparse combinations of dictionary atoms with coefficients that capture their compositional rules. Specifically, we reinterpret the attention block as a mapping of inputs into outputs through projections onto two sets of learned dictionary atoms: an encoding dictionary and a decoding dictionary. The encoding dictionary decomposes the input into a set of coefficients, which represent the compositional structure of the input. To enhance structured representations, we impose sparsity on these coefficients. The sparse coefficients are then used to linearly combine the decoding dictionary atoms to generate the output. Furthermore, to assist compositional generalization tasks, we propose estimating the coefficients of the target problem as a linear combination of the coefficients obtained from the context examples. We demonstrate the effectiveness of our approach on the S-RAVEN and RAVEN datasets. For certain compositional generalization tasks, our method maintains performance even when standard Transformers fail, owing to its ability to learn and apply compositional rules.
Authors: Ruxandra-Stefania Tudose, Moritz H. W. Gr\"uss, Grace Ra Kim, Karl H. Johansson, Nicola Bastianello
Abstract: Satellite constellations in low-Earth orbit are now widespread, enabling positioning, Earth imaging, and communications. In this paper we address the solution of learning problems using these satellite constellations. In particular, we focus on a federated approach, where satellites collect and locally process data, with the ground station aggregating local models. We focus on designing a novel, communication-efficient algorithm that still yields accurate trained models. To this end, we employ several mechanisms to reduce the number of communications with the ground station (local training) and their size (compression). We then propose an error feedback mechanism that enhances accuracy, which yields, as a byproduct, an algorithm-agnostic error feedback scheme that can be more broadly applied. We analyze the convergence of the resulting algorithm, and compare it with the state of the art through simulations in a realistic space scenario, showcasing superior performance.
Authors: Lian Shen, Zhendan Chen, Yinhui jiang, Meijia Song, Ziming Su, Juan Liu, Xiangrong Liu
Abstract: In critical web applications such as e-commerce and recommendation systems, multimodal graphs integrating rich visual and textual attributes are increasingly central, yet their large scale introduces substantial computational burdens for training Graph Neural Networks (GNNs). While Graph Condensation (GC) offers a promising solution by synthesizing smaller datasets, existing methods falter in the multimodal setting. We identify a dual challenge causing this failure: (1) conflicting gradients arising from semantic misalignments between modalities, and (2) the GNN's message-passing architecture pathologically amplifying this gradient noise across the graph structure. To address this, we propose Structurally-Regularized Gradient Matching (SR-GM), a novel condensation framework tailored for multimodal graphs. SR-GM introduces two synergistic components: first, a gradient decoupling mechanism that resolves inter-modality conflicts at their source via orthogonal projection; and second, a structural damping regularizer that acts directly on the gradient field. By leveraging the graph's Dirichlet energy, this regularizer transforms the topology from a noise amplifier into a stabilizing force during optimization. Extensive experiments demonstrate that SR-GM significantly improves accuracy and accelerates convergence compared to baseline methods. Ablation studies confirm that addressing both gradient conflict and structural amplification in tandem is essential for achieving superior performance. Moreover, the condensed multimodal graphs exhibit strong cross-architecture generalization and promise to accelerate applications like Neural Architecture Search. This research provides a scalable methodology for multimodal graph-based learning in resource-constrained environments.
Authors: Bo Han, Zhuoming Li, Xiaoyu Wang, Yaxin Hou, Hui Liu, Junhui Hou, Yuheng Jia
Abstract: Semi-supervised multi-label learning (SSMLL) aims to address the challenge of limited labeled data in multi-label learning (MLL) by leveraging unlabeled data to improve the model's performance. While pseudo-labeling has become a dominant strategy in SSMLL, most existing methods assign equal weights to all pseudo-labels regardless of their quality, which can amplify the impact of noisy or uncertain predictions and degrade the overall performance. In this paper, we theoretically verify that the optimal weight for a pseudo-label should reflect its correctness likelihood. Empirically, we observe that on the same dataset, the correctness likelihood distribution of unlabeled data remains stable, even as the number of labeled training samples varies. Building on this insight, we propose Distribution-Calibrated Pseudo-labeling (DiCaP), a correctness-aware framework that estimates posterior precision to calibrate pseudo-label weights. We further introduce a dual-thresholding mechanism to separate confident and ambiguous regions: confident samples are pseudo-labeled and weighted accordingly, while ambiguous ones are explored by unsupervised contrastive learning. Experiments conducted on multiple benchmark datasets verify that our method achieves consistent improvements, surpassing state-of-the-art methods by up to 4.27%.
Authors: Olivier Moulin, Vincent Francois-lavet, Paul Elbers, Mark Hoogendoorn
Abstract: Generalizability of Reinforcement Learning (RL) agents (ability to perform on environments different from the ones they have been trained on) is a key problem as agents have the tendency to overfit to their training environments. In order to address this problem and offer a solution to increase the generalizability of RL agents, we introduce a new methodology to predict the generalizability score of RL agents based on the internal weights of the agent's neural networks. Using this prediction capability, we propose some changes in the Proximal Policy Optimization (PPO) loss function to boost the generalization score of the agents trained with this upgraded version. Experimental results demonstrate that our improved PPO algorithm yields agents with stronger generalizability compared to the original version.
Authors: Zhiguo Zhang, Xiaoliang Ma, Daniel Schlesinger
Abstract: Accurate and interpretable air pollution forecasting is crucial for public health, but most models face a trade-off between performance and interpretability. This study proposes a physics-guided, interpretable-by-design spatiotemporal learning framework. The model decomposes the spatiotemporal behavior of air pollutant concentrations into two transparent, additive modules. The first is a physics-guided transport kernel with directed weights conditioned on wind and geography (advection). The second is an explainable attention mechanism that learns local responses and attributes future concentrations to specific historical lags and exogenous drivers. Evaluated on a comprehensive dataset from the Stockholm region, our model consistently outperforms state-of-the-art baselines across multiple forecasting horizons. Our model's integration of high predictive performance and spatiotemporal interpretability provides a more reliable foundation for operational air-quality management in real-world applications.
Authors: Areeb Ahmad, Abhinav Joshi, Ashutosh Modi
Abstract: Transformer-based language models exhibit complex and distributed behavior, yet their internal computations remain poorly understood. Existing mechanistic interpretability methods typically treat attention heads and multilayer perceptron layers (MLPs) (the building blocks of a transformer architecture) as indivisible units, overlooking possibilities of functional substructure learned within them. In this work, we introduce a more fine-grained perspective that decomposes these components into orthogonal singular directions, revealing superposed and independent computations within a single head or MLP. We validate our perspective on widely used standard tasks like Indirect Object Identification (IOI), Gender Pronoun (GP), and Greater Than (GT), showing that previously identified canonical functional heads, such as the name mover, encode multiple overlapping subfunctions aligned with distinct singular directions. Nodes in a computational graph, that are previously identified as circuit elements show strong activation along specific low-rank directions, suggesting that meaningful computations reside in compact subspaces. While some directions remain challenging to interpret fully, our results highlight that transformer computations are more distributed, structured, and compositional than previously assumed. This perspective opens new avenues for fine-grained mechanistic interpretability and a deeper understanding of model internals.
Authors: Yiheng Zhang, Shaowu Wu, Yuanzhuo Xu, Jiajun Wu, Shang Xu, Steve Drew, Xiaoguang Niu
Abstract: Adaptive optimizers such as Adam have achieved great success in training large-scale models like large language models and diffusion models. However, they often generalize worse than non-adaptive methods, such as SGD on classical architectures like CNNs. We identify a key cause of this performance gap: adaptivity in pre-conditioners, which limits the optimizer's ability to adapt to diverse optimization landscapes. To address this, we propose Anon (Adaptivity Non-restricted Optimizer with Novel convergence technique), a novel optimizer with continuously tunable adaptivity , allowing it to interpolate between SGD-like and Adam-like behaviors and even extrapolate beyond both. To ensure convergence across the entire adaptivity spectrum, we introduce incremental delay update (IDU), a novel mechanism that is more flexible than AMSGrad's hard max-tracking strategy and enhances robustness to gradient noise. We theoretically establish convergence guarantees under both convex and non-convex settings. Empirically, Anon consistently outperforms state-of-the-art optimizers on representative image classification, diffusion, and language modeling tasks. These results demonstrate that adaptivity can serve as a valuable tunable design principle, and Anon provides the first unified and reliable framework capable of bridging the gap between classical and modern optimizers and surpassing their advantageous properties.
Authors: Abhinav Joshi, Divyanshu Bhatt, Ashutosh Modi
Abstract: Large Language Models (LLMs) show strong generalization across diverse tasks, yet the internal decision-making processes behind their predictions remain opaque. In this work, we study the geometry of hidden representations in LLMs through the lens of \textit{intrinsic dimension} (ID), focusing specifically on decision-making dynamics in a multiple-choice question answering (MCQA) setting. We perform a large-scale study, with 28 open-weight transformer models and estimate ID across layers using multiple estimators, while also quantifying per-layer performance on MCQA tasks. Our findings reveal a consistent ID pattern across models: early layers operate on low-dimensional manifolds, middle layers expand this space, and later layers compress it again, converging to decision-relevant representations. Together, these results suggest LLMs implicitly learn to project linguistic inputs onto structured, low-dimensional manifolds aligned with task-specific decisions, providing new geometric insights into how generalization and reasoning emerge in language models.
Authors: Michael Kilgour, Mark E. Tuckerman, Jutta Rogal
Abstract: We present MXtalTools, a flexible Python package for the data-driven modelling of molecular crystals, facilitating machine learning studies of the molecular solid state. MXtalTools comprises several classes of utilities: (1) synthesis, collation, and curation of molecule and crystal datasets, (2) integrated workflows for model training and inference, (3) crystal parameterization and representation, (4) crystal structure sampling and optimization, (5) end-to-end differentiable crystal sampling, construction and analysis. Our modular functions can be integrated into existing workflows or combined and used to build novel modelling pipelines. MXtalTools leverages CUDA acceleration to enable high-throughput crystal modelling. The Python code is available open-source on our GitHub page, with detailed documentation on ReadTheDocs.
Authors: Chang Gao, Chujie Zheng, Xiong-Hui Chen, Kai Dang, Shixuan Liu, Bowen Yu, An Yang, Shuai Bai, Jingren Zhou, Junyang Lin
Abstract: Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often exhibit high variance-a phenomenon exacerbated in Mixture-of-Experts models-leading to unstable updates. Existing group-based policy optimization methods, such as GSPO and GRPO, alleviate this problem via hard clipping, making it difficult to maintain both stability and effective learning. We propose Soft Adaptive Policy Optimization (SAPO), which replaces hard clipping with a smooth, temperature-controlled gate that adaptively attenuates off-policy updates while preserving useful learning signals. Compared with GSPO and GRPO, SAPO is both sequence-coherent and token-adaptive. Like GSPO, SAPO maintains sequence-level coherence, but its soft gating forms a continuous trust region that avoids the brittle hard clipping band used in GSPO. When a sequence contains a few highly off-policy tokens, GSPO suppresses all gradients for that sequence, whereas SAPO selectively down-weights only the offending tokens and preserves the learning signal from the near-on-policy ones, improving sample efficiency. Relative to GRPO, SAPO replaces hard token-level clipping with smooth, temperature-controlled scaling, enabling more informative and stable updates. Empirical results on mathematical reasoning benchmarks indicate that SAPO exhibits improved training stability and higher Pass@1 performance under comparable training budgets. Moreover, we employ SAPO to train the Qwen3-VL model series, demonstrating that SAPO yields consistent performance gains across diverse tasks and different model sizes. Overall, SAPO provides a more reliable, scalable, and effective optimization strategy for RL training of LLMs.
Authors: M. E. A. Kherchouche, F. Galpin, T. Dumas, F. Schnitzler, D. Menard, L. Zhang
Abstract: In this paper, a complexity study is conducted for Versatile Video Codec (VVC) intra partitioning to accelerate the exhaustive search involved in Rate-Distortion Optimization (RDO) process. To address this problem, two main machine learning techniques are proposed and compared. Unlike existing methods, the proposed approaches are size independent and incorporate the Rate-Distortion (RD) costs of neighboring blocks as input features. The first method is a regression based technique that predicts normalized RD costs of a given Coding Unit (CU). As partitioning possesses the Markov property, the associated decision-making problem can be modeled as a Markov Decision Process (MDP) and solved by Reinforcement Learning (RL). The second approach is a RL agent learned from trajectories of CU decision across two depths with Deep Q-Network (DQN) algorithm. Then a pre-determined thresholds are applied for both methods to select a suitable split for the current CU.
Authors: \`Alex Sol\'e, Albert Mosella-Montoro, Joan Cardona, Daniel Aravena, Silvia G\'omez-Coca, Eliseo Ruiz, Javier Ruiz-Hidalgo
Abstract: Crystal structures are characterised by repeating atomic patterns within unit cells across three-dimensional space, posing unique challenges for graph-based representation learning. Current methods often overlook essential periodic boundary conditions and multiscale interactions inherent to crystalline structures. In this paper, we introduce PRISM, a graph neural network framework that explicitly integrates multiscale representations and periodic feature encoding by employing a set of expert modules, each specialised in encoding distinct structural and chemical aspects of periodic systems. Extensive experiments across crystal structure-based benchmarks demonstrate that PRISM improves state-of-the-art predictive accuracy, significantly enhancing crystal property prediction.
Authors: Audrey Pei-Hsuan Chen
Abstract: Representation learning on multi-omics data is challenging due to extreme dimensionality, modality heterogeneity, and cohort-specific batch effects. While pre-trained transformer backbones have shown broad generalization capabilities in biological sequence modeling, their application to multi-omics integration remains underexplored. We present MoRE (Multi-Omics Representation Embedding), a framework that repurposes frozen pre-trained transformers to align heterogeneous assays into a shared latent space. Unlike purely generative approaches, MoRE employs a parameter-efficient fine-tuning (PEFT) strategy, prioritizing cross-sample and cross-modality alignment over simple sequence reconstruction. Specifically, MoRE attaches lightweight, modality-specific adapters and a task-adaptive fusion layer to the frozen backbone. It optimizes a masked modeling objective jointly with supervised contrastive and batch-invariant alignment losses, yielding structure-preserving embeddings that generalize across unseen cell types and platforms. We benchmark MoRE against established baselines, including scGPT, scVI, and Harmony with scArches, evaluating integration fidelity, rare population detection, and modality transfer. Our results demonstrate that MoRE achieves competitive batch robustness and biological conservation while significantly reducing trainable parameters compared to fully fine-tuned models. This work positions MoRE as a practical step toward general-purpose omics foundation models.
Authors: M. C. Schoppema, B. H. M. van der Velden, A. H\"urriyeto\u{g}lu, M. D. Klijnstra, E. J. Faassen, A. Gerssen, H. J. van der Fels-Klerx
Abstract: Since 2012, tetrodotoxin (TTX) has been found in seafoods such as bivalve mollusks in temperate European waters. TTX contamination leads to food safety risks and economic losses, making early prediction of TTX contamination vital to the food industry and competent authorities. Recent studies have pointed to shallow habitats and water temperature as main drivers to TTX contamination in bivalve mollusks. However, the temporal relationships between abiotic factors, biotic factors, and TTX contamination remain unexplored. We have developed an explainable, deep learning-based model to predict TTX contamination in the Dutch Zeeland estuary. Inputs for the model were meteorological and hydrological features; output was the presence or absence of TTX contamination. Results showed that the time of sunrise, time of sunset, global radiation, water temperature, and chloride concentration contributed most to TTX contamination. Thus, the effective number of sun hours, represented by day length and global radiation, was an important driver for tetrodotoxin contamination in bivalve mollusks. To conclude, our explainable deep learning model identified the aforementioned environmental factors (number of sun hours, global radiation, water temperature, and water chloride concentration) to be associated with tetrodotoxin contamination in bivalve mollusks; making our approach a valuable tool to mitigate marine toxin risks for food industry and competent authorities.
Authors: Jo\"el Charles-Rebuff\'e, Nicolas Gast, Bruno Gaujal
Abstract: We present BLINQ, a new model-based algorithm that learns the Whittle indices of an indexable, communicating and unichain Markov Decision Process (MDP). Our approach relies on building an empirical estimate of the MDP and then computing its Whittle indices using an extended version of a state-of-the-art existing algorithm. We provide a proof of convergence to the Whittle indices we want to learn as well as a bound on the time needed to learn them with arbitrary precision. Moreover, we investigate its computational complexity. Our numerical experiments suggest that BLINQ significantly outperforms existing Q-learning approaches in terms of the number of samples needed to get an accurate approximation. In addition, it has a total computational cost even lower than Q-learning for any reasonably high number of samples. These observations persist even when the Q-learning algorithms are speeded up using pre-trained neural networks to predict Q-values.
Authors: Yaaqov Mishayev, Yonatan Sverdlov, Tal Amir, Nadav Dym
Abstract: Message Passing Neural Networks (MPNNs) are widely used for learning on graphs, but their ability to process long-range information is limited by the phenomenon of oversquashing. This limitation has led some researchers to advocate Graph Transformers as a better alternative, whereas others suggest that it can be mitigated within the MPNN framework, using virtual nodes or other rewiring techniques. In this work, we demonstrate that oversquashing is not limited to long-range tasks, but can also arise in short-range problems. This observation allows us to disentangle two distinct mechanisms underlying oversquashing: (1) the bottleneck phenomenon, which can arise even in low-range settings, and (2) the vanishing gradient phenomenon, which is closely associated with long-range tasks. We further show that the short-range bottleneck effect is not captured by existing explanations for oversquashing, and that adding virtual nodes does not resolve it. In contrast, transformers do succeed in such tasks, positioning them as the more compelling solution to oversquashing, compared to specialized MPNNs.
Authors: Kasper Green Larsen, Natascha Schalburg
Abstract: We prove the first margin-based generalization bound for voting classifiers, that is asymptotically tight in the tradeoff between the size of the hypothesis set, the margin, the fraction of training points with the given margin, the number of training samples and the failure probability.
Authors: Misha Padidar, Teresa Huang, Andrew Giuliani, Marina Spivak
Abstract: Stellarators are a prospective class of fusion-based power plants that confine a hot plasma with three-dimensional magnetic fields. Typically framed as a PDE-constrained optimization problem, stellarator design is a time-consuming process that can take hours to solve on a computing cluster. Developing fast methods for designing stellarators is crucial for advancing fusion research. Given the recent development of large datasets of optimized stellarators, machine learning approaches have emerged as a potential candidate. Motivated by this, we present an open inverse problem to the machine learning community: to rapidly generate high-quality stellarator designs which have a set of desirable characteristics. As a case study in the problem space, we train a conditional diffusion model on data from the QUASR database to generate quasisymmetric stellarator designs with desirable characteristics (aspect ratio and mean rotational transform). The diffusion model is applied to design stellarators with characteristics not seen during training. We provide evaluation protocols and show that many of the generated stellarators exhibit solid performance: less than 5% deviation from quasisymmetry and the target characteristics. The modest deviation from quasisymmetry highlights an opportunity to reach the sub 1% target. Beyond the case study, we share multiple promising avenues for generative modeling to advance stellarator design.
Authors: Shreevanth Krishnaa Gopalakrishnan, Stephen Hailes
Abstract: Machine learning has become integral to Channel State Information (CSI)-based human sensing systems and is expected to power applications such as device-free activity recognition and identity detection in future cellular and Wi-Fi generations. However, these systems rely on models whose decisions can be subtly perturbed, raising concerns for security and reliability in ubiquitous sensing. Quantifying and understanding the robustness of such models, defined as their ability to maintain accurate predictions under adversarial perturbations, is therefore critical before wireless sensing can be safely deployed in real-world environments. This work presents a systematic evaluation of the robustness of CSI deep learning models under diverse threat models (white-box, black-box/transfer, and universal perturbations) and varying degrees of attack realism. We establish a framework to compare compact temporal autoencoder models with larger deep architectures across three public datasets, quantifying how model scale, training regime, and physical constraints influence robustness. Our experiments show that smaller models, while efficient and equally performant on clean data, are markedly less robust. We further confirm that physically realizable signal-space perturbations, designed to be feasible in real wireless channels, significantly reduce attack success compared to unconstrained feature-space attacks. Adversarial training mitigates these vulnerabilities, improving mean robust accuracy with only moderate degradation in clean performance across both model classes. As wireless sensing advances towards reliable, cross-domain operation, these findings provide quantitative baselines for robustness estimation and inform design principles for secure and trustworthy human-centered sensing systems.
Authors: Kateryna Chumachenko, Amala Sanjay Deshmukh, Jarno Seppanen, Ilia Karmanov, Chia-Chih Chen, Lukas Voegtle, Philipp Fischer, Marek Wawrzos, Saeid Motiian, Roman Ageev, Kedi Wu, Alexandre Milesi, Maryam Moosaei, Krzysztof Pawelec, Padmavathy Subramanian, Mehrzad Samadi, Xin Yu, Celina Dear, Sarah Stoddard, Jenna Diamond, Jesse Oliver, Leanna Chraghchian, Patrick Skelly, Tom Balough, Yao Xu, Jane Polak Scowcroft, Daniel Korzekwa, Darragh Hanley, Sandip Bhaskar, Timo Roman, Karan Sapra, Andrew Tao, Bryan Catanzaro
Abstract: We introduce Nemotron-Parse-1.1, a lightweight document parsing and OCR model that advances the capabilities of its predecessor, Nemoretriever-Parse-1.0. Nemotron-Parse-1.1 delivers improved capabilities across general OCR, markdown formatting, structured table parsing, and text extraction from pictures, charts, and diagrams. It also supports a longer output sequence length for visually dense documents. As with its predecessor, it extracts bounding boxes of text segments, as well as corresponding semantic classes. Nemotron-Parse-1.1 follows an encoder-decoder architecture with 885M parameters, including a compact 256M-parameter language decoder. It achieves competitive accuracy on public benchmarks making it a strong lightweight OCR solution. We release the model weights publicly on Huggingface, as well as an optimized NIM container, along with a subset of the training data as part of the broader Nemotron-VLM-v2 dataset. Additionally, we release Nemotron-Parse-1.1-TC which operates on a reduced vision token length, offering a 20% speed improvement with minimal quality degradation.
Authors: Sidahmed Benabderrahmane, James Cheney, Talal Rahwan
Abstract: Advanced Persistent Threats (APTs) pose a significant challenge in cybersecurity due to their stealthy and long-term nature. Modern supervised learning methods require extensive labeled data, which is often scarce in real-world cybersecurity environments. In this paper, we propose an innovative approach that leverages AutoEncoders for unsupervised anomaly detection, augmented by active learning to iteratively improve the detection of APT anomalies. By selectively querying an oracle for labels on uncertain or ambiguous samples, we minimize labeling costs while improving detection rates, enabling the model to improve its detection accuracy with minimal data while reducing the need for extensive manual labeling. We provide a detailed formulation of the proposed Attention Adversarial Dual AutoEncoder-based anomaly detection framework and show how the active learning loop iteratively enhances the model. The framework is evaluated on real-world imbalanced provenance trace databases produced by the DARPA Transparent Computing program, where APT-like attacks constitute as little as 0.004\% of the data. The datasets span multiple operating systems, including Android, Linux, BSD, and Windows, and cover two attack scenarios. The results have shown significant improvements in detection rates during active learning and better performance compared to other existing approaches.
Authors: Kiril Vasilev, Alexandre Misrahi, Eeshaan Jain, Phil F Cheng, Petros Liakopoulos, Olivier Michielin, Michael Moor, Charlotte Bunne
Abstract: Multimodal Large Language Models (LLMs) hold promise for biomedical reasoning, but current benchmarks fail to capture the complexity of real-world clinical workflows. Existing evaluations primarily assess unimodal, decontextualized question-answering, overlooking multi-agent decision-making environments such as Molecular Tumor Boards (MTBs). MTBs bring together diverse experts in oncology, where diagnostic and prognostic tasks require integrating heterogeneous data and evolving insights over time. Current benchmarks lack this longitudinal and multimodal complexity. We introduce MTBBench, an agentic benchmark simulating MTB-style decision-making through clinically challenging, multimodal, and longitudinal oncology questions. Ground truth annotations are validated by clinicians via a co-developed app, ensuring clinical relevance. We benchmark multiple open and closed-source LLMs and show that, even at scale, they lack reliability -- frequently hallucinating, struggling with reasoning from time-resolved data, and failing to reconcile conflicting evidence or different modalities. To address these limitations, MTBBench goes beyond benchmarking by providing an agentic framework with foundation model-based tools that enhance multi-modal and longitudinal reasoning, leading to task-level performance gains of up to 9.0% and 11.2%, respectively. Overall, MTBBench offers a challenging and realistic testbed for advancing multimodal LLM reasoning, reliability, and tool-use with a focus on MTB environments in precision oncology.
Authors: Sidahmed Benabderrahmane, Talal Rahwan
Abstract: Advanced Persistent Threats (APT) pose a major cybersecurity challenge due to their stealth, persistence, and adaptability. Traditional machine learning detectors struggle with class imbalance, high dimensional features, and scarce real world traces. They often lack transferability-performing well in the training domain but degrading in novel attack scenarios. We propose a hybrid transfer framework that integrates Transfer Learning, Explainable AI (XAI), contrastive learning, and Siamese networks to improve cross-domain generalization. An attention-based autoencoder supports knowledge transfer across domains, while Shapley Additive exPlanations (SHAP) select stable, informative features to reduce dimensionality and computational cost. A Siamese encoder trained with a contrastive objective aligns source and target representations, increasing anomaly separability and mitigating feature drift. We evaluate on real-world traces from the DARPA Transparent Computing (TC) program and augment with synthetic attack scenarios to test robustness. Across source to target transfers, the approach delivers improved detection scores with classical and deep baselines, demonstrating a scalable, explainable, and transferable solution for APT detection.
Authors: Mihaela Hudi\c{s}teanu, Edwige Cyffers, Nikita P. Kalinin
Abstract: Adaptive optimizers are the de facto standard in non-private training as they often enable faster convergence and improved performance. In contrast, differentially private (DP) training is still predominantly performed with DP-SGD, typically requiring extensive compute and hyperparameter tuning. We propose DP-MicroAdam, a memory-efficient and sparsity-aware adaptive DP optimizer. We prove that DP-MicroAdam converges in stochastic non-convex optimization at the optimal $\mathcal{O}(1/\sqrt{T})$ rate, up to privacy-dependent constants. Empirically, DP-MicroAdam outperforms existing adaptive DP optimizers and achieves competitive or superior accuracy compared to DP-SGD across a range of benchmarks, including CIFAR-10, large-scale ImageNet training, and private fine-tuning of pretrained transformers. These results demonstrate that adaptive optimization can improve both performance and stability under differential privacy.
Authors: Sam Laing, Antonio Orvieto
Abstract: The Adam optimizer is a cornerstone of modern deep learning, yet the empirical necessity of each of its individual components is often taken for granted. This paper presents a focused investigation into the role of bias-correction, a feature whose contribution remains poorly understood. Through a series of systematic ablations on vision and language modelling tasks, we demonstrate that the conventional wisdom surrounding bias correction is misleading. In particular, we demonstrate that in the optimal hyper-parameter configuration, the inclusion of bias correction leads to no improvement in final test performance. Moreover, unless appropriate learning rate scheduling is implemented, the inclusion of bias correction can sometimes be detrimental to performance. We further reinterpret bias correction as a form of implicit learning rate scheduling whose behaviour is strongly dependent on the choice of smoothing hyper-parameters $\beta_1, \beta_2 \in [0,1)$. Our findings challenge the universal inclusion of this component.
Authors: Alhasan Abdellatif, Hannah P. Menke, Ahmed H. Elsheikh, Florian Doster, Kamaljit Singh
Abstract: The UNet-enhanced Fourier Neural Operator (UFNO) extends the Fourier Neural Operator (FNO) by incorporating a parallel UNet pathway, enabling the retention of both high- and low-frequency components. While UFNO improves predictive accuracy over FNO, it inefficiently treats scalar inputs (e.g., temperature, injection rate) as spatially distributed fields by duplicating their values across the domain. This forces the model to process redundant constant signals within the frequency domain. Additionally, its standard loss function does not account for spatial variations in error sensitivity, limiting performance in regions of high physical importance. We introduce UFNO-FiLM, an enhanced architecture that incorporates two key innovations. First, we decouple scalar inputs from spatial features using a Feature-wise Linear Modulation (FiLM) layer, allowing the model to modulate spatial feature maps without introducing constant signals into the Fourier transform. Second, we employ a spatially weighted loss function that prioritizes learning in critical regions. Our experiments on subsurface multiphase flow demonstrate a 21\% reduction in gas saturation Mean Absolute Error (MAE) compared to UFNO, highlighting the effectiveness of our approach in improving predictive accuracy.
Authors: Rui Xue, Shichao Zhu, Liang Qin, Guangmou Pan, Yang Song, Tianfu Wu
Abstract: Graph Neural Networks (GNNs) have emerged as powerful tools for modeling graph-structured data and have been widely used in recommender systems, such as for capturing complex user-item and item-item relations. However, most industrial deployments adopt a two-stage pipeline: GNNs are first pre-trained offline to generate node embeddings, which are then used as static features for downstream recommender systems. This decoupled paradigm leads to two key limitations: (1) high computational overhead, since large-scale GNN inference must be repeatedly executed to refresh embeddings; and (2) lack of joint optimization, as the gradient from the recommender system cannot directly influence the GNN learning process, causing the GNN to be suboptimally informative for the recommendation task. In this paper, we propose E2E-GRec, a novel end-to-end training framework that unifies GNN training with the recommender system. Our framework is characterized by three key components: (i) efficient subgraph sampling from a large-scale cross-domain heterogeneous graph to ensure training scalability and efficiency; (ii) a Graph Feature Auto-Encoder (GFAE) serving as an auxiliary self-supervised task to guide the GNN to learn structurally meaningful embeddings; and (iii) a two-level feature fusion mechanism combined with Gradnorm-based dynamic loss balancing, which stabilizes graph-aware multi-task end-to-end training. Extensive offline evaluations, online A/B tests (e.g., a +0.133% relative improvement in stay duration, a 0.3171% reduction in the average number of videos a user skips) on large-scale production data, together with theoretical analysis, demonstrate that E2E-GRec consistently surpasses traditional approaches, yielding significant gains across multiple recommendation metrics.
Authors: Sumit S Shevtekar, Chandresh K Maurya, Gourab Sil
Abstract: Real-world time-series data is highly non stationary and complex in dynamics that operate across multiple timescales, ranging from fast, short-term changes to slow, long-term trends. Most existing models rely on fixed-scale structural priors, such as patch-based tokenization, fixed frequency transformations, or frozen backbone architectures. This often leads to over-regularization of temporal dynamics, which limits their ability to adaptively model the full spectrum of temporal variations and impairs their performance on unpredictable, Sudden, high-magnitude events. To address this, we introduce the Multi-scale Temporal Network (MSTN), a novel deep learning architecture founded on a hierarchical multi-scale and sequence modeling principle. The MSTN framework integrates: (i) a multi-scale convolutional encoder that constructs a hierarchical feature pyramid for local patterns (ii) a sequence modeling component for long-range temporal dependencies. We empirically validate this with BiLSTM and Transformer variants, establishing a flexible foundation for future architectural advancements. and (iii) a gated fusion mechanism augmented with squeeze-and-excitation (SE) and multi-head temporal attention (MHTA) for dynamic, context-aware feature integration. This design enables MSTN to adaptively model temporal patterns from milliseconds to long-range dependencies within a unified framework. Extensive evaluations across time-series long-horizon forecasting, imputation, classification and generalizability study demonstrate that MSTN achieves competitive state-of-the-art (SOTA) performance, showing improvements over contemporary approaches including EMTSF, LLM4TS, HiMTM, TIME-LLM, MTST, SOFTS, iTransformer, TimesNet, and PatchTST. In total, MSTN establishes new SOTA performance on 24 of 32 benchmark datasets, demonstrating its consistent performance across diverse temporal tasks.
Authors: Shuo Xie, Tianhao Wang, Beining Wu, Zhiyuan Li
Abstract: Adaptive optimizers can reduce to normalized steepest descent (NSD) when only adapting to the current gradient, suggesting a close connection between the two algorithmic families. A key distinction between their analyses, however, lies in the geometries, e.g., smoothness notions, they rely on. In the convex setting, adaptive optimizers are governed by a stronger adaptive smoothness condition, while NSD relies on the standard notion of smoothness. We extend the theory of adaptive smoothness to the nonconvex setting and show that it precisely characterizes the convergence of adaptive optimizers. Moreover, we establish that adaptive smoothness enables acceleration of adaptive optimizers with Nesterov momentum in the convex setting, a guarantee unattainable under standard smoothness for certain non-Euclidean geometry. We further develop an analogous comparison for stochastic optimization by introducing adaptive gradient variance, which parallels adaptive smoothness and leads to dimension-free convergence guarantees that cannot be achieved under standard gradient variance for certain non-Euclidean geometry.
Authors: Karim Kadry, Abdallah Abdelwahed, Shoaib Goraya, Ajay Manicka, Naravich Chutisilp, Farhad Nezami, Elazer Edelman
Abstract: We present Anatomica: an inference-time framework for generating multi-class anatomical voxel maps with localized geo-topological control. During generation, we use cuboidal control domains of varying dimensionality, location, and shape to slice out relevant substructures. These local substructures are used to compute differentiable penalty functions that steer the sample towards target constraints. We control geometric features such as size, shape, and position through voxel-wise moments, while topological features such as connected components, loops, and voids are enforced through persistent homology. Lastly, we implement Anatomica for latent diffusion models, where neural field decoders partially extract substructures, enabling the efficient control of anatomical properties. Anatomica applies flexibly across diverse anatomical systems, composing constraints to control complex structures over arbitrary dimensions and coordinate systems, thereby enabling the rational design of synthetic datasets for virtual trials or machine learning workflows.
Authors: Charlotte Beylier, Hannah Selder, Arthur Fleig, Simon M. Hofmann, Nico Scherf
Abstract: The learning process of a reinforcement learning (RL) agent remains poorly understood beyond the mathematical formulation of its learning algorithm. To address this gap, we introduce attention-oriented metrics (ATOMs) to investigate the development of an RL agent's attention during training. In a controlled experiment, we tested ATOMs on three variations of a Pong game, each designed to teach the agent distinct behaviours, complemented by a behavioural assessment. ATOMs successfully delineate the attention patterns of an agent trained on each game variation, and that these differences in attention patterns translate into differences in the agent's behaviour. Through continuous monitoring of ATOMs during training, we observed that the agent's attention developed in phases, and that these phases were consistent across game variations. Overall, we believe that ATOM could help improve our understanding of the learning processes of RL agents and better understand the relationship between attention and learning.
Authors: Mingxing Rao, Bowen Qu, Daniel Moyer
Abstract: The recovery of training data from generative models (``model inversion'') has been extensively studied for diffusion models in the data domain. The encoder/decoder pair and corresponding latent codes have largely been ignored by inversion techniques applied to latent space generative models, e.g., Latent Diffusion models (LDMs). In this work we describe two key findings: (1) The diffusion model exhibits non-uniform memorization across latent codes, tending to overfit samples located in high-distortion regions of the decoder pullback metric. (2) Even within a single latent code, different dimensions contribute unequally to memorization. We introduce a principled method to rank latent dimensions by their per-dimensional contribution to the decoder pullback metric, identifying those most responsible for memorization. Empirically, removing less-memorizing dimensions when computing attack statistics for score-based membership inference attacker significantly improves performance, with average AUROC gains of 2.7\% and substantial increases in TPR@1\%FPR (6.42\%) across diverse datasets including CIFAR-10, CelebA, ImageNet-1K, Pok\'emon, MS-COCO, and Flickr. This indicates stronger confidence in identifying members under extremely low false-positive tolerance. Our results highlight the overlooked influence of the auto-encoder geometry on LDM memorization and provide a new perspective for analyzing privacy risks in diffusion-based generative models.
Authors: Kaiyuan Zhang, Mark Tenenholtz, Kyle Polley, Jerry Ma, Denis Yarats, Ninghui Li
Abstract: The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web agents, yet the resulting impact within real-world environments remains insufficiently understood. In this work, we examine the landscape of prompt injection attacks and synthesize a benchmark of attacks embedded in realistic HTML payloads. Our benchmark goes beyond prior work by emphasizing injections that can influence real-world actions rather than mere text outputs, and by presenting attack payloads with complexity and distractor frequency similar to what real-world agents encounter. We leverage this benchmark to conduct a comprehensive empirical evaluation of existing defenses, assessing their effectiveness across a suite of frontier AI models. We propose a multi-layered defense strategy comprising both architectural and model-based defenses to protect against evolving prompt injection attacks. Our work offers a blueprint for designing practical, secure web agents through a defense-in-depth approach.
Authors: Heman Shakeri
Abstract: Deep sequence models for blood glucose forecasting consistently fail to leverage clinically informative drivers--insulin, meals, and activity--despite well-understood physiological mechanisms. We term this Driver-Blindness and formalize it via $\Delta_{\text{drivers}}$, the performance gain of multivariate models over matched univariate baselines. Across the literature, $\Delta_{\text{drivers}}$ is typically near zero. We attribute this to three interacting factors: architectural biases favoring autocorrelation (C1), data fidelity gaps that render drivers noisy and confounded (C2), and physiological heterogeneity that undermines population-level models (C3). We synthesize strategies that partially mitigate Driver-Blindness--including physiological feature encoders, causal regularization, and personalization--and recommend that future work routinely report $\Delta_{\text{drivers}}$ to prevent driver-blind models from being considered state-of-the-art.
Authors: Xiwen Huang, Pierre Pinson
Abstract: We introduce and analyse active learning markets as a way to purchase labels, in situations where analysts aim to acquire additional data to improve model fitting, or to better train models for predictive analytics applications. This comes in contrast to the many proposals that already exist to purchase features and examples. By originally formalising the market clearing as an optimisation problem, we integrate budget constraints and improvement thresholds into the label acquisition process. We focus on a single-buyer-multiple-seller setup and propose the use of two active learning strategies (variance based and query-by-committee based), paired with distinct pricing mechanisms. They are compared to a benchmark random sampling approach. The proposed strategies are validated on real-world datasets from two critical application domains: real estate pricing and energy forecasting. Results demonstrate the robustness of our approach, consistently achieving superior performance with fewer labels acquired compared to conventional methods. Our proposal comprises an easy-to-implement practical solution for optimising data acquisition in resource-constrained environments.
Authors: Shurong Wang, Yuqi Pan, Zhuoyang Shen, Meng Zhang, Hongwei Wang, Guoqi Li
Abstract: Associative memory models are content-addressable memory systems fundamental to biological intelligence and are notable for their high interpretability. However, existing models evaluate the quality of retrieval based on proximity, which cannot guarantee that the retrieved pattern has the strongest association with the query, failing correctness. We reframe this problem by proposing that a query is a generative variant of a stored memory pattern, and define a variant distribution to model this subtle context-dependent generative process. Consequently, correct retrieval should return the memory pattern with the maximum a posteriori probability of being the query's origin. This perspective reveals that an ideal similarity measure should approximate the likelihood of each stored pattern generating the query in accordance with variant distribution, which is impossible for fixed and pre-defined similarities used by existing associative memories. To this end, we develop adaptive similarity, a novel mechanism that learns to approximate this insightful but unknown likelihood from samples drawn from context, aiming for correct retrieval. We theoretically prove that our proposed adaptive similarity achieves optimal correct retrieval under three canonical and widely applicable types of variants: noisy, masked, and biased. We integrate this mechanism into a novel adaptive Hopfield network (A-Hop), and empirical results show that it achieves state-of-the-art performance across diverse tasks, including memory retrieval, tabular classification, image classification, and multiple instance learning.
Authors: Yujin Kim, Sarah Dean
Abstract: Many consequential real-world systems, like wind fields and ocean currents, are dynamic and hard to model. Learning their governing dynamics remains a central challenge in scientific machine learning. Dynamic Mode Decomposition (DMD) provides a simple, data-driven approximation, but practical use is limited by sparse/noisy observations from continuous fields, reliance on linear approximations, and the lack of principled uncertainty quantification. To address these issues, we introduce Stochastic NODE-DMD, a probabilistic extension of DMD that models continuous-time, nonlinear dynamics while remaining interpretable. Our approach enables continuous spatiotemporal reconstruction at arbitrary coordinates and quantifies predictive uncertainty. Across four benchmarks, a synthetic setting and three physics-based flows, it surpasses a baseline in reconstruction accuracy when trained from only 10% observation density. It further recovers the dynamical structure by aligning learned modes and continuous-time eigenvalues with ground truth. Finally, on datasets with multiple realizations, our method learns a calibrated distribution over latent dynamics that preserves ensemble variability rather than averaging across regimes. Our code is available at: https://github.com/sedan-group/Stochastic-NODE-DMD
Authors: Panayiotis Danassis, Naman Goel
Abstract: The rapid proliferation of Large Language Models (LLMs) has revolutionized AI-assisted code generation. This rapid development of LLMs has outpaced our ability to properly benchmark them. Prevailing benchmarks emphasize unit-test pass rates and syntactic correctness. Such metrics understate the difficulty of many real-world problems that require planning, optimization, and strategic interaction. We introduce a multi-agent reasoning-driven benchmark based on a real-world logistics optimization problem (Auction, Pickup, and Delivery Problem) that couples competitive auctions with capacity-constrained routing. The benchmark requires building agents that can (i) bid strategically under uncertainty and (ii) optimize planners that deliver tasks while maximizing profit. We evaluate 40 LLM-coded agents (by a wide range of state-of-the-art LLMs under multiple prompting methodologies, including vibe coding) against 17 human-coded agents developed before the advent of LLMs. Our results over 12 double all-play-all tournaments and $\sim 40$k matches demonstrate (i) a clear superiority of human(graduate students)-coded agents: the top 5 spots are consistently won by human-coded agents, (ii) the majority of LLM-coded agents (33 out of 40) are beaten by very simple baselines, and (iii) given the best human solution as an input and prompted to improve upon, the best performing LLM makes the solution significantly worse instead of improving it. Our results highlight a gap in LLMs' ability to produce code that works competitively in the real-world, and motivate new evaluations that emphasize reasoning-driven code synthesis in real-world scenarios.
Authors: Adam Karvonen, Daniel Reuter, Roy Rinberg, Luke Marks, Adri\`a Garriga-Alonso, Keri Warr
Abstract: As demand for LLM inference grows, it is becoming increasingly important that providers and their customers can verify that inference processes are performed correctly, without errors or tampering. However, re-running the same inference process twice often leads to different results due to benign numerical noise, making it difficult to distinguish legitimate variation from actual problems. To address this problem, we introduce Token-DiFR (Token-Divergence-From-Reference), a method for verifying inference outputs by comparing generated tokens against predictions made by a trusted reference implementation conditioned on the same random seed. Sampling seed synchronization tightly constrains valid outputs, leaving providers minimal room to deviate from correct inference, which allows output tokens themselves to serve as auditable evidence of correctness at zero additional cost to the provider. Token-DiFR reliably identifies sampling errors, simulated bugs, and model quantization, detecting 4-bit quantization with AUC $>$ 0.999 within 300 output tokens. For applications requiring sample-efficient forward-pass verification, we additionally introduce Activation-DiFR, a scheme that uses random orthogonal projections to compress activations into compact fingerprints for subsequent verification. Activation-DiFR detects 4-bit quantization with AUC $>$ 0.999 using just 2 output tokens, while reducing communication overhead by 25-75% relative to existing methods. We release an open-source integration with vLLM to accelerate practical deployment of verifiable inference.
Authors: Wei He, Kai Han, Hang Zhou, Hanting Chen, Zhicheng Liu, Xinghao Chen, Yunhe Wang
Abstract: The optimization of large language models (LLMs) remains a critical challenge, particularly as model scaling exacerbates sensitivity to algorithmic imprecision and training instability. Recent advances in optimizers have improved convergence efficiency through momentum orthogonalization, but suffer from two key robustness limitations: dimensional fragility in orthogonalization precision and vulnerability to outlier-induced noise. To address these robustness challenges, we introduce ROOT, a Robust Orthogonalized Optimizer that enhances training stability through dual robustness mechanisms. First, we develop a dimension-robust orthogonalization scheme using adaptive Newton iterations with fine-grained coefficients tailored to specific matrix sizes, ensuring consistent precision across diverse architectural configurations. Second, we introduce an optimization-robust framework via proximal optimization that suppresses outlier noise while preserving meaningful gradient directions. Extensive experiments demonstrate that ROOT achieves significantly improved robustness, with faster convergence and superior final performance compared to both Muon and Adam-based optimizers, particularly in noisy and non-convex scenarios. Our work establishes a new paradigm for developing robust and precise optimizers capable of handling the complexities of modern large-scale model training. The code will be available at https://github.com/huawei-noah/noah-research/tree/master/ROOT.
URLs: https://github.com/huawei-noah/noah-research/tree/master/ROOT.
Authors: Ziyue Wang, Yayati Jadhav, Peter Pak, Amir Barati Farimani
Abstract: Mechanical design and manufacturing workflows conventionally begin with conceptual design, followed by the creation of a computer-aided design (CAD) model and fabrication through material-extrusion (MEX) printing. This process requires converting CAD geometry into machine-readable G-code through slicing and path planning. While each step is well established, dependence on CAD modeling remains a major bottleneck: constructing object-specific 3D geometry is slow and poorly suited to rapid prototyping. Even minor design variations typically necessitate manual updates in CAD software, making iteration time-consuming and difficult to scale. To address this limitation, we introduce Image2Gcode, an end-to-end data-driven framework that bypasses the CAD stage and generates printer-ready G-code directly from images and part drawings. Instead of relying on an explicit 3D model, a hand-drawn or captured 2D image serves as the sole input. The framework first extracts slice-wise structural cues from the image and then employs a denoising diffusion probabilistic model (DDPM) over G-code sequences. Through iterative denoising, the model transforms Gaussian noise into executable print-move trajectories with corresponding extrusion parameters, establishing a direct mapping from visual input to native toolpaths. By producing structured G-code directly from 2D imagery, Image2Gcode eliminates the need for CAD or STL intermediates, lowering the entry barrier for additive manufacturing and accelerating the design-to-fabrication cycle. This approach supports on-demand prototyping from simple sketches or visual references and integrates with upstream 2D-to-3D reconstruction modules to enable an automated pipeline from concept to physical artifact. The result is a flexible, computationally efficient framework that advances accessibility in design iteration, repair workflows, and distributed manufacturing.
Authors: Wei Zhang, Jiajun Chu, Xinci Liu, Chen Tong, Xinyue Li
Abstract: Spatial Transcriptomics (ST) is a technology that measures gene expression profiles within tissue sections while retaining spatial context. It reveals localized gene expression patterns and tissue heterogeneity, both of which are essential for understanding disease etiology. However, its high cost has driven efforts to predict spatial gene expression from whole slide images. Despite recent advancements, current methods still face significant limitations, such as under-exploitation of high-level biological context, over-reliance on exemplar retrievals, and inadequate alignment of heterogeneous modalities. To address these challenges, we propose DKAN, a novel Dual-path Knowledge-Augmented contrastive alignment Network that predicts spatially resolved gene expression by integrating histopathological images and gene expression profiles through a biologically informed approach. Specifically, we introduce an effective gene semantic representation module that leverages the external gene database to provide additional biological insights, thereby enhancing gene expression prediction. Further, we adopt a unified, one-stage contrastive learning paradigm, seamlessly combining contrastive learning and supervised learning to eliminate reliance on exemplars, complemented with an adaptive weighting mechanism. Additionally, we propose a dual-path contrastive alignment module that employs gene semantic features as dynamic cross-modal coordinators to enable effective heterogeneous feature integration. Through extensive experiments across three public ST datasets, DKAN demonstrates superior performance over state-of-the-art models, establishing a new benchmark for spatial gene expression prediction and offering a powerful tool for advancing biological and clinical research.
Authors: Marcio Pohlmann, Alex Severo, Geft\'e Almeida, Diego Kreutz, Tiago Heinrich, Louren\c{c}o Pereira
Abstract: SOCs and CSIRTs face increasing pressure to automate incident categorization, yet the use of cloud-based LLMs introduces costs, latency, and confidentiality risks. We investigate whether locally executed SLMs can meet this challenge. We evaluated 21 models ranging from 1B to 20B parameters, varying the temperature hyperparameter and measuring execution time and precision across two distinct architectures. The results indicate that temperature has little influence on performance, whereas the number of parameters and GPU capacity are decisive factors.
Authors: Penghao Rao, Runmin Jiang, Min Xu
Abstract: Approximating training-point influence on test predictions is critical for deploying deep-learning vision models, essential for locating noisy data. Though the influence function was proposed for attributing how infinitesimal up-weighting or removal of individual training examples affects model outputs, its implementation is still challenging in deep-learning vision models: inverse-curvature computations are expensive, and training non-stationarity invalidates static approximations. Prior works use iterative solvers and low-rank surrogates to reduce cost, but offline computation lags behind training dynamics, and missing confidence calibration yields fragile rankings that misidentify critical examples. To address these challenges, we introduce a Stability-Guided Online Influence Framework (SG-OIF), the first framework that treats algorithmic stability as a real-time controller, which (i) maintains lightweight anchor IHVPs via stochastic Richardson and preconditioned Neumann; (ii) proposes modular curvature backends to modulate per-example influence scores using stability-guided residual thresholds, anomaly gating, and confidence. Experimental results show that SG-OIF achieves SOTA (State-Of-The-Art) on noise-label and out-of-distribution detection tasks across multiple datasets with various corruption. Notably, our approach achieves 91.1\% accuracy in the top 1\% prediction samples on the CIFAR-10 (20\% asym), and gets 99.8\% AUPR score on MNIST, effectively demonstrating that this framework is a practical controller for online influence estimation.
Authors: Blaise Ag\"uera y Arcas, Travis Beals, Maria Biggs, Jessica V. Bloom, Thomas Fischbacher, Konstantin Gromov, Urs K\"oster, Rishiraj Pravahan, James Manyika
Abstract: If AI is a foundational general-purpose technology, we should anticipate that demand for AI compute -- and energy -- will continue to grow. The Sun is by far the largest energy source in our solar system, and thus it warrants consideration how future AI infrastructure could most efficiently tap into that power. This work explores a scalable compute system for machine learning in space, using fleets of satellites equipped with solar arrays, inter-satellite links using free-space optics, and Google tensor processing unit (TPU) accelerator chips. To facilitate high-bandwidth, low-latency inter-satellite communication, the satellites would be flown in close proximity. We illustrate the basic approach to formation flight via a 81-satellite cluster of 1 km radius, and describe an approach for using high-precision ML-based models to control large-scale constellations. Trillium TPUs are radiation tested. They survive a total ionizing dose equivalent to a 5 year mission life without permanent failures, and are characterized for bit-flip errors. Launch costs are a critical part of overall system cost; a learning curve analysis suggests launch to low-Earth orbit (LEO) may reach $\lesssim$\$200/kg by the mid-2030s.
Authors: Jin Cui (State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University), Boran Zhao (School of Software Engineering, Xi'an Jiaotong University), Jiajun Xu (School of Software Engineering, Xi'an Jiaotong University), Jiaqi Guo (School of Mathematical Sciences, Nankai University), Shuo Guan (School of Software Engineering, Xi'an Jiaotong University), Pengju Ren (State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, and Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University)
Abstract: Coreset selection compresses large datasets into compact, representative subsets, reducing the energy and computational burden of training deep neural networks. Existing methods are either: (i) DNN-based, which are tied to model-specific parameters and introduce architectural bias; or (ii) DNN-free, which rely on heuristics lacking theoretical guarantees. Neither approach explicitly constrains distributional equivalence, largely because continuous distribution matching is considered inapplicable to discrete sampling. Moreover, prevalent metrics (e.g., MSE, KL, MMD, CE) cannot accurately capture higher-order moment discrepancies, leading to suboptimal coresets. In this work, we propose FAST, the first DNN-free distribution-matching coreset selection framework that formulates the coreset selection task as a graph-constrained optimization problem grounded in spectral graph theory and employs the Characteristic Function Distance (CFD) to capture full distributional information in the frequency domain. We further discover that naive CFD suffers from a "vanishing phase gradient" issue in medium and high-frequency regions; to address this, we introduce an Attenuated Phase-Decoupled CFD. Furthermore, for better convergence, we design a Progressive Discrepancy-Aware Sampling strategy that progressively schedules frequency selection from low to high, preserving global structure before refining local details and enabling accurate matching with fewer frequencies while avoiding overfitting. Extensive experiments demonstrate that FAST significantly outperforms state-of-the-art coreset selection methods across all evaluated benchmarks, achieving an average accuracy gain of 9.12%. Compared to other baseline coreset methods, it reduces power consumption by 96.57% and achieves a 2.2x average speedup, underscoring its high performance and energy efficiency.
Authors: Wanqi Wang, Chun Yang, Jianbo Shao, Yaokai Zhang, Xuehua Peng, Jin Sun, Chao Xiong, Long Lu, Lianting Hu
Abstract: Pediatric liver tumors are one of the most common solid tumors in pediatrics, with differentiation of benign or malignant status and pathological classification critical for clinical treatment. While pathological examination is the gold standard, the invasive biopsy has notable limitations: the highly vascular pediatric liver and fragile tumor tissue raise complication risks such as bleeding; additionally, young children with poor compliance require anesthesia for biopsy, increasing medical costs or psychological trauma. Although many efforts have been made to utilize AI in clinical settings, most researchers have overlooked its importance in pediatric liver tumors. To establish a non-invasive examination procedure, we developed a multi-stage deep learning (DL) framework for automated pediatric liver tumor diagnosis using multi-phase contrast-enhanced CT. Two retrospective and prospective cohorts were enrolled. We established a novel PKCP-MixUp data augmentation method to address data scarcity and class imbalance. We also trained a tumor detection model to extract ROIs, and then set a two-stage diagnosis pipeline with three backbones with ROI-masked images. Our tumor detection model has achieved high performance (mAP=0.871), and the first stage classification model between benign and malignant tumors reached an excellent performance (AUC=0.989). Final diagnosis models also exhibited robustness, including benign subtype classification (AUC=0.915) and malignant subtype classification (AUC=0.979). We also conducted multi-level comparative analyses, such as ablation studies on data and training pipelines, as well as Shapley-Value and CAM interpretability analyses. This framework fills the pediatric-specific DL diagnostic gap, provides actionable insights for CT phase selection and model design, and paves the way for precise, accessible pediatric liver tumor diagnosis.
Authors: Sangam Ghimire, Paribartan Timalsina, Nirjal Bhurtel, Bishal Neupane, Bigyan Byanju Shrestha, Subarna Bhattarai, Prajwal Gaire, Jessica Thapa, Sudan Jha
Abstract: As the demand grows for scalable and privacy-aware AI systems, Federated Learning (FL) has emerged as a promising solution, allowing decentralized model training without moving raw data. At the same time, the combination of high- performance computing (HPC) and cloud infrastructure offers vast computing power but introduces new complexities, especially when dealing with heteroge- neous hardware, communication limits, and non-uniform data. In this work, we present a federated learning framework built to run efficiently across mixed HPC and cloud environments. Our system addresses key challenges such as system het- erogeneity, communication overhead, and resource scheduling, while maintaining model accuracy and data privacy. Through experiments on a hybrid testbed, we demonstrate strong performance in terms of scalability, fault tolerance, and convergence, even under non-Independent and Identically Distributed (non-IID) data distributions and varied hardware. These results highlight the potential of federated learning as a practical approach to building scalable Artificial Intelligence (AI) systems in modern, distributed computing settings.
Authors: Randall Balestriero, Hugues Van Assel, Sami BuGhanem, Lucas Maes
Abstract: Foundation models and self-supervised learning (SSL) have become central to modern AI, yet research in this area remains hindered by complex codebases, redundant re-implementations, and the heavy engineering burden of scaling experiments. We present stable-pretraining, a modular, extensible, and performance-optimized library built on top of PyTorch, Lightning, Hugging Face, and TorchMetrics. Unlike prior toolkits focused narrowly on reproducing state-of-the-art results, stable-pretraining is designed for flexibility and iteration speed: it unifies essential SSL utilities--including probes, collapse detection metrics, augmentation pipelines, and extensible evaluation routines--within a coherent and reliable framework. A central design principle is logging everything, enabling fine-grained visibility into training dynamics that makes debugging, monitoring, and reproducibility seamless. We validate the library by demonstrating its ability to generate new research insights with minimal overhead, including depthwise representation probing and the analysis of CLIP degradation under synthetic data finetuning. By lowering barriers to entry while remaining scalable to large experiments, stable-pretraining aims to accelerate discovery and expand the possibilities of foundation model research.
Authors: Hou Hei Lam, Jiangjie Qiu, Xiuyuan Hu, Wentao Li, Fankun Zeng, Siwei Fu, Hao Zhang, Xiaonan Wang
Abstract: Organic photovoltaic (OPV) materials offer a promising path toward sustainable energy generation, but their development is limited by the difficulty of identifying high performance donor and acceptor pairs with strong power conversion efficiencies (PCEs). Existing design strategies typically focus on either the donor or the acceptor alone, rather than using a unified approach capable of modeling both components. In this work, we introduce a dual machine learning framework for OPV discovery that combines predictive modeling with generative molecular design. We present the Organic Photovoltaic Donor Acceptor Dataset (OPV2D), the largest curated dataset of its kind, containing 2000 experimentally characterized donor acceptor pairs. Using this dataset, we develop the Organic Photovoltaic Classifier (OPVC) to predict whether a material exhibits OPV behavior, and a hierarchical graph neural network that incorporates multi task learning and donor acceptor interaction modeling. This framework includes the Molecular Orbital Energy Estimator (MOE2) for predicting HOMO and LUMO energy levels, and the Photovoltaic Performance Predictor (P3) for estimating PCE. In addition, we introduce the Material Generative Pretrained Transformer (MatGPT) to produce synthetically accessible organic semiconductors, guided by a reinforcement learning strategy with three objective policy optimization. By linking molecular representation learning with performance prediction, our framework advances data driven discovery of high performance OPV materials.
Authors: Zhaoqi Xu, Yingying Zhang, Jian Li, Jianwei Guo, Qiannan Zhu, Hua Huang
Abstract: Recent advances in vision-language models (VLMs) have shown remarkable performance across multimodal tasks, yet their ever-growing scale poses severe challenges for deployment and efficiency. Existing compression methods often rely on heuristic importance metrics or empirical pruning rules, lacking theoretical guarantees about information preservation. In this work, we propose InfoPrune, an information-theoretic framework for adaptive structural compression of VLMs. Grounded in the Information Bottleneck principle, we formulate pruning as a trade-off between retaining task-relevant semantics and discarding redundant dependencies. To quantify the contribution of each attention head, we introduce an entropy-based effective rank (eRank) and employ the Kolmogorov--Smirnov (KS) distance to measure the divergence between original and compressed structures. This yields a unified criterion that jointly considers structural sparsity and informational efficiency. Building on this foundation, we further design two complementary schemes: (1) a training-based head pruning guided by the proposed information loss objective, and (2) a training-free FFN compression via adaptive low-rank approximation. Extensive experiments on VQAv2, TextVQA, and GQA demonstrate that InfoPrune achieves up to 3.2x FLOP reduction and 1.8x acceleration with negligible performance degradation, establishing a theoretically grounded and practically effective step toward efficient multimodal large models.
Authors: Mathis Wolter, Julie Stephany Berrio Perez, Mao Shan
Abstract: Detecting driver drowsiness reliably is crucial for enhancing road safety and supporting advanced driver assistance systems (ADAS). We introduce the Eyelid Angle (ELA), a novel, reproducible metric of eye openness derived from 3D facial landmarks. Unlike conventional binary eye state estimators or 2D measures, such as the Eye Aspect Ratio (EAR), the ELA provides a stable geometric description of eyelid motion that is robust to variations in camera angle. Using the ELA, we design a blink detection framework that extracts temporal characteristics, including the closing, closed, and reopening durations, which are shown to correlate with drowsiness levels. To address the scarcity and risk of collecting natural drowsiness data, we further leverage ELA signals to animate rigged avatars in Blender 3D, enabling the creation of realistic synthetic datasets with controllable noise, camera viewpoints, and blink dynamics. Experimental results in public driver monitoring datasets demonstrate that the ELA offers lower variance under viewpoint changes compared to EAR and achieves accurate blink detection. At the same time, synthetic augmentation expands the diversity of training data for drowsiness recognition. Our findings highlight the ELA as both a reliable biometric measure and a powerful tool for generating scalable datasets in driver state monitoring.
Authors: Il\'an Carretero, Roshni Mahtani, Silvia Perez-Deben, Jos\'e Francisco Gonz\'alez-Mu\~noz, Carlos Monteagudo, Valery Naranjo, Roc\'io del Amor
Abstract: Accurate diagnosis of spitzoid tumors (ST) is critical to ensure a favorable prognosis and to avoid both under- and over-treatment. Epigenetic data, particularly DNA methylation, provide a valuable source of information for this task. However, prior studies assume complete data, an unrealistic setting as methylation profiles frequently contain missing entries due to limited coverage and experimental artifacts. Our work challenges these favorable scenarios and introduces ReMAC, an extension of ReMasker designed to tackle classification tasks on high-dimensional data under complete and incomplete regimes. Evaluation on real clinical data demonstrates that ReMAC achieves strong and robust performance compared to competing classification methods in the stratification of ST. Code is available: https://github.com/roshni-mahtani/ReMAC.
Authors: Muhao Guo, Yang Weng
Abstract: The rapid expansion of distributed photovoltaic (PV) systems poses challenges for power grid management, as many installations remain undocumented. While satellite imagery provides global coverage, traditional computer vision (CV) models such as CNNs and U-Nets require extensive labeled data and fail to generalize across regions. This study investigates the cross-domain generalization of a multimodal large language model (LLM) for global PV assessment. By leveraging structured prompts and fine-tuning, the model integrates detection, localization, and quantification within a unified schema. Cross-regional evaluation using the $\Delta$F1 metric demonstrates that the proposed model achieves the smallest performance degradation across unseen regions, outperforming conventional CV and transformer baselines. These results highlight the robustness of multimodal LLMs under domain shift and their potential for scalable, transferable, and interpretable global PV mapping.
Authors: Ehsan Karimi, Nhut Le, Maryam Rahnemoonfar
Abstract: Timely and accurate assessment of damages following natural disasters is essential for effective emergency response and recovery. Recent AI-based frameworks have been developed to analyze large volumes of aerial imagery collected by Unmanned Aerial Vehicles, providing actionable insights rapidly. However, creating and annotating data for training these models is costly and time-consuming, resulting in datasets that are limited in size and diversity. Furthermore, most existing approaches rely on traditional classification-based frameworks with fixed answer spaces, restricting their ability to provide new information without additional data collection or model retraining. Using pre-trained generative models built on in-context learning (ICL) allows for flexible and open-ended answer spaces. However, these models often generate hallucinated outputs or produce generic responses that lack domain-specific relevance. To address these limitations, we propose ThiFAN-VQA, a two-stage reasoning-based framework for visual question answering (VQA) in disaster scenarios. ThiFAN-VQA first generates structured reasoning traces using chain-of-thought (CoT) prompting and ICL to enable interpretable reasoning under limited supervision. A subsequent answer selection module evaluates the generated responses and assigns the most coherent and contextually accurate answer, effectively improve the model performance. By integrating a custom information retrieval system, domain-specific prompting, and reasoning-guided answer selection, ThiFAN-VQA bridges the gap between zero-shot and supervised methods, combining flexibility with consistency. Experiments on FloodNet and RescueNet-VQA, UAV-based datasets from flood- and hurricane-affected regions, demonstrate that ThiFAN-VQA achieves superior accuracy, interpretability, and adaptability for real-world post-disaster damage assessment tasks.
Authors: Mohammed Talha Alam, Nada Saadi, Fahad Shamshad, Nils Lukas, Karthik Nandakumar, Fahkri Karray, Samuele Poppi
Abstract: Text-to-image diffusion models can emit copyrighted, unsafe, or private content. Safety alignment aims to suppress specific concepts, yet evaluations seldom test whether safety persists under benign downstream fine-tuning routinely applied after deployment (e.g., LoRA personalization, style/domain adapters). We study the stability of current safety methods under benign fine-tuning and observe frequent breakdowns. As true safety alignment must withstand even benign post-deployment adaptations, we introduce the SPQR benchmark (Safety-Prompt adherence-Quality-Robustness). SPQR is a single-scored metric that provides a standardized and reproducible framework to evaluate how well safety-aligned diffusion models preserve safety, utility, and robustness under benign fine-tuning, by reporting a single leaderboard score to facilitate comparisons. We conduct multilingual, domain-specific, and out-of-distribution analyses, along with category-wise breakdowns, to identify when safety alignment fails after benign fine-tuning, ultimately showcasing SPQR as a concise yet comprehensive benchmark for T2I safety alignment techniques for T2I models.
Authors: Jared N. Lakhani, Etienne Pienaar
Abstract: This study investigates the limitations of applying Markov Chain Monte Carlo (MCMC) methods to arbitrary objective functions, focusing on a two-block MCMC framework which alternates between Metropolis-Hastings and Gibbs sampling. While such approaches are often considered advantageous for enabling data-driven regularization, we show that their performance critically depends on the sharpness of the employed likelihood form. By introducing a sharpness parameter and exploring alternative likelihood formulations proportional to the target objective function, we demonstrate how likelihood curvature governs both in-sample performance and the degree of regularization inferred by the training data. Empirical applications are conducted on reinforcement learning tasks: including a navigation problem and the game of tic-tac-toe. The study concludes with a separate analysis examining the implications of extreme likelihood sharpness on arbitrary objective functions stemming from the classic game of blackjack, where the first block of the two-block MCMC framework is replaced with an iterative optimization step. The resulting hybrid approach achieves performance nearly identical to the original MCMC framework, indicating that excessive likelihood sharpness effectively collapses posterior mass onto a single dominant mode.
Authors: Abhi Chivukula, Jay Somasundaram, Vijay Somasundaram
Abstract: LLM-based coding agents are increasingly common but still face challenges in context management, latency, reliability, reproducibility, and scalability. We present Agint, an agentic graph compiler, interpreter, and runtime that incrementally and hierarchically converts natural-language instructions into typed, effect-aware code DAGs. Agint introduces explicit type floors (text to data to spec to code) grounded in semantic graph transformations and a hybrid LLM and function-based JIT runtime. This enables dynamic graph refinement, reproducible and optimizable execution, speculative evaluation, and interoperability with existing developer tools. Agint's typed graph bindings improve reliability and allow concurrent composition of concurrent codebases by construction, supporting accelerated development with smaller and faster models, lower latency, efficient context utilization, and higher throughput. Hierarchical compilation allows scalable graph edits, while the graph structure supports reproducibility and efficient parallel generation. Agint provides a composable unix-style toolchain: dagify (DAG compiler), dagent (hybrid JIT runtime), schemagin (schema generator), and datagin (data transformer) for realtime, low-latency code and dataflow creation. Human developers and coding agents refine graphs through the Agint CLI, while non-technical users use Agint Flow GUI for visual editing, conversational refinement, and debugging to promote prototype agentic workflows to production code. This continuous co-creation model allows teams to prototype quickly, refine seamlessly, and deploy reliably, bridging natural language, compiler methods, and developer tooling to enable a new generation of composable, team-centric coding agents at scale.
Authors: Angelo Gaspar Diniz Nogueira, Kayua Oleques Paim, Hendrio Bragan\c{c}a, Rodrigo Brand\~ao Mansilha, Diego Kreutz
Abstract: The ever-increasing number of Android devices and the accelerated evolution of malware, reaching over 35 million samples by 2024, highlight the critical importance of effective detection methods. Attackers are now using Artificial Intelligence to create sophisticated malware variations that can easily evade traditional detection techniques. Although machine learning has shown promise in malware classification, its success relies heavily on the availability of up-to-date, high-quality datasets. The scarcity and high cost of obtaining and labeling real malware samples presents significant challenges in developing robust detection models. In this paper, we propose MalSynGen, a Malware Synthetic Data Generation methodology that uses a conditional Generative Adversarial Network (cGAN) to generate synthetic tabular data. This data preserves the statistical properties of real-world data and improves the performance of Android malware classifiers. We evaluated the effectiveness of this approach using various datasets and metrics that assess the fidelity of the generated data, its utility in classification, and the computational efficiency of the process. Our experiments demonstrate that MalSynGen can generalize across different datasets, providing a viable solution to address the issues of obsolescence and low quality data in malware detection.
Authors: A. Massarenti, M. Mella
Abstract: We study neurovarieties for polynomial neural networks and fully characterize when they attain the expected dimension in the single-output case. As consequences, we establish non-defectiveness and global identifiability for multi-output architectures.
Authors: Mitchell Scott, Tianshi Xu, Ziyuan Tang, Alexandra Pichette-Emmons, Qiang Ye, Yousef Saad, Yuanzhe Xi
Abstract: Stochastic Gradient Descent (SGD) often slows in the late stage of training due to anisotropic curvature and gradient noise. We analyze preconditioned SGD in the geometry induced by a symmetric positive definite matrix $\mathbf{M}$, deriving bounds in which both the convergence rate and the stochastic noise floor are governed by $\mathbf{M}$-dependent quantities: the rate through an effective condition number in the $\mathbf{M}$-metric, and the floor through the product of that condition number and the preconditioned noise level. For nonconvex objectives, we establish a preconditioner-dependent basin-stability guarantee: when smoothness and basin size are measured in the $\mathbf{M}$-norm, the probability that the iterates remain in a well-behaved local region admits an explicit lower bound. This perspective is particularly relevant in Scientific Machine Learning (SciML), where achieving small training loss under stochastic updates is closely tied to physical fidelity, numerical stability, and constraint satisfaction. The framework applies to both diagonal/adaptive and curvature-aware preconditioners and yields a simple design principle: choose $\mathbf{M}$ to improve local conditioning while attenuating noise. Experiments on a quadratic diagnostic and three SciML benchmarks validate the predicted rate-floor behavior.
Authors: Vikram Ramavarapu, Jo\~ao Alfredo Cardoso Lamy, Mohammad Dindoost, David A. Bader
Abstract: Community detection, or network clustering, is used to identify latent community structure in networks. Due to the scarcity of labeled ground truth in real-world networks, evaluating these algorithms poses significant challenges. To address this, researchers use synthetic network generators that produce networks with ground-truth community labels. RECCS is one such algorithm that takes a network and its clustering as input and generates a synthetic network through a modular pipeline. Each generated ground truth cluster preserves key characteristics of the corresponding input cluster, including connectivity, minimum degree, and degree sequence distribution. The output consists of a synthetically generated network, and disjoint ground truth cluster labels for all nodes. In this paper, we present two enhanced versions: RECCS+ and RECCS++. RECCS+ maintains algorithmic fidelity to the original RECCS while introducing parallelization through an orchestrator that coordinates algorithmic components across multiple processes and employs multithreading. RECCS++ builds upon this foundation with additional algorithmic optimizations to achieve further speedup. Our experimental results demonstrate that RECCS+ and RECCS++ achieve speedups of up to 49x and 139x respectively on our benchmark datasets, with RECCS++'s additional performance gains involving a modest accuracy tradeoff. With this newfound performance, RECCS++ can now scale to networks with over 100 million nodes and nearly 2 billion edges.
Authors: Ilya O. Ryzhov, John Gunnar Carlsson, Yinchu Zhu
Abstract: Socioeconomic segregation often arises in school districting and other contexts, causing some groups to be over- or under-represented within a particular district. This phenomenon is closely linked with disparities in opportunities and outcomes. We formulate a new class of geographical partitioning problems in which the population is heterogeneous, and it is necessary to ensure fair representation for each group at each facility. We prove that the optimal solution is a novel generalization of the additively weighted Voronoi diagram, and we propose a simple and efficient algorithm to compute it, thus resolving an open question dating back to Dvoretzky et al. (1951). The efficacy and potential for practical insight of the approach are demonstrated in a realistic case study involving seven demographic groups and $78$ district offices.
Authors: Roberto Garrone
Abstract: Multi-agent systems often operate under feedback, adaptation, and non-stationarity, yet many simulation studies retain static decision rules and fixed control parameters. This paper introduces a general adaptive multi-agent learning framework that integrates: (i) four dynamic regimes distinguishing static versus adaptive agents and fixed versus adaptive system parameters; (ii) information-theoretic diagnostics (entropy rate, statistical complexity, and predictive information) to assess predictability and structure; (iii) structural causal models for explicit intervention semantics; (iv) procedures for generating agent-level priors from aggregate or sample data; and (v) unsupervised methods for identifying emergent behavioral regimes. The framework offers a domain-neutral architecture for analyzing how learning agents and adaptive controls jointly shape system trajectories, enabling systematic comparison of stability, performance, and interpretability across non-equilibrium, oscillatory, or drifting dynamics. Mathematical definitions, computational operators, and an experimental design template are provided, yielding a structured methodology for developing explainable and contestable multi-agent decision processes.
Authors: Shu Yang, Margaret Gamalo, Haoda Fu
Abstract: Randomized controlled trials (RCTs) have been the cornerstone of clinical evidence; however, their cost, duration, and restrictive eligibility criteria limit power and external validity. Studies using real-world data (RWD), historically considered less reliable for establishing causality, are now recognized to be important for generating real-world evidence (RWE). In parallel, artificial intelligence and machine learning (AI/ML) are being increasingly used throughout the drug development process, providing scalability and flexibility but also presenting challenges in interpretability and rigor that traditional statistics do not face. This Perspective argues that the future of evidence generation will not depend on RCTs versus RWD, or statistics versus AI/ML, but on their principled integration. To this end, a causal roadmap is needed to clarify inferential goals, make assumptions explicit, and ensure transparency about tradeoffs. We highlight key objectives of integrative evidence synthesis, including transporting RCT results to broader populations, embedding AI-assisted analyses within RCTs, designing hybrid controlled trials, and extending short-term RCTs with long-term RWD. We also outline future directions in privacy-preserving analytics, uncertainty quantification, and small-sample methods. By uniting statistical rigor with AI/ML innovation, integrative approaches can produce robust, transparent, and policy-relevant evidence, making them a key component of modern regulatory science.
Authors: Richard J. Young, Alice M. Matthews
Abstract: Domain-specific text embeddings are critical for clinical natural language processing, yet systematic comparisons across model architectures remain limited. This study evaluates ten transformer-based embedding models adapted for cardiology through Low-Rank Adaptation (LoRA) fine-tuning on 106,535 cardiology text pairs derived from authoritative medical textbooks. Results demonstrate that encoder-only architectures, particularly BioLinkBERT, achieve superior domain-specific performance (separation score: 0.510) compared to larger decoder-based models, while requiring significantly fewer computational resources. The findings challenge the assumption that larger language models necessarily produce better domain-specific embeddings and provide practical guidance for clinical NLP system development. All models, training code, and evaluation datasets are publicly available to support reproducible research in medical informatics.
Authors: Tergel Molom-Ochir, Benjamin F. Morris, Mark Horton, Chiyue Wei, Cong Guo, Brady Taylor, Peter Liu, Shan X. Wang, Deliang Fan, Hai Helen Li, Yiran Chen
Abstract: Transformers face scalability challenges due to the quadratic cost of attention, which involves dense similarity computations between queries and keys. We propose CAMformer, a novel accelerator that reinterprets attention as an associative memory operation and computes attention scores using a voltage-domain Binary Attention Content Addressable Memory (BA-CAM). This enables constant-time similarity search through analog charge sharing, replacing digital arithmetic with physical similarity sensing. CAMformer integrates hierarchical two-stage top-k filtering, pipelined execution, and high-precision contextualization to achieve both algorithmic accuracy and architectural efficiency. Evaluated on BERT and Vision Transformer workloads, CAMformer achieves over 10x energy efficiency, up to 4x higher throughput, and 6-8x lower area compared to state-of-the-art accelerators--while maintaining near-lossless accuracy.
Authors: Badih Ghattas, Alvaro Sanchez San-Benito
Abstract: Clustering is widely used in unsupervised learning to find homogeneous groups of observations within a dataset. However, clustering mixed-type data remains a challenge, as few existing approaches are suited for this task. This study presents the state-of-the-art of these approaches and compares them using various simulation models. The compared methods include the distance-based approaches k-prototypes, PDQ, and convex k-means, and the probabilistic methods KAy-means for MIxed LArge data (KAMILA), the mixture of Bayesian networks (MBNs), and latent class model (LCM). The aim is to provide insights into the behavior of different methods across a wide range of scenarios by varying some experimental factors such as the number of clusters, cluster overlap, sample size, dimension, proportion of continuous variables in the dataset, and clusters' distribution. The degree of cluster overlap and the proportion of continuous variables in the dataset and the sample size have a significant impact on the observed performances. When strong interactions exist between variables alongside an explicit dependence on cluster membership, none of the evaluated methods demonstrated satisfactory performance. In our experiments KAMILA, LCM, and k-prototypes exhibited the best performance, with respect to the adjusted rand index (ARI). All the methods are available in R.
Authors: Weizhi Liu, Xi Chen, Zekun Jiang, Liang Zhao, Kunyuan Jiang, Ruisi Tang, Li Wang, Mingke You, Hanyu Zhou, Hongyu Chen, Qiankun Xiong, Yong Nie, Kang Li, Jian Li
Abstract: Knee osteoarthritis (KOA) affects more than 600 million individuals globally and is associated with significant pain, functional impairment, and disability. While personalized multidisciplinary interventions have the potential to slow disease progression and enhance quality of life, they typically require substantial medical resources and expertise, making them difficult to implement in resource-limited settings. To address this challenge, we developed KOM, a multi-agent system designed to automate KOA evaluation, risk prediction, and treatment prescription. This system assists clinicians in performing essential tasks across the KOA care pathway and supports the generation of tailored management plans based on individual patient profiles, disease status, risk factors, and contraindications. In benchmark experiments, KOM demonstrated superior performance compared to several general-purpose large language models in imaging analysis and prescription generation. A randomized three-arm simulation study further revealed that collaboration between KOM and clinicians reduced total diagnostic and planning time by 38.5% and resulted in improved treatment quality compared to each approach used independently. These findings indicate that KOM could help facilitate automated KOA management and, when integrated into clinical workflows, has the potential to enhance care efficiency. The modular architecture of KOM may also offer valuable insights for developing AI-assisted management systems for other chronic conditions.
Authors: Y. A. Rouzoumka, E. Terreaux, C. Morisseau, J. -P. Ovarlez, C. Ren
Abstract: We investigate complex-valued Variational AutoEncoders (CVAE) for radar Out-Of-Distribution (OOD) detection in complex radar environments. We proposed several detection metrics: the reconstruction error of CVAE (CVAE-MSE), the latent-based scores (Mahalanobis, Kullback-Leibler divergence (KLD)), and compared their performance against the classical ANMF-Tyler detector (ANMF-FP). The performance of all these detectors is analyzed on synthetic and experimental radar data, showing the advantages and the weaknesses of each detector.
Authors: Debin Meng, Chen Jin, Zheng Gao, Yanran Li, Ioannis Patras, Georgios Tzimiropoulos
Abstract: Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity models tend to generate repetitive outputs, increasing sampling redundancy and hindering both creative exploration and downstream applications. A primary cause is that generation often collapses toward a strong mode in the learned distribution. Existing attempts to improve diversity, such as noise resampling, prompt rewriting, or steering-based guidance, often still collapse to dominant modes or introduce distortions that degrade image quality. In light of this, we propose Token-Prompt embedding Space Optimization (TPSO), a training-free and model-agnostic module. TPSO introduces learnable parameters to explore underrepresented regions of the token embedding space, reducing the tendency of the model to repeatedly generate samples from strong modes of the learned distribution. At the same time, the prompt-level space provides a global semantic constraint that regulates distribution shifts, preventing quality degradation while maintaining high fidelity. Extensive experiments on MS-COCO and three diffusion backbones show that TPSO significantly enhances generative diversity, improving baseline performance from 1.10 to 4.18 points, without sacrificing image quality. Code will be released upon acceptance.
Authors: Miguel Carvalho, Helder Dias, Bruno Martins
Abstract: Vision-Language Models (VLMs) often struggle with tasks that require fine-grained image understanding, such as scene-text recognition or document analysis, due to perception limitations and visual fragmentation. To address these challenges, we introduce CropVLM as an external low-cost method for boosting performance, enabling VLMs to dynamically ''zoom in'' on relevant image regions, enhancing their ability to capture fine details. CropVLM is trained using reinforcement learning, without using human-labeled bounding boxes as a supervision signal, and without expensive synthetic evaluations. The model is trained once and can be paired with both open-source and proprietary VLMs to improve their performance. Our approach delivers significant improvements on tasks that require high-resolution image understanding, notably for benchmarks that are out-of-domain for the target VLM, without modifying or fine-tuning the VLM, thus avoiding catastrophic forgetting.
Authors: Dominik Wagner, Leon Witzman, Luke Ong
Abstract: Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of $\omega$-regular objectives addresses this by precisely specifying rich behavioural properties. Even still, measuring performance by a single scalar (be it reward or satisfaction probability) masks safety-performance trade-offs that arise in settings with a tolerable level of risk. We address both limitations simultaneously by combining $\omega$-regular objectives with explicit constraints, allowing safety requirements and optimisation targets to be treated separately. We develop a model-based RL algorithm based on linear programming, which in the limit produces a policy maximising the probability of satisfying an $\omega$-regular objective while also adhering to $\omega$-regular constraints within specified thresholds. Furthermore, we establish a translation to constrained limit-average problems with optimality-preserving guarantees.
Authors: Arun Chowdary Sanna
Abstract: As AI agents become integral to enterprise workflows, their reliance on shared tool libraries and pre-trained components creates significant supply chain vulnerabilities. While previous work has demonstrated behavioral backdoor detection within individual LLM architectures, the critical question of cross-LLM generalization remains unexplored, a gap with serious implications for organizations deploying multiple AI systems. We present the first systematic study of cross-LLM behavioral backdoor detection, evaluating generalization across six production LLMs (GPT-5.1, Claude Sonnet 4.5, Grok 4.1, Llama 4 Maverick, GPT-OSS 120B, and DeepSeek Chat V3.1). Through 1,198 execution traces and 36 cross-model experiments, we quantify a critical finding: single-model detectors achieve 92.7% accuracy within their training distribution but only 49.2% across different LLMs, a 43.4 percentage point generalization gap equivalent to random guessing. Our analysis reveals that this gap stems from model-specific behavioral signatures, particularly in temporal features (coefficient of variation > 0.8), while structural features remain stable across architectures. We show that model-aware detection incorporating model identity as an additional feature achieves 90.6% accuracy universally across all evaluated models. We release our multi-LLM trace dataset and detection framework to enable reproducible research.
Authors: Xiangyu Zhao, Yaling Shen, Yiwen Jiang, Zimu Wang, Jiahe Liu, Maxmartwell H Cheng, Guilherme C Oliveira, Robert Desimone, Dominic Dwyer, Zongyuan Ge
Abstract: Depression is one of the most prevalent mental health disorders globally. In recent years, multi-modal data, such as speech, video, and transcripts, has been increasingly used to develop AI-assisted depression assessment systems. Large language models have further advanced this field due to their strong language understanding and generalization capabilities. However, conventional LLMs remain text-centric and cannot process the rich non-verbal cues found in audio and visual modalities, which are critical components in mental health evaluation. While multi-modal LLMs offer a promising direction, few are tailored for psychological applications. In this study, we propose a novel multi-modal LLM framework for depression detection. Our approach augments an audio language model with visual understanding and aligns audio-visual features at the timestamp level. This fine-grained alignment improves modeling of temporal dynamics across modalities while reducing the need for extensive training data and computational resources. Experiments on the DAIC-WoZ dataset demonstrate that our model outperforms both single-modality approaches and previous multi-modal methods. Moreover, the proposed framework can be extended to incorporate additional physiological signals, paving the way for broader clinical applications beyond mental health.
Authors: Chengyue Huang, Mellon M. Zhang, Robert Azarcon, Glen Chou, Zsolt Kira
Abstract: Vision-Language-Action (VLA) models inherit strong priors from pretrained Vision-Language Models (VLMs), but naive fine-tuning often disrupts these representations and harms generalization. Existing fixes -- freezing modules or applying uniform regularization -- either overconstrain adaptation or ignore the differing roles of VLA components. We present MAPS (Module-Wise Proximity Scheduling), the first robust fine-tuning framework for VLAs. Through systematic analysis, we uncover an empirical order in which proximity constraints should be relaxed to balance stability and flexibility. MAPS linearly schedules this relaxation, enabling visual encoders to stay close to their pretrained priors while action-oriented language layers adapt more freely. MAPS introduces no additional parameters or data, and can be seamlessly integrated into existing VLAs. Across MiniVLA-VQ, MiniVLA-OFT, OpenVLA-OFT, and challenging benchmarks such as SimplerEnv, CALVIN, LIBERO, as well as real-world evaluations on the Franka Emika Panda platform, MAPS consistently boosts both in-distribution and out-of-distribution performance (up to +30%). Our findings highlight empirically guided proximity to pretrained VLMs as a simple yet powerful principle for preserving broad generalization in VLM-to-VLA transfer.
Authors: Jackson C. Glass, Gia-Wei Chern
Abstract: We show that Restricted Boltzmann Machines (RBMs) provide a flexible generative framework for modeling spin configurations in disordered yet strongly correlated phases of frustrated magnets. As a benchmark, we first demonstrate that an RBM can learn the zero-temperature ground-state manifold of the one-dimensional ANNNI model at its multiphase point, accurately reproducing its characteristic oscillatory and exponentially decaying correlations. We then apply RBMs to kagome spin ice and show that they successfully learn the local ice rules and short-range correlations of the extensively degenerate ice-I manifold. Correlation functions computed from RBM-generated configurations closely match those from direct Monte Carlo simulations. For the partially ordered ice-II phase -- featuring long-range charge order and broken time-reversal symmetry -- accurate modeling requires RBMs with uniform-sign bias fields, mirroring the underlying symmetry breaking. These results highlight the utility of RBMs as generative models for learning constrained and highly frustrated magnetic states.
Authors: Chenglu Sun, Shuo Shen, Haonan Hu, Wei Zhou, Chen Chen
Abstract: Despite advancements in language-controlled reinforcement learning (LC-RL) for basic domains and straightforward commands (e.g., object manipulation and navigation), effectively extending LC-RL to comprehend and execute high-level or abstract instructions in complex, multi-agent environments, such as football games, remains a significant challenge. To address this gap, we introduce Language-Controlled Diverse Style Policies (LCDSP), a novel LC-RL paradigm specifically designed for complex scenarios. LCDSP comprises two key components: a Diverse Style Training (DST) method and a Style Interpreter (SI). The DST method efficiently trains a single policy capable of exhibiting a wide range of diverse behaviors by modulating agent actions through style parameters (SP). The SI is designed to accurately and rapidly translate high-level language instructions into these corresponding SP. Through extensive experiments in a complex 5v5 football environment, we demonstrate that LCDSP effectively comprehends abstract tactical instructions and accurately executes the desired diverse behavioral styles, showcasing its potential for complex, real-world applications.
Authors: Kenta Yamamoto, Teruaki Hayashi
Abstract: Recent advances in machine learning and big data analytics have intensified the demand for high-quality cross-domain datasets and accelerated the growth of data trading across organizations. As data become increasingly recognized as an economic asset, data marketplaces have emerged as a key infrastructure for data-driven innovation. However, unlike mature product or service markets, data-trading environments remain nascent and suffer from pronounced information asymmetry. Buyers cannot verify the content or quality before purchasing data, making trust and quality assurance central challenges. To address these issues, this study develops a multi-agent data-market simulator that models participant behavior and evaluates the institutional mechanisms for trust formation. Focusing on the manufacturing sector, where initiatives such as GAIA-X and Catena-X are advancing, the simulator integrates reinforcement learning (RL) for adaptive agent behavior and inverse reinforcement learning (IRL) to estimate utility functions from empirical behavioral data. Using the simulator, we examine the market-level effects of five representative reputation systems-Time-decay, Bayesian-beta, PageRank, PowerTrust, and PeerTrust-and found that PeerTrust achieved the strongest alignment between data price and quality, while preventing monopolistic dominance. Building on these results, we develop a hybrid reputation mechanism that integrates the strengths of existing systems to achieve improved price-quality consistency and overall market stability. This study extends simulation-based data-market analysis by incorporating trust and reputation as endogenous mechanisms and offering methodological and institutional insights into the design of reliable and efficient data ecosystems.
Authors: Akash Doshi, Pinar Sen, Kirill Ivanov, Wei Yang, June Namgoong, Runxin Wang, Rachel Wang, Taesang Yoo, Jing Jiang, Tingfang Ji
Abstract: Channel coding from 2G to 5G has assumed the inputs bits at the physical layer to be uniformly distributed. However, hybrid automatic repeat request acknowledgement (HARQ-ACK) bits transmitted in the uplink are inherently non-uniformly distributed. For such sources, significant performance gains could be obtained by employing joint source channel coding, aided by deep learning-based techniques. In this paper, we learn a transformer-based encoder using a novel "free-lunch" training algorithm and propose per-codeword power shaping to exploit the source prior at the encoder whilst being robust to small changes in the HARQ-ACK distribution. Furthermore, any HARQ-ACK decoder has to achieve a low negative acknowledgement (NACK) error rate to avoid radio link failures resulting from multiple NACK errors. We develop an extension of the Neyman-Pearson test to a coded bit system with multiple information bits to achieve Unequal Error Protection of NACK over ACK bits at the decoder. Finally, we apply the proposed encoder and decoder designs to a 5G New Radio (NR) compliant uplink setup under a fading channel, describing the optimal receiver design and a low complexity coherent approximation to it. Our results demonstrate 3-6 dB reduction in the average transmit power required to achieve the target error rates compared to the NR baseline, while also achieving a 2-3 dB reduction in the maximum transmit power, thus providing for significant coverage gains and power savings.
Authors: Hongjian Jiang, Michael Hahn, Georg Zetzsche, Anthony Widjaja Lin
Abstract: Hard attention Chain-of-Thought (CoT) transformers are known to be Turing-complete. However, it is an open problem whether softmax attention Chain-of-Thought (CoT) transformers are Turing-complete. In this paper, we prove a stronger result that length-generalizable softmax CoT transformers are Turing-complete. More precisely, our Turing-completeness proof goes via the CoT extension of the Counting RASP (C-RASP), which correspond to softmax CoT transformers that admit length generalization. We prove Turing-completeness for CoT C-RASP with causal masking over a unary alphabet (more generally, for letter-bounded languages). While we show this is not Turing-complete for arbitrary languages, we prove that its extension with relative positional encoding is Turing-complete for arbitrary languages. We empirically validate our theory by training transformers for languages requiring complex (non-linear) arithmetic reasoning.
Authors: Petr Molodyk, Jaemoo Choi, David W. Romero, Ming-Yu Liu, Yongxin Chen
Abstract: In recent years, point cloud generation has gained significant attention in 3D generative modeling. Among existing approaches, point-based methods directly generate point clouds without relying on other representations such as latent features, meshes, or voxels. These methods offer low training cost and algorithmic simplicity, but often underperform compared to representation-based approaches. In this paper, we propose MFM-Point, a multi-scale Flow Matching framework for point cloud generation that substantially improves the scalability and performance of point-based methods while preserving their simplicity and efficiency. Our multi-scale generation algorithm adopts a coarse-to-fine generation paradigm, enhancing generation quality and scalability without incurring additional training or inference overhead. A key challenge in developing such a multi-scale framework lies in preserving the geometric structure of unordered point clouds while ensuring smooth and consistent distributional transitions across resolutions. To address this, we introduce a structured downsampling and upsampling strategy that preserves geometry and maintains alignment between coarse and fine resolutions. Our experimental results demonstrate that MFM-Point achieves best-in-class performance among point-based methods and challenges the best representation-based methods. In particular, MFM-point demonstrates strong results in multi-category and high-resolution generation tasks.
Authors: Zixiao Huang, Wen Zeng, Tianyu Fu, Tengxuan Liu, Yizhou Sun, Ke Hong, Xinhao Yang, Chengchun Liu, Yan Li, Quanlu Zhang, Guohao Dai, Zhenhua Zhu, Yu Wang
Abstract: LLM-based search agents achieve strong performance but suffer from severe latency, as each step requires serialized LLM reasoning followed by action of tool execution. We revisit this bottleneck through the lens of speculation. While traditional predict-verify speculation paradigm can break serial execution, its benefit remains limited, as it retains the full original workload and adds extra inference overhead. We observe that early agent steps often involve simple evidence-gathering, where correct actions can often be predicted without full reasoning. Building on these observations, we present SPAgent, an algorithm-system co-design framework that expands the role of speculation in search agents to reduce latency. Algorithmically, SPAgent introduces a two-phase adaptive speculation mechanism that selectively omits verification when safe. System-wise, a two-level scheduler regulates speculative requests based on engine load to ensure speculation remains beneficial. We implement SPAgent in real-world systems. Across extensive experimental settings, SPAgent achieves up to $1.65\times$ end-to-end speedup while maintaining same or even achieving higher accuracy, enabling practical deployment of multi-step search agents.
Authors: Jason Lo, Mohammadnima Jafari
Abstract: A wiring diagram is a labeled directed graph that represents an abstract concept such as a temporal process. In this article, we introduce the notion of a quasi-skeleton wiring diagram graph, and prove that quasi-skeleton wiring diagram graphs correspond to Hasse diagrams. Using this result, we designed algorithms that extract wiring diagrams from sequential data. We used our algorithms in analyzing the behavior of an autonomous agent playing a computer game, and the algorithms correctly identified the winning strategies. We compared the performance of our main algorithm with two other algorithms based on standard clustering techniques (DBSCAN and agglomerative hierarchical), including when some of the data was perturbed. Overall, this article brings together techniques in category theory, graph theory, clustering, reinforcement learning, and data engineering.
Authors: Haebin Seong, Sungmin Kim, Minchan Kim, Yongjun Cho, Myunchul Joe, Suhwan Choi, Jaeyoon Jung, Jiyong Youn, Yoonshik Kim, Samwoo Seong, Yubeen Park, Youngjae Yu, Yunsung Lee
Abstract: Existing navigation benchmarks focus on task success metrics while overlooking economic viability -- critical for commercial deployment of autonomous delivery robots. We introduce \emph{CostNav}, a \textbf{Micro-Navigation Economic Testbed} that evaluates embodied agents through comprehensive cost-revenue analysis aligned with real-world business operations. CostNav models the complete economic lifecycle including hardware, training, energy, maintenance costs, and delivery revenue with service-level agreements, using industry-derived parameters. \textbf{To our knowledge, CostNav is the first work to quantitatively expose the gap between navigation research metrics and commercial viability}, revealing that optimizing for task success fundamentally differs from optimizing for economic deployment. Our cost model uses parameters derived from industry data sources (energy rates, delivery service pricing), and we project from a reduced-scale simulation to realistic deliveries. Under this projection, the baseline achieves 43.0\% SLA compliance but is \emph{not} commercially viable: yielding a loss of \$30.009 per run with no finite break-even point, because operating costs are dominated by collision-induced maintenance, which accounts for 99.7\% of per-run costs and highlights collision avoidance as a key optimization target. We demonstrate a learning-based on-device navigation baseline and establish a foundation for evaluating rule-based navigation, imitation learning, and cost-aware RL training. CostNav bridges the gap between navigation research and commercial deployment, enabling data-driven decisions about economic trade-offs across navigation paradigms.
Authors: Szymon Bobek, {\L}ukasz Ba{\l}ec, Grzegorz J. Nalepa
Abstract: Counterfactual explanations enhance the actionable interpretability of machine learning models by identifying the minimal changes required to achieve a desired outcome of the model. However, existing methods often ignore the complex dependencies in real-world datasets, leading to unrealistic or impractical modifications. Motivated by cybersecurity applications in the email marketing domain, we propose a method for generating Diverse, Actionable, and kNowledge-Constrained Explanations (DANCE), which incorporates feature dependencies and causal constraints to ensure plausibility and real-world feasibility of counterfactuals. Our method learns linear and nonlinear constraints from data or integrates expert-provided dependency graphs, ensuring counterfactuals are plausible and actionable. By maintaining consistency with feature relationships, the method produces explanations that align with real-world constraints. Additionally, it balances plausibility, diversity, and sparsity, effectively addressing key limitations in existing algorithms. The work is developed based on a real-life case study with Freshmail, the largest email marketing company in Poland and supported by a joint R&D project Sendguard. Furthermore, we provide an extensive evaluation using 140 public datasets, which highlights its ability to generate meaningful, domain-relevant counterfactuals that outperform other existing approaches based on widely used metrics. The source code for reproduction of the results can be found in a GitHub repository we provide.
Authors: Zeynab Kaseb, Matthias Moller, Lindsay Spoor, Jerry J. Guo, Yu Xiang, Peter Palensky, Pedro P. Vergara
Abstract: The Newton-Raphson (NR) method is widely used for solving power flow (PF) equations due to its quadratic convergence. However, its performance deteriorates under poor initialization or extreme operating scenarios, e.g., high levels of renewable energy penetration. Traditional NR initialization strategies often fail to address these challenges, resulting in slow convergence or even divergence. We propose the use of reinforcement learning (RL) to optimize the initialization of NR, and introduce a novel quantum-enhanced RL environment update mechanism to mitigate the significant computational cost of evaluating power system states over a combinatorially large action space at each RL timestep by formulating the voltage adjustment task as a quadratic unconstrained binary optimization problem. Specifically, quantum/digital annealers are integrated into the RL environment update to evaluate state transitions using a problem Hamiltonian designed for PF. Results demonstrate significant improvements in convergence speed, a reduction in NR iteration counts, and enhanced robustness under different operating conditions.
Authors: Daniel Kienzle, Katja Ludwig, Julian Lorenz, Shin'ichi Satoh, Rainer Lienhart
Abstract: Obtaining the precise 3D motion of a table tennis ball from standard monocular videos is a challenging problem, as existing methods trained on synthetic data struggle to generalize to the noisy, imperfect ball and table detections of the real world. This is primarily due to the inherent lack of 3D ground truth trajectories and spin annotations for real-world video. To overcome this, we propose a novel two-stage pipeline that divides the problem into a front-end perception task and a back-end 2D-to-3D uplifting task. This separation allows us to train the front-end components with abundant 2D supervision from our newly created TTHQ dataset, while the back-end uplifting network is trained exclusively on physically-correct synthetic data. We specifically re-engineer the uplifting model to be robust to common real-world artifacts, such as missing detections and varying frame rates. By integrating a ball detector and a table keypoint detector, our approach transforms a proof-of-concept uplifting method into a practical, robust, and high-performing end-to-end application for 3D table tennis trajectory and spin analysis.
Authors: Xiaohan Wang, Zhangtao Cheng, Ting Zhong, Leiting Chen, Fan Zhou
Abstract: Weight Averaging (WA) has emerged as a powerful technique for enhancing generalization by promoting convergence to a flat loss landscape, which correlates with stronger out-of-distribution performance. However, applying WA directly to multi-modal domain generalization (MMDG) is challenging: differences in optimization speed across modalities lead WA to overfit to faster-converging ones in early stages, suppressing the contribution of slower yet complementary modalities, thereby hindering effective modality fusion and skewing the loss surface toward sharper, less generalizable minima. To address this issue, we propose MBCD, a unified collaborative distillation framework that retains WA's flatness-inducing advantages while overcoming its shortcomings in multi-modal contexts. MBCD begins with adaptive modality dropout in the student model to curb early-stage bias toward dominant modalities. A gradient consistency constraint then aligns learning signals between uni-modal branches and the fused representation, encouraging coordinated and smoother optimization. Finally, a WA-based teacher conducts cross-modal distillation by transferring fused knowledge to each uni-modal branch, which strengthens cross-modal interactions and steer convergence toward flatter solutions. Extensive experiments on MMDG benchmarks show that MBCD consistently outperforms existing methods, achieving superior accuracy and robustness across diverse unseen domains.
Authors: Marta Grzeskiewicz
Abstract: Understanding household behaviour is essential for modelling macroeconomic dynamics and designing effective policy. While heterogeneous agent models offer a more realistic alternative to representative agent frameworks, their implementation poses significant computational challenges, particularly in continuous time. The Aiyagari-Bewley-Huggett (ABH) framework, recast as a system of partial differential equations, typically relies on grid-based solvers that suffer from the curse of dimensionality, high computational cost, and numerical inaccuracies. This paper introduces the ABH-PINN solver, an approach based on Physics-Informed Neural Networks (PINNs), which embeds the Hamilton-Jacobi-Bellman and Kolmogorov Forward equations directly into the neural network training objective. By replacing grid-based approximation with mesh-free, differentiable function learning, the ABH-PINN solver benefits from the advantages of PINNs of improved scalability, smoother solutions, and computational efficiency. Preliminary results show that the PINN-based approach is able to obtain economically valid results matching the established finite-difference solvers.
Authors: Chaowei He, Yuanjun Liu, Qingzhi Ma, Shenyuan Ren, Xizhao Luo, Lei Zhao, An Liu
Abstract: Machine unlearning in learned cardinality estimation (CE) systems presents unique challenges due to the complex distributional dependencies in multi-table relational data. Specifically, data deletion, a core component of machine unlearning, faces three critical challenges in learned CE models: attribute-level sensitivity, inter-table propagation and domain disappearance leading to severe overestimation in multi-way joins. We propose Cardinality Estimation Pruning (CEP), the first unlearning framework specifically designed for multi-table learned CE systems. CEP introduces Distribution Sensitivity Pruning, which constructs semi-join deletion results and computes sensitivity scores to guide parameter pruning, and Domain Pruning, which removes support for value domains entirely eliminated by deletion. We evaluate CEP on state-of-the-art architectures NeuroCard and FACE across IMDB and TPC-H datasets. Results demonstrate CEP consistently achieves the lowest Q-error in multi-table scenarios, particularly under high deletion ratios, often outperforming full retraining. Furthermore, CEP significantly reduces convergence iterations, incurring negligible computational overhead of 0.3%-2.5% of fine-tuning time.
Authors: Roman Kochnev, Waleed Khalid, Tolgay Atinc Uzun, Xi Zhang, Yashkumar Sanjaybhai Dhameliya, Furui Qin, Chandini Vysyaraju, Raghuvir Duvvuri, Avi Goyal, Dmitry Ignatov, Radu Timofte
Abstract: Building self-improving AI systems remains a fundamental challenge in the AI domain. We present NNGPT, an open-source framework that turns a large language model (LLM) into a self-improving AutoML engine for neural network development, primarily for computer vision. Unlike previous frameworks, NNGPT extends the dataset of neural networks by generating new models, enabling continuous fine-tuning of LLMs based on closed-loop system of generation, assessment, and self-improvement. It integrates within one unified workflow five synergistic LLM-based pipelines: zero-shot architecture synthesis, hyperparameter optimization (HPO), code-aware accuracy/early-stop prediction, retrieval-augmented synthesis of scope-closed PyTorch blocks (NN-RAG), and reinforcement learning. Built on the LEMUR dataset as an audited corpus with reproducible metrics, NNGPT emits from a single prompt and validates network architecture, preprocessing code, and hyperparameters, executes them end-to-end, and learns from result. The PyTorch adapter makes NNGPT framework-agnostic, enabling strong performance: NN-RAG achieves 73% executability on 1,289 targets, 3-shot prompting boosts accuracy on common datasets, and hash-based deduplication saves hundreds of runs. One-shot prediction matches search-based AutoML, reducing the need for numerous trials. HPO on LEMUR achieves RMSE 0.60, outperforming Optuna (0.64), while the code-aware predictor reaches RMSE 0.14 with Pearson r=0.78. The system has already generated over 5K validated models, proving NNGPT as an autonomous AutoML engine. Upon acceptance, the code, prompts, and checkpoints will be released for public access to enable reproducibility and facilitate community usage.
Authors: Maarten V. de Hoop, Nikola B. Kovachki, Matti Lassas, Nicholas H. Nelsen
Abstract: This paper considers the problem of noise-robust neural operator approximation for the solution map of Calder\'on's inverse conductivity problem. In this continuum model of electrical impedance tomography (EIT), the boundary measurements are realized as a noisy perturbation of the Neumann-to-Dirichlet map's integral kernel. The theoretical analysis proceeds by extending the domain of the inversion operator to a Hilbert space of kernel functions. The resulting extension shares the same stability properties as the original inverse map from kernels to conductivities, but is now amenable to neural operator approximation. Numerical experiments demonstrate that Fourier neural operators excel at reconstructing infinite-dimensional piecewise constant and lognormal conductivities in noisy setups both within and beyond the theory's assumptions. The methodology developed in this paper for EIT exemplifies a broader strategy for addressing nonlinear inverse problems with a noise-aware operator learning framework.
Authors: Ilias Ibnyahya, Joshua D. Reiss
Abstract: We introduce a novel method for designing attenuation filters in digital audio reverberation systems based on Feedback Delay Net- works (FDNs). Our approach uses Second Order Sections (SOS) of Infinite Impulse Response (IIR) filters arranged as parametric equalizers (PEQ), enabling fine control over frequency-dependent reverberation decay. Unlike traditional graphic equalizer designs, which require numerous filters per delay line, we propose a scal- able solution where the number of filters can be adjusted. The fre- quency, gain, and quality factor (Q) parameters are shared parame- ters across delay lines and only the gain is adjusted based on delay length. This design not only reduces the number of optimization parameters, but also remains fully differentiable and compatible with gradient-based learning frameworks. Leveraging principles of analog filter design, our method allows for efficient and accu- rate filter fitting using supervised learning. Our method delivers a flexible and differentiable design, achieving state-of-the-art per- formance while significantly reducing computational cost.
Authors: Matvei Shelukhan, Timur Mamedov, Karina Kvanchiani
Abstract: Multi-object tracking (MOT) is one of the most challenging tasks in computer vision, where it is important to correctly detect objects and associate these detections across frames. Current approaches mainly focus on tracking objects in each frame of a video stream, making it almost impossible to run the model under conditions of limited computing resources. To address this issue, we propose StableTrack, a novel approach that stabilizes the quality of tracking on low-frequency detections. Our method introduces a new two-stage matching strategy to improve the cross-frame association between low-frequency detections. We propose a novel Bbox-Based Distance instead of the conventional Mahalanobis distance, which allows us to effectively match objects using the Re-ID model. Furthermore, we integrate visual tracking into the Kalman Filter and the overall tracking pipeline. Our method outperforms current state-of-the-art trackers in the case of low-frequency detections, achieving $\textit{11.6%}$ HOTA improvement at $\textit{1}$ Hz on MOT17-val, while keeping up with the best approaches on the standard MOT17, MOT20, and DanceTrack benchmarks with full-frequency detections.
Authors: Afra Kilic, Kim Batselier
Abstract: Modeling nonlinear systems with Volterra series is challenging because the number of kernel coefficients grows exponentially with the model order. This work introduces Bayesian Tensor Network Volterra kernel machines (BTN-V), extending the Bayesian Tensor Network framework to Volterra system identification. BTN-V represents Volterra kernels using canonical polyadic decomposition, reducing model complexity from O(I^D) to O(DIR). By treating all tensor components and hyperparameters as random variables, BTN-V provides predictive uncertainty estimation at no additional computational cost. Sparsity-inducing hierarchical priors enable automatic rank determination and the learning of fading-memory behavior directly from data, improving interpretability and preventing overfitting. Empirical results demonstrate competitive accuracy, enhanced uncertainty quantification, and reduced computational cost.
Authors: Jiatao Gu, Ying Shen, Tianrong Chen, Laurent Dinh, Yuyang Wang, Miguel Angel Bautista, David Berthelot, Josh Susskind, Shuangfei Zhai
Abstract: Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, state-of-the-art systems almost exclusively rely on diffusion-based models. In this work, we revisit this design space by presenting STARFlow-V, a normalizing flow-based video generator with substantial benefits such as end-to-end learning, robust causal prediction, and native likelihood estimation. Building upon the recently proposed STARFlow, STARFlow-V operates in the spatiotemporal latent space with a global-local architecture which restricts causal dependencies to a global latent space while preserving rich local within-frame interactions. This eases error accumulation over time, a common pitfall of standard autoregressive diffusion model generation. Additionally, we propose flow-score matching, which equips the model with a light-weight causal denoiser to improve the video generation consistency in an autoregressive fashion. To improve the sampling efficiency, STARFlow-V employs a video-aware Jacobi iteration scheme that recasts inner updates as parallelizable iterations without breaking causality. Thanks to the invertible structure, the same model can natively support text-to-video, image-to-video as well as video-to-video generation tasks. Empirically, STARFlow-V achieves strong visual fidelity and temporal consistency with practical sampling throughput relative to diffusion-based baselines. These results present the first evidence, to our knowledge, that NFs are capable of high-quality autoregressive video generation, establishing them as a promising research direction for building world models. Code and generated samples are available at https://github.com/apple/ml-starflow.
Authors: Ben Hamscher, Arnold Brosch, Nicolas Binninger, Maksymilian Jan Dejna, Kira Maag
Abstract: Dance is an essential component of human culture and serves as a tool for conveying emotions and telling stories. Identifying and distinguishing dance genres based on motion data is a complex problem in human activity recognition, as many styles share similar poses, gestures, and temporal motion patterns. This work presents a lightweight framework for classifying dance styles that determines motion characteristics based on pose estimates extracted from videos. We propose temporal-spatial descriptors inspired by Laban Movement Analysis. These features capture local joint dynamics such as velocity, acceleration, and angular movement of the upper body, enabling a structured representation of spatial coordination. To further encode rhythmic and periodic aspects of movement, we integrate Fast Fourier Transform features that characterize movement patterns in the frequency domain. The proposed approach achieves robust classification of different dance styles with low computational effort, as complex model architectures are not required, and shows that interpretable motion representations can effectively capture stylistic nuances.
Authors: Akshit Pramod Anchan, Jewelith Thomas, Sritama Roy
Abstract: Developing comprehensive assistive technologies requires the seamless integration of visual and auditory perception. This research evaluates the feasibility of a modular architecture inspired by core functionalities of perceptive systems like 'Smart Eye.' We propose and benchmark three independent sensing modules: a Convolutional Neural Network (CNN) for eye state detection (drowsiness/attention), a deep CNN for facial expression recognition, and a Long Short-Term Memory (LSTM) network for voice-based speaker identification. Utilizing the Eyes Image, FER2013, and customized audio datasets, our models achieved accuracies of 93.0%, 97.8%, and 96.89%, respectively. This study demonstrates that lightweight, domain-specific models can achieve high fidelity on discrete tasks, establishing a validated foundation for future real-time, multimodal integration in resource-constrained assistive devices.
Authors: Kanchan Chowdhury, Lixi Zhou, Lulu Xie, Xinwei Fu, Jia Zou
Abstract: Real-world AI/ML workflows often apply inference computations to feature vectors joined from multiple datasets. To avoid the redundant AI/ML computations caused by repeated data records in the join's output, factorized ML has been proposed to decompose ML computations into sub-computations to be executed on each normalized dataset. However, there is insufficient discussion on how factorized ML could impact AI/ML inference over multi-way joins. To address the limitations, we propose a novel declarative InferF system, focusing on the factorization of arbitrary inference workflows represented as analyzable expressions over the multi-way joins. We formalize our problem to flexibly push down partial factorized computations to qualified nodes in the join tree to minimize the overall inference computation and join costs and propose two algorithms to resolve the problem: (1) a greedy algorithm based on a per-node cost function that estimates the influence on overall latency if a subset of factorized computations is pushed to a node, and (2) a genetic algorithm for iteratively enumerating and evaluating promising factorization plans. We implement InferF on Velox, an open-sourced database engine from Meta, evaluate it on real-world datasets, observed up to 11.3x speedups, and systematically summarized the factors that determine when factorized ML can benefit AI/ML inference workflows.
Authors: Muhammad Irfan, Nasir Rahim, Khalid Mahmood Malik
Abstract: Accurate extraction and segmentation of the cerebral arteries from digital subtraction angiography (DSA) sequences is essential for developing reliable clinical management models of complex cerebrovascular diseases. Conventional loss functions often rely solely on pixel-wise overlap, overlooking the geometric and physical consistency of vascular boundaries, which can lead to fragmented or unstable vessel predictions. To overcome this limitation, we propose a novel \textit{Physics-Informed Loss} (PIL) that models the interaction between the predicted and ground-truth boundaries as an elastic process inspired by dislocation theory in materials physics. This formulation introduces a physics-based regularization term that enforces smooth contour evolution and structural consistency, allowing the network to better capture fine vascular geometry. The proposed loss is integrated into several segmentation architectures, including U-Net, U-Net++, SegFormer, and MedFormer, and evaluated on two public benchmarks: DIAS and DSCA. Experimental results demonstrate that PIL consistently outperforms conventional loss functions such as Cross-Entropy, Dice, Active Contour, and Surface losses, achieving superior sensitivity, F1 score, and boundary coherence. These findings confirm that the incorporation of physics-based boundary interactions into deep neural networks improves both the precision and robustness of vascular segmentation in dynamic angiographic imaging. The implementation of the proposed method is publicly available at https://github.com/irfantahir301/Physicsis_loss.
Authors: Rui Tong
Abstract: Generative modeling is typically framed as learning mapping rules, but from an observer's perspective without access to these rules, the task manifests as disentangling the geometric support from the probability distribution. We propose that Continuum Percolation is uniquely suited for this support analysis, as the sampling process effectively projects high-dimensional density estimation onto a geometric counting problem on the support. In this work, we establish a rigorous isomorphism between the topological phase transitions of Random Geometric Graphs and the underlying data manifold in high-dimensional space. By analyzing the relationship between our proposed Percolation Shift metric and FID, we demonstrate that our metric captures structural pathologies (such as implicit mode collapse) where statistical metrics fail. Finally, we translate this topological phenomenon into a differentiable loss function to guide training. Experimental results confirm that this approach not only prevents manifold shrinkage but drives the model toward a state of "Hyper-Generalization," achieving good fidelity and verified topological expansion.
Authors: Shamima Hossain
Abstract: Visual Language Models (VLMs) are powerful generative tools but often produce factually in- accurate outputs due to a lack of robust reason- ing capabilities. While extensive research has been conducted on integrating external knowl- edge for reasoning in large language models (LLMs), such efforts remain underexplored in VLMs, where the challenge is compounded by the need to bridge multiple modalities seam- lessly. This work introduces a framework for knowledge-guided reasoning in VLMs, leverag- ing structured knowledge graphs for multi-hop verification using image-captioning task to il- lustrate our framework. Our approach enables systematic reasoning across multiple steps, in- cluding visual entity recognition, knowledge graph traversal, and fact-based caption refine- ment. We evaluate the framework using hi- erarchical, triple-based and bullet-point based knowledge representations, analyzing their ef- fectiveness in factual accuracy and logical infer- ence. Empirical results show that our approach improves factual accuracy by approximately 31% on preliminary experiments on a curated dataset of mixtures from Google Landmarks v2, Conceptual captions and Coco captions re- vealing key insights into reasoning patterns and failure modes. This work demonstrates the po- tential of integrating external knowledge for advancing reasoning in VLMs, paving the way for more reliable and knowledgable multimodal systems.
Authors: Andrea Ranieri, Giorgio Palmieri, Silvia Biasotti
Abstract: This paper addresses the critical need for automated crack detection in the preservation of cultural heritage through semantic segmentation. We present a comparative study of U-Net architectures, using various convolutional neural network (CNN) encoders, for pixel-level crack identification on statues and monuments. A comparative quantitative evaluation is performed on the test set of the OmniCrack30k dataset [1] using popular segmentation metrics including Mean Intersection over Union (mIoU), Dice coefficient, and Jaccard index. This is complemented by an out-of-distribution qualitative evaluation on an unlabeled test set of real-world cracked statues and monuments. Our findings provide valuable insights into the capabilities of different CNN- based encoders for fine-grained crack segmentation. We show that the models exhibit promising generalization capabilities to unseen cultural heritage contexts, despite never having been explicitly trained on images of statues or monuments.
Authors: Ege Ozguroglu, Junbang Liang, Ruoshi Liu, Mia Chiquier, Michael DeTienne, Wesley Wei Qian, Alexandra Horowitz, Andrew Owens, Carl Vondrick
Abstract: While olfaction is central to how animals perceive the world, this rich chemical sensory modality remains largely inaccessible to machines. One key bottleneck is the lack of diverse, multimodal olfactory training data collected in natural settings. We present New York Smells, a large dataset of paired image and olfactory signals captured ``in the wild.'' Our dataset contains 7,000 smell-image pairs from 3,500 distinct objects across indoor and outdoor environments, with approximately 70$\times$ more objects than existing olfactory datasets. Our benchmark has three tasks: cross-modal smell-to-image retrieval, recognizing scenes, objects, and materials from smell alone, and fine-grained discrimination between grass species. Through experiments on our dataset, we find that visual data enables cross-modal olfactory representation learning, and that our learned olfactory representations outperform widely-used hand-crafted features.
Authors: Xintong Li, Haoran Zhang, Xiao Zhou
Abstract: The abundance of fine-grained spatio-temporal data, such as traffic sensor networks, offers vast opportunities for scientific discovery. However, inferring causal relationships from such observational data remains challenging, particularly due to unobserved confounders that are specific to units (e.g., geographical locations) yet influence outcomes over time. Most existing methods for spatio-temporal causal inference assume that all confounders are observed, an assumption that is often violated in practice. In this paper, we introduce Spatio-Temporal Hierarchical Causal Models (ST-HCMs), a novel graphical framework that extends hierarchical causal modeling to the spatio-temporal domain. At the core of our approach is the Spatio-Temporal Collapse Theorem, which shows that a complex ST-HCM converges to a simpler flat causal model as the amount of subunit data increases. This theoretical result enables a general procedure for causal identification, allowing ST-HCMs to recover causal effects even in the presence of unobserved, time-invariant unit-level confounders, a scenario where standard non-hierarchical models fail. We validate the effectiveness of our framework on both synthetic and real-world datasets, demonstrating its potential for robust causal inference in complex dynamic systems.
Authors: Tasha Kim, Oiwi Parker Jones
Abstract: Safety-critical assistive systems that directly decode user intent from neural signals require rigorous guarantees of reliability and trust. We present GUARDIAN (Gated Uncertainty-Aware Runtime Dual Invariants), a framework for real-time neuro-symbolic verification for neural signal-controlled robotics. GUARDIAN enforces both logical safety and physiological trust by coupling confidence-calibrated brain signal decoding with symbolic goal grounding and dual-layer runtime monitoring. On the BNCI2014 motor imagery electroencephalogram (EEG) dataset with 9 subjects and 5,184 trials, the system performs at a high safety rate of 94-97% even with lightweight decoder architectures with low test accuracies (27-46%) and high ECE confidence miscalibration (0.22-0.41). We demonstrate 1.7x correct interventions in simulated noise testing versus at baseline. The monitor operates at 100Hz and sub-millisecond decision latency, making it practically viable for closed-loop neural signal-based systems. Across 21 ablation results, GUARDIAN exhibits a graduated response to signal degradation, and produces auditable traces from intent, plan to action, helping to link neural evidence to verifiable robot action.
Authors: Koffi Ismael Ouattara, Ioannis Krontiris, Theo Dimitrakos, Dennis Eisermann, Frank Kargl
Abstract: Trustworthiness has become a key requirement for the deployment of artificial intelligence systems in safety-critical applications. Conventional evaluation metrics such as accuracy and precision fail to capture uncertainty or the reliability of model predictions, particularly under adversarial or degraded conditions. This paper introduces the \emph{Parallel Trust Assessment System (PaTAS)}, a framework for modeling and propagating trust in neural networks using Subjective Logic (SL). PaTAS operates in parallel with standard neural computation through \emph{Trust Nodes} and \emph{Trust Functions} that propagate input, parameter, and activation trust across the network. The framework defines a \emph{Parameter Trust Update} mechanism to refine parameter reliability during training and an \emph{Inference-Path Trust Assessment (IPTA)} method to compute instance-specific trust at inference. Experiments on real-world and adversarial datasets demonstrate that PaTAS produces interpretable, symmetric, and convergent trust estimates that complement accuracy and expose reliability gaps in poisoned, biased, or uncertain data scenarios. The results show that PaTAS effectively distinguishes between benign and adversarial inputs and identifies cases where model confidence diverges from actual reliability. By enabling transparent and quantifiable trust reasoning within neural architectures, PaTAS provides a principled foundation for evaluating model reliability across the AI lifecycle.
Authors: Yixin Liu, Pengfei Liu, Arman Cohan
Abstract: Alignment with human preferences is an important evaluation aspect of LLMs, requiring them to be helpful, honest, safe, and to precisely follow human instructions. Evaluating large language models' (LLMs) alignment typically involves directly assessing their open-ended responses, requiring human annotators or strong LLM judges. Conversely, LLMs themselves have also been extensively evaluated as judges for assessing alignment. In this work, we examine the relationship between LLMs' generation and evaluation capabilities in aligning with human preferences. To this end, we first conduct a comprehensive analysis of the generation-evaluation consistency (GE-consistency) among various LLMs, revealing a strong correlation between their generation and evaluation capabilities when evaluated by a strong LLM preference oracle. Utilizing this finding, we propose a benchmarking paradigm that measures LLM alignment with human preferences without directly evaluating their generated outputs, instead assessing LLMs in their role as evaluators. Our evaluation shows that our proposed benchmark, AlignEval, matches or surpasses widely used automatic LLM evaluation benchmarks, such as AlpacaEval and Arena-Hard, in capturing human preferences when ranking LLMs. Our study offers valuable insights into the connection between LLMs' generation and evaluation capabilities, and introduces a benchmark that assesses alignment without directly evaluating model outputs.
Authors: Chieh-Yun Chen, Zhonghao Wang, Qi Chen, Zhifan Ye, Min Shi, Yue Zhao, Yinan Zhao, Hui Qu, Wei-An Lin, Yiru Shen, Ajinkya Kale, Irfan Essa, Humphrey Shi
Abstract: Reinforcement learning from human feedback (RLHF) with reward models has advanced alignment of generative models to human aesthetic and perceptual preferences. However, jointly optimizing multiple rewards often incurs an alignment tax, improving one dimension while degrading others. To address this, we introduce two complementary methods: MapReduce LoRA and Reward-aware Token Embedding (RaTE). MapReduce LoRA trains preference-specific LoRA experts in parallel and iteratively merges them to refine a shared base model; RaTE learns reward-specific token embeddings that compose at inference for flexible preference control. Experiments on Text-to-Image generation (Stable Diffusion 3.5 Medium and FLUX.1-dev) show improvements of 36.1%, 4.6%, and 55.7%, and 32.7%, 4.3%, and 67.1% on GenEval, PickScore, and OCR, respectively. On Text-to-Video generation (HunyuanVideo), visual and motion quality improve by 48.1% and 90.0%, respectively. On the language task, Helpful Assistant, with Llama-2 7B, helpful and harmless improve by 43.4% and 136.7%, respectively. Our framework sets a new state-of-the-art multi-preference alignment recipe across modalities.
Authors: Jiaru Zou, Xiyuan Yang, Ruizhong Qiu, Gaotang Li, Katherine Tieu, Pan Lu, Ke Shen, Hanghang Tong, Yejin Choi, Jingrui He, James Zou, Mengdi Wang, Ling Yang
Abstract: Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we take a step forward by enabling models to collaborate directly within the continuous latent space. We introduce LatentMAS, an end-to-end training-free framework that enables pure latent collaboration among LLM agents. In LatentMAS, each agent first performs auto-regressive latent thoughts generation through last-layer hidden embeddings. A shared latent working memory then preserves and transfers each agent's internal representations, ensuring lossless information exchange. We provide theoretical analyses establishing that LatentMAS attains higher expressiveness and lossless information preservation with substantially lower complexity than vanilla text-based MAS. In addition, empirical evaluations across 9 comprehensive benchmarks spanning math and science reasoning, commonsense understanding, and code generation show that LatentMAS consistently outperforms strong single-model and text-based MAS baselines, achieving up to 14.6% higher accuracy, reducing output token usage by 70.8%-83.7%, and providing 4x-4.3x faster end-to-end inference. These results demonstrate that our new latent collaboration framework enhances system-level reasoning quality while offering substantial efficiency gains without any additional training. Code and data are fully open-sourced at https://github.com/Gen-Verse/LatentMAS.
Authors: Ryan Burgert, Charles Herrmann, Forrester Cole, Michael S Ryoo, Neal Wadhwa, Andrey Voynov, Nataniel Ruiz
Abstract: While generative video models have achieved remarkable fidelity and consistency, applying these capabilities to video editing remains a complex challenge. Recent research has explored motion controllability as a means to enhance text-to-video generation or image animation; however, we identify precise motion control as a promising yet under-explored paradigm for editing existing videos. In this work, we propose modifying video motion by directly editing sparse trajectories extracted from the input. We term the deviation between input and output trajectories a "motion edit" and demonstrate that this representation, when coupled with a generative backbone, enables powerful video editing capabilities. To achieve this, we introduce a pipeline for generating "motion counterfactuals", video pairs that share identical content but distinct motion, and we fine-tune a motion-conditioned video diffusion architecture on this dataset. Our approach allows for edits that start at any timestamp and propagate naturally. In a four-way head-to-head user study, our model achieves over 65 percent preference against prior work. Please see our project page: https://ryanndagreat.github.io/MotionV2V
Authors: Wei Tang, Zuo-Zheng Wang, Kun Zhang, Tong Wei, Min-Ling Zhang
Abstract: Long-tailed multi-label visual recognition poses a significant challenge, as images typically contain multiple labels with highly imbalanced class distributions, leading to biased models that favor head classes while underperforming on tail classes. Recent efforts have leveraged pre-trained vision-language models, such as CLIP, alongside long-tailed learning techniques to exploit rich visual-textual priors for improved performance. However, existing methods often derive semantic inter-class relationships directly from imbalanced datasets, resulting in unreliable correlations for tail classes due to data scarcity. Moreover, CLIP's zero-shot paradigm is optimized for single-label image-text matching, making it suboptimal for multi-label tasks. To address these issues, we propose the correlation adaptation prompt network (CAPNET), a novel end-to-end framework that explicitly models label correlations from CLIP's textual encoder. The framework incorporates a graph convolutional network for label-aware propagation and learnable soft prompts for refined embeddings. It utilizes a distribution-balanced Focal loss with class-aware re-weighting for optimized training under imbalance. Moreover, it improves generalization through test-time ensembling and realigns visual-textual modalities using parameter-efficient fine-tuning to avert overfitting on tail classes without compromising head class performance. Extensive experiments and ablation studies on benchmarks including VOC-LT, COCO-LT, and NUS-WIDE demonstrate that CAPNET achieves substantial improvements over state-of-the-art methods, validating its effectiveness for real-world long-tailed multi-label visual recognition.
Authors: Adhiraj Ghosh, Vishaal Udandarao, Thao Nguyen, Matteo Farina, Mehdi Cherti, Jenia Jitsev, Sewoong Oh, Elisa Ricci, Ludwig Schmidt, Matthias Bethge
Abstract: What data should a vision-language model be trained on? To answer this question, many data curation efforts center on the quality of a dataset. However, most of these existing methods are (i) offline, i.e. they produce a static dataset from a set of predetermined filtering criteria, and (ii) concept-agnostic, i.e. they use model-based filters which induce additional data biases. In this work, we go beyond such offline, concept-agnostic methods and advocate for more flexible, task-adaptive online concept-based curation. Our first contribution is DataConcept, a collection of 128M web-crawled image-text pairs annotated with fine-grained details about their concept composition. Building on DataConcept, we introduce Concept-Aware Batch Sampling (CABS), a simple yet effective batch sampling framework that flexibly constructs batches on-the-fly based on specific target distributions. We propose two variants: (i) Diversity Maximization (CABS-DM) to curate batches with a broad coverage of available concepts, and (ii) Frequency Maximization (CABS-FM) to curate batches with high object multiplicity. Through extensive evaluations across 28 benchmarks, we demonstrate that our CABS method significantly benefits CLIP/SigLIP model classes and yields highly performant models. Overall, CABS represents a strong open-source alternative to proprietary online data curation algorithms, enabling practitioners to define custom concept distributions that optimize for specific downstream tasks.
Authors: Luca Cosmo, Giorgia Minello, Alessandro Bicciato, Michael Bronstein, Emanuele Rodol\`a, Luca Rossi, Andrea Torsello
Abstract: The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an input matrix and a filter. While this is readily applicable to data such as images, which can be represented as regular grids in the Euclidean space, extending the convolution operator to work on graphs proves more challenging, due to their irregular structure. In this paper, we propose to use graph kernels, i.e. kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type of graph kernels and has the added benefit of providing some interpretability in terms of the structural masks that are learned during the training process, similarly to what happens for convolutional masks in traditional convolutional neural networks. We perform an extensive ablation study to investigate the model hyper-parameters' impact and show that our model achieves competitive performance on standard graph classification and regression datasets.
Authors: Gavin Brown, Samuel B. Hopkins, Adam Smith
Abstract: We present a fast, differentially private algorithm for high-dimensional covariance-aware mean estimation with nearly optimal sample complexity. Only exponential-time estimators were previously known to achieve this guarantee. Given $n$ samples from a (sub-)Gaussian distribution with unknown mean $\mu$ and covariance $\Sigma$, our $(\varepsilon,\delta)$-differentially private estimator produces $\tilde{\mu}$ such that $\|\mu - \tilde{\mu}\|_{\Sigma} \leq \alpha$ as long as $n \gtrsim \tfrac d {\alpha^2} + \tfrac{d \sqrt{\log 1/\delta}}{\alpha \varepsilon}+\frac{d\log 1/\delta}{\varepsilon}$. The Mahalanobis error metric $\|\mu - \hat{\mu}\|_{\Sigma}$ measures the distance between $\hat \mu$ and $\mu$ relative to $\Sigma$; it characterizes the error of the sample mean. Our algorithm runs in time $\tilde{O}(nd^{\omega - 1} + nd/\varepsilon)$, where $\omega < 2.38$ is the matrix multiplication exponent. We adapt an exponential-time approach of Brown, Gaboardi, Smith, Ullman, and Zakynthinou (2021), giving efficient variants of stable mean and covariance estimation subroutines that also improve the sample complexity to the nearly optimal bound above. Our stable covariance estimator can be turned to private covariance estimation for unrestricted subgaussian distributions. With $n\gtrsim d^{3/2}$ samples, our estimate is accurate in spectral norm. This is the first such algorithm using $n= o(d^2)$ samples, answering an open question posed by Alabi et al. (2022). With $n\gtrsim d^2$ samples, our estimate is accurate in Frobenius norm. This leads to a fast, nearly optimal algorithm for private learning of unrestricted Gaussian distributions in TV distance. Duchi, Haque, and Kuditipudi (2023) obtained similar results independently and concurrently.
Authors: Xiaoyun Liu, Divya Saxena, Jiannong Cao, Yuqing Zhao, Penghui Ruan
Abstract: Neural architecture search (NAS) has gained significant traction in automating the design of neural networks. To reduce search time, differentiable architecture search (DAS) reframes the traditional paradigm of discrete candidate sampling and evaluation into a differentiable optimization over a super-net, followed by discretization. However, most existing DAS methods primarily focus on optimizing the coarse-grained operation-level topology, while neglecting finer-grained structures such as filter-level and weight-level patterns. This limits their ability to balance model performance with model size. Additionally, many methods compromise search quality to save memory during the search process. To tackle these issues, we propose Multi-Granularity Differentiable Architecture Search (MG-DARTS), a unified framework which aims to discover both effective and efficient architectures from scratch by comprehensively yet memory-efficiently exploring a multi-granularity search space. Specifically, we improve the existing DAS methods in two aspects. First, we adaptively adjust the retention ratios of searchable units across different granularity levels through adaptive pruning, which is achieved by learning granularity-specific discretization functions along with the evolving architecture. Second, we decompose the super-net optimization and discretization into multiple stages, each operating on a sub-net, and introduce progressive re-evaluation to enable re-pruning and regrowth of previous units, thereby mitigating potential bias. Extensive experiments on CIFAR-10, CIFAR-100 and ImageNet demonstrate that MG-DARTS outperforms other state-of-the-art methods in achieving a better trade-off between model accuracy and parameter efficiency. Codes are available at https://github.com/lxy12357/MG_DARTS.
Authors: Phai Vu Dinh, Diep N. Nguyen, Dinh Thai Hoang, Quang Uy Nguyen, Eryk Dutkiewicz, Son Pham Bao
Abstract: While intrusion detection systems (IDSs) benefit from the diversity and generalization of IoT data features, the data diversity (e.g., the heterogeneity and high dimensions of data) also makes it difficult to train effective machine learning models in IoT IDSs. This also leads to potentially redundant/noisy features that may decrease the accuracy of the detection engine in IDSs. This paper first introduces a novel neural network architecture called Multiple-Input Auto-Encoder (MIAE). MIAE consists of multiple sub-encoders that can process inputs from different sources with different characteristics. The MIAE model is trained in an unsupervised learning mode to transform the heterogeneous inputs into lower-dimensional representation, which helps classifiers distinguish between normal behaviour and different types of attacks. To distil and retain more relevant features but remove less important/redundant ones during the training process, we further design and embed a feature selection layer right after the representation layer of MIAE resulting in a new model called MIAEFS. This layer learns the importance of features in the representation vector, facilitating the selection of informative features from the representation vector. The results on three IDS datasets, i.e., NSLKDD, UNSW-NB15, and IDS2017, show the superior performance of MIAE and MIAEFS compared to other methods, e.g., conventional classifiers, dimensionality reduction models, unsupervised representation learning methods with different input dimensions, and unsupervised feature selection models. Moreover, MIAE and MIAEFS combined with the Random Forest (RF) classifier achieve accuracy of 96.5% in detecting sophisticated attacks, e.g., Slowloris. The average running time for detecting an attack sample using RF with the representation of MIAE and MIAEFS is approximate 1.7E-6 seconds, whilst the model size is lower than 1 MB.
Authors: Yiyuan Yang, Ming Jin, Haomin Wen, Chaoli Zhang, Yuxuan Liang, Lintao Ma, Yi Wang, Chenghao Liu, Bin Yang, Zenglin Xu, Shirui Pan, Qingsong Wen
Abstract: Diffusion models have been widely used in time series and spatio-temporal data, enhancing generative, inferential, and downstream capabilities. These models are applied across diverse fields such as healthcare, recommendation, climate, energy, audio, and traffic. By separating applications for time series and spatio-temporal data, we offer a structured perspective on model category, task type, data modality, and practical application domain. This study aims to provide a solid foundation for researchers and practitioners, inspiring future innovations that tackle traditional challenges and foster novel solutions in diffusion model-based data mining tasks and applications. For more detailed information, we have open-sourced a repository at https://github.com/yyysjz1997/Awesome-TimeSeries-SpatioTemporal-Diffusion-Model.
URLs: https://github.com/yyysjz1997/Awesome-TimeSeries-SpatioTemporal-Diffusion-Model.
Authors: Chaoran Cheng, Jiahan Li, Jian Peng, Ge Liu
Abstract: We introduce Statistical Flow Matching (SFM), a novel and mathematically rigorous flow-matching framework on the manifold of parameterized probability measures inspired by the results from information geometry. We demonstrate the effectiveness of our method on the discrete generation problem by instantiating SFM on the manifold of categorical distributions whose geometric properties remain unexplored in previous discrete generative models. Utilizing the Fisher information metric, we equip the manifold with a Riemannian structure whose intrinsic geometries are effectively leveraged by following the shortest paths of geodesics. We develop an efficient training and sampling algorithm that overcomes numerical stability issues with a diffeomorphism between manifolds. Our distinctive geometric perspective of statistical manifolds allows us to apply optimal transport during training and interpret SFM as following the steepest direction of the natural gradient. Unlike previous models that rely on variational bounds for likelihood estimation, SFM enjoys the exact likelihood calculation for arbitrary probability measures. We manifest that SFM can learn more complex patterns on the statistical manifold where existing models often fail due to strong prior assumptions. Comprehensive experiments on real-world generative tasks ranging from image, text to biological domains further demonstrate that SFM achieves higher sampling quality and likelihood than other discrete diffusion or flow-based models.
Authors: Yaniv Oren, Moritz A. Zanger, Pascal R. van der Vaart, Mustafa Mert Celikok, Matthijs T. J. Spaan, Wendelin Bohmer
Abstract: To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greedification operators to iteratively improve it. The reliance on DNNs suggests an improvement that is gradient based, which is per step much less greedy than the improvement possible by greedier operators such as the greedy update used by Q-learning algorithms. On the other hand, slow changes to the policy can also be beneficial for the stability of the learning process, resulting in a tradeoff between greedification and stability. To better address this tradeoff, we propose to decouple the acting policy from the policy evaluated by the critic. This allows the agent to separately improve the critic's policy (e.g. value improvement) with greedier updates while maintaining the slow gradient-based improvement to the parameterized acting policy. We investigate the convergence of this approach using the popular analysis scheme of generalized Policy Iteration in the finite-horizon domain. Empirically, incorporating value-improvement into the popular off-policy actor-critic algorithms TD3 and SAC significantly improves or matches performance over their respective baselines, across different environments from the DeepMind continuous control domain, with negligible compute and implementation cost.
Authors: Maciej Besta, Florian Scheidl, Lukas Gianinazzi, Grzegorz Kwasniewski, Shachar Klaiman, J\"urgen M\"uller, Torsten Hoefler
Abstract: Higher-order graph neural networks (HOGNNs) and the related architectures from Topological Deep Learning are an important class of GNN models that harness polyadic relations between vertices beyond plain edges. They have been used to eliminate issues such as over-smoothing or over-squashing, to significantly enhance the accuracy of GNN predictions, to improve the expressiveness of GNN architectures, and for numerous other goals. A plethora of HOGNN models have been introduced, and they come with diverse neural architectures, and even with different notions of what the "higher-order" means. This richness makes it very challenging to appropriately analyze and compare HOGNN models, and to decide in what scenario to use specific ones. To alleviate this, we first design an in-depth taxonomy and a blueprint for HOGNNs. This facilitates designing models that maximize performance. Then, we use our taxonomy to analyze and compare the available HOGNN models. The outcomes of our analysis are synthesized in a set of insights that help to select the most beneficial GNN model in a given scenario, and a comprehensive list of challenges and opportunities for further research into more powerful HOGNNs.
Authors: Tianyu Fu, Haofeng Huang, Xuefei Ning, Genghan Zhang, Boju Chen, Tianqi Wu, Hongyi Wang, Zixiao Huang, Shiyao Li, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
Abstract: Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods typically employ a single window length across all attention heads and input sizes. However, this uniform approach fails to capture the heterogeneous attention patterns inherent in LLMs, ignoring their distinct accuracy-latency trade-offs. To address this challenge, we propose *Mixture of Attention Spans* (MoA), which automatically tailors distinct sliding-window length configurations to different heads and layers. MoA constructs and navigates a search space of various window lengths and their scaling rules relative to input sizes. It profiles the model, evaluates potential configurations, and pinpoints the optimal length configurations for each head. MoA adapts to varying input sizes, revealing that some attention heads expand their focus to accommodate longer inputs, while other heads consistently concentrate on fixed-length local contexts. Experiments show that MoA increases the effective context length by 3.9x with the same average sliding-window length, boosting retrieval accuracy by 1.5-7.1x over the uniform-window baseline across Vicuna-{7B, 13B} and Llama3-{8B, 70B} models. Moreover, MoA narrows the performance gap with full attention, reducing the maximum relative performance drop from 9%-36% to within 5% across three long-context understanding benchmarks. MoA achieves a 1.2-1.4x GPU memory reduction, boosting decode throughput by 6.6-8.2x and 1.7-1.9x over FlashAttention2 and vLLM, with minimal performance impact. Our code is available at: https://github.com/thu-nics/MoA
Authors: Andrew Dennehy, Xiaoyu Zou, Shabnam J. Semnani, Yuri Fialko, Alexander Cloninger
Abstract: DBSCAN and OPTICS are powerful algorithms for identifying clusters of points in domains where few assumptions can be made about the structure of the data. In this paper, we leverage these strengths and introduce a new algorithm, LINSCAN, designed to seek lineated clusters that are difficult to find and isolate with existing methods. In particular, by embedding points as normal distributions approximating their local neighborhoods and leveraging a distance function derived from the Kullback Leibler Divergence, LINSCAN can detect and distinguish lineated clusters that are spatially close but have orthogonal covariances. We demonstrate how LINSCAN can be applied to seismic data to identify active faults, including intersecting faults, and determine their orientation. Finally, we discuss the properties a generalization of DBSCAN and OPTICS must have in order to retain the stability benefits of these algorithms.
Authors: Astrit Tola, Funmilola Mary Taiwo, Cuneyt Gurcan Akcora, Baris Coskunuzer
Abstract: Graph embeddings play a critical role in graph representation learning, allowing machine learning models to explore and interpret graph-structured data. However, existing methods often rely on opaque, high-dimensional embeddings, limiting interpretability and practical visualization. In this work, we introduce Topological Evolution Rate (TopER), a novel, low-dimensional embedding approach grounded in topological data analysis. TopER simplifies a key topological approach, Persistent Homology, by calculating the evolution rate of graph substructures, resulting in intuitive and interpretable visualizations of graph data. This approach not only enhances the exploration of graph datasets but also delivers competitive performance in graph clustering and classification tasks. Our TopER-based models achieve or surpass state-of-the-art results across molecular, biological, and social network datasets in tasks such as classification, clustering, and visualization.
Authors: Md Joshem Uddin, Astrit Tola, Varin Sikand, Cuneyt Gurcan Akcora, Baris Coskunuzer
Abstract: Effective node representation lies at the heart of Graph Neural Networks (GNNs), as it directly impacts their ability to perform downstream tasks such as node classification and link prediction. Most existing GNNs, particularly message passing graph neural networks, rely on neighborhood aggregation to iteratively compute node embeddings. While powerful, this paradigm suffers from well-known limitations of oversquashing, oversmoothing, and underreaching that degrade representation quality. More critically, MPGNNs often assume homophily, where connected nodes share similar features or labels, leading to poor generalization in heterophilic graphs where this assumption breaks down. To address these challenges, we propose \textit{SCNode}, a \textit{Spatial-Contextual Node Embedding} framework designed to perform consistently well in both homophilic and heterophilic settings. SCNode integrates spatial and contextual information, yielding node embeddings that are not only more discriminative but also structurally aware. Our approach introduces new homophily matrices for understanding class interactions and tendencies. Extensive experiments on benchmark datasets show that SCNode achieves superior performance over conventional GNN models, demonstrating its robustness and adaptability in diverse graph structures.
Authors: Matthew V Macfarlane, Clement Bonnet
Abstract: General intelligence requires systems that acquire new skills efficiently and generalize beyond their training distributions. Although program synthesis approaches have strong generalization power, they face scaling issues due to the large combinatorial spaces that quickly render them impractical, requiring human-generated DSLs or pre-trained priors to narrow this search space. On the other hand, deep learning methods have had high successes, but they lack structured test-time adaptation and rely on heavy stochastic sampling or expensive gradient updates for fine-tuning. In this work, we propose the Latent Program Network (LPN), a novel architecture that builds in test-time search directly into neural models. LPN learns a latent space of implicit programs -- neurally mapping inputs to outputs -- through which it can search using gradients at test time. LPN combines the adaptability of symbolic approaches and the scalability of neural methods. It searches through a compact latent space at test time and bypasses the need for pre-defined domain-specific languages. On a range of programming-by-examples tasks, LPN either outperforms or matches performance compared to in-context learning and test-time training methods. Tested on the ARC-AGI benchmark, we demonstrate that LPN can both learn a compact program space and search through it at test time to adapt to novel tasks. LPN doubles its performance on out-of-distribution tasks when test-time search is switched on.
Authors: Till Freihaut, Giorgia Ramponi
Abstract: Multi-agent Inverse Reinforcement Learning (MAIRL) aims to recover agent reward functions from expert demonstrations. We characterize the feasible reward set in Markov games, identifying all reward functions that rationalize a given equilibrium. However, equilibrium-based observations are often ambiguous: a single Nash equilibrium can correspond to many reward structures, potentially changing the game's nature in multi-agent systems. We address this by introducing entropy-regularized Markov games, which yield a unique equilibrium while preserving strategic incentives. For this setting, we provide a sample complexity analysis detailing how errors affect learned policy performance. Our work establishes theoretical foundations and practical insights for MAIRL.
Authors: Xiangkai Ma, Xiaobin Hong, Mingkai Lin, Han Zhang, Wenzhong Li, Sanglu Lu
Abstract: Conventional deep models have achieved unprecedented success in time series forecasting. However, facing the challenge of cross-domain generalization, existing studies utilize statistical prior as prompt engineering fails under the huge distribution shift among various domains. In this paper, a novel time series generalization diffusion model (TimeControl) that pioneers the Domain-Fusion paradigm, systematically integrating information from multiple time series domains into a unified generative process via diffusion models. Unlike the autoregressive models that capture the conditional probabilities of the prediction horizon to the historical sequence, we use the diffusion denoising process to model the mixed distribution of the cross-domain data and generate the prediction sequence for the target domain directly utilizing conditional sampling. The proposed TimeControl contains three pivotal designs: (1) The condition network captures the multi-scale fluctuation patterns from the observation sequence, which are utilized as context representations to guide the denoising network to generate the prediction sequence; (2) Adapter-based fine-tuning strategy, the multi-domain universal representation learned in the pretraining stage is utilized for downstream tasks in target domains; (3) A novel hybrid architecture is designed to align the observation and prediction spaces, enabling TimeControl to generate prediction sequences of arbitrary lengths with flexibility. We conduct extensive experiments on mainstream 49 benchmarks and 30 baselines, and the TimeControl outperforms existing baselines on all data domains, exhibiting superior zero-shot generalization ability.
Authors: James Queeney, Xiaoyi Cai, Alexander Schperberg, Radu Corcodel, Mouhacine Benosman, Jonathan P. How
Abstract: The reliable deployment of deep reinforcement learning in real-world settings requires the ability to generalize across a variety of conditions, including both in-distribution scenarios seen during training as well as novel out-of-distribution scenarios. In this work, we present a framework for dynamics generalization in deep reinforcement learning that unifies these two distinct types of generalization within a single architecture. We introduce a robust adaptation module that provides a mechanism for identifying and reacting to both in-distribution and out-of-distribution environment dynamics, along with a joint training pipeline that combines the goals of in-distribution adaptation and out-of-distribution robustness. Our algorithm GRAM achieves strong generalization performance across in-distribution and out-of-distribution scenarios upon deployment, which we demonstrate through extensive simulation and hardware locomotion experiments on a quadruped robot.
Authors: Feng Chen, Allan Raventos, Nan Cheng, Surya Ganguli, Shaul Druckmann
Abstract: Recent progress in large language models (LLMs) highlights the power of scaling test-time compute to achieve strong performance on complex tasks, such as mathematical reasoning and code generation. This raises a critical question: how should model training be modified to optimize performance under a subsequent test-time compute strategy and budget? To explore this, we focus on pass@N, a simple test-time strategy that searches for a correct answer in $N$ independent samples. We show, surprisingly, that training with cross-entropy (CE) loss can be ${\it misaligned}$ with pass@N in that pass@N accuracy ${\it decreases}$ with longer training. We explain the origins of this misalignment in terms of model overconfidence induced by CE, and experimentally verify our prediction of overconfidence as an impediment to scaling test-time compute via pass@N. Furthermore we suggest a principled, modified training loss that is better aligned to pass@N by limiting model confidence and rescuing pass@N test performance. Our algorithm demonstrates improved mathematical reasoning on MATH and MiniF2F benchmarks under several scenarios: (1) providing answers to math questions; and (2) proving theorems by searching over proof trees of varying shapes. Overall our work underscores the importance of co-designing two traditionally separate phases of LLM development: training-time protocols and test-time search and reasoning strategies.
Authors: Jiyue Tao, Tongsheng Shen, Dexin Zhao, Feitian Zhang
Abstract: The target defense problem (TDP) for unmanned surface vehicles (USVs) concerns intercepting an adversarial USV before it breaches a designated target region, using one or more defending USVs. A particularly challenging scenario arises when the attacker exhibits superior maneuverability compared to the defenders, significantly complicating effective interception. To tackle this challenge, this letter introduces ARBoids, a novel adaptive residual reinforcement learning framework that integrates deep reinforcement learning (DRL) with the biologically inspired, force-based Boids model. Within this framework, the Boids model serves as a computationally efficient baseline policy for multi-agent coordination, while DRL learns a residual policy to adaptively refine and optimize the defenders' actions. The proposed approach is validated in a high-fidelity Gazebo simulation environment, demonstrating superior performance over traditional interception strategies, including pure force-based approaches and vanilla DRL policies. Furthermore, the learned policy exhibits strong adaptability to attackers with diverse maneuverability profiles, highlighting its robustness and generalization capability. The code of ARBoids will be released upon acceptance of this letter.
Authors: Eshed Gal, Moshe Eliasof, Carola-Bibiane Sch\"onlieb, Ivan I. Kyrchei, Eldad Haber, Eran Treister
Abstract: Graph Neural Networks (GNNs) have become powerful tools for learning from graph-structured data, finding applications across diverse domains. However, as graph sizes and connectivity increase, standard GNN training methods face significant computational and memory challenges, limiting their scalability and efficiency. In this paper, we present a novel framework for efficient multiscale training of GNNs. Our approach leverages hierarchical graph representations and subgraphs, enabling the integration of information across multiple scales and resolutions. By utilizing coarser graph abstractions and subgraphs, each with fewer nodes and edges, we significantly reduce computational overhead during training. Building on this framework, we propose a suite of scalable training strategies, including coarse-to-fine learning, subgraph-to-full-graph transfer, and multiscale gradient computation. We also provide some theoretical analysis of our methods and demonstrate their effectiveness across various datasets and learning tasks. Our results show that multiscale training can substantially accelerate GNN training for large scale problems while maintaining, or even improving, predictive performance.
Authors: Neil He, Jiahong Liu, Buze Zhang, Ngoc Bui, Ali Maatouk, Menglin Yang, Irwin King, Melanie Weber, Rex Ying
Abstract: In the era of foundation models and Large Language Models (LLMs), Euclidean space has been the de facto geometric setting for machine learning architectures. However, recent literature has demonstrated that this choice comes with fundamental limitations. At a large scale, real-world data often exhibits inherently non-Euclidean structures, such as multi-way relationships, hierarchies, symmetries, and non-isotropic scaling, in a variety of domains, such as languages, vision, and the natural sciences. It is challenging to effectively capture these structures within the constraints of Euclidean spaces. This position paper argues that moving beyond Euclidean geometry is not merely an optional enhancement but a necessity to maintain the scaling law for the next-generation of foundation models. By adopting these geometries, foundation models could more efficiently leverage the aforementioned structures. Task-aware adaptability that dynamically reconfigures embeddings to match the geometry of downstream applications could further enhance efficiency and expressivity. Our position is supported by a series of theoretical and empirical investigations of prevalent foundation models. Finally, we outline a roadmap for integrating non-Euclidean geometries into foundation models, including strategies for building geometric foundation models via fine-tuning, training from scratch, and hybrid approaches.
Authors: Gang Li, Ming Lin, Tomer Galanti, Zhengzhong Tu, Tianbao Yang
Abstract: The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning models (LRMs). In this work, we analyze the GRPO objective under a binary reward setting and reveal an inherent limitation of question-level difficulty bias. We also identify a connection between GRPO and traditional discriminative methods in supervised learning. Motivated by these insights, we introduce a new Discriminative Constrained Optimization (DisCO) framework for reinforcing LRMs, grounded in the principle of discriminative learning. The main differences between DisCO and GRPO and its recent variants are: (1) it replaces the group relative objective with a discriminative objective defined by a scoring function; (2) it abandons clipping-based surrogates in favor of non-clipping RL surrogate objectives used as scoring functions; (3) it employs a simple yet effective constrained optimization approach to enforce the KL divergence constraint. As a result, DisCO offers notable advantages over GRPO and its variants: (i) it completely eliminates difficulty bias by adopting discriminative objectives; (ii) it addresses the entropy instability in GRPO and its variants through the use of non-clipping scoring functions and a constrained optimization approach, yielding long and stable training dynamics; (iii) it allows the incorporation of advanced discriminative learning techniques to address data imbalance, where a significant number of questions have more negative than positive generated answers during training. Our experiments on enhancing the mathematical reasoning capabilities of SFT-finetuned models show that DisCO significantly outperforms GRPO and its improved variants such as DAPO, achieving average gains of 7\% over GRPO and 6\% over DAPO across six benchmark tasks for an 1.5B model.
Authors: Gonzalo E. Constante-Flores, Hao Chen, Can Li
Abstract: Deep learning models are increasingly deployed in safety-critical tasks where predictions must satisfy hard constraints, such as physical laws, fairness requirements, or safety limits. However, standard architectures lack built-in mechanisms to enforce such constraints, and existing approaches based on regularization or projection are often limited to simple constraints, computationally expensive, or lack feasibility guarantees. This paper proposes a model-agnostic framework for enforcing input-dependent linear equality and inequality constraints on neural network outputs. The architecture combines a task network trained for prediction accuracy with a safe network trained using decision rules from the stochastic and robust optimization literature to ensure feasibility across the entire input space. The final prediction is a convex combination of the two subnetworks, guaranteeing constraint satisfaction during both training and inference without iterative procedures or runtime optimization. We prove that the architecture is a universal approximator of constrained functions and derive computationally tractable formulations based on linear decision rules. Empirical results on benchmark regression tasks show that our method consistently satisfies constraints while maintaining competitive accuracy and low inference latency.
Authors: Beier Luo, Shuoyuan Wang, Sharon Li, Hongxin Wei
Abstract: Post-training of large language models is essential for adapting pre-trained language models (PLMs) to align with human preferences and downstream tasks. While PLMs typically exhibit well-calibrated confidence, post-trained language models (PoLMs) often suffer from over-confidence, assigning high confidence to both correct and incorrect outputs, which can undermine reliability in critical applications. A major obstacle in calibrating PoLMs is the scarcity of labeled data for individual downstream tasks. To address this, we propose Disagreement-Aware Confidence Alignment (DACA), a novel unsupervised method to optimize the parameters (e.g., temperature $\tau$) in post-hoc confidence calibration. Our method is motivated by the under-confidence issue caused by prediction disagreement between the PLM and PoLM while aligning their confidence via temperature scaling. Theoretically, the PLM's confidence underestimates PoLM's prediction accuracy on disagreement examples, causing a larger $\tau$ and producing under-confident predictions. DACA mitigates this by selectively using only agreement examples for calibration, effectively decoupling the influence of disagreement. In this manner, our method avoids an overly large $\tau$ in temperature scaling caused by disagreement examples, improving calibration performance. Extensive experiments demonstrate the effectiveness of our method, improving the average ECE of open-sourced and API-based LLMs (e.g. GPT-4o) by up to 15.08$\%$ on common benchmarks.
Authors: Bingguang Hao, ZengZhuang Xu, Maolin Wang, Yuntao Wen, Yicheng Chen, Cunyin Peng, Long Chen, Dong Wang, Xiangyu Zhao, Jinjie Gu, Chenyi Zhuang, Ji Zhang
Abstract: The integration of large language models (LLMs) with function calling has emerged as a crucial capability for enhancing their practical utility in real-world applications. However, effectively combining reasoning processes with accurate function execution remains a significant challenge. Traditional training approaches often struggle to balance the detailed reasoning steps with the precision of function calls, leading to suboptimal performance. To address these limitations, we introduce FunReason, a novel framework that enhances LLMs' function calling capabilities through an automated data refinement strategy and a Self-Refinement Multiscale Loss (SRML) approach. FunReason leverages LLMs' natural reasoning abilities to generate high-quality training examples, focusing on query parseability, reasoning coherence, and function call precision. The SRML approach dynamically balances the contribution of reasoning processes and function call accuracy during training, addressing the inherent trade-off between these two critical aspects. FunReason achieves performance comparable to GPT-4o while effectively mitigating catastrophic forgetting during fine-tuning. FunReason provides a comprehensive solution for enhancing LLMs' function calling capabilities by introducing a balanced training methodology and a data refinement pipeline. For code and dataset, please refer to our repository at GitHub https://github.com/BingguangHao/FunReason
Authors: Ari S. Benjamin, Kyle Daruwalla, Christian Pehle, Abdul-Malik Zekri, Anthony M. Zador
Abstract: One frequently wishes to learn a range of similar tasks as efficiently as possible, re-using knowledge across tasks. In artificial neural networks, this is typically accomplished by conditioning a network upon task context by injecting context as input. Brains have a different strategy: the parameters themselves are modulated as a function of various neuromodulators such as serotonin. Here, we take inspiration from neuromodulation and propose to learn weights which are smoothly parameterized functions of task context variables. Rather than optimize a weight vector, i.e. a single point in weight space, we optimize a smooth manifold in weight space with a predefined topology. To accomplish this, we derive a formal treatment of optimization of manifolds as the minimization of a loss functional subject to a constraint on volumetric movement, analogous to gradient descent. During inference, conditioning selects a single point on this manifold which serves as the effective weight matrix for a particular sub-task. This strategy for conditioning has two main advantages. First, the topology of the manifold (whether a line, circle, or torus) is a convenient lever for inductive biases about the relationship between tasks. Second, learning in one state smoothly affects the entire manifold, encouraging generalization across states. To verify this, we train manifolds with several topologies, including straight lines in weight space (for conditioning on e.g. noise level in input data) and ellipses (for rotated images). Despite their simplicity, these parameterizations outperform conditioning identical networks by input concatenation and better generalize to out-of-distribution samples. These results suggest that modulating weights over low-dimensional manifolds offers a principled and effective alternative to traditional conditioning.
Authors: Wei Fu, Jiaxuan Gao, Xujie Shen, Chen Zhu, Zhiyu Mei, Chuyi He, Shusheng Xu, Guo Wei, Jun Mei, Jiashu Wang, Tongkai Yang, Binhang Yuan, Yi Wu
Abstract: Reinforcement learning (RL) has become a dominant paradigm for training large language models (LLMs), particularly for reasoning tasks. Effective RL for LLMs requires massive parallelization and poses an urgent need for efficient training systems. Most existing large-scale RL systems for LLMs are synchronous, alternating generation and training in a batch setting where rollouts in each training batch are generated by the same model. This approach stabilizes RL training but suffers from severe system-level inefficiency: generation must wait until the longest output in the batch is completed before model updates, resulting in GPU underutilization. We present AReaL, a fully asynchronous RL system that completely decouples generation from training. Rollout workers in AReaL continuously generate new outputs without waiting, while training workers update the model whenever a batch of data is collected. AReaL also incorporates a collection of system-level optimizations, leading to substantially higher GPU utilization. To stabilize RL training, AReaL balances the workload of rollout and training workers to control data staleness, and adopts a staleness-enhanced PPO variant to better handle outdated training samples. Extensive experiments on math and code reasoning benchmarks show that AReaL achieves up to 2.77$\times$ training speedup compared to synchronous systems with the same number of GPUs and matched or improved final performance. The code of AReaL is available at https://github.com/inclusionAI/AReaL/.
Authors: Sifan Wang, Zehao Dou, Siming Shan, Tong-Rui Liu, Lu Lu
Abstract: Recent advances in generative modeling -- particularly diffusion models and flow matching -- have achieved remarkable success in synthesizing discrete data such as images and videos. However, adapting these models to physical applications remains challenging, as the quantities of interest are continuous functions governed by complex physical laws. Here, we introduce $\textbf{FunDiff}$, a novel framework for generative modeling in function spaces. FunDiff combines a latent diffusion process with a function autoencoder architecture to handle input functions with varying discretizations, generate continuous functions evaluable at arbitrary locations, and seamlessly incorporate physical priors. These priors are enforced through architectural constraints or physics-informed loss functions, ensuring that generated samples satisfy fundamental physical laws. We theoretically establish minimax optimality guarantees for density estimation in function spaces, showing that diffusion-based estimators achieve optimal convergence rates under suitable regularity conditions. We demonstrate the practical effectiveness of FunDiff across diverse applications in fluid dynamics and solid mechanics. Empirical results show that our method generates physically consistent samples with high fidelity to the target distribution and exhibits robustness to noisy and low-resolution data. Code and datasets are publicly available at https://github.com/sifanexisted/fundiff.
Authors: Xin Wang, Zeyang Zhang, Linxin Xiao, Haibo Chen, Chendi Ge, Wenwu Zhu
Abstract: Multi-modal graphs, which integrate diverse multi-modal features and relations, are ubiquitous in real-world applications. However, existing multi-modal graph learning methods are typically trained from scratch for specific graph data and tasks, failing to generalize across various multi-modal graph data and tasks. To bridge this gap, we explore the potential of Multi-modal Graph Large Language Models (MG-LLM) to unify and generalize across diverse multi-modal graph data and tasks. We propose a unified framework of multi-modal graph data, task, and model, discovering the inherent multi-granularity and multi-scale characteristics in multi-modal graphs. Specifically, we present five key desired characteristics for MG-LLM: 1) unified space for multi-modal structures and attributes, 2) capability of handling diverse multi-modal graph tasks, 3) multi-modal graph in-context learning, 4) multi-modal graph interaction with natural language, and 5) multi-modal graph reasoning. We then elaborate on the key challenges, review related works, and highlight promising future research directions towards realizing these ambitious characteristics. Finally, we summarize existing multi-modal graph datasets pertinent for model training. We believe this paper can contribute to the ongoing advancement of the research towards MG-LLM for generalization across multi-modal graph data and tasks.
Authors: Mariya Hendriksen, Tabish Rashid, David Bignell, Raluca Georgescu, Abdelhak Lemkhenter, Katja Hofmann, Sam Devlin, Sarah Parisot
Abstract: World models - generative models that simulate environment dynamics conditioned on past observations and actions - are gaining prominence in planning, simulation, and embodied AI. However, evaluating their rollouts remains a fundamental challenge, requiring fine-grained, temporally grounded assessment of action alignment and semantic consistency - capabilities not captured by existing metrics. Vision-Language Models (VLMs) have shown promise as automatic evaluators of generative content due to their strong multimodal reasoning abilities. Yet, their use in fine-grained, temporally sensitive evaluation tasks remains limited and requires targeted adaptation. We introduce an evaluation protocol targeting two recognition tasks - action recognition and character recognition - each assessed across binary, multiple-choice, and open-ended formats. To support this, we present UNIVERSE (UNIfied Vision-language Evaluator for Rollouts in Simulated Environments), a VLM-based evaluator for video world model rollouts adapted under data and compute constraints. In our extensive experiments totaling over 5,154 GPU-days, we explore full, partial, and parameter-efficient adaptation methods across various task formats, context lengths, sampling methods, and data compositions. The resulting unified evaluator achieves parity with task-specific checkpoints. Human studies across seven diverse environments confirm strong alignment with human judgments, establishing UNIVERSE as a lightweight, adaptable, and semantics-aware evaluator for video world models.
Authors: Jaemoo Choi, Yongxin Chen, Molei Tao, Guan-Horng Liu
Abstract: Recently, there has been significant progress in learning-based diffusion samplers, which aim to sample from a given unnormalized density. Many of these approaches formulate the sampling task as a stochastic optimal control (SOC) problem using a canonical uninformative reference process, which limits their ability to efficiently guide trajectories toward the target distribution. In this work, we propose the Non-Equilibrium Annealed Adjoint Sampler (NAAS), a novel SOC-based diffusion framework that employs annealed reference dynamics as a non-stationary base SDE. This annealing structure provides a natural progression toward the target distribution and generates informative reference trajectories, thereby enhancing the stability and efficiency of learning the control. Owing to our SOC formulation, our framework can incorporate a variety of SOC solvers, thereby offering high flexibility in algorithmic design. As one instantiation, we employ a lean adjoint system inspired by adjoint matching, enabling efficient and scalable training. We demonstrate the effectiveness of NAAS across a range of tasks, including sampling from classical energy landscapes and molecular Boltzmann distributions.
Authors: Salva R\"uhling Cachay, Miika Aittala, Karsten Kreis, Noah Brenowitz, Arash Vahdat, Morteza Mardani, Rose Yu
Abstract: Diffusion models are a powerful tool for probabilistic forecasting, yet most applications in high-dimensional complex systems predict future states individually. This approach struggles to model complex temporal dependencies and fails to explicitly account for the progressive growth of uncertainty inherent to the systems. While rolling diffusion frameworks, which apply increasing noise to forecasts at longer lead times, have been proposed to address this, their integration with state-of-the-art, high-fidelity diffusion techniques remains a significant challenge. We tackle this problem by introducing Elucidated Rolling Diffusion Models (ERDM), the first framework to successfully unify a rolling forecast structure with the principled, performant design of Elucidated Diffusion Models (EDM). To do this, we adapt the core EDM components-its noise schedule, network preconditioning, and Heun sampler-to the rolling forecast setting. The success of this integration is driven by three key contributions: (i) a novel loss weighting scheme that focuses model capacity on the mid-range forecast horizons where determinism gives way to stochasticity; (ii) an efficient initialization strategy using a pre-trained EDM for the initial window; and (iii) a bespoke hybrid sequence architecture for robust spatiotemporal feature extraction under progressive denoising. On 2D Navier-Stokes simulations and ERA5 global weather forecasting at 1.5-degree resolution, ERDM consistently outperforms key diffusion-based baselines, including conditional autoregressive EDM. ERDM offers a flexible and powerful general framework for tackling diffusion-based dynamics forecasting problems where modeling uncertainty propagation is paramount.
Authors: Jun Ohkubo
Abstract: It is sometimes difficult to achieve a complete observation for a full set of observables, and partial observations are necessary. For deterministic systems, the Mori-Zwanzig formalism provides a theoretical framework for handling partial observations. Recently, data-driven algorithms based on the Koopman operator theory have made significant progress, and there is a discussion to connect the Mori-Zwanzig formalism with the Koopman operator theory. In this work, we discuss the effects of partial observation in stochastic systems using the Koopman operator theory. The discussion clarifies the importance of distinguishing the state space and the function space in stochastic systems. Even in stochastic systems, the delay-embedding technique is beneficial for partial observation, and several numerical experiments show a power-law behavior of error with respect to the amplitude of the additive noise. We also discuss the relation between the exponent of the power-law behavior and the effects of partial observation.
Authors: Sooyeon Kim, Giung Nam, Byoungwoo Park, Juho Lee
Abstract: Recent work has framed constrained text generation with autoregressive language models as a probabilistic inference problem. Among these, Zhao et al. (2024) introduced a promising approach based on twisted Sequential Monte Carlo, which incorporates learned twist functions and twist-induced proposals to guide the generation process. However, in constrained generation settings where the target distribution concentrates on outputs that are unlikely under the base model, learning becomes challenging due to sparse and uninformative reward signals. We show that iteratively refining the base model through self-distillation alleviates this issue by making the model progressively more aligned with the target, leading to substantial gains in generation quality.
Authors: Zixiao Huang, Junhao Hu, Hao Lin, Chunyang Zhu, Yueran Tang, Quanlu Zhang, Zhen Guo, Zhenhua Li, Shengen Yan, Zhenhua Zhu, Guohao Dai, Yu Wang
Abstract: The rapid scaling of large language models (LLMs) has significantly increased GPU memory pressure, which is further aggravated by training optimization techniques such as virtual pipeline and recomputation that disrupt tensor lifespans and introduce considerable memory fragmentation. Such fragmentation stems from the use of online GPU memory allocators in popular deep learning frameworks like PyTorch, which disregard tensor lifespans. As a result, this inefficiency can waste as much as 43% of memory and trigger out-of-memory errors, undermining the effectiveness of optimization methods. To address this, we introduce STAlloc, a GPU memory allocator for deep learning frameworks that reduces fragmentation by exploiting the spatial and temporal regularity in memory allocation behaviors of training workloads. STAlloc introduces a novel paradigm that combines offline planning with online allocation. The offline planning leverages spatio-temporal regularities to generate a near-optimal allocation plan, while the online allocation handles complex and dynamic models such as Mixture-of-Experts (MoE). Built as a pluggable PyTorch memory allocator, STAlloc reduces fragmentation ratio on average by 85.1% (up to 100%) across both dense and MoE models, with negligible overhead. This enables more efficient, high-throughput training configurations and improves throughput performance by up to 32.5%.
Authors: Ruichen Xu, Kexin Chen
Abstract: Modern large language models (LLMs) demonstrate exceptional performance on knowledge-intensive tasks, yet the theoretical mechanisms underlying knowledge acquisition (storage and memorization) during pre-training and extraction (retrieval and recall) during inference after fine-tuning remain poorly understood. Although prior theoretical studies have explored these processes through analyses of training dynamics, they overlook critical components essential for a comprehensive theory: (1) the multi-layer perceptron (MLP), empirically identified as the primary module for knowledge storage; (2) out-of-distribution (OOD) adaptivity, which enables LLMs to generalize to unseen scenarios post-pre-training; and (3) next-token prediction, the standard autoregressive objective that encodes knowledge as conditional probabilities. In this work, we introduce, to the best of our knowledge, the first theoretical framework that addresses these limitations by examining the training dynamics of one-layer transformers. Under regularity assumptions, we establish that: (i) transformers attain near-optimal training loss during pre-training, demonstrating effective knowledge acquisition; (ii) given a sufficiently large fine-tuning dataset and appropriate data multiplicity conditions, transformers achieve low generalization error on factual knowledge acquired during pre-training but not revisited in fine-tuning, indicating robust knowledge extraction; and (iii) violation of these conditions leads to elevated generalization error, manifesting as hallucinations. Our analysis encompasses both full fine-tuning and low-rank fine-tuning, yielding insights into the efficacy of practical low-rank adaptation methods. We validate our theoretical findings through experiments on synthetic datasets and the real-world PopQA benchmark, employing GPT-2 and Llama-3.2-1B models.
Authors: Pavankumar Koratikere, Leifur Leifsson
Abstract: Bayesian Optimization (BO) is a widely used approach for blackbox optimization that leverages a Gaussian process (GP) model and an acquisition function to guide future sampling. While effective in low-dimensional settings, BO faces scalability challenges in high-dimensional spaces and with large number of function evaluations due to the computational complexity of GP models. In contrast, neural networks (NNs) offer better scalability and can model complex functions, which led to the development of NN-based BO approaches. However, these methods typically rely on estimating model uncertainty in NN prediction -- a process that is often computationally intensive and complex, particularly in high dimensions. To address these limitations, a novel method, called scalable neural network-based blackbox optimization (SNBO), is proposed that does not rely on model uncertainty estimation. Specifically, SNBO adds new samples using separate criteria for exploration and exploitation, while adaptively controlling the sampling region to ensure efficient optimization. SNBO is evaluated on a range of optimization problems spanning from 10 to 102 dimensions and compared against four state-of-the-art baseline algorithms. Across the majority of test problems, SNBO attains function values better than the best-performing baseline algorithm, while requiring 40-60% fewer function evaluations and reducing the runtime by at least an order of magnitude.
Authors: Shuyi Zhang, Wei Shi, Sihang Li, Jiayi Liao, Hengxing Cai, Xiang Wang
Abstract: Large language models (LLMs) have been widely deployed across numerous fields. Reinforcement Learning from Human Feedback (RLHF) leverages reward models (RMs) as proxies for human preferences to align LLM behaviors with human values, making the accuracy, reliability, and interpretability of RMs critical for effective alignment. However, traditional RMs lack interpretability, offer limited insight into the reasoning behind reward assignments, and are inflexible toward user preference shifts. While recent multidimensional RMs aim for improved interpretability, they often fail to provide feature-level attribution and require costly annotations. To overcome these limitations, we introduce the Sparse Autoencoder-enhanced Reward Model (SARM), a novel architecture that integrates a pretrained Sparse Autoencoder (SAE) into a reward model. SARM maps the hidden activations of LLM-based RM into an interpretable, sparse, and monosemantic feature space, from which a scalar head aggregates feature activations to produce transparent and conceptually meaningful reward scores. Empirical evaluations demonstrate that SARM facilitates direct feature-level attribution of reward assignments, allows dynamic adjustment to preference shifts, and achieves superior alignment performance compared to conventional reward models. Our code is available at https://github.com/schrieffer-z/sarm.
Authors: Gabrielle Berrada, Jannik Kossen, Freddie Bickford Smith, Muhammed Razzak, Yarin Gal, Tom Rainforth
Abstract: Active testing enables label-efficient evaluation of predictive models through careful data acquisition, but it can pose a significant computational cost. We identify cost-saving measures that enable active testing to be scaled up to large language models (LLMs). In particular we show that the surrogate model used to guide data acquisition can be constructed cheaply using in-context learning, does not require updating within an active-testing loop, and can be smaller than the target model. We even find we can make good data-acquisition decisions without making predictions with the target model. As a result we are able to achieve much more accurate evaluations of LLM performance relative to using randomly acquired data. We additionally introduce a bootstrap estimator of evaluation error, which we show to be a useful indicator of how well active testing is working within a single run.
Authors: Emily Liu, Kuan Han, Minfeng Zhan, Bocheng Zhao, Guanyu Mu, Yang Song
Abstract: Watch time is widely used as a proxy for user satisfaction in video recommendation platforms. However, raw watch times are influenced by confounding factors such as video duration, popularity, and individual user behaviors, potentially distorting preference signals and resulting in biased recommendation models. We propose a novel relative advantage debiasing framework that corrects watch time by comparing it to empirically derived reference distributions conditioned on user and item groups. This approach yields a quantile-based preference signal and introduces a two-stage architecture that explicitly separates distribution estimation from preference learning. Additionally, we present distributional embeddings to efficiently parameterize watch-time quantiles without requiring online sampling or storage of historical data. Both offline and online experiments demonstrate significant improvements in recommendation accuracy and robustness compared to existing baseline methods.
Authors: Frederik L. Dennig, Daniel A. Keim
Abstract: Recently, autoencoders (AEs) have gained interest for creating parametric and invertible projections of multidimensional data. Parametric projections make it possible to embed new, unseen samples without recalculating the entire projection, while invertible projections allow the synthesis of new data instances. However, existing methods perform poorly when dealing with out-of-distribution samples in either the data or embedding space. Thus, we propose DE-VAE, an uncertainty-aware variational AE using differential entropy (DE) to improve the learned parametric and invertible projections. Given a fixed projection, we train DE-VAE to learn a mapping into 2D space and an inverse mapping back to the original space. We conduct quantitative and qualitative evaluations on four well-known datasets, using UMAP and t-SNE as baseline projection methods. Our findings show that DE-VAE can create parametric and inverse projections with comparable accuracy to other current AE-based approaches while enabling the analysis of embedding uncertainty.
Authors: Robert Yang
Abstract: Bold claims about AI's role in science-from "AGI will cure all diseases" to promises of radically accelerated discovery-raise a central epistemic question: do large language models (LLMs) truly generate new knowledge, or do they merely remix memorized fragments? We propose unlearning-as-ablation as a falsifiable probe of constructive scientific discovery. The idea is to systematically remove a target result together with its forget-closure (supporting lemmas, paraphrases, and multi-hop entailments) and then evaluate whether the model can re-derive the result from only permitted axioms and tools. Success would indicate generative capability beyond recall; failure would expose current limits. Unlike prevailing motivations for unlearning-privacy, copyright, or safety-our framing repositions it as an epistemic probe for AI-for-Science. We outline a minimal pilot in mathematics and algorithms to illustrate feasibility, and sketch how the same approach could later be extended to domains such as physics or chemistry. This is a position paper: our contribution is conceptual and methodological, not empirical. We aim to stimulate discussion on how principled ablation tests could help distinguish models that reconstruct knowledge from those that merely retrieve it, and how such probes might guide the next generation of AI-for-Science benchmarks.
Authors: Elias Sandmann, Sebastian Lapuschkin, Wojciech Samek
Abstract: Do neural networks build their representations through smooth, gradual refinement, or via more complex computational processes? We investigate this by extending the logit lens to analyze the policy network of Leela Chess Zero, a superhuman chess engine. Although playing strength and puzzle-solving ability improve consistently across layers, capability progression occurs in distinct computational phases with move preferences undergoing continuous reevaluation--move rankings remain poorly correlated with final outputs until late, and correct puzzle solutions found in middle layers are sometimes overridden. This late-layer reversal is accompanied by concept preference analyses showing final layers prioritize safety over aggression, suggesting a mechanism by which heuristic priors can override tactical solutions.
Authors: Quan Nguyen, Adji Bousso Dieng
Abstract: While monitoring biodiversity through camera traps has become an important endeavor for ecological research, identifying species in the captured image data remains a major bottleneck due to limited labeling resources. Active learning -- a machine learning paradigm that selects the most informative data to label and train a predictive model -- offers a promising solution, but typically focuses on uncertainty in the individual predictions without considering uncertainty across the entire dataset. We introduce a new active learning policy, Vendi information gain (VIG), that selects images based on their impact on dataset-wide prediction uncertainty, capturing both informativeness and diversity. We applied VIG to the Snapshot Serengeti dataset and compared it against common active learning methods. VIG needs only 3% of the available data to reach 75% accuracy, a level that baselines require more than 10% of the data to achieve. With 10% of the data, VIG attains 88% predictive accuracy, 12% higher than the best of the baselines. This improvement in performance is consistent across metrics and batch sizes, and we show that VIG also collects more diverse data in the feature space. VIG has broad applicability beyond ecology, and our results highlight its value for biodiversity monitoring in data-limited environments.
Authors: Yulei Qin, Xiaoyu Tan, Zhengbao He, Gang Li, Haojia Lin, Zongyi Li, Zihan Xu, Yuchen Shi, Siqi Cai, Renting Rui, Shaofei Cai, Yuzheng Cai, Xuan Zhang, Sheng Ye, Ke Li, Xing Sun
Abstract: Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing studies stimulate exploration through the lens of policy entropy, but such mechanical entropy maximization is prone to RL instability due to the multi-turn distribution shifting. In this paper, we target the progressive exploration-exploitation balance under the guidance of the agent's own experiences without succumbing to either entropy collapsing or runaway divergence. We propose SPEAR, a self-imitation learning (SIL) recipe for training agentic LLMs. It extends the vanilla SIL, where a replay buffer stores good experience for off-policy update, by gradually steering the policy entropy across stages. Specifically, the proposed curriculum scheduling harmonizes intrinsic reward shaping and self-imitation to 1) expedite exploration via frequent tool interactions at the beginning, and 2) strengthen exploitation of successful tactics upon convergence towards familiarity with the environment. We also combine bag-of-tricks of industrial RL optimizations for a strong baseline Dr.BoT to demonstrate our effectiveness. In ALFWorld and WebShop, SPEAR increases the success rates of GRPO/GiGPO/Dr.BoT by up to 16.1%/5.1%/8.6% and 20.7%/11.8%/13.9%, respectively. In AIME24 and AIME25, SPEAR boosts Dr.BoT by up to 3.8% and 6.1%, respectively. Such gains incur only 10%-25% extra theoretical complexity and negligible runtime overhead in practice, demonstrating the plug-and-play scalability of SPEAR.
Authors: Ahmad Ayaz Amin, Baha Uddin Kazi
Abstract: We introduce Random Projection Flows (RPFs), a principled framework for injective normalizing flows that leverages tools from random matrix theory and the geometry of random projections. RPFs employ random semi-orthogonal matrices, drawn from Haar-distributed orthogonal ensembles via QR decomposition of Gaussian matrices, to project data into lower-dimensional latent spaces for the base distribution. Unlike PCA-based flows or learned injective maps, RPFs are plug-and-play, efficient, and yield closed-form expressions for the Riemannian volume correction term. We demonstrate that RPFs are both theoretically grounded and practically effective, providing a strong baseline for generative modeling and a bridge between random projection theory and normalizing flows.
Authors: Will Y. Zou, Jean Feng, Alexandre Kalimouttou, Jennifer Yuntong Zhang, Christopher W. Seymour, Romain Pirracchio
Abstract: Reinforcement learning (RL) applications in Clinical Decision Support Systems (CDSS) frequently encounter skepticism because models may recommend inoperable dosing decisions. We propose an end-to-end offline RL framework for dual vasopressor administration in Intensive Care Units (ICUs) that directly addresses this challenge through principled action space design. Our method integrates discrete, continuous, and directional dosing strategies with conservative Q-learning and incorporates a novel recurrent modeling using a replay buffer to capture temporal dependencies in ICU time-series data. Our comparative analysis of norepinephrine dosing strategies across different action space formulations reveals that the designed action spaces improve interpretability and facilitate clinical adoption while preserving efficacy. Empirical results on eICU and MIMIC demonstrate that action space design profoundly influences learned behavioral policies. Compared with baselines, the proposed methods achieve more than 3x expected reward improvements, while aligning with established clinical protocols.
Authors: Agnieszka Polowczyk, Alicja Polowczyk, Joanna Waczy\'nska, Piotr Borycki, Przemys{\l}aw Spurek
Abstract: The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawful content. This has accelerated the push for machine unlearning. This new field seeks to selectively remove specific knowledge from a model's training data without causing a drop in its overall performance. However, it turns out that actually forgetting a given concept is an extremely difficult task. Models exposed to attacks using adversarial prompts show the ability to generate so-called unlearned concepts, which can be not only harmful but also illegal. In this paper, we present considerations regarding the ability of models to forget and recall knowledge, introducing the Memory Self-Regeneration task. Furthermore, we present MemoRa strategy, which we consider to be a regenerative approach supporting the effective recovery of previously lost knowledge. Moreover, we propose that robustness in knowledge retrieval is a crucial yet underexplored evaluation measure for developing more robust and effective unlearning techniques. Finally, we demonstrate that forgetting occurs in two distinct ways: short-term, where concepts can be quickly recalled, and long-term, where recovery is more challenging. Code is available at https://gmum.github.io/MemoRa/.
Authors: Yunbo Li, Jiaping Gui, Zhihang Deng, Fanchao Meng, Yue Wu
Abstract: Federated learning (FL) enables collaborative model training across multiple parties without sharing raw data, with semi-asynchronous FL (SAFL) emerging as a balanced approach between synchronous and asynchronous FL. However, SAFL faces significant challenges in optimizing both gradient-based (e.g., FedSGD) and model-based (e.g., FedAvg) aggregation strategies, which exhibit distinct trade-offs in accuracy, convergence speed, and stability. While gradient aggregation achieves faster convergence and higher accuracy, it suffers from pronounced fluctuations, whereas model aggregation offers greater stability but slower convergence and suboptimal accuracy. This paper presents FedQS, the first framework to theoretically analyze and address these disparities in SAFL. FedQS introduces a divide-and-conquer strategy to handle client heterogeneity by classifying clients into four distinct types and adaptively optimizing their local training based on data distribution characteristics and available computational resources. Extensive experiments on computer vision, natural language processing, and real-world tasks demonstrate that FedQS achieves the highest accuracy, attains the lowest loss, and ranks among the fastest in convergence speed, outperforming state-of-the-art baselines. Our work bridges the gap between aggregation strategies in SAFL, offering a unified solution for stable, accurate, and efficient federated learning. The code and datasets are available at https://github.com/bkjod/FedQS_.
Authors: Shaharyar Ahmed Khan Tareen, Filza Khan Tareen
Abstract: Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints. Typically, powerful architectures are trained at full depths but not all datasets or tasks require such high model capacity. Training big and deep architectures on relatively low-complexity datasets frequently leads to wasted computation, unnecessary energy consumption, and excessive memory usage, which in turn makes deployment of models on resource-constrained devices impractical. To address this problem, we introduce the concept of Optimally Deep Networks (ODNs), which provides a balance between model depth and task complexity. Specifically, we propose a NAS like training strategy called progressive depth expansion, which begins by training neural networks at shallower depths and incrementally increases their depth as the earlier blocks converge, continuing this process until the target accuracy is reached. ODNs use only the optimal depth for the tasks at hand, removing redundant layers. This cuts down future training and inference costs, lowers the model memory footprint, enhances computational efficiency, and facilitates deployment on edge devices. Empirical results show that the optimal depths of ResNet-18 and ResNet-34 for MNIST and SVHN, achieve up to 98.64 % and 96.44 % reduction in memory footprint, while maintaining a competitive accuracy of 99.31 % and 96.08 %, respectively.
Authors: Xin Nie, Liang Dong, Haicheng Zhang, Jiawang Xiao, G. Sun
Abstract: Weight quantization effectively reduces memory consumption and enables the deployment of large language models on CPU-based edge devices, yet existing hardware-friendly methods often rely on uniform quantization, which suffers from poor weight-distribution fitting and high dequantization overhead under low-bit settings. In this paper, we propose ELUTQ, an efficient quantization framework featuring a novel quantization format termed Hierarchical Linear Quantization (HLQ). HLQ is designed to better capture the statistical characteristics of weights without increasing the computational cost of bit-serial LUT-based GEMM operations, thereby eliminating dequantization overhead. HLQ is orthogonal to existing quantization algorithms. For the LLaMA3.1-8B model, when combined with post-training quantization, HLQ improves uniform quantization by achieving approximately 8 percent perplexity reduction at 3-bit precision and 85 percent perplexity reduction at 2-bit precision. When combined with efficient finetuning techniques, HLQ further improves model accuracy. We also integrate a disk-offload technique into ELUTQ, enabling it to complete the quantization of LLaMA3.1-70B using only 64 GB of CPU memory and 48 GB of VRAM, significantly reducing the hardware requirements for large-scale model quantization. To enable efficient deployment on edge devices, ELUTQ provides high-performance CPU kernels to support end-to-end inference. Under a 4-thread configuration with batch size 1, our 2-bit quantized LLaMA2-7B model achieves a throughput of more than 25 tokens per second on an Apple M2 chip. All the code is available at https://github.com/Nkniexin/ELUTQ.
Authors: Antoine Ledent, Rodrigo Alves, Yunwen Lei
Abstract: It has been recently observed in much of the literature that neural networks exhibit a bottleneck rank property: for larger depths, the activation and weights of neural networks trained with gradient-based methods tend to be of approximately low rank. In fact, the rank of the activations of each layer converges to a fixed value referred to as the ``bottleneck rank'', which is the minimum rank required to represent the training data. This perspective is in line with the observation that regularizing linear networks (without activations) with weight decay is equivalent to minimizing the Schatten $p$ quasi norm of the neural network. In this paper we investigate the implications of this phenomenon for generalization. More specifically, we prove generalization bounds for neural networks which exploit the approximate low rank structure of the weight matrices if present. The final results rely on the Schatten $p$ quasi norms of the weight matrices: for small $p$, the bounds exhibit a sample complexity $ \widetilde{O}(WrL^2)$ where $W$ and $L$ are the width and depth of the neural network respectively and where $r$ is the rank of the weight matrices. As $p$ increases, the bound behaves more like a norm-based bound instead.
Authors: Zhiyu Wang, Suman Raj, Rajkumar Buyya
Abstract: Multiple Unmanned Aerial Vehicles (UAVs) cooperative Mobile Edge Computing (MEC) systems face critical challenges in coordinating trajectory planning, task offloading, and resource allocation while ensuring Quality of Service (QoS) under dynamic and uncertain environments. Existing approaches suffer from limited scalability, slow convergence, and inefficient knowledge sharing among UAVs, particularly when handling large-scale IoT device deployments with stringent deadline constraints. This paper proposes AirFed, a novel federated graph-enhanced multi-agent reinforcement learning framework that addresses these challenges through three key innovations. First, we design dual-layer dynamic Graph Attention Networks (GATs) that explicitly model spatial-temporal dependencies among UAVs and IoT devices, capturing both service relationships and collaborative interactions within the network topology. Second, we develop a dual-Actor single-Critic architecture that jointly optimizes continuous trajectory control and discrete task offloading decisions. Third, we propose a reputation-based decentralized federated learning mechanism with gradient-sensitive adaptive quantization, enabling efficient and robust knowledge sharing across heterogeneous UAVs. Extensive experiments demonstrate that AirFed achieves 42.9% reduction in weighted cost compared to state-of-the-art baselines, attains over 99% deadline satisfaction and 94.2% IoT device coverage rate, and reduces communication overhead by 54.5%. Scalability analysis confirms robust performance across varying UAV numbers, IoT device densities, and system scales, validating AirFed's practical applicability for large-scale UAV-MEC deployments.
Authors: Aiqing Zhu, Beatrice W. Soh, Grigorios A. Pavliotis, Qianxiao Li
Abstract: Complex dissipative systems appear across science and engineering, from polymers and active matter to learning algorithms. These systems operate far from equilibrium, where energy dissipation and time irreversibility govern their behavior but are difficult to quantify from data. Here, we introduce a universal and identifiable neural framework that learns dissipative stochastic dynamics directly from trajectories while ensuring interpretability, expressiveness, and uniqueness. Our method identifies a unique energy landscape, separates reversible from irreversible motion, and allows direct computation of the entropy production, providing a principled measure of irreversibility and deviations from equilibrium. Applications to polymer stretching in elongational flow and to stochastic gradient Langevin dynamics reveal new insights, including super-linear scaling of barrier heights and sub-linear scaling of entropy production rates with the strain rate, and the suppression of irreversibility with increasing batch size. Our methodology thus establishes a general, data-driven framework for discovering and interpreting non-equilibrium dynamics.
Authors: Satchel Grant, Simon Jerome Han, Alexa R. Tartaglini, Christopher Potts
Abstract: A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encode. Here we ask whether such interventions create out-of-distribution (divergent) representations, and whether this raises concerns about how faithful their resulting explanations are to the target model in its natural state. First, we demonstrate theoretically and empirically that common causal intervention techniques often do shift internal representations away from the natural distribution of the target model. Then, we provide a theoretical analysis of two classes of such divergences: "harmless" divergences that occur in the null-space of the weights and from covariance within behavioral decision boundaries, and "pernicious" divergences that activate hidden network pathways and cause dormant behavioral changes. Finally, in an effort to mitigate the pernicious cases, we apply and modify the Counterfactual Latent (CL) loss from Grant (2025) allowing representations from causal interventions to remain closer to the natural distribution, reducing the likelihood of harmful divergences while preserving the interpretive power of the interventions. Together, these results highlight a path towards more reliable interpretability methods.
Authors: Zerui Bao, Di Zhu, Liu Jiang, Shiqi Sheng, Ziwei Wang, Haoyun Zhang
Abstract: Large-scale networked services rely on deep soft-ware stacks and microservice orchestration, which increase instruction footprints and create frontend stalls that inflate tail latency and energy. We revisit instruction prefetching for these cloud workloads and present a design that aligns with SLO driven and self optimizing systems. Building on the Entangling Instruction Prefetcher (EIP), we introduce a Compressed Entry that captures up to eight destinations around a base using 36 bits by exploiting spatial clustering, and a Hierarchical Metadata Storage scheme that keeps only L1 resident and frequently queried entries on chip while virtualizing bulk metadata into lower levels. We further add a lightweight Online ML Controller that scores prefetch profitability using context features and a bandit adjusted threshold. On data center applications, our approach preserves EIP like speedups with smaller on chip state and improves efficiency for networked services in the ML era.
Authors: Gimun Bae, Seung Jun Shin
Abstract: The ROC-SVM, originally proposed by Rakotomamonjy, directly maximizes the area under the ROC curve (AUC) and has become an attractive alternative of the conventional binary classification under the presence of class imbalance. However, its practical use is limited by high computational cost, as training involves evaluating all $O(n^2)$. To overcome this limitation, we develop a scalable variant of the ROC-SVM that leverages incomplete U-statistics, thereby substantially reducing computational complexity. We further extend the framework to nonlinear classification through a low-rank kernel approximation, enabling efficient training in reproducing kernel Hilbert spaces. Theoretical analysis establishes an error bound that justifies the proposed approximation, and empirical results on both synthetic and real datasets demonstrate that the proposed method achieves comparable AUC performance to the original ROC-SVM with drastically reduced training time.
Authors: Qinghong Guo, Yu Wang, Ji Cao, Tongya Zheng, Junshu Dai, Bingde Hu, Shunyu Liu, Canghong Jin
Abstract: Road network representation learning (RNRL) has attracted increasing attention from both researchers and practitioners as various spatiotemporal tasks are emerging. Recent advanced methods leverage Graph Neural Networks (GNNs) and contrastive learning to characterize the spatial structure of road segments in a self-supervised paradigm. However, spatial heterogeneity and temporal dynamics of road networks raise severe challenges to the neighborhood smoothing mechanism of self-supervised GNNs. To address these issues, we propose a $\textbf{D}$ual-branch $\textbf{S}$patial-$\textbf{T}$emporal self-supervised representation framework for enhanced road representations, termed as DST. On one hand, DST designs a mix-hop transition matrix for graph convolution to incorporate dynamic relations of roads from trajectories. Besides, DST contrasts road representations of the vanilla road network against that of the hypergraph in a spatial self-supervised way. The hypergraph is newly built based on three types of hyperedges to capture long-range relations. On the other hand, DST performs next token prediction as the temporal self-supervised task on the sequences of traffic dynamics based on a causal Transformer, which is further regularized by differentiating traffic modes of weekdays from those of weekends. Extensive experiments against state-of-the-art methods verify the superiority of our proposed framework. Moreover, the comprehensive spatiotemporal modeling facilitates DST to excel in zero-shot learning scenarios.
Authors: Paul Strang, Zacharie Al\`es, C\^ome Bissuel, Olivier Juan, Safia Kedad-Sidhoum, Emmanuel Rachelson
Abstract: Mixed-Integer Linear Programming (MILP) lies at the core of many real-world combinatorial optimization (CO) problems, traditionally solved by branch-and-bound (B&B). A key driver influencing B&B solvers efficiency is the variable selection heuristic that guides branching decisions. Looking to move beyond static, hand-crafted heuristics, recent work has explored adapting traditional reinforcement learning (RL) algorithms to the B&B setting, aiming to learn branching strategies tailored to specific MILP distributions. In parallel, RL agents have achieved remarkable success in board games, a very specific type of combinatorial problems, by leveraging environment simulators to plan via Monte Carlo Tree Search (MCTS). Building on these developments, we introduce Plan-and-Branch-and-Bound (PlanB&B), a model-based reinforcement learning (MBRL) agent that leverages a learned internal model of the B&B dynamics to discover improved branching strategies. Computational experiments empirically validate our approach, with our MBRL branching agent outperforming previous state-of-the-art RL methods across four standard MILP benchmarks.
Authors: Georgios C. Chasparis
Abstract: Reinforcement-based learning has attracted considerable attention both in modeling human behavior as well as in engineering, for designing measurement- or payoff-based optimization schemes. Such learning schemes exhibit several advantages, especially in relation to filtering out noisy observations. However, they may exhibit several limitations when applied in a distributed setup. In multi-player weakly-acyclic games, and when each player applies an independent copy of the learning dynamics, convergence to (usually desirable) pure Nash equilibria cannot be guaranteed. Prior work has only focused on a small class of games, namely potential and coordination games. To address this main limitation, this paper introduces a novel payoff-based learning scheme for distributed optimization, namely aspiration-based perturbed learning automata (APLA). In this class of dynamics, and contrary to standard reinforcement-based learning schemes, each player's probability distribution for selecting actions is reinforced both by repeated selection and an aspiration factor that captures the player's satisfaction level. We provide a stochastic stability analysis of APLA in multi-player positive-utility games under the presence of noisy observations. This is the first part of the paper that characterizes stochastic stability in generic non-zero-sum games by establishing equivalence of the induced infinite-dimensional Markov chain with a finite dimensional one. In the second part, stochastic stability is further specialized to weakly acyclic games.
Authors: Wanlong Fang, Tianle Zhang, Alvin Chan
Abstract: Multimodal learning often relies on aligning representations across modalities to enable effective information integration, an approach traditionally assumed to be universally beneficial. However, prior research has primarily taken an observational approach, examining naturally occurring alignment in multimodal data and exploring its correlation with model performance, without systematically studying the direct effects of explicitly enforced alignment between representations of different modalities. In this work, we investigate how explicit alignment influences both model performance and representation alignment under different modality-specific information structures. Specifically, we introduce a controllable contrastive learning module that enables precise manipulation of alignment strength during training, allowing us to explore when explicit alignment improves or hinders performance. Our results on synthetic and real datasets under different data characteristics show that the impact of explicit alignment on the performance of unimodal models is related to the characteristics of the data: the optimal level of alignment depends on the amount of redundancy between the different modalities. We identify an optimal alignment strength that balances modality-specific signals and shared redundancy in the mixed information distributions. This work provides practical guidance on when and how explicit alignment should be applied to achieve optimal unimodal encoder performance.
Authors: Akira Tamamori
Abstract: Kernel-based learning methods can dramatically increase the storage capacity of Hopfield networks, yet the dynamical mechanism behind this enhancement remains poorly understood. We address this gap by unifying the geometric analysis of the attractor landscape with the spectral theory of kernel machines. Using a novel metric, "Pinnacle Sharpness," we first uncover a rich phase diagram of attractor stability, identifying a "Ridge of Optimization" where the network achieves maximal robustness under high-load conditions. Phenomenologically, this ridge is characterized by a "Force Antagonism," where a strong driving force is balanced by a collective feedback force. Theoretically, we reveal that this phenomenon arises from a specific reorganization of the weight spectrum, which we term \textit{Spectral Concentration}. Unlike a simple rank-1 collapse, our analysis shows that the network on the ridge self-organizes into a critical state: the leading eigenvalue is amplified to maximize global stability (Direct Force), while the trailing eigenvalues are preserved to maintain high memory capacity (Indirect Force). These findings provide a complete physical picture of how high-capacity associative memories are formed, demonstrating that optimal performance is achieved by tuning the system to a spectral "Goldilocks zone" between rank collapse and diffusion.
Authors: Falk Dippel, Yinan Yu, Annika Rosengren, Martin Lindgren, Christina E. Lundberg, Erik Aerts, Martin Adiels, Helen Sj\"oland
Abstract: Transformers have defined the state-of-the-art for clinical prediction tasks involving electronic health records (EHRs). The recently introduced Mamba architecture outperformed an advanced Transformer (Transformer++) based on Llama in handling long context lengths, while using fewer model parameters. Despite the impressive performance of these architectures, a systematic approach to empirically analyze model performance and efficiency under various settings is not well established in the medical domain. The performances of six sequence models were investigated across three architecture classes (Transformers, Transformers++, Mambas) in a large Swedish heart failure (HF) cohort (N = 42820), providing a clinically relevant case study. Patient data included diagnoses, vital signs, laboratories, medications and procedures extracted from in-hospital EHRs. The models were evaluated on three one-year prediction tasks: clinical instability (a readmission phenotype) after initial HF hospitalization, mortality after initial HF hospitalization and mortality after latest hospitalization. Ablations account for modifications of the EHR-based input patient sequence, architectural model configurations, and temporal preprocessing techniques for data collection. Llama achieves the highest predictive discrimination, best calibration, and showed robustness across all tasks, followed by Mambas. Both architectures demonstrate efficient representation learning, with tiny configurations surpassing other large-scaled Transformers. At equal model size, Llama and Mambas achieve superior performance using 25% less training data. This paper presents a first ablation study with systematic design choices for input tokenization, model configuration and temporal data preprocessing. Future model development in clinical prediction tasks using EHRs could build upon this study's recommendation as a starting point.
Authors: Kang He, Boyu Chen, Yuzhe Ding, Fei Li, Chong Teng, Donghong Ji
Abstract: Multimodal Sentiment Analysis (MSA) seeks to understand human emotions by integrating textual, acoustic, and visual signals. Although multimodal fusion is designed to leverage cross-modal complementarity, real-world scenarios often exhibit modality competition: dominant modalities tend to overshadow weaker ones, leading to suboptimal performance. In this paper, we propose PaSE, a novel Prototype-aligned Calibration and Shapley-optimized Equilibrium framework, which enhances collaboration while explicitly mitigating modality competition. PaSE first applies Prototype-guided Calibration Learning (PCL) to refine unimodal representations and align them through an Entropic Optimal Transport mechanism that ensures semantic consistency. To further stabilize optimization, we introduce a Dual-Phase Optimization strategy. A prototype-gated fusion module is first used to extract shared representations, followed by Shapley-based Gradient Modulation (SGM), which adaptively adjusts gradients according to the contribution of each modality. Extensive experiments on IEMOCAP, MOSI, and MOSEI confirm that PaSE achieves the superior performance and effectively alleviates modality competition.
Authors: Fanbo Ju, Haiyuan Shi, Qingjian Ni
Abstract: Precipitation nowcasting, which aims to provide high spatio-temporal resolution precipitation forecasts by leveraging current radar observations, is a core task in regional weather forecasting. Recently, the cascaded architecture has emerged as the mainstream paradigm for deep learning-based precipitation nowcasting. This paradigm involves a deterministic model to predict posterior mean, followed by a probabilistic model to generate local stochasticity. However, existing methods commonly overlook the conflation of the systematic distribution shift in deterministic predictions and the local stochasticity. As a result, the distribution shift of the deterministic component contaminates the predictions of the probabilistic component, leading to inaccuracies in precipitation patterns and intensity, particularly over longer lead times. To address this issue, we introduce RectiCast, a two-stage framework that explicitly decouples the rectification of mean-field shift from the generation of local stochasticity via a dual Flow Matching model. In the first stage, a deterministic model generates the posterior mean. In the second stage, we introduce a Rectifier to explicitly learn the distribution shift and produce a rectified mean. Subsequently, a Generator focuses on modeling the local stochasticity conditioned on the rectified mean. Experiments on two radar datasets demonstrate that RectiCast achieves significant performance improvements over existing state-of-the-art methods.
Authors: Mostafa Mozafari, Farooq Ahmad Wani, Maria Sofia Bucarelli, Fabrizio Silvestri
Abstract: Corrupted training data are ubiquitous. Corrective Machine Unlearning (CMU) seeks to remove the influence of such corruption post-training. Prior CMU typically assumes access to identified corrupted training samples (a "forget set"). However, in many real-world scenarios the training data are no longer accessible. We formalize source-free CMU, where the original training data are unavailable and, consequently, no forget set of identified corrupted training samples can be specified. Instead, we assume a small proxy (surrogate) set of corrupted samples that reflect the suspected corruption type without needing to be the original training samples. In this stricter setting, methods relying on forget set are ineffective or narrow in scope. We introduce Corrective Unlearning in Task Space (CUTS), a lightweight weight space correction method guided by the proxy set using task arithmetic principles. CUTS treats the clean and the corruption signal as distinct tasks. Specifically, we briefly fine-tune the corrupted model on the proxy to amplify the corruption mechanism in the weight space, compute the difference between the corrupted and fine-tuned weights as a proxy task vector, and subtract a calibrated multiple of this vector to cancel the corruption. Without access to clean data or a forget set, CUTS recovers a large fraction of the lost utility under label noise and, for backdoor triggers, nearly eliminates the attack with minimal damage to utility, outperforming state-of-the-art specialized CMU methods in source-free setting.
Authors: Qisen Chai, Yansong Wang, Junjie Huang, Tao Jia
Abstract: As graph-structured data grow increasingly large, evaluating their robustness under adversarial attacks becomes computationally expensive and difficult to scale. To address this challenge, we propose to compress graphs into compact representations that preserve both topological structure and robustness profile, enabling efficient and reliable evaluation. We propose Cutter, a dual-agent reinforcement learning framework composed of a Vital Detection Agent (VDA) and a Redundancy Detection Agent (RDA), which collaboratively identify structurally vital and redundant nodes for guided compression. Cutter incorporates three key strategies to enhance learning efficiency and compression quality: trajectory-level reward shaping to transform sparse trajectory returns into dense, policy-equivalent learning signals; prototype-based shaping to guide decisions using behavioral patterns from both high- and low-return trajectories; and cross-agent imitation to enable safer and more transferable exploration. Experiments on multiple real-world graphs demonstrate that Cutter generates compressed graphs that retain essential static topological properties and exhibit robustness degradation trends highly consistent with the original graphs under various attack scenarios, thereby significantly improving evaluation efficiency without compromising assessment fidelity.
Authors: Nikita Neveditsin, Pawan Lingras, Vijay Mago
Abstract: Clustering short text embeddings is a foundational task in natural language processing, yet remains challenging due to the need to specify the number of clusters in advance. We introduce a scalable spectral method that estimates the number of clusters directly from the structure of the Laplacian eigenspectrum, constructed using cosine similarities and guided by an adaptive sampling strategy. This sampling approach enables our estimator to efficiently scale to large datasets without sacrificing reliability. To support intrinsic evaluation of cluster quality without ground-truth labels, we propose the Cohesion Ratio, a simple and interpretable evaluation metric that quantifies how much intra-cluster similarity exceeds the global similarity background. It has an information-theoretic motivation inspired by mutual information, and in our experiments it correlates closely with extrinsic measures such as normalized mutual information and homogeneity. Extensive experiments on six short-text datasets and four modern embedding models show that standard algorithms like K-Means and HAC, when guided by our estimator, significantly outperform popular parameter-light methods such as HDBSCAN, OPTICS, and Leiden. These results demonstrate the practical value of our spectral estimator and Cohesion Ratio for unsupervised organization and evaluation of short text data. Implementation of our estimator of k and Cohesion Ratio, along with code for reproducing the experiments, is available at https://anonymous.4open.science/r/towards_clustering-0C2E.
URLs: https://anonymous.4open.science/r/towards_clustering-0C2E.
Authors: Diego Garc\'ia-Mart\'in, Paolo Braccia, M. Cerezo
Abstract: Parametrized and random unitary (or orthogonal) $n$-qubit circuits play a central role in quantum information. As such, one could naturally assume that circuits implementing symplectic transformations would attract similar attention. However, this is not the case, as $\mathbb{SP} (d/2)$ -- the group of $d\times d$ unitary symplectic matrices -- has thus far been overlooked. In this work, we aim at starting to fill this gap. We begin by presenting a universal set of generators $\mathcal{G}$ for the symplectic algebra $\mathfrak{sp}(d/2)$, consisting of one- and two-qubit Pauli operators acting on neighboring sites in a one-dimensional lattice. Here, we uncover two critical differences between such set, and equivalent ones for unitary and orthogonal circuits. Namely, we find that the operators in $\mathcal{G}$ cannot generate arbitrary local symplectic unitaries and that they are not translationally invariant. We then review the Schur-Weyl duality between the symplectic group and the Brauer algebra, and use tools from Weingarten calculus to prove that Pauli measurements at the output of Haar random symplectic circuits can converge to Gaussian processes. As a by-product, such analysis provides us with concentration bounds for Pauli measurements in circuits that form $t$-designs over $\mathbb{SP}(d/2)$. To finish, we present tensor-network tools to analyze shallow random symplectic circuits, and we use these to numerically show that computational-basis measurements anti-concentrate at logarithmic depth.
Authors: Dhrumil Patel, Daniel Koch, Saahil Patel, Mark M. Wilde
Abstract: Estimating the ground-state energy of Hamiltonians is a fundamental task for which it is believed that quantum computers can be helpful. Several approaches have been proposed toward this goal, including algorithms based on quantum phase estimation and hybrid quantum-classical optimizers involving parameterized quantum circuits, the latter falling under the umbrella of the variational quantum eigensolver. Here, we analyze the performance of quantum Boltzmann machines for this task, which is a less explored ansatz based on parameterized thermal states and which is not known to suffer from the barren-plateau problem. We delineate a hybrid quantum-classical algorithm for this task and rigorously prove that it converges to an $\varepsilon$-approximate stationary point of the energy function optimized over parameter space, while using a number of parameterized-thermal-state samples that is polynomial in $\varepsilon^{-1}$, the number of parameters, and the norm of the Hamiltonian being optimized. Our algorithm estimates the gradient of the energy function efficiently by means of a quantum circuit construction that combines classical random sampling, Hamiltonian simulation, and the Hadamard test. Additionally, supporting our main claims are calculations of the gradient and Hessian of the energy function, as well as an upper bound on the matrix elements of the latter that is used in the convergence analysis.
Authors: Felix J. Yu, Nicholas Kamp, Carlos A. Arg\"uelles
Abstract: Neutrino telescopes detect rare interactions of particles produced in some of the most extreme environments in the Universe. This is accomplished by instrumenting a cubic-kilometer scale volume of naturally occurring transparent medium with light sensors. Given their substantial size and the high frequency of background interactions, these telescopes amass an enormous quantity of large variance, high-dimensional data. These attributes create substantial challenges for analyzing and reconstructing interactions, particularly when utilizing machine learning (ML) techniques. In this paper, we present a novel approach, called om2vec, that employs transformer-based variational autoencoders to efficiently represent the detected photon arrival time distributions of neutrino telescope events by learning compact and descriptive latent representations. We demonstrate that these latent representations offer enhanced flexibility and improved computational efficiency, thereby facilitating downstream tasks in data analysis.
Authors: Isack Lee, Haebin Seong
Abstract: Although large language models (LLMs) demonstrate impressive proficiency in various tasks, they present potential safety risks, such as `jailbreaks', where malicious inputs can coerce LLMs into generating harmful content bypassing safety alignments. In this paper, we delve into the ethical biases in LLMs and examine how those biases could be exploited for jailbreaks. Notably, these biases result in a jailbreaking success rate in GPT-4o models that differs by 20\% between non-binary and cisgender keywords and by 16\% between white and black keywords, even when the other parts of the prompts are identical. We introduce the concept of BiasJailbreak, highlighting the inherent risks posed by these safety-induced biases. BiasJailbreak generates biased keywords automatically by asking the target LLM itself, and utilizes the keywords to generate harmful output. Additionally, we propose an efficient defense method BiasDefense, which prevents jailbreak attempts by injecting defense prompts prior to generation. BiasDefense stands as an appealing alternative to Guard Models, such as Llama-Guard, that require additional inference cost after text generation. Our findings emphasize that ethical biases in LLMs can actually lead to generating unsafe output, and suggest a method to make the LLMs more secure and unbiased. To enable further research and improvements, we open-source our code and artifacts of BiasJailbreak, providing the community with tools to better understand and mitigate safety-induced biases in LLMs.
Authors: Benji Peng, Keyu Chen, Qian Niu, Ziqian Bi, Ming Liu, Pohsun Feng, Tianyang Wang, Lawrence K. Q. Yan, Yizhu Wen, Yichao Zhang, Caitlyn Heqi Yin, Xinyuan Song
Abstract: Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems. Despite these advancements in the past few years, LLMs have shown considerable vulnerabilities, particularly to prompt injection and jailbreaking attacks. This review analyzes the state of research on these vulnerabilities and presents available defense strategies. We roughly categorize attack approaches into prompt-based, model-based, multimodal, and multilingual, covering techniques such as adversarial prompting, backdoor injections, and cross-modality exploits. We also review various defense mechanisms, including prompt filtering, transformation, alignment techniques, multi-agent defenses, and self-regulation, evaluating their strengths and shortcomings. We also discuss key metrics and benchmarks used to assess LLM safety and robustness, noting challenges like the quantification of attack success in interactive contexts and biases in existing datasets. Identifying current research gaps, we suggest future directions for resilient alignment strategies, advanced defenses against evolving attacks, automation of jailbreak detection, and consideration of ethical and societal impacts. This review emphasizes the need for continued research and cooperation within the AI community to enhance LLM security and ensure their safe deployment.
Authors: Luca Franceschi, Michele Donini, Valerio Perrone, Aaron Klein, C\'edric Archambeau, Matthias Seeger, Massimiliano Pontil, Paolo Frasconi
Abstract: Hyperparameters are configuration variables controlling the behavior of machine learning algorithms. They are ubiquitous in machine learning and artificial intelligence and the choice of their values determines the effectiveness of systems based on these technologies. Manual hyperparameter search is often time-consuming and becomes infeasible when the number of hyperparameters is large. Automating the search is an important step towards advancing, streamlining, and systematizing machine learning, freeing researchers and practitioners alike from the burden of finding a good set of hyperparameters by trial and error. In this survey, we present a unified treatment of hyperparameter optimization, providing the reader with examples, insights into the state-of-the-art, and numerous links to further reading. We cover the main families of techniques to automate hyperparameter search, often referred to as hyperparameter optimization or tuning, including random and quasi-random search, bandit-, model-, population-, and gradient-based approaches. We further discuss extensions, including online, constrained, and multi-objective formulations, touch upon connections with other fields, such as meta-learning and neural architecture search, and conclude with open questions and future research directions.
Authors: Harshit Sikchi, Siddhant Agarwal, Pranaya Jajoo, Samyak Parajuli, Caleb Chuck, Max Rudolph, Peter Stone, Amy Zhang, Scott Niekum
Abstract: The reward hypothesis states that all goals and purposes can be understood as the maximization of a received scalar reward signal. However, in practice, defining such a reward signal is notoriously difficult, as humans are often unable to predict the optimal behavior corresponding to a reward function. Natural language offers an intuitive alternative for instructing reinforcement learning (RL) agents, yet previous language-conditioned approaches either require costly supervision or test-time training given a language instruction. In this work, we present a new approach that uses a pretrained RL agent trained using only unlabeled, offline interactions--without task-specific supervision or labeled trajectories--to get zero-shot test-time policy inference from arbitrary natural language instructions. We introduce a framework comprising three steps: imagine, project, and imitate. First, the agent imagines a sequence of observations corresponding to the provided language description using video generative models. Next, these imagined observations are projected into the target environment domain. Finally, an agent pretrained in the target environment with unsupervised RL instantly imitates the projected observation sequence through a closed-form solution. To the best of our knowledge, our method, RLZero, is the first approach to show direct language-to-behavior generation abilities on a variety of tasks and environments without any in-domain supervision. We further show that components of RLZero can be used to generate policies zero-shot from cross-embodied videos, such as those available on YouTube, even for complex embodiments like humanoids.
Authors: Andrew H. Zhang, Alex He-Mo, Richard Fei Yin, Chunlin Li, Yuzhi Tang, Dharmendra Gurve, Veronique van der Horst, Aron S. Buchman, Nasim Montazeri Ghahjaverestan, Maged Goubran, Bo Wang, Andrew S. P. Lim
Abstract: Study Objectives: We investigate a Mamba-based deep learning approach for sleep staging on signals from ANNE One (Sibel Health, Evanston, IL), a non-intrusive dual-module wireless wearable system measuring chest electrocardiography (ECG), triaxial accelerometry, and chest temperature, and finger photoplethysmography and finger temperature. Methods: We obtained wearable sensor recordings from 357 adults undergoing concurrent polysomnography (PSG) at a tertiary care sleep lab. Each PSG recording was manually scored and these annotations served as ground truth labels for training and evaluation of our models. PSG and wearable sensor data were automatically aligned using their ECG channels with manual confirmation by visual inspection. We trained a Mamba-based recurrent neural network architecture on these recordings. Ensembling of model variants with similar architectures was performed. Results: After ensembling, the model attains a 3-class (wake, non rapid eye movement [NREM] sleep, rapid eye movement [REM] sleep) balanced accuracy of 84.02%, F1 score of 84.23%, Cohen's $\kappa$ of 72.89%, and a Matthews correlation coefficient (MCC) score of 73.00%; a 4-class (wake, light NREM [N1/N2], deep NREM [N3], REM) balanced accuracy of 75.30%, F1 score of 74.10%, Cohen's $\kappa$ of 61.51%, and MCC score of 61.95%; a 5-class (wake, N1, N2, N3, REM) balanced accuracy of 65.11%, F1 score of 66.15%, Cohen's $\kappa$ of 53.23%, MCC score of 54.38%. Conclusions: Our Mamba-based deep learning model can successfully infer major sleep stages from the ANNE One, a wearable system without electroencephalography (EEG), and can be applied to data from adults attending a tertiary care sleep clinic.
Authors: Facundo Roffet, Gustavo Deco, Claudio Delrieux, Gustavo Patow
Abstract: Background: Brain network models offer insights into brain dynamics, but the utility of model-derived bifurcation parameters as biomarkers remains underexplored. Objective: This study evaluates bifurcation parameters from a whole-brain network model as biomarkers for distinguishing brain states associated with resting-state and task-based cognitive conditions. Methods: Synthetic BOLD signals were generated using a supercritical Hopf brain network model to train deep learning models for bifurcation parameter prediction. Inference was performed on Human Connectome Project data, including both resting-state and task-based conditions. Statistical analyses assessed the separability of brain states based on bifurcation parameter distributions. Results: Bifurcation parameter distributions differed significantly across task and resting-state conditions ($p < 0.0001$ for all but one comparison). Task-based brain states exhibited higher bifurcation values compared to rest. Conclusion: Bifurcation parameters effectively differentiate cognitive and resting states, warranting further investigation as biomarkers for brain state characterization and neurological disorder assessment.
Authors: Muhammed Fadera
Abstract: Recurrent neural networks trained via the reservoir computing paradigm have demonstrated remarkable success in learning and reconstructing attractors from chaotic systems, often replicating quantities such as Lyapunov exponents and fractal dimensions. It has recently been conjectured that this is because the reservoir computer embeds the dynamics of the chaotic system in its state space before learning. This conjecture has been established for reservoir computers with linear activation functions and remains open for more general reservoir systems. In this work, we employ a non-autonomous dynamical systems approach to establish an upper bound for the box-counting dimension of the pullback attractor, a subset of the reservoir state space that is approximated during training and prediction phases. We prove that the box-counting dimension of the pullback attractor is bounded above by the box-counting dimension of the space of input sequences with respect to the product topology. In particular, for input sequences originating from an Nin-dimensional smooth dynamical system or their generic continuously differentiable observations, the box-counting dimension of the pullback attractor is bounded above by Nin. The results obtained here highlight the fact that, while a reservoir computer may possess a very high-dimensional state space, it exhibits effective low-dimensional dynamics. Our findings also partly explain why reservoir computers are successful in tasks such as attractor reconstruction and the computation of dynamic invariants like Lyapunov exponents and fractal dimensions.
Authors: M. Umar B. Niazi, John Cao, Matthieu Barreau, Karl Henrik Johansson
Abstract: This paper proposes a novel learning approach for designing Kazantzis-Kravaris/Luenberger (KKL) observers for autonomous nonlinear systems. The design of a KKL observer involves finding an injective map that transforms the system state into a higher-dimensional observer state, whose dynamics is linear and stable. The observer's state is then mapped back to the original system coordinates via the inverse map to obtain the state estimate. However, finding this transformation and its inverse is quite challenging. We propose learning the forward mapping using a physics-informed neural network, and then learning its inverse mapping with a conventional feedforward neural network. Theoretical guarantees for the robustness of state estimation against approximation error and system uncertainties are provided, including non-asymptotic learning guarantees that link approximation quality to finite sample sizes. The effectiveness of the proposed approach is demonstrated through numerical simulations on benchmark examples, showing superior generalization capability outside the training domain compared to state-of-the-art methods.
Authors: Zixue Zeng, Xiaoyan Zhao, Matthew Cartier, Tong Yu, Jing Wang, Xin Meng, Zhiyu Sheng, Maryam Satarpour, John M Cormack, Allison Bean, Ryan Nussbaum, Maya Maurer, Emily Landis-Walkenhorst, Dinesh Kumbhare, Kang Kim, Ajay Wasan, Jiantao Pu
Abstract: We introduce a novel segmentation-aware joint training framework called generative reinforcement network (GRN) that integrates segmentation loss feedback to optimize both image generation and segmentation performance in a single stage. An image enhancement technique called segmentation-guided enhancement (SGE) is also developed, where the generator produces images tailored specifically for the segmentation model. Two variants of GRN were also developed, including GRN for sample-efficient learning (GRN-SEL) and GRN for semi-supervised learning (GRN-SSL). GRN's performance was evaluated using a dataset of 69 fully annotated 3D ultrasound scans from 29 subjects. The annotations included six anatomical structures: dermis, superficial fat, superficial fascial membrane (SFM), deep fat, deep fascial membrane (DFM), and muscle. Our results show that GRN-SEL with SGE reduces labeling efforts by up to 70% while achieving a 1.98% improvement in the Dice Similarity Coefficient (DSC) compared to models trained on fully labeled datasets. GRN-SEL alone reduces labeling efforts by 60%, GRN-SSL with SGE decreases labeling requirements by 70%, and GRN-SSL alone by 60%, all while maintaining performance comparable to fully supervised models. These findings suggest the effectiveness of the GRN framework in optimizing segmentation performance with significantly less labeled data, offering a scalable and efficient solution for ultrasound image analysis and reducing the burdens associated with data annotation.
Authors: Vlad Hondru, Eduard Hogea, Darian Onchis, Radu Tudor Ionescu
Abstract: The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake detectors. However, deepfake detectors are also prone to errors, and their decisions are not explainable, leaving humans vulnerable to deepfake-based fraud and misinformation. To this end, we introduce ExDDV, the first dataset and benchmark for Explainable Deepfake Detection in Video. ExDDV comprises around 5.4K real and deepfake videos that are manually annotated with text descriptions (to explain the artifacts) and clicks (to point out the artifacts). We evaluate a number of vision-language models on ExDDV, performing experiments with various fine-tuning and in-context learning strategies. Our results show that text and click supervision are both required to develop robust explainable models for deepfake videos, which are able to localize and describe the observed artifacts. Our novel dataset and code to reproduce the results are available at https://github.com/vladhondru25/ExDDV.
Authors: Jiaheng Liu, Dawei Zhu, Zhiqi Bai, Yancheng He, Huanxuan Liao, Haoran Que, Zekun Wang, Chenchen Zhang, Ge Zhang, Jiebin Zhang, Yuanxing Zhang, Zhuo Chen, Hangyu Guo, Shilong Li, Ziqiang Liu, Yong Shan, Yifan Song, Jiayi Tian, Wenhao Wu, Zhejian Zhou, Ruijie Zhu, Junlan Feng, Yang Gao, Shizhu He, Zhoujun Li, Tianyu Liu, Fanyu Meng, Wenbo Su, Yingshui Tan, Zili Wang, Jian Yang, Wei Ye, Bo Zheng, Wangchunshu Zhou, Wenhao Huang, Sujian Li, Zhaoxiang Zhang
Abstract: Efficient processing of long contexts has been a persistent pursuit in Natural Language Processing. With the growing number of long documents, dialogues, and other textual data, it is important to develop Long Context Language Models (LCLMs) that can process and analyze extensive inputs in an effective and efficient way. In this paper, we present a comprehensive survey on recent advances in long-context modeling for large language models. Our survey is structured around three key aspects: how to obtain effective and efficient LCLMs, how to train and deploy LCLMs efficiently, and how to evaluate and analyze LCLMs comprehensively. For the first aspect, we discuss data strategies, architectural designs, and workflow approaches oriented with long context processing. For the second aspect, we provide a detailed examination of the infrastructure required for LCLM training and inference. For the third aspect, we present evaluation paradigms for long-context comprehension and long-form generation, as well as behavioral analysis and mechanism interpretability of LCLMs. Beyond these three key aspects, we thoroughly explore the diverse application scenarios where existing LCLMs have been deployed and outline promising future development directions. This survey provides an up-to-date review of the literature on long-context LLMs, which we wish to serve as a valuable resource for both researchers and engineers. An associated GitHub repository collecting the latest papers and repos is available at: \href{https://github.com/LCLM-Horizon/A-Comprehensive-Survey-For-Long-Context-Language-Modeling}{\color[RGB]{175,36,67}{LCLM-Horizon}}.
URLs: https://github.com/LCLM-Horizon/A-Comprehensive-Survey-For-Long-Context-Language-Modeling
Authors: Jing Bi, Susan Liang, Xiaofei Zhou, Pinxin Liu, Junjia Guo, Yunlong Tang, Luchuan Song, Chao Huang, Ali Vosoughi, Guangyu Sun, Jinxi He, Jiarui Wu, Shu Yang, Daoan Zhang, Chen Chen, Lianggong Bruce Wen, Zhang Liu, Jiebo Luo, Chenliang Xu
Abstract: Reasoning is central to human intelligence, enabling structured problem-solving across diverse tasks. Recent advances in large language models (LLMs) have greatly enhanced their reasoning abilities in arithmetic, commonsense, and symbolic domains. However, effectively extending these capabilities into multimodal contexts-where models must integrate both visual and textual inputs-continues to be a significant challenge. Multimodal reasoning introduces complexities, such as handling conflicting information across modalities, which require models to adopt advanced interpretative strategies. Addressing these challenges involves not only sophisticated algorithms but also robust methodologies for evaluating reasoning accuracy and coherence. This paper offers a concise yet insightful overview of reasoning techniques in both textual and multimodal LLMs. Through a thorough and up-to-date comparison, we clearly formulate core reasoning challenges and opportunities, highlighting practical methods for post-training optimization and test-time inference. Our work provides valuable insights and guidance, bridging theoretical frameworks and practical implementations, and sets clear directions for future research.
Authors: Abhimanyu Rajeshkumar Bambhaniya, Hanjiang Wu, Suvinay Subramanian, Sudarshan Srinivasan, Souvik Kundu, Amir Yazdanbakhsh, Midhilesh Elavazhagan, Madhu Kumar, Tushar Krishna
Abstract: The rapid evolution of Large Language Models (LLMs) has driven the need for increasingly sophisticated inference pipelines and hardware platforms. Modern LLM serving extends beyond traditional prefill-decode workflows, incorporating multi-stage processes such as Retrieval Augmented Generation (RAG), key-value (KV) cache retrieval, dynamic model routing, and multi step reasoning. These stages exhibit diverse computational demands, requiring distributed systems that integrate GPUs, ASICs, CPUs, and memory-centric architectures. However, existing simulators lack the fidelity to model these heterogeneous, multi-engine workflows, limiting their ability to inform architectural decisions. To address this gap, we introduce HERMES, a Heterogeneous Multi-stage LLM inference Execution Simulator. HERMES models diverse request stages; including RAG, KV retrieval, reasoning, prefill, and decode across complex hardware hierarchies. HERMES supports heterogeneous clients executing multiple models concurrently unlike prior frameworks while incorporating advanced batching strategies and multi-level memory hierarchies. By integrating real hardware traces with analytical modeling, HERMES captures critical trade-offs such as memory bandwidth contention, inter-cluster communication latency, and batching efficiency in hybrid CPU-accelerator deployments. Through case studies, we explore the impact of reasoning stages on end-to-end latency, optimal batching strategies for hybrid pipelines, and the architectural implications of remote KV cache retrieval. HERMES empowers system designers to navigate the evolving landscape of LLM inference, providing actionable insights into optimizing hardware-software co-design for next-generation AI workloads.
Authors: Jonas Latz, Aretha L. Teckentrup, Simon Urbainczyk
Abstract: Gaussian processes (GPs) have gained popularity as flexible machine learning models for regression and function approximation with an in-built method for uncertainty quantification. However, GPs suffer when the amount of training data is large or when the underlying function contains multi-scale features that are difficult to represent by a stationary kernel. To address the former, training of GPs with large-scale data is often performed through inducing point approximations, also known as sparse GP regression (GPR), where the size of the covariance matrices in GPR is reduced considerably through a greedy search on the data set. To aid the latter, deep GPs have gained traction as hierarchical models that resolve multi-scale features by combining multiple GPs. Posterior inference in deep GPs requires a sampling or, more usual, a variational approximation. Variational approximations lead to large-scale stochastic, non-convex optimisation problems and the resulting approximation tends to represent uncertainty incorrectly. In this work, we combine variational learning with MCMC to develop a particle-based expectation-maximisation method to simultaneously find inducing points within the large-scale data (variationally) and accurately train the deep GPs (sampling-based). The result is a highly efficient and accurate methodology for deep GP training on large-scale data. We test our method on standard benchmark problems.
Authors: Jiahao Yu, Qizhen Ying, Leyang Wang, Ziyue Jiang, Song Liu
Abstract: This paper introduces a novel iterative method for missing data imputation that sequentially reduces the mutual information between data and the corresponding missingness mask. Inspired by GAN-based approaches that train generators to decrease the predictability of missingness patterns, our method explicitly targets this reduction in mutual information. Specifically, our algorithm iteratively minimizes the KL divergence between the joint distribution of the imputed data and missingness mask, and the product of their marginals from the previous iteration. We show that the optimal imputation under this framework can be achieved by solving an ODE whose velocity field minimizes a rectified flow training objective. We further illustrate that some existing imputation techniques can be interpreted as approximate special cases of our mutual-information-reducing framework. Comprehensive experiments on synthetic and real-world datasets validate the efficacy of our proposed approach, demonstrating its superior imputation performance. Our implementation is available at https://github.com/yujhml/MIRI-Imputation.
Authors: Ahmet Berke Gokmen, Yigit Ekin, Bahri Batuhan Bilecen, Aysegul Dundar
Abstract: We propose RoPECraft, a training-free video motion transfer method for diffusion transformers that operates solely by modifying their rotary positional embeddings (RoPE). We first extract dense optical flow from a reference video, and utilize the resulting motion offsets to warp the complex-exponential tensors of RoPE, effectively encoding motion into the generation process. These embeddings are then further optimized during denoising time steps via trajectory alignment between the predicted and target velocities using a flow-matching objective. To keep the output faithful to the text prompt and prevent duplicate generations, we incorporate a regularization term based on the phase components of the reference video's Fourier transform, projecting the phase angles onto a smooth manifold to suppress high-frequency artifacts. Experiments on benchmarks reveal that RoPECraft outperforms all recently published methods, both qualitatively and quantitatively.
Authors: Naoki Hayashi, Takuro Kutsuna, Sawa Takamuku
Abstract: In statistical learning, models are classified as regular or singular depending on whether the mapping from parameters to probability distributions is injective. Most models with hierarchical structures or latent variables are singular, for which conventional criteria such as the Akaike Information Criterion and the Bayesian Information Criterion are inapplicable due to the breakdown of normal approximations for the likelihood and posterior. To address this, the Widely Applicable Information Criterion (WAIC) and the Widely Applicable Bayesian Information Criterion (WBIC) have been proposed. Since WAIC and WBIC are computed using posterior distributions at different temperature settings, separate posterior sampling is generally required. In this paper, we theoretically derive an asymptotic equation that links WAIC and WBIC, despite their dependence on different posteriors. This equation yields an asymptotically unbiased expression of WAIC in terms of the posterior distribution used for WBIC. The result clarifies the structural relationship between these criteria within the framework of singular learning theory, and deepens understanding of their asymptotic behavior. This theoretical contribution provides a foundation for future developments in the computational efficiency of model selection in singular models.
Authors: Bolin Lai, Sangmin Lee, Xu Cao, Xiang Li, James M. Rehg
Abstract: Text-image-to-video (TI2V) generation is a critical problem for controllable video generation using both semantic and visual conditions. Most existing methods typically add visual conditions to text-to-video (T2V) foundation models by finetuning, which is costly in resources and only limited to a few pre-defined conditioning settings. To tackle these constraints, we introduce a unified formulation for TI2V generation with flexible visual conditioning. Furthermore, we propose an innovative training-free approach, dubbed FlexTI2V, that can condition T2V foundation models on an arbitrary amount of images at arbitrary positions. Specifically, we firstly invert the condition images to noisy representation in a latent space. Then, in the denoising process of T2V models, our method uses a novel random patch swapping strategy to incorporate visual features into video representations through local image patches. To balance creativity and fidelity, we use a dynamic control mechanism to adjust the strength of visual conditioning to each video frame. Extensive experiments validate that our method surpasses previous training-free image conditioning methods by a notable margin. Our method can also generalize to both UNet-based and transformer-based architectures.
Authors: Benjamin Arnav, Pablo Bernabeu-P\'erez, Nathan Helm-Burger, Tim Kostolansky, Hannes Whittingham, Mary Phuong
Abstract: As AI models are deployed with increasing autonomy, it is important to ensure they do not take harmful actions unnoticed. As a potential mitigation, we investigate Chain-of-Thought (CoT) monitoring, wherein a weaker trusted monitor model continuously oversees the intermediate reasoning steps of a more powerful but untrusted model. We compare CoT monitoring to action-only monitoring, where only final outputs are reviewed, in a red-teaming setup where the untrusted model is instructed to pursue harmful side tasks while completing a coding problem. We find that while CoT monitoring is more effective than overseeing only model outputs in scenarios where action-only monitoring fails to reliably identify sabotage, reasoning traces can contain misleading rationalizations that deceive the CoT monitors, reducing performance in obvious sabotage cases. To address this, we introduce a hybrid protocol that independently scores model reasoning and actions, and combines them using a weighted average. Our hybrid monitor consistently outperforms both CoT and action-only monitors across all tested models and tasks, with detection rates twice higher than action-only monitoring for subtle deception scenarios.
Authors: Junjie Xing, Yeye He, Mengyu Zhou, Haoyu Dong, Shi Han, Lingjiao Chen, Dongmei Zhang, Surajit Chaudhuri, H. V. Jagadish
Abstract: Tables and table-based use cases play a crucial role in many important real-world applications, such as spreadsheets, databases, and computational notebooks, which traditionally require expert-level users like data engineers, data analysts, and database administrators to operate. Although LLMs have shown remarkable progress in working with tables (e.g., in spreadsheet and database copilot scenarios), comprehensive benchmarking of such capabilities remains limited. In contrast to an extensive and growing list of NLP benchmarks, evaluations of table-related tasks are scarce, and narrowly focus on tasks like NL-to-SQL and Table-QA, overlooking the broader spectrum of real-world tasks that professional users face. This gap limits our understanding and model progress in this important area. In this work, we introduce MMTU, a large-scale benchmark with over 28K questions across 25 real-world table tasks, designed to comprehensively evaluate models ability to understand, reason, and manipulate real tables at the expert-level. These tasks are drawn from decades' worth of computer science research on tabular data, with a focus on complex table tasks faced by professional users. We show that MMTU require a combination of skills -- including table understanding, reasoning, and coding -- that remain challenging for today's frontier models, where even frontier reasoning models like OpenAI GPT-5 and DeepSeek R1 score only around 69\% and 57\% respectively, suggesting significant room for improvement. We highlight key findings in our evaluation using MMTU and hope that this benchmark drives further advances in understanding and developing foundation models for structured data processing and analysis. Our code and data are available at https://github.com/MMTU-Benchmark/MMTU and https://huggingface.co/datasets/MMTU-benchmark/MMTU.
URLs: https://github.com/MMTU-Benchmark/MMTU, https://huggingface.co/datasets/MMTU-benchmark/MMTU.
Authors: Zelin He, Sarah Alnegheimish, Matthew Reimherr
Abstract: Time-series anomaly detection (TSAD) has played a vital role in a variety of fields, including healthcare, finance, and sensor-based condition monitoring. Prior methods, which mainly focus on training domain-specific models on numerical data, lack the visual-temporal understanding capacity that human experts have to identify contextual anomalies. To fill this gap, we explore a solution based on vision language models (VLMs). Recent studies have shown the ability of VLMs for visual understanding tasks, yet their direct application to time series has fallen short on both accuracy and efficiency. To harness the power of VLMs for TSAD, we propose a two-stage solution, with (1) ViT4TS, a vision-screening stage built on a relatively lightweight pre-trained vision encoder, which leverages 2D time series representations to accurately localize candidate anomalies; (2) VLM4TS, a VLM-based stage that integrates global temporal context and VLM's visual understanding capacity to refine the detection upon the candidates provided by ViT4TS. We show that without any time-series training, VLM4TS outperforms time-series pre-trained and from-scratch baselines in most cases, yielding a 24.6% improvement in F1-max score over the best baseline. Moreover, VLM4TS also consistently outperforms existing language model-based TSAD methods and is on average 36x more efficient in token usage.
Authors: Yichuan Wang, Zhifei Li, Shu Liu, Yongji Wu, Ziming Mao, Yilong Zhao, Xiao Yan, Zhiying Xu, Yang Zhou, Ion Stoica, Sewon Min, Matei Zaharia, Joseph E. Gonzalez
Abstract: Embedding-based vector search underpins many important applications, such as recommendation and retrieval-augmented generation (RAG). It relies on vector indices to enable efficient search. However, these indices require storing high-dimensional embeddings and large index metadata, whose total size can be several times larger than the original data (e.g., text chunks). Such high storage overhead makes it difficult, or even impractical, to deploy vector search on personal devices or large-scale datasets. To tackle this problem, we propose LEANN, a storage-efficient index for vector search that recomputes embeddings on the fly instead of storing them, and compresses state-of-the-art proximity graph indices while preserving search accuracy. LEANN delivers high-quality vector search while using only a fraction of the storage (e.g., 5% of the original data) and supporting storage-efficient index construction and updates. On real-world benchmarks, LEANN reduces index size by up to 50x compared with conventional indices, while maintaining SOTA accuracy and comparable latency for RAG applications.
Authors: Guan-Horng Liu, Jaemoo Choi, Yongxin Chen, Benjamin Kurt Miller, Ricky T. Q. Chen
Abstract: Computational methods for learning to sample from the Boltzmann distribution -- where the target distribution is known only up to an unnormalized energy function -- have advanced significantly recently. Due to the lack of explicit target samples, however, prior diffusion-based methods, known as diffusion samplers, often require importance-weighted estimation or complicated learning processes. Both trade off scalability with extensive evaluations of the energy and model, thereby limiting their practical usage. In this work, we propose Adjoint Schr\"odinger Bridge Sampler (ASBS), a new diffusion sampler that employs simple and scalable matching-based objectives yet without the need to estimate target samples during training. ASBS is grounded on a mathematical model -- the Schr\"odinger Bridge -- which enhances sampling efficiency via kinetic-optimal transportation. Through a new lens of stochastic optimal control theory, we demonstrate how SB-based diffusion samplers can be learned at scale via Adjoint Matching and prove convergence to the global solution. Notably, ASBS generalizes the recent Adjoint Sampling (Havens et al., 2025) to arbitrary source distributions by relaxing the so-called memoryless condition that largely restricts the design space. Through extensive experiments, we demonstrate the effectiveness of ASBS on sampling from classical energy functions, amortized conformer generation, and molecular Boltzmann distributions. Code available at https://github.com/facebookresearch/adjoint_samplers
Authors: Yuxiang Wan, Ryan Devera, Wenjie Zhang, Ju Sun
Abstract: We present FMPlug, a novel plug-in framework that enhances foundation flow-matching (FM) priors for solving ill-posed inverse problems. Unlike traditional approaches that rely on domain-specific or untrained priors, FMPlug smartly leverages two simple but powerful insights: the similarity between observed and desired objects and the Gaussianity of generative flows. By introducing a time-adaptive warm-up strategy and sharp Gaussianity regularization, FMPlug unlocks the true potential of domain-agnostic foundation models. Our method beats state-of-the-art methods that use foundation FM priors by significant margins, on image super-resolution and Gaussian deblurring.
Authors: Matteo Caligiuri, Francesco Barbato, Donald Shenaj, Umberto Michieli, Pietro Zanuttigh
Abstract: Federated Learning (FL) is an established paradigm for training deep learning models on decentralized data. However, as the size of the models grows, conventional FL approaches often require significant computational resources on client devices, which may not be feasible. We introduce FedPromo, a novel framework that enables efficient adaptation of large-scale foundation models stored on a central server to new domains encountered only by remote clients. Instead of directly training the large model on client devices, FedPromo optimizes lightweight proxy models via FL, significantly reducing computational overhead while maintaining privacy. Our method follows a two-stage process: first, server-side knowledge distillation aligns the representations of a large-scale foundation model (e.g., a transformer) with those of a compact counterpart (e.g., a CNN). Then, the compact model encoder is deployed to client devices, where trainable classifiers are learned locally. These classifiers are subsequently aggregated and seamlessly transferred back to the foundation model, facilitating personalized adaptation without requiring direct access to user data. Through novel regularization strategies, our framework enables decentralized multi-domain learning, balancing performance, privacy, and resource efficiency. Extensive experiments on five image classification benchmarks demonstrate that FedPromo outperforms existing methods while assuming limited-resource clients.
Authors: Ouyang Xu, Baoming Zhang, Ruiyu Mao, Yunhui Guo
Abstract: Deep learning models for visual recognition often exhibit systematic errors due to underrepresented semantic subpopulations. Although existing debugging frameworks can pinpoint these failures by identifying key failure attributes, repairing the model effectively remains difficult. Current solutions often rely on manually designed prompts to generate synthetic training images -- an approach prone to distribution shift and semantic errors. To overcome these challenges, we introduce a model repair module that builds on an interpretable failure attribution pipeline. Our approach uses a conditional text-to-image model to generate semantically faithful and targeted images for failure cases. To preserve the quality and relevance of the generated samples, we further employ a large vision-language model (LVLM) to filter the outputs, enforcing alignment with the original data distribution and maintaining semantic consistency. By retraining vision models with this rare-case-augmented synthetic dataset, we significantly reduce errors associated with rare cases. Our experiments demonstrate that this targeted repair strategy improves model robustness without introducing new bugs. Code is available at https://github.com/oxu2/SafeFix
Authors: Michael Poppel, David Bucher, Maximilian Zorn, Nico Kraus, Philipp Altmann, Jonas Stein, Claudia Linnhoff-Popien
Abstract: Quantum machine learning research has expanded rapidly due to potential computational advantages over classical methods. Angle encoding has emerged as a popular choice as feature map (FM) for embedding classical data into quantum models due to its simplicity and natural generation of truncated Fourier series, providing universal function approximation capabilities. Efficient FMs within quantum circuits can exploit exponential scaling of Fourier frequencies, with multi-dimensional inputs introducing additional exponential growth through mixed-frequency terms. Despite this promising expressive capability, practical implementation faces significant challenges. Through controlled experiments with white-box target functions, we demonstrate that training failures can occur even when all relevant frequencies are theoretically accessible. We illustrate how two primary known causes lead to unsuccessful optimization: insufficient trainable parameters relative to the model's frequency content, and limitations imposed by the ansatz's dynamic lie algebra dimension, but also uncover an additional parameter burden: the necessity of controlling non-unique frequencies within the model. To address this, we propose near-zero weight initialization to suppress unnecessary duplicate frequencies. For target functions with a priori frequency knowledge, we introduce frequency selection as a practical solution that reduces parameter requirements and mitigates the exponential growth that would otherwise render problems intractable due to parameter insufficiency. Our frequency selection approach achieved near-optimal performance (median $R^2 \approx 0.95$) with 78\% of the parameters needed by the best standard approach in 10 randomly chosen target functions.
Authors: Vivin Vinod, Peter Zaspel
Abstract: Active learning promises to provide an optimal training sample selection procedure in the construction of machine learning models. It often relies on minimizing the model's variance, which is assumed to decrease the prediction error. Still, it is frequently even less efficient than pure random sampling. Motivated by the bias-variance decomposition, we propose to minimize the model's bias instead of its variance. By doing so, we are able to almost exactly match the best-case error over all possible greedy sample selection procedures for a relevant application. Our bias approximation is based on using cheap to calculate low fidelity data as known from $\Delta$-ML or multifidelity machine learning. We exemplify our approach for a wider class of applications in quantum chemistry including predicting excitation energies and ab initio potential energy surfaces. Here, the proposed method reduces training data consumption by up to an order of magnitude compared to standard active learning.
Authors: Hanzhi Chang, Ruijie Zhu, Wenjie Chang, Mulin Yu, Yanzhe Liang, Jiahao Lu, Zhuoyuan Li, Tianzhu Zhang
Abstract: Surface reconstruction has been widely studied in computer vision and graphics. However, existing surface reconstruction works struggle to recover accurate scene geometry when the input views are extremely sparse. To address this issue, we propose MeshSplat, a generalizable sparse-view surface reconstruction framework via Gaussian Splatting. Our key idea is to leverage 2DGS as a bridge, which connects novel view synthesis to learned geometric priors and then transfers these priors to achieve surface reconstruction. Specifically, we incorporate a feed-forward network to predict per-view pixel-aligned 2DGS, which enables the network to synthesize novel view images and thus eliminates the need for direct 3D ground-truth supervision. To improve the accuracy of 2DGS position and orientation prediction, we propose a Weighted Chamfer Distance Loss to regularize the depth maps, especially in overlapping areas of input views, and also a normal prediction network to align the orientation of 2DGS with normal vectors predicted by a monocular normal estimator. Extensive experiments validate the effectiveness of our proposed improvement, demonstrating that our method achieves state-of-the-art performance in generalizable sparse-view mesh reconstruction tasks. Project Page: https://hanzhichang.github.io/meshsplat_web
Authors: Ismail Hossain, Sai Puppala, Md Jahangir Alam, Sajedul Talukder
Abstract: Scams exploiting real-time social engineering -- such as phishing, impersonation, and phone fraud -- remain a persistent and evolving threat across digital platforms. Existing defenses are largely reactive, offering limited protection during active interactions. We propose a privacy-preserving, AI-in-the-loop framework that proactively detects and disrupts scam conversations in real time. The system combines instruction-tuned artificial intelligence with a safety-aware utility function that balances engagement with harm minimization, and employs federated learning to enable continual model updates without raw data sharing. Experimental evaluations show that the system produces fluent and engaging responses (perplexity as low as 22.3, engagement $\approx$0.80), while human studies confirm significant gains in realism, safety, and effectiveness over strong baselines. In federated settings, models trained with FedAvg sustain up to 30 rounds while preserving high engagement ($\approx$0.80), strong relevance ($\approx$0.74), and low PII leakage ($\leq$0.0085). Even with differential privacy, novelty and safety remain stable, indicating that robust privacy can be achieved without sacrificing performance. The evaluation of guard models (LlamaGuard, LlamaGuard2/3, MD-Judge) shows a straightforward pattern: stricter moderation settings reduce the chance of exposing personal information, but they also limit how much the model engages in conversation. In contrast, more relaxed settings allow longer and richer interactions, which improve scam detection, but at the cost of higher privacy risk. To our knowledge, this is the first framework to unify real-time scam-baiting, federated privacy preservation, and calibrated safety moderation into a proactive defense paradigm.
Authors: Karim Kadry, Shoaib Goraya, Ajay Manicka, Abdalla Abdelwahed, Naravich Chutisilp, Farhad Nezami, Elazer Edelman
Abstract: Generative models of 3D cardiovascular anatomy can synthesize informative structures for clinical research and medical device evaluation, but face a trade-off between geometric controllability and realism. We propose CardioComposer: a programmable, inference-time framework for generating multi-class anatomical label maps based on interpretable ellipsoidal primitives. These primitives represent geometric attributes such as the size, shape, and position of discrete substructures. We specifically develop differentiable measurement functions based on voxel-wise geometric moments, enabling loss-based gradient guidance during diffusion model sampling. We demonstrate that these losses can constrain individual geometric attributes in a disentangled manner and provide compositional control over multiple substructures. Finally, we show that our method is compatible with a wide array of anatomical systems containing non-convex substructures, spanning cardiac, vascular, and skeletal organs.
Authors: Bowen Qin, Chen Yue, Fang Yin, Hui Wang, JG Yao, Jiakang Liu, Jing-Shu Zheng, Miguel Hu Chen, Richeng Xuan, Shibei Meng, Shiqi Zhou, Teng Dai, Tong-Shuai Ren, Wei Cui, Xi Yang, Xialin Du, Xiaojing Xu, Xue Sun, Xuejing Li, Yaming Liu, Yesheng Liu, Ying Liu, Yonghua Lin, Yu Zhao, Yunduo Zhang, Yuwen Luo, Zheqi He, Zhiyuan He, Zhongyuan Wang
Abstract: We conduct a moderate-scale contamination-free (to some extent) evaluation of current large reasoning models (LRMs) with some preliminary findings. We also release ROME, our evaluation benchmark for vision language models intended to test reasoning from visual clues. We attach links to the benchmark, evaluation data, and other updates on this website: https://flageval-baai.github.io/LRM-Eval/
Authors: Yida Xue, Mingjun Mao, Xiangyuan Ru, Yuqi Zhu, Baochang Ren, Shuofei Qiao, Mengru Wang, Shumin Deng, Xinyu An, Ningyu Zhang, Ying Chen, Huajun Chen
Abstract: We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments. Unlike terrestrial or aerial domains, underwater settings present extreme perceptual and decision-making challenges, including low visibility, dynamic ocean currents, making effective agent deployment exceptionally difficult. OceanGym encompasses eight realistic task domains and a unified agent framework driven by Multi-modal Large Language Models (MLLMs), which integrates perception, memory, and sequential decision-making. Agents are required to comprehend optical and sonar data, autonomously explore complex environments, and accomplish long-horizon objectives under these harsh conditions. Extensive experiments reveal substantial gaps between state-of-the-art MLLM-driven agents and human experts, highlighting the persistent difficulty of perception, planning, and adaptability in ocean underwater environments. By providing a high-fidelity, rigorously designed platform, OceanGym establishes a testbed for developing robust embodied AI and transferring these capabilities to real-world autonomous ocean underwater vehicles, marking a decisive step toward intelligent agents capable of operating in one of Earth's last unexplored frontiers. The code and data are available at https://github.com/OceanGPT/OceanGym.
Authors: Buxin Su, Natalie Collina, Garrett Wen, Didong Li, Kyunghyun Cho, Jianqing Fan, Bingxin Zhao, Weijie Su
Abstract: Peer review in academic research aims not only to ensure factual correctness but also to identify work of high scientific potential that can shape future research directions. This task is especially critical in fast-moving fields such as artificial intelligence (AI), yet it has become increasingly difficult given the rapid growth of submissions. In this paper, we investigate an underexplored measure for identifying high-impact research: authors' own rankings of their multiple submissions to the same AI conference. Grounded in game-theoretic reasoning, we hypothesize that self-rankings are informative because authors possess unique understanding of their work's conceptual depth and long-term promise. To test this hypothesis, we conducted a large-scale experiment at a leading AI conference, where 1,342 researchers self-ranked their 2,592 submissions by perceived quality. Tracking outcomes over more than a year, we found that papers ranked highest by their authors received twice as many citations as their lowest-ranked counterparts; self-rankings were especially effective at identifying highly cited papers (those with over 150 citations). Moreover, we showed that self-rankings outperformed peer review scores in predicting future citation counts. Our results remained robust after accounting for confounders such as preprint posting time and self-citations. Together, these findings demonstrate that authors' self-rankings provide a reliable and valuable complement to peer review for identifying and elevating high-impact research in AI.
Authors: William Hao-Cheng Huang
Abstract: In high-dimensional learning, models remain stable until they collapse abruptly once the sample size falls below a critical level. This instability is not algorithm-specific but a geometric mechanism: when the weakest Fisher eigendirection falls beneath sample-level fluctuations, identifiability fails. Our Fisher Threshold Theorem formalizes this by proving that stability requires the minimal Fisher eigenvalue to exceed an explicit $O(\sqrt{d/n})$ bound. Unlike prior asymptotic or model-specific criteria, this threshold is finite-sample and necessary, marking a sharp phase transition between reliable concentration and inevitable failure. To make the principle constructive, we introduce the Fisher floor, a verifiable spectral regularization robust to smoothing and preconditioning. Synthetic experiments on Gaussian mixtures and logistic models confirm the predicted transition, consistent with $d/n$ scaling. Statistically, the threshold sharpens classical eigenvalue conditions into a non-asymptotic law; learning-theoretically, it defines a spectral sample-complexity frontier, bridging theory with diagnostics for robust high-dimensional inference.
Authors: Tian Guo, Emmanuel Hauptmann
Abstract: In quantitative investing, return prediction supports various tasks, including stock selection, portfolio optimization, and risk management. Quantitative factors, such as valuation, quality, and growth, capture various characteristics of stocks. Unstructured data, like news and transcripts, has attracted growing attention, driven by recent advances in large language models (LLMs). This paper examines effective methods for leveraging multimodal factors and newsflow in return prediction and stock selection. First, we introduce a fusion learning framework to learn a unified representation from factors and newsflow representations generated by an LLM. Within this framework, we compare three methods of different architectural complexities: representation combination, representation summation, and attentive representations. Next, building on the limitation of fusion learning observed in empirical comparison, we explore the mixture model that adaptively combines predictions made by single modalities and their fusion. To mitigate the training instability of the mixture model, we introduce a decoupled training approach with theoretical insights. Finally, our experiments on real investment universes yield several insights into effective multimodal modeling of factors and news for stock return prediction and selection.
Authors: Pengfei Gao, Chao Peng
Abstract: LLM-powered coding agents, which operate in iterative loops (turns) to solve software engineering tasks, are becoming increasingly powerful. However, their practical deployment is hindered by significant and unpredictable costs. This challenge arises from a combination of factors: quadratically growing token counts with each turn, the high price of models, the large number of turns required for real-world tasks, and the tendency of agents to take inefficient or unnecessary actions. While existing research focuses on optimizing individual turns, the strategic control of the total number of turns remains an underexplored area for managing agent performance and cost. To address this gap, we conduct a comprehensive empirical study on SWE-bench using three state-of-the-art models and evaluate the impact of three distinct turn-control strategies: an unrestricted baseline, a fixed-turn limit with reminders, and a novel dynamic-turn strategy that grants extensions on-demand. Our findings first reveal a fundamental trade-off in the unrestricted setting, where no single model excels across performance, cost, and turn efficiency. We then show that a fixed-turn limit, specifically at the 75th percentile of the baseline, serves as a "sweet spot", substantially reducing costs (by 24%-68%) with minimal impact on solve rates. Most significantly, the dynamic-turn strategy consistently outperforms fixed-limit approaches, achieving comparable or better solve rates while further reducing costs by an additional 12%-24% by intelligently allocating resources only to tasks that need them. This work provides the first systematic analysis of turn-control strategies, offering simple yet effective guidelines for developers to balance cost and efficacy. We demonstrate that dynamic resource allocation is a superior, easy-to-implement approach for deploying powerful yet economically viable coding agents.
Authors: Jizhan Fang, Xinle Deng, Haoming Xu, Ziyan Jiang, Yuqi Tang, Ziwen Xu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Huajun Chen, Ningyu Zhang
Abstract: Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory systems enable LLMs to move beyond stateless interactions by introducing persistent information storage, retrieval, and utilization mechanisms. However, existing memory systems often introduce substantial time and computational overhead. To this end, we introduce a new memory system called LightMem, which strikes a balance between the performance and efficiency of memory systems. Inspired by the Atkinson-Shiffrin model of human memory, LightMem organizes memory into three complementary stages. First, cognition-inspired sensory memory rapidly filters irrelevant information through lightweight compression and groups information according to their topics. Next, topic-aware short-term memory consolidates these topic-based groups, organizing and summarizing content for more structured access. Finally, long-term memory with sleep-time update employs an offline procedure that decouples consolidation from online inference. On LongMemEval and LoCoMo, using GPT and Qwen backbones, LightMem consistently surpasses strong baselines, improving QA accuracy by up to 7.7% / 29.3%, reducing total token usage by up to 38x / 20.9x and API calls by up to 30x / 55.5x, while purely online test-time costs are even lower, achieving up to 106x / 117x token reduction and 159x / 310x fewer API calls. The code is available at https://github.com/zjunlp/LightMem.
Authors: Aleksandr Mazur, Roman Sharypov, Andrey Shirokov
Abstract: An ensemble of neural networks is employed to extrapolate no-core shell model (NCSM) results to infinite model space for light nuclei. We present a review of our neural network extrapolations of the NCSM results obtained with the Daejeon16 NN interaction in different model spaces and with different values of the NCSM basis parameter $\hbar\Omega$ for energies of nuclear states and root-mean-square (rms) radii of proton, neutron and matter distributions in light nuclei. The method yields convergent predictions with quantifiable uncertainties. Ground-state energies for $^{6}$Li, $^{6}$He, and the unbound $^{6}$Be, as well as the excited $(3^{+},0)$ and $(0^{+},1)$ states of $^{6}$Li, are obtained within a few hundred keV of experiment. The extrapolated radii of bound states converge well. In contrast, radii of unbound states in $^{6}$Be and $^{6}$Li do not stabilize.
Authors: Pietro Cappelli, Gaia Grosso, Marco Letizia, Humberto Reyes-Gonz\'alez, Marco Zanetti
Abstract: Generative models are increasingly central to scientific workflows, yet their systematic use and interpretation require a proper understanding of their limitations through rigorous validation. Classic approaches struggle with scalability, statistical power, or interpretability when applied to high-dimensional data, making it difficult to certify the reliability of these models in realistic, high-dimensional scientific settings. Here, we propose the use of the New Physics Learning Machine (NPLM), a learning-based approach to goodness-of-fit testing inspired by the Neyman--Pearson construction, to test generative networks trained on high-dimensional scientific data. We demonstrate the performance of NPLM for validation in two benchmark cases: generative models trained on mixtures of Gaussian models with increasing dimensionality, and a public end-to-end model, known as FlowSim, developed to generate high-energy physics collision events. We demonstrate that the NPLM can serve as a powerful validation method while also providing a means to diagnose sub-optimally modeled regions of the data.
Authors: Eric Xue, Ruiyi Zhang, Zijun Zhang, Pengtao Xie
Abstract: Transformer models are foundational to natural language processing (NLP) applications, yet remain vulnerable to backdoor attacks introduced through poisoned data, which implant hidden behaviors during training. To strengthen the ability to prevent such compromises, recent research has focused on designing increasingly stealthy attacks to stress-test existing defenses, pairing backdoor behaviors with stylized artifact or token-level perturbation triggers. However, this trend diverts attention from the harder and more realistic case: making the model respond to semantic triggers such as specific names or entities, where a successful backdoor could manipulate outputs tied to real people or events in deployed systems. Motivated by this growing disconnect, we introduce SteganoBackdoor, bringing stealth techniques back into line with practical threat models. Leveraging innocuous properties from natural-language steganography, SteganoBackdoor applies a gradient-guided data optimization process to transform semantic trigger seeds into steganographic carriers that embed a high backdoor payload, remain fluent, and exhibit no representational resemblance to the trigger. Across diverse experimental settings, SteganoBackdoor achieves over 99% attack success at an order-of-magnitude lower data-poisoning rate than prior approaches while maintaining unparalleled evasion against a comprehensive suite of data-level defenses. By revealing this practical and covert attack, SteganoBackdoor highlights an urgent blind spot in current defenses and demands immediate attention to adversarial data defenses and real-world threat modeling.
Authors: Khaled Hamidouche (NVIDIA Corporation), John Bachan (NVIDIA Corporation), Pak Markthub (NVIDIA Corporation), Peter-Jan Gootzen (NVIDIA Corporation), Elena Agostini (NVIDIA Corporation), Sylvain Jeaugey (NVIDIA Corporation), Aamir Shafi (NVIDIA Corporation), Georgios Theodorakis (NVIDIA Corporation), Manjunath Gorentla Venkata (NVIDIA Corporation)
Abstract: Modern AI workloads, especially Mixture-of-Experts (MoE) architectures, increasingly demand low-latency, fine-grained GPU-to-GPU communication with device-side control. Traditional GPU communication follows a host-initiated model, where the CPU orchestrates all communication operations - a characteristic of the CUDA runtime. Although robust for collective operations, applications requiring tight integration of computation and communication can benefit from device-initiated communication that eliminates CPU coordination overhead. NCCL 2.28 introduces the Device API with three operation modes: Load/Store Accessible (LSA) for NVLink/PCIe, Multimem for NVLink SHARP, and GPU-Initiated Networking (GIN) for network RDMA. This paper presents the GIN architecture, design, semantics, and highlights its impact on MoE communication. GIN builds on a three-layer architecture: i) NCCL Core host-side APIs for device communicator setup and collective memory window registration; ii) Device-side APIs for remote memory operations callable from CUDA kernels; and iii) A network plugin architecture with dual semantics (GPUDirect Async Kernel-Initiated and Proxy) for broad hardware support. The GPUDirect Async Kernel-Initiated backend leverages DOCA GPUNetIO for direct GPU-to-NIC communication, while the Proxy backend provides equivalent functionality via lock-free GPU-to-CPU queues over standard RDMA networks. We demonstrate GIN's practicality through integration with DeepEP, an MoE communication library. Comprehensive benchmarking shows that GIN provides device-initiated communication within NCCL's unified runtime, combining low-latency operations with NCCL's collective algorithms and production infrastructure.
Authors: Qi Jiang, Xiaolong Qian, Yao Gao, Lei Sun, Kailun Yang, Zhonghua Yi, Wenyong Li, Ming-Hsuan Yang, Luc Van Gool, Kaiwei Wang
Abstract: Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demonstrating strong capability in handling diverse unknown optical degradations. This work proposes the OmniLens++ framework, which resolves two challenges that hinder the generalization ability of existing pipelines: the difficulty of scaling data and the absence of prior guidance characterizing optical degradation. To improve data scalability, we expand the design specifications to increase the degradation diversity of the lens source, and we sample a more uniform distribution by quantifying the spatial-variation patterns and severity of optical degradation. In terms of model design, to leverage the Point Spread Functions (PSFs), which intuitively describe optical degradation, as guidance in a blind paradigm, we propose the Latent PSF Representation (LPR). The VQVAE framework is introduced to learn latent features of LensLib's PSFs, which is assisted by modeling the optical degradation process to constrain the learning of degradation priors. Experiments on diverse aberrations of real-world lenses and synthetic LensLib show that OmniLens++ exhibits state-of-the-art generalization capacity in blind aberration correction. Beyond performance, the AODLibpro is verified as a scalable foundation for more effective training across diverse aberrations, and LPR can further tap the potential of large-scale LensLib. The source code and datasets will be made publicly available at https://github.com/zju-jiangqi/OmniLens2.
Authors: Valentin Roth, Marco Avella-Medina
Abstract: Dependent data underlies many statistical studies in the social and health sciences, which often involve sensitive or private information. Differential privacy (DP) and in particular \textit{user-level} DP provide a natural formalization of privacy requirements for processing dependent data where each individual provides multiple observations to the dataset. However, dependence introduced, e.g., through repeated measurements challenges the existing statistical theory under DP-constraints. In \iid{} settings, noisy Winsorized mean estimators have been shown to be minimax optimal for standard (\textit{item-level}) and \textit{user-level} DP estimation of a mean $\mu \in \R^d$. Yet, their behavior on potentially dependent observations has not previously been studied. We fill this gap and show that Winsorized mean estimators can also be used under dependence for bounded and unbounded data, and can lead to asymptotic and finite sample guarantees that resemble their \iid{} counterparts under a weak notion of dependence. For this, we formalize dependence via log-Sobolev inequalities on the joint distribution of observations. This enables us to adapt the stable histogram by Karwa and Vadhan (2018) to a non-\iid{} setting, which we then use to estimate the private projection intervals of the Winsorized estimator. The resulting guarantees for our item-level mean estimator extend to \textit{user-level} mean estimation and transfer to the local model via a randomized response histogram. Using the mean estimators as building blocks, we provide extensions to random effects models, longitudinal linear regression and nonparametric regression. Therefore, our work constitutes a first step towards a systematic study of DP for dependent data.