Authors: Tingjia Miao (School of Artificial Intelligence, Shanghai Jiao Tong University, School of Physics and Astronomy, Shanghai Jiao Tong University, Zhiyuan College, Shanghai Jiao Tong University), Jiawen Dai (School of Physics and Astronomy, Shanghai Jiao Tong University), Jingkun Liu (School of Physics and Astronomy, Shanghai Jiao Tong University), Jinxin Tan (School of Physics and Astronomy, Shanghai Jiao Tong University, State Key Laboratory of Dark Matter Physics, Shanghai Jiao Tong University, Tsung-Dao Lee Institute, Shanghai Jiao Tong University), Muhua Zhang (School of Physics and Astronomy, Shanghai Jiao Tong University, State Key Laboratory of Dark Matter Physics, Shanghai Jiao Tong University, Tsung-Dao Lee Institute, Shanghai Jiao Tong University), Wenkai Jin (School of Artificial Intelligence, Shanghai Jiao Tong University), Yuwen Du (School of Artificial Intelligence, Shanghai Jiao Tong University), Tian Jin (School of Artificial Intelligence, Shanghai Jiao Tong University), Xianghe Pang (School of Artificial Intelligence, Shanghai Jiao Tong University), Zexi Liu (School of Artificial Intelligence, Shanghai Jiao Tong University), Tu Guo (School of Physics and Astronomy, Shanghai Jiao Tong University, Tsung-Dao Lee Institute, Shanghai Jiao Tong University), Zhengliang Zhang (School of Physics and Astronomy, Shanghai Jiao Tong University, Tsung-Dao Lee Institute, Shanghai Jiao Tong University, Zhiyuan College, Shanghai Jiao Tong University), Yunjie Huang (School of Artificial Intelligence, Shanghai Jiao Tong University), Shuo Chen (Institute of Theoretical Physics, Chinese Academy of Sciences), Rui Ye (School of Artificial Intelligence, Shanghai Jiao Tong University), Yuzhi Zhang (DP Technology), Linfeng Zhang (DP Technology), Kun Chen (Institute of Theoretical Physics, Chinese Academy of Sciences), Wei Wang (School of Physics and Astronomy, Shanghai Jiao Tong University, State Key Laboratory of Dark Matter Physics, Shanghai Jiao Tong University, Tsung-Dao Lee Institute, Shanghai Jiao Tong University), Weinan E (School of Artificial Intelligence, Shanghai Jiao Tong University), Siheng Chen (School of Artificial Intelligence, Shanghai Jiao Tong University)
Abstract: Advances in LLMs have produced agents with knowledge and operational capabilities comparable to human scientists, suggesting potential to assist, accelerate, and automate research. However, existing studies mainly evaluate such systems on well-defined benchmarks or general tasks like literature retrieval, limiting their end-to-end problem-solving ability in open scientific scenarios. This is particularly true in physics, which is abstract, mathematically intensive, and requires integrating analytical reasoning with code-based computation. To address this, we propose PhysMaster, an LLM-based agent functioning as an autonomous theoretical and computational physicist. PhysMaster couples absract reasoning with numerical computation and leverages LANDAU, the Layered Academic Data Universe, which preserves retrieved literature, curated prior knowledge, and validated methodological traces, enhancing decision reliability and stability. It also employs an adaptive exploration strategy balancing efficiency and open-ended exploration, enabling robust performance in ultra-long-horizon tasks. We evaluate PhysMaster on problems from high-energy theory, condensed matter theory to astrophysics, including: (i) acceleration, compressing labor-intensive research from months to hours; (ii) automation, autonomously executing hypothesis-driven loops ; and (iii) autonomous discovery, independently exploring open problems.
Authors: Mahdi Mostajabdaveh, F. Sibel Salman, Walter J. Gutjahr
Abstract: The distribution of relief supplies to shelters is a critical aspect of post-disaster humanitarian logistics. In major disasters, prepositioned supplies often fall short of meeting all demands. We address the problem of planning vehicle routes from a distribution center to shelters while allocating limited relief supplies. To balance efficiency and equity, we formulate a bi-objective problem: minimizing a Gini-index-based measure of inequity in unsatisfied demand for fair distribution and minimizing total travel time for timely delivery. We propose a Mixed Integer Programming (MIP) model and use the $\epsilon$-constraint method to handle the bi-objective nature. By deriving mathematical properties of the optimal solution, we introduce valid inequalities and design an algorithm for optimal delivery allocations given feasible vehicle routes. A branch-and-price (B&P) algorithm is developed to solve the problem efficiently. Computational tests on realistic datasets from a past earthquake in Van, Turkey, and predicted data for Istanbul's Kartal region show that the B&P algorithm significantly outperforms commercial MIP solvers. Our bi-objective approach reduces aid distribution inequity by 34% without compromising efficiency. Results indicate that when time constraints are very loose or tight, lexicographic optimization prioritizing demand coverage over fairness is effective. For moderately restrictive time constraints, a balanced approach is essential to avoid inequitable outcomes.
Authors: Eric Yeh, John Cadigan, Ran Chen, Dick Crouch, Melinda Gervasio, Dayne Freitag
Abstract: Recent research has explored using very large language models (LLMs) as proxies for humans in tasks such as simulation, surveys, and studies. While LLMs do not possess a human psychology, they often can emulate human behaviors with sufficiently high fidelity to drive simulations to test human behavioral hypotheses, exhibiting more nuance and range than the rule-based agents often employed in behavioral economics. One key area of interest is the effect of personality on decision making, but the requirement that a prompt must be created for every tested personality profile introduces experimental overhead and degrades replicability. To address this issue, we leverage interpolative decoding, representing each dimension of personality as a pair of opposed prompts and employing an interpolation parameter to simulate behavior along the dimension. We show that interpolative decoding reliably modulates scores along each of the Big Five dimensions. We then show how interpolative decoding causes LLMs to mimic human decision-making behavior in economic games, replicating results from human psychological research. Finally, we present preliminary results of our efforts to ``twin'' individual human players in a collaborative game through systematic search for points in interpolation space that cause the system to replicate actions taken by the human subject.
Authors: Luciano Araujo Dourado Filho, Almir Moreira da Silva Neto, Rodrigo Pereira David, Rodrigo Tripodi Calumby
Abstract: This paper presents an approach developed to address the PlantClef 2025 challenge, which consists of a fine-grained multi-label species identification, over high-resolution images. Our solution focused on employing class prototypes obtained from the training dataset as a proxy guidance for training a segmentation Vision Transformer (ViT) on the test set images. To obtain these representations, the proposed method extracts features from training dataset images and create clusters, by applying K-Means, with $K$ equals to the number of classes in the dataset. The segmentation model is a customized narrow ViT, built by replacing the patch embedding layer with a frozen DinoV2, pre-trained on the training dataset for individual species classification. This model is trained to reconstruct the class prototypes of the training dataset from the test dataset images. We then use this model to obtain attention scores that enable to identify and localize areas of interest and consequently guide the classification process. The proposed approach enabled a domain-adaptation from multi-class identification with individual species, into multi-label classification from high-resolution vegetation plots. Our method achieved fifth place in the PlantCLEF 2025 challenge on the private leaderboard, with an F1 score of 0.33331. Besides that, in absolute terms our method scored 0.03 lower than the top-performing submission, suggesting that it may achieved competitive performance in the benchmark task. Our code is available at \href{https://github.com/ADAM-UEFS/PlantCLEF2025}{https://github.com/ADAM-UEFS/PlantCLEF2025}.
URLs: https://github.com/ADAM-UEFS/PlantCLEF2025, https://github.com/ADAM-UEFS/PlantCLEF2025
Authors: Luciano Araujo Dourado Filho, Rodrigo Tripodi Calumby
Abstract: Intra-class variability is given according to the significance in the degree of dissimilarity between images within a class. In that sense, depending on its intensity, intra-class variability can hinder the learning process for DL models, specially when such classes are also underrepresented, which is a very common scenario in Fine-Grained Visual Categorization (FGVC) tasks. This paper proposes a novel method that aims at leveraging classification performance in FGVC tasks by learning fine-grained features via classification of class-wise cluster assignments. Our goal is to apply clustering over each class individually, which can allow to discover pseudo-labels that encodes a latent degree of similarity between images. In turn, those labels can be employed in a hierarchical classification process that allows to learn more fine-grained visual features and thereby mitigating intra-class variability issues. Initial experiments over the PlantNet300k enabled to shed light upon several key points in which future work will have to be developed in order to find more conclusive evidence regarding the effectiveness of our method. Our method still achieves state-of-the-art performance on the PlantNet300k dataset even though some of its components haven't been shown to be fully optimized. Our code is available at \href{https://github.com/ADAM-UEFS/FGDCC}{https://github.com/ADAM-UEFS/FGDCC}.
URLs: https://github.com/ADAM-UEFS/FGDCC, https://github.com/ADAM-UEFS/FGDCC
Authors: Zhe Sun, Xueyuan Yang, Yujie Lu, Zhenliang Zhang
Abstract: The integration of embodied agents into human environments demands embodied social intelligence: reasoning over both social norms and physical constraints. However, existing evaluations fail to address this integration, as they are limited to either disembodied social reasoning (e.g., in text) or socially-agnostic physical tasks. Both approaches fail to assess an agent's ability to integrate and trade off both physical and social constraints within a realistic, embodied context. To address this challenge, we introduce Spatially Situated Social Intelligence Test (S$^{3}$IT), a benchmark specifically designed to evaluate embodied social intelligence. It is centered on a novel and challenging seat-ordering task, requiring an agent to arrange seating in a 3D environment for a group of large language model-driven (LLM-driven) NPCs with diverse identities, preferences, and intricate interpersonal relationships. Our procedurally extensible framework generates a vast and diverse scenario space with controllable difficulty, compelling the agent to acquire preferences through active dialogue, perceive the environment via autonomous exploration, and perform multi-objective optimization within a complex constraint network. We evaluate state-of-the-art LLMs on S$^{3}$IT and found that they still struggle with this problem, showing an obvious gap compared with the human baseline. Results imply that LLMs have deficiencies in spatial intelligence, yet simultaneously demonstrate their ability to achieve near human-level competence in resolving conflicts that possess explicit textual cues.
Authors: Jung Yeon Park, Yuxuan Chen, Floor Eijkelboom, Jan-Willem van de Meent, Lawson L. S. Wong, Robin Walters
Abstract: Symmetry is fundamental to understanding physical systems, and at the same time, can improve performance and sample efficiency in machine learning. Both pursuits require knowledge of the underlying symmetries in data. To address this, we propose learning symmetries directly from data via flow matching on Lie groups. We formulate symmetry discovery as learning a distribution over a larger hypothesis group, such that the learned distribution matches the symmetries observed in data. Relative to previous works, our method, \lieflow, is more flexible in terms of the types of groups it can discover and requires fewer assumptions. Experiments on 2D and 3D point clouds demonstrate the successful discovery of discrete groups, including reflections by flow matching over the complex domain. We identify a key challenge where the symmetric arrangement of the target modes causes ``last-minute convergence,'' where samples remain stationary until relatively late in the flow, and introduce a novel interpolation scheme for flow matching for symmetry discovery.
Authors: Hung-Chieh Fang, Kuo-Han Hung, Chu-Rong Chen, Po-Jung Chou, Chun-Kai Yang, Po-Chen Ko, Yu-Chiang Wang, Yueh-Hua Wu, Min-Hung Chen, Shao-Hua Sun
Abstract: Learning from videos offers a promising path toward generalist robots by providing rich visual and temporal priors beyond what real robot datasets contain. While existing video generative models produce impressive visual predictions, they are difficult to translate into low-level actions. Conversely, latent-action models better align videos with actions, but they typically operate at the single-step level and lack high-level planning capabilities. We bridge this gap by introducing Skill Abstraction from Optical Flow (SOF), a framework that learns latent skills from large collections of action-free videos. Our key idea is to learn a latent skill space through an intermediate representation based on optical flow that captures motion information aligned with both video dynamics and robot actions. By learning skills in this flow-based latent space, SOF enables high-level planning over video-derived skills and allows for easier translation of these skills into actions. Experiments show that our approach consistently improves performance in both multitask and long-horizon settings, demonstrating the ability to acquire and compose skills directly from raw visual data.
Authors: Hao Li, Fabian Deuser, Wenping Yin, Steffen Knoblauch, Wufan Zhao, Filip Biljecki, Yong Xue, Wei Huang
Abstract: As Earth's climate changes, it is impacting disasters and extreme weather events across the planet. Record-breaking heat waves, drenching rainfalls, extreme wildfires, and widespread flooding during hurricanes are all becoming more frequent and more intense. Rapid and efficient response to disaster events is essential for climate resilience and sustainability. A key challenge in disaster response is to accurately and quickly identify disaster locations to support decision-making and resources allocation. In this paper, we propose a Probabilistic Cross-view Geolocalization approach, called ProbGLC, exploring new pathways towards generative location awareness for rapid disaster response. Herein, we combine probabilistic and deterministic geolocalization models into a unified framework to simultaneously enhance model explainability (via uncertainty quantification) and achieve state-of-the-art geolocalization performance. Designed for rapid diaster response, the ProbGLC is able to address cross-view geolocalization across multiple disaster events as well as to offer unique features of probabilistic distribution and localizability score. To evaluate the ProbGLC, we conduct extensive experiments on two cross-view disaster datasets (i.e., MultiIAN and SAGAINDisaster), consisting diverse cross-view imagery pairs of multiple disaster types (e.g., hurricanes, wildfires, floods, to tornadoes). Preliminary results confirms the superior geolocalization accuracy (i.e., 0.86 in Acc@1km and 0.97 in Acc@25km) and model explainability (i.e., via probabilistic distributions and localizability scores) of the proposed ProbGLC approach, highlighting the great potential of leveraging generative cross-view approach to facilitate location awareness for better and faster disaster response. The data and code is publicly available at https://github.com/bobleegogogo/ProbGLC
Authors: Hamed Firooz, Rui Liu, Yuchen Lu, Zhenyu Hou, Fangzhou Xiong, Xiaoyang Zhang, Changshu Jian, Zhicheng Zhu, Jiayuan Ma, Jacob Tao, Chaitali Gupta, Xiaochang Peng, Shike Mei, Hang Cui, Yang Qin, Shuo Tang, Jason Gaedtke, Arpit Mittal
Abstract: Content moderation at scale remains one of the most pressing challenges in today's digital ecosystem, where billions of user- and AI-generated artifacts must be continuously evaluated for policy violations. Although recent advances in large language models (LLMs) have demonstrated strong potential for policy-grounded moderation, the practical challenges of training these systems to achieve expert-level accuracy in real-world settings remain largely unexplored, particularly in regimes characterized by label sparsity, evolving policy definitions, and the need for nuanced reasoning beyond shallow pattern matching. In this work, we present a comprehensive empirical investigation of scaling reinforcement learning (RL) for content classification, systematically evaluating multiple RL training recipes and reward-shaping strategies-including verifiable rewards and LLM-as-judge frameworks-to transform general-purpose language models into specialized, policy-aligned classifiers across three real-world content moderation tasks. Our findings provide actionable insights for industrial-scale moderation systems, demonstrating that RL exhibits sigmoid-like scaling behavior in which performance improves smoothly with increased training data, rollouts, and optimization steps before gradually saturating. Moreover, we show that RL substantially improves performance on tasks requiring complex policy-grounded reasoning while achieving up to 100x higher data efficiency than supervised fine-tuning, making it particularly effective in domains where expert annotations are scarce or costly.
Authors: H M Quamran Hasan, Housam Khalifa Bashier, Jiayi Dai, Mi-Young Kim, Randy Goebel
Abstract: Despite the wide adoption of Large Language Models (LLM)s, clinical decision support systems face a critical challenge: achieving high predictive accuracy while generating explanations aligned with the predictions. Current approaches suffer from exposure bias leading to misaligned explanations. We propose Reason2Decide, a two-stage training framework that addresses key challenges in self-rationalization, including exposure bias and task separation. In Stage-1, our model is trained on rationale generation, while in Stage-2, we jointly train on label prediction and rationale generation, applying scheduled sampling to gradually transition from conditioning on gold labels to model predictions. We evaluate Reason2Decide on three medical datasets, including a proprietary triage dataset and public biomedical QA datasets. Across model sizes, Reason2Decide outperforms other fine-tuning baselines and some zero-shot LLMs in prediction (F1) and rationale fidelity (BERTScore, BLEU, LLM-as-a-Judge). In triage, Reason2Decide is rationale source-robust across LLM-generated, nurse-authored, and nurse-post-processed rationales. In our experiments, while using only LLM-generated rationales in Stage-1, Reason2Decide outperforms other fine-tuning variants. This indicates that LLM-generated rationales are suitable for pretraining models, reducing reliance on human annotations. Remarkably, Reason2Decide achieves these gains with models 40x smaller than contemporary foundation models, making clinical reasoning more accessible for resource-constrained deployments while still providing explainable decision support.
Authors: Chaithra, Kamesh Kadimisetty, Biju R Mohan
Abstract: Financial sentiment analysis plays a crucial role in informing investment decisions, assessing market risk, and predicting stock price trends. Existing works in financial sentiment analysis have not considered the impact of stock prices or market feedback on sentiment analysis. In this paper, we propose an adaptive framework that integrates large language models (LLMs) with real-world stock market feedback to improve sentiment classification in the context of the Indian stock market. The proposed methodology fine-tunes the LLaMA 3.2 3B model using instruction-based learning on the SentiFin dataset. To enhance sentiment predictions, a retrieval-augmented generation (RAG) pipeline is employed that dynamically selects multi-source contextual information based on the cosine similarity of the sentence embeddings. Furthermore, a feedback-driven module is introduced that adjusts the reliability of the source by comparing predicted sentiment with actual next-day stock returns, allowing the system to iteratively adapt to market behavior. To generalize this adaptive mechanism across temporal data, a reinforcement learning agent trained using proximal policy optimization (PPO) is incorporated. The PPO agent learns to optimize source weighting policies based on cumulative reward signals from sentiment-return alignment. Experimental results on NIFTY 50 news headlines collected from 2024 to 2025 demonstrate that the proposed system significantly improves classification accuracy, F1-score, and market alignment over baseline models and static retrieval methods. The results validate the potential of combining instruction-tuned LLMs with dynamic feedback and reinforcement learning for robust, market-aware financial sentiment modeling.
Authors: Zhuo Yang, Yeyun chen, Jiaqing Xie, Ben Gao, Shuaike Shen, Wanhao Liu, Liujia Yang, Beilun Wang, Tianfan Fu, Yuqiang Li
Abstract: Molecular editing and optimization are multi-step problems that require iteratively improving properties while keeping molecules chemically valid and structurally similar. We frame both tasks as sequential, tool-guided decisions and introduce MolAct, an agentic reinforcement learning framework that employs a two-stage training paradigm: first building editing capability, then optimizing properties while reusing the learned editing behaviors. To the best of our knowledge, this is the first work to formalize molecular design as an Agentic Reinforcement Learning problem, where an LLM agent learns to interleave reasoning, tool-use, and molecular optimization. The framework enables agents to interact in multiple turns, invoking chemical tools for validity checking, property assessment, and similarity control, and leverages their feedback to refine subsequent edits. We instantiate the MolAct framework to train two model families: MolEditAgent for molecular editing tasks and MolOptAgent for molecular optimization tasks. In molecular editing, MolEditAgent-7B delivers 100, 95, and 98 valid add, delete, and substitute edits, outperforming strong closed "thinking" baselines such as DeepSeek-R1; MolEditAgent-3B approaches the performance of much larger open "thinking" models like Qwen3-32B-think. In molecular optimization, MolOptAgent-7B (trained on MolEditAgent-7B) surpasses the best closed "thinking" baseline (e.g., Claude 3.7) on LogP and remains competitive on solubility, while maintaining balanced performance across other objectives. These results highlight that treating molecular design as a multi-step, tool-augmented process is key to reliable and interpretable improvements.
Authors: Xingyou Yin, Ceyao Zhang, Min Hu, Kai Chen
Abstract: Large Language Models (LLMs) have demonstrated effectiveness as zero-shot time series (TS) forecasters. The key challenge lies in tokenizing TS data into textual representations that align with LLMs' pre-trained knowledge. While existing work often relies on fine-tuning specialized modules to bridge this gap, a distinct, yet challenging, paradigm aims to leverage truly off-the-shelf LLMs without any fine-tuning whatsoever, relying solely on strategic tokenization of numerical sequences. The performance of these fully frozen models is acutely sensitive to the textual representation of the input data, as their parameters cannot adapt to distribution shifts. In this paper, we introduce a simple yet highly effective strategy to overcome this brittleness: injecting noise into the raw time series before tokenization. This non-invasive intervention acts as a form of inference-time augmentation, compelling the frozen LLM to extrapolate based on robust underlying temporal patterns rather than superficial numerical artifacts. We theoretically analyze this phenomenon and empirically validate its effectiveness across diverse benchmarks. Notably, to fully eliminate potential biases from data contamination during LLM pre-training, we introduce two novel TS datasets that fall outside all utilized LLMs' pre-training scopes, and consistently observe improved performance. This study provides a further step in directly leveraging off-the-shelf LLMs for time series forecasting.
Authors: Dhivya Dharshini Kannan, Anupam Trivedi, Dipti Srinivasan
Abstract: Data centers account for significant global energy consumption and a carbon footprint. The recent increasing demand for edge computing and AI advancements drives the growth of data center storage capacity. Energy efficiency is a cost-effective way to combat climate change, cut energy costs, improve business competitiveness, and promote IT and environmental sustainability. Thus, optimizing data center energy management is the most important factor in the sustainability of the world. Power Usage Effectiveness (PUE) is used to represent the operational efficiency of the data center. Predicting PUE using Neural Networks provides an understanding of the effect of each feature on energy consumption, thus enabling targeted modifications of those key features to improve energy efficiency. In this paper, we have developed Bidirectional Gated Recurrent Unit (BiGRU) based PUE prediction model and compared the model performance with GRU. The data set comprises 52,560 samples with 117 features using EnergyPlus, simulating a DC in Singapore. Sets of the most relevant features are selected using the Recursive Feature Elimination with Cross-Validation (RFECV) algorithm for different parameter settings. These feature sets are used to find the optimal hyperparameter configuration and train the BiGRU model. The performance of the optimized BiGRU-based PUE prediction model is then compared with that of GRU using mean squared error (MSE), mean absolute error (MAE), and R-squared metrics.
Authors: Arghavan Bazigaran, Hansem Sohn
Abstract: We compare human and large language model (LLM) generalization in the number game, a concept inference task. Using a Bayesian model as an analytical framework, we examined the inductive biases and inference strategies of humans and LLMs. The Bayesian model captured human behavior better than LLMs in that humans flexibly infer rule-based and similarity-based concepts, whereas LLMs rely more on mathematical rules. Humans also demonstrated a few-shot generalization, even from a single example, while LLMs required more samples to generalize. These contrasts highlight the fundamental differences in how humans and LLMs infer and generalize mathematical concepts.
Authors: Ze Gong, Pradeep Varakantham, Akshat Kumar
Abstract: Offline Preference-based Reinforcement Learning (PbRL) learns rewards and policies aligned with human preferences without the need for extensive reward engineering and direct interaction with human annotators. However, ensuring safety remains a critical challenge across many domains and tasks. Previous works on safe RL from human feedback (RLHF) first learn reward and cost models from offline data, then use constrained RL to optimize a safe policy. While such an approach works in the contextual bandits settings (LLMs), in long horizon continuous control tasks, errors in rewards and costs accumulate, leading to impairment in performance when used with constrained RL methods. To address these challenges, (a) instead of indirectly learning policies (from rewards and costs), we introduce a framework that learns a policy directly based on pairwise preferences regarding the agent's behavior in terms of rewards, as well as binary labels indicating the safety of trajectory segments; (b) we propose \textsc{PreSa} (Preference and Safety Alignment), a method that combines preference learning module with safety alignment in a constrained optimization problem. This optimization problem is solved within a Lagrangian paradigm that directly learns reward-maximizing safe policy \textit{without explicitly learning reward and cost models}, avoiding the need for constrained RL; (c) we evaluate our approach on continuous control tasks with both synthetic and real human feedback. Empirically, our method successfully learns safe policies with high rewards, outperforming state-of-the-art baselines, and offline safe RL approaches with ground-truth reward and cost.
Authors: Zhe Sun, Kunlun Wu, Chuanjian Fu, Zeming Song, Langyong Shi, Zihe Xue, Bohan Jing, Ying Yang, Xiaomeng Gao, Aijia Li, Tianyu Guo, Huiying Li, Xueyuan Yang, Rongkai Liu, Xinyi He, Yuxi Wang, Yue Li, Mingyuan Liu, Yujie Lu, Hongzhao Xie, Shiyun Zhao, Bo Dai, Wei Wang, Tao Yuan, Song-Chun Zhu, Yujia Peng, Zhenliang Zhang
Abstract: As artificial intelligence (AI) rapidly advances, especially in multimodal large language models (MLLMs), research focus is shifting from single-modality text processing to the more complex domains of multimodal and embodied AI. Embodied intelligence focuses on training agents within realistic simulated environments, leveraging physical interaction and action feedback rather than conventionally labeled datasets. Yet, most existing simulation platforms remain narrowly designed, each tailored to specific tasks. A versatile, general-purpose training environment that can support everything from low-level embodied navigation to high-level composite activities, such as multi-agent social simulation and human-AI collaboration, remains largely unavailable. To bridge this gap, we introduce TongSIM, a high-fidelity, general-purpose platform for training and evaluating embodied agents. TongSIM offers practical advantages by providing over 100 diverse, multi-room indoor scenarios as well as an open-ended, interaction-rich outdoor town simulation, ensuring broad applicability across research needs. Its comprehensive evaluation framework and benchmarks enable precise assessment of agent capabilities, such as perception, cognition, decision-making, human-robot cooperation, and spatial and social reasoning. With features like customized scenes, task-adaptive fidelity, diverse agent types, and dynamic environmental simulation, TongSIM delivers flexibility and scalability for researchers, serving as a unified platform that accelerates training, evaluation, and advancement toward general embodied intelligence.
Authors: Xingbo Du, Loka Li, Duzhen Zhang, Le Song
Abstract: Memory systems have been designed to leverage past experiences in Large Language Model (LLM) agents. However, many deployed memory systems primarily optimize compression and storage, with comparatively less emphasis on explicit, closed-loop control of memory retrieval. From this observation, we build memory retrieval as an autonomous, accurate, and compatible agent system, named MemR$^3$, which has two core mechanisms: 1) a router that selects among retrieve, reflect, and answer actions to optimize answer quality; 2) a global evidence-gap tracker that explicitly renders the answering process transparent and tracks the evidence collection process. This design departs from the standard retrieve-then-answer pipeline by introducing a closed-loop control mechanism that enables autonomous decision-making. Empirical results on the LoCoMo benchmark demonstrate that MemR$^3$ surpasses strong baselines on LLM-as-a-Judge score, and particularly, it improves existing retrievers across four categories with an overall improvement on RAG (+7.29%) and Zep (+1.94%) using GPT-4.1-mini backend, offering a plug-and-play controller for existing memory stores.
Authors: Divya Vijay, Vignesh Ethiraj
Abstract: As networks evolve toward 5G Standalone and 6G, operators face orchestration challenges that exceed the limits of static automation and Deep Reinforcement Learning. Although Large Language Model (LLM) agents offer a path toward intent-based networking, they introduce stochastic risks, including topology hallucinations and policy non-compliance. To mitigate this, we propose Graph-Symbolic Policy Enforcement and Control (G-SPEC), a neuro-symbolic framework that constrains probabilistic planning with deterministic verification. The architecture relies on a Governance Triad - a telecom-adapted agent (TSLAM-4B), a Network Knowledge Graph (NKG), and SHACL constraints. We evaluated G-SPEC on a simulated 450-node 5G Core, achieving zero safety violations and a 94.1% remediation success rate, significantly outperforming the 82.4% baseline. Ablation analysis indicates that NKG validation drives the majority of safety gains (68%), followed by SHACL policies (24%). Scalability tests on topologies ranging from 10K to 100K nodes demonstrate that validation latency scales as $O(k^{1.2})$ where $k$ is subgraph size. With a processing overhead of 142ms, G-SPEC is viable for SMO-layer operations.
Authors: Yuntao Dai, Hang Gu, Teng Wang, Qianyu Cheng, Yifei Zheng, Zhiyong Qiu, Lei Gong, Wenqi Lou, Xuehai Zhou
Abstract: Vision-Language-Action (VLA) models have emerged as a unified paradigm for robotic perception and control, enabling emergent generalization and long-horizon task execution. However, their deployment in dynamic, real-world environments is severely hin dered by high inference latency. While smooth robotic interaction requires control frequencies of 20 to 30 Hz, current VLA models typi cally operate at only 3-5 Hz on edge devices due to the memory bound nature of autoregressive decoding. Existing optimizations often require extensive retraining or compromise model accuracy. To bridge this gap, we introduce ActionFlow, a system-level inference framework tailored for resource-constrained edge plat forms. At the core of ActionFlow is a Cross-Request Pipelin ing strategy, a novel scheduler that redefines VLA inference as a macro-pipeline of micro-requests. The strategy intelligently batches memory-bound Decode phases with compute-bound Prefill phases across continuous time steps to maximize hardware utilization. Furthermore, to support this scheduling, we propose a Cross Request State Packed Forward operator and a Unified KV Ring Buffer, which fuse fragmented memory operations into efficient dense computations. Experimental results demonstrate that ActionFlow achieves a 2.55x improvement in FPS on the OpenVLA-7B model without retraining, enabling real-time dy namic manipulation on edge hardware. Our work is available at https://anonymous.4open.science/r/ActionFlow-1D47.
Authors: Nishant Gaurav, Adit Akarsh, Ankit Ranjan, Manoj Bajaj
Abstract: While CodeMem establishes executable code as the optimal representation for agentic procedural memory, the mechanism for autonomously synthesizing this memory from a blank slate remains underexplored. This paper operationalizes the transition of Large Language Models from passive tool-users to active workflow architects. Through a high-fidelity case study of a cross-service orchestration task involving Outlook and OneDrive, we identify and address four structural bottlenecks in automated skill generation: the Discovery Gap involving navigation of large tool registries, the Verification Gap regarding grounding tool response structures, the Decomposition Gap which replaces inefficient search with Linear State Anchoring, and the Scaling Gap focused on concurrency and persistence. We demonstrate that by enforcing a scientific methodology of hypothesize, probe, and code, agents can autonomously write robust, production-grade code skills.
Authors: Junren Li, Luhua Lai
Abstract: Generative artificial intelligence has revolutionized the exploration of chemical space, yet a critical bottleneck remains that a substantial fraction of generated molecules is synthetically inaccessible. Current solutions, such as post-hoc filtering or projection-based methods, often compromise structural novelty or disrupt key pharmacophores by forcing molecules into pre-defined synthetic templates. Herein, we introduce SynCraft, a reasoning-based framework that reframes synthesizability optimization not as a sequence translation task, but as a precise structural editing problem. Leveraging the emergent reasoning capabilities of Large Language Models, SynCraft navigates the "synthesis cliff" where minimal structural modifications yield significant gains in synthetic feasibility. By predicting executable sequences of atom-level edits rather than generating SMILES strings directly, SynCraft circumvents the syntactic fragility of LLMs while harnessing their chemical intuition. Extensive benchmarks demonstrate that SynCraft outperforms state-of-the-art baselines in generating synthesizable analogs with high structural fidelity. Furthermore, through interaction-aware prompting, SynCraft successfully replicates expert medicinal chemistry intuition in editing PLK1 inhibitors and rescuing high-scoring but previously discarded RIPK1 candidates in previous molecular generation literatures.
Authors: Yaowei Bai, Ruiheng Zhang, Yu Lei, Xuhua Duan, Jingfeng Yao, Shuguang Ju, Chaoyang Wang, Wei Yao, Yiwan Guo, Guilin Zhang, Chao Wan, Qian Yuan, Lei Chen, Wenjuan Tang, Biqiang Zhu, Xinggang Wang, Tao Sun, Wei Zhou, Dacheng Tao, Yongchao Xu, Chuansheng Zheng, Huangxuan Zhao, Bo Du
Abstract: A global shortage of radiologists has been exacerbated by the significant volume of chest X-ray workloads, particularly in primary care. Although multimodal large language models show promise, existing evaluations predominantly rely on automated metrics or retrospective analyses, lacking rigorous prospective clinical validation. Janus-Pro-CXR (1B), a chest X-ray interpretation system based on DeepSeek Janus-Pro model, was developed and rigorously validated through a multicenter prospective trial (NCT07117266). Our system outperforms state-of-the-art X-ray report generation models in automated report generation, surpassing even larger-scale models including ChatGPT 4o (200B parameters), while demonstrating reliable detection of six clinically critical radiographic findings. Retrospective evaluation confirms significantly higher report accuracy than Janus-Pro and ChatGPT 4o. In prospective clinical deployment, AI assistance significantly improved report quality scores, reduced interpretation time by 18.3% (P < 0.001), and was preferred by a majority of experts in 54.3% of cases. Through lightweight architecture and domain-specific optimization, Janus-Pro-CXR improves diagnostic reliability and workflow efficiency, particularly in resource-constrained settings. The model architecture and implementation framework will be open-sourced to facilitate the clinical translation of AI-assisted radiology solutions.
Authors: YuChe Hsu, AnJui Wang, TsaiChing Ni, YuanFu Yang
Abstract: We propose a Vision-Language Simulation Model (VLSM) that unifies visual and textual understanding to synthesize executable FlexScript from layout sketches and natural-language prompts, enabling cross-modal reasoning for industrial simulation systems. To support this new paradigm, the study constructs the first large-scale dataset for generative digital twins, comprising over 120,000 prompt-sketch-code triplets that enable multimodal learning between textual descriptions, spatial structures, and simulation logic. In parallel, three novel evaluation metrics, Structural Validity Rate (SVR), Parameter Match Rate (PMR), and Execution Success Rate (ESR), are proposed specifically for this task to comprehensively evaluate structural integrity, parameter fidelity, and simulator executability. Through systematic ablation across vision encoders, connectors, and code-pretrained language backbones, the proposed models achieve near-perfect structural accuracy and high execution robustness. This work establishes a foundation for generative digital twins that integrate visual reasoning and language understanding into executable industrial simulation systems.
Authors: Linfeng Zhang, Siheng Chen, Yuzhu Cai, Jingyi Chai, Junhan Chang, Kun Chen, Zhi X. Chen, Zhaohan Ding, Yuwen Du, Yuanpeng Gao, Yuan Gao, Jing Gao, Zhifeng Gao, Qiangqiang Gu, Yanhui Hong, Yuan Huang, Xi Fang, Xiaohong Ji, Guolin Ke, Zixing Lei, Xinyu Li, Yongge Li, Ruoxue Liao, Hang Lin, Xiaolu Lin, Yuxiang Liu, Xinzijian Liu, Zexi Liu, Jintan Lu, Tingjia Miao, Haohui Que, Weijie Sun, Yanfeng Wang, Bingyang Wu, Tianju Xue, Rui Ye, Jinzhe Zeng, Duo Zhang, Jiahui Zhang, Linfeng Zhang, Tianhan Zhang, Wenchang Zhang, Yuzhi Zhang, Zezhong Zhang, Hang Zheng, Hui Zhou, Tong Zhu, Xinyu Zhu, Qingguo Zhou, Weinan E
Abstract: AI agents are emerging as a practical way to run multi-step scientific workflows that interleave reasoning with tool use and verification, pointing to a shift from isolated AI-assisted steps toward \emph{agentic science at scale}. This shift is increasingly feasible, as scientific tools and models can be invoked through stable interfaces and verified with recorded execution traces, and increasingly necessary, as AI accelerates scientific output and stresses the peer-review and publication pipeline, raising the bar for traceability and credible evaluation. However, scaling agentic science remains difficult: workflows are hard to observe and reproduce; many tools and laboratory systems are not agent-ready; execution is hard to trace and govern; and prototype AI Scientist systems are often bespoke, limiting reuse and systematic improvement from real workflow signals. We argue that scaling agentic science requires an infrastructure-and-ecosystem approach, instantiated in Bohrium+SciMaster. Bohrium acts as a managed, traceable hub for AI4S assets -- akin to a HuggingFace of AI for Science -- that turns diverse scientific data, software, compute, and laboratory systems into agent-ready capabilities. SciMaster orchestrates these capabilities into long-horizon scientific workflows, on which scientific agents can be composed and executed. Between infrastructure and orchestration, a \emph{scientific intelligence substrate} organizes reusable models, knowledge, and components into executable building blocks for workflow reasoning and action, enabling composition, auditability, and improvement through use. We demonstrate this stack with eleven representative master agents in real workflows, achieving orders-of-magnitude reductions in end-to-end scientific cycle time and generating execution-grounded signals from real workloads at multi-million scale.
Authors: Chehak Malhotra, Mehak Gopal, Akshaya Devadiga, Pradeep Singh, Ridam Pal, Ritwik Kashyap, Tavpritesh Sethi
Abstract: With the advent of LLMs, various tasks across the natural language processing domain have been transformed. However, their application in predictive tasks remains less researched. This study compares large language models, including GatorTron-Base (trained on clinical data), Llama 8B, and Mistral 7B, against models like BioBERT, DocBERT, BioClinicalBERT, Word2Vec, and Doc2Vec, setting benchmarks for predicting Shock in critically ill patients. Timely prediction of shock can enable early interventions, thus improving patient outcomes. Text data from 17,294 ICU stays of patients in the MIMIC III database were scored for length of stay > 24 hours and shock index (SI) > 0.7 to yield 355 and 87 patients with normal and abnormal SI-index, respectively. Both focal and cross-entropy losses were used during finetuning to address class imbalances. Our findings indicate that while GatorTron Base achieved the highest weighted recall of 80.5%, the overall performance metrics were comparable between SLMs and LLMs. This suggests that LLMs are not inherently superior to SLMs in predicting future clinical events despite their strong performance on text-based tasks. To achieve meaningful clinical outcomes, future efforts in training LLMs should prioritize developing models capable of predicting clinical trajectories rather than focusing on simpler tasks such as named entity recognition or phenotyping.
Authors: Zhiyi Duan, Xiangren Wang, Hongyu Yuan, Qianli Xing
Abstract: Teachers' emotional states are critical in educational scenarios, profoundly impacting teaching efficacy, student engagement, and learning achievements. However, existing studies often fail to accurately capture teachers' emotions due to the performative nature and overlook the critical impact of instructional information on emotional expression.In this paper, we systematically investigate teacher sentiment analysis by building both the dataset and the model accordingly. We construct the first large-scale teacher multimodal sentiment analysis dataset, T-MED.To ensure labeling accuracy and efficiency, we employ a human-machine collaborative labeling process.The T-MED dataset includes 14,938 instances of teacher emotional data from 250 real classrooms across 11 subjects ranging from K-12 to higher education, integrating multimodal text, audio, video, and instructional information.Furthermore, we propose a novel asymmetric attention-based multimodal teacher sentiment analysis model, AAM-TSA.AAM-TSA introduces an asymmetric attention mechanism and hierarchical gating unit to enable differentiated cross-modal feature fusion and precise emotional classification. Experimental results demonstrate that AAM-TSA significantly outperforms existing state-of-the-art methods in terms of accuracy and interpretability on the T-MED dataset.
Authors: Humza Nusrat, Luke Francisco, Bing Luo, Hassan Bagher-Ebadian, Joshua Kim, Karen Chin-Snyder, Salim Siddiqui, Mira Shah, Eric Mellon, Mohammad Ghassemi, Anthony Doemer, Benjamin Movsas, Kundan Thind
Abstract: Stereotactic radiosurgery (SRS) demands precise dose shaping around critical structures, yet black-box AI systems have limited clinical adoption due to opacity concerns. We tested whether chain-of-thought reasoning improves agentic planning in a retrospective cohort of 41 patients with brain metastases treated with 18 Gy single-fraction SRS. We developed SAGE (Secure Agent for Generative Dose Expertise), an LLM-based planning agent for automated SRS treatment planning. Two variants generated plans for each case: one using a non-reasoning model, one using a reasoning model. The reasoning variant showed comparable plan dosimetry relative to human planners on primary endpoints (PTV coverage, maximum dose, conformity index, gradient index; all p > 0.21) while reducing cochlear dose below human baselines (p = 0.022). When prompted to improve conformity, the reasoning model demonstrated systematic planning behaviors including prospective constraint verification (457 instances) and trade-off deliberation (609 instances), while the standard model exhibited none of these deliberative processes (0 and 7 instances, respectively). Content analysis revealed that constraint verification and causal explanation concentrated in the reasoning agent. The optimization traces serve as auditable logs, offering a path toward transparent automated planning.
Authors: Runtao Liu, Ziyi Liu, Jiaqi Tang, Yue Ma, Renjie Pi, Jipeng Zhang, Qifeng Chen
Abstract: Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed LongTVQA and LongTVQA+ which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent. Code and data will be shared at https://longvideoagent.github.io/.
Authors: Sandro Andric
Abstract: Interpretability methods for large language models (LLMs) typically derive directions from textual supervision, which can lack external grounding. We propose using human brain activity not as a training signal but as a coordinate system for reading and steering LLM states. Using the SMN4Lang MEG dataset, we construct a word-level brain atlas of phase-locking value (PLV) patterns and extract latent axes via ICA. We validate axes with independent lexica and NER-based labels (POS/log-frequency used as sanity checks), then train lightweight adapters that map LLM hidden states to these brain axes without fine-tuning the LLM. Steering along the resulting brain-derived directions yields a robust lexical (frequency-linked) axis in a mid TinyLlama layer, surviving perplexity-matched controls, and a brain-vs-text probe comparison shows larger log-frequency shifts (relative to the text probe) with lower perplexity for the brain axis. A function/content axis (axis 13) shows consistent steering in TinyLlama, Qwen2-0.5B, and GPT-2, with PPL-matched text-level corroboration. Layer-4 effects in TinyLlama are large but inconsistent, so we treat them as secondary (Appendix). Axis structure is stable when the atlas is rebuilt without GPT embedding-change features or with word2vec embeddings (|r|=0.64-0.95 across matched axes), reducing circularity concerns. Exploratory fMRI anchoring suggests potential alignment for embedding change and log frequency, but effects are sensitive to hemodynamic modeling assumptions and are treated as population-level evidence only. These results support a new interface: neurophysiology-grounded axes provide interpretable and controllable handles for LLM behavior.
Authors: Sebastian Racedo, Brigitte Jaumard, Oscar Delgado, Meysam Masoudi
Abstract: Open Radio Access Network (O RAN) disaggregates conventional RAN into interoperable components, enabling flexible resource allocation, energy savings, and agile architectural design. In legacy deployments, the binding between logical functions and physical locations is static, which leads to inefficiencies under time varying traffic and resource conditions. We address this limitation by relaxing the fixed mapping and performing dynamic service function chain (SFC) provisioning with on the fly O CU selection. We formulate the problem as a Markov decision process and solve it using GRLDyP, i.e., a graph neural network (GNN) assisted deep reinforcement learning (DRL). The proposed agent jointly selects routes and the O-CU location (from candidate sites) for each incoming service flow to minimize network energy consumption while satisfying quality of service (QoS) constraints. The GNN encodes the instantaneous network topology and resource utilization (e.g., CPU and bandwidth), and the DRL policy learns to balance grade of service, latency, and energy. We perform the evaluation of GRLDyP on a data set with 24-hour traffic traces from the city of Montreal, showing that dynamic O CU selection and routing significantly reduce energy consumption compared to a static mapping baseline, without violating QoS. The results highlight DRL based SFC provisioning as a practical control primitive for energy-aware, resource-adaptive O-RAN deployments.
Authors: Parsa Hatami, Ahmadreza Majlesara, Ali Majlesi, Babak Hossein Khalaj
Abstract: With the rapid growth of data volume in modern telecommunication networks and the continuous expansion of their scale, maintaining high reliability has become a critical requirement. These networks support a wide range of applications and services, including highly sensitive and mission-critical ones, which demand rapid and accurate detection and resolution of network errors. Traditional fault-diagnosis methods are no longer efficient for such complex environments.\cite{b1} In this study, we leverage Large Language Models (LLMs) to automate network fault detection and classification. Various types of network errors were intentionally injected into a Kubernetes-based test network, and data were collected under both healthy and faulty conditions. The dataset includes logs from different network components (pods), along with complementary data such as system descriptions, events, Round Trip Time (RTT) tests, and pod status information. The dataset covers common fault types such as pod failure, pod kill, network delay, network loss, and disk I/O failures. We fine-tuned the GPT-4.1 nano model via its API on this dataset, resulting in a significant improvement in fault-detection accuracy compared to the base model. These findings highlight the potential of LLM-based approaches for achieving closed-loop, and operator-free fault management, which can enhance network reliability and reduce downtime-related operational costs for service providers.
Authors: Yuxuan Yin, Shengke Zhou, Yunjie Zhang, Ajay Mohindra, Boxun Xu, Peng Li
Abstract: The rapid growth of cloud computing in the Electronic Design Automation (EDA) industry has created a critical need for resource and job lifetime prediction to achieve optimal scheduling. Traditional machine learning methods often struggle with the complexity and heterogeneity of EDA workloads, requiring extensive feature engineering and domain expertise. We propose a novel framework that fine-tunes Large Language Models (LLMs) to address this challenge through text-to-text regression. We introduce the scientific notation and prefix filling to constrain the LLM, significantly improving output format reliability. Moreover, we found that full-attention finetuning and inference improves the prediction accuracy of sliding-window-attention LLMs. We demonstrate the effectiveness of our proposed framework on real-world cloud datasets, setting a new baseline for performance prediction in the EDA domain.
Authors: Jian Xue, Qian Zhang, Wu Zhu
Abstract: We study how generative artificial intelligence (AI) transforms the work of financial analysts. Using the 2023 launch of FactSet's AI platform as a natural experiment, we find that adoption produces markedly richer and more comprehensive reports -- featuring 40% more distinct information sources, 34% broader topical coverage, and 25% greater use of advanced analytical methods -- while also improving timeliness. However, forecast errors rise by 59% as AI-assisted reports convey a more balanced mix of positive and negative information that is harder to synthesize, particularly for analysts facing heavier cognitive demands. Placebo tests using other data vendors confirm that these effects are unique to FactSet's AI integration. Overall, our findings reveal both the productivity gains and cognitive limits of generative AI in financial information production.
Authors: James K Ruffle, Samia Mohinta, Guilherme Pombo, Asthik Biswas, Alan Campbell, Indran Davagnanam, David Doig, Ahmed Hamman, Harpreet Hyare, Farrah Jabeen, Emma Lim, Dermot Mallon, Stephanie Owen, Sophie Wilkinson, Sebastian Brandner, Parashkev Nachev
Abstract: The benefits of artificial intelligence (AI) human partnerships-evaluating how AI agents enhance expert human performance-are increasingly studied. Though rarely evaluated in healthcare, an inverse approach is possible: AI benefiting from the support of an expert human agent. Here, we investigate both human-AI clinical partnership paradigms in the magnetic resonance imaging-guided characterisation of patients with brain tumours. We reveal that human-AI partnerships improve accuracy and metacognitive ability not only for radiologists supported by AI, but also for AI agents supported by radiologists. Moreover, the greatest patient benefit was evident with an AI agent supported by a human one. Synergistic improvements in agent accuracy, metacognitive performance, and inter-rater agreement suggest that AI can create more capable, confident, and consistent clinical agents, whether human or model-based. Our work suggests that the maximal value of AI in healthcare could emerge not from replacing human intelligence, but from AI agents that routinely leverage and amplify it.
Authors: Md Nahid Hasan Shuvo, Moinul Hossain
Abstract: Connected autonomous vehicles (CAVs) rely on vision-based deep neural networks (DNNs) and low-latency (Vehicle-to-Everything) V2X communication to navigate safely and efficiently. Despite their advances, these systems remain vulnerable to physical adversarial attacks. In this paper, we introduce PHANTOM (PHysical ANamorphic Threats Obstructing connected vehicle Mobility), a novel framework for crafting and deploying perspective-dependent adversarial examples using \textit{anamorphic art}. PHANTOM exploits geometric distortions that appear natural to humans but are misclassified with high confidence by state-of-the-art object detectors. Unlike conventional attacks, PHANTOM operates in black-box settings without model access and demonstrates strong transferability across four diverse detector architectures (YOLOv5, SSD, Faster R-CNN, and RetinaNet). Comprehensive evaluation in CARLA across varying speeds, weather conditions, and lighting scenarios shows that PHANTOM achieves over 90\% attack success rate under optimal conditions and maintains 60-80\% effectiveness even in degraded environments. The attack activates within 6-10 meters of the target, providing insufficient time for safe maneuvering. Beyond individual vehicle deception, PHANTOM triggers network-wide disruption in CAV systems: SUMO-OMNeT++ co-simulation demonstrates that false emergency messages propagate through V2X links, increasing Peak Age of Information by 68-89\% and degrading safety-critical communication. These findings expose critical vulnerabilities in both perception and communication layers of CAV ecosystems.
Authors: Behrooz Mamandipoor, Chun-Nan Hsu, Martin Krause, Ulrich H. Schmidt, Rodney A. Gabriel
Abstract: Early prediction of in-hospital mortality in critically ill patients can aid clinicians in optimizing treatment. The objective was to develop a multimodal deep learning model, using structured and unstructured clinical data, to predict in-hospital mortality risk among critically ill patients after their initial 24 hour intensive care unit (ICU) admission. We used data from MIMIC-III, MIMIC-IV, eICU, and HiRID. A multimodal model was developed on the MIMIC datasets, featuring time series components occurring within the first 24 hours of ICU admission and predicting risk of subsequent inpatient mortality. Inputs included time-invariant variables, time-variant variables, clinical notes, and chest X-ray images. External validation occurred in a temporally separated MIMIC population, HiRID, and eICU datasets. A total of 203,434 ICU admissions from more than 200 hospitals between 2001 to 2022 were included, in which mortality rate ranged from 5.2% to 7.9% across the four datasets. The model integrating structured data points had AUROC, AUPRC, and Brier scores of 0.92, 0.53, and 0.19, respectively. We externally validated the model on eight different institutions within the eICU dataset, demonstrating AUROCs ranging from 0.84-0.92. When including only patients with available clinical notes and imaging data, inclusion of notes and imaging into the model, the AUROC, AUPRC, and Brier score improved from 0.87 to 0.89, 0.43 to 0.48, and 0.37 to 0.17, respectively. Our findings highlight the importance of incorporating multiple sources of patient information for mortality prediction and the importance of external validation.
Authors: Zhan Zhang
Abstract: Finding rare but useful solutions in very large candidate spaces is a recurring practical challenge across language generation, planning, and reinforcement learning. We present a practical framework, \emph{Inverted Causality Focusing Algorithm} (ICFA), that treats search as a target-conditioned reweighting process. ICFA reuses an available proposal sampler and a task-specific similarity function to form a focused sampling distribution, while adaptively controlling focusing strength to avoid degeneracy. We provide a clear recipe, a stability diagnostic based on effective sample size, a compact theoretical sketch explaining when ICFA can reduce sample needs, and two reproducible experiments: constrained language generation and sparse-reward navigation. We further show how structured prompts instantiate an approximate, language-level form of ICFA and describe a hybrid architecture combining prompted inference with algorithmic reweighting.
Authors: Zihao Lv, Siqi Ai, Yanbin Zhang
Abstract: Targeted maintenance strategies, ensuring the dependability and safety of industrial machinery. However, current modeling techniques for assessing both local and global correlation of battery degradation sequences are inefficient and difficult to meet the needs in real-life applications. For this reason, we propose a novel deep learning architecture, multiscale dual-path feature aggregation network (MDFA-Net), for RUL prediction. MDFA-Net consists of dual-path networks, the first path network, multiscale feature network (MF-Net) that maintains the shallow information and avoids missing information, and the second path network is an encoder network (EC-Net) that captures the continuous trend of the sequences and retains deep details. Integrating both deep and shallow attributes effectively grasps both local and global patterns. Testing conducted with two publicly available Lithium-ion battery datasets reveals our approach surpasses existing top-tier methods in RUL forecasting, accurately mapping the capacity degradation trajectory.
Authors: Carlos Purves
Abstract: Reinforcement learning (RL) has achieved strong results, but deploying visual policies on resource-constrained edge devices remains challenging due to computational cost and communication latency. Many deployments therefore offload policy inference to a remote server, incurring network round trips and requiring transmission of high-dimensional observations. We introduce a split-policy architecture in which a small on-device encoder, implemented as OpenGL fragment-shader passes for broad embedded GPU support, transforms each observation into a compact feature tensor that is transmitted to a remote policy head. In RL, this communication overhead manifests as closed-loop decision latency rather than only per-request inference latency. The proposed approach reduces transmitted data, lowers decision latency in bandwidth-limited settings, and reduces server-side compute per request, whilst achieving broadly comparable learning performance by final return (mean over the final 100 episodes) in single-run benchmarks, with modest trade-offs in mean return. We evaluate across an NVIDIA Jetson Nano, a Raspberry Pi 4B, and a Raspberry Pi Zero 2 W, reporting learning results, on-device execution behaviour under sustained load, and end-to-end decision latency and scalability measurements under bandwidth shaping. Code for training, deployment, and measurement is released as open source.
Authors: Kosuke Ukita, Tsuyoshi Okita
Abstract: Diffusion models can learn rich representations during data generation, showing potential for Self-Supervised Learning (SSL), but they face a trade-off between generative quality and discriminative performance. Their iterative sampling also incurs substantial computational and energy costs, hindering industrial and edge AI applications. To address these issues, we propose the Flow Matching-based Foundation Model (FlowFM), which jointly trains a representation encoder and a conditional flow matching generator. This decoupled design achieves both high-fidelity generation and effective recognition. By using flow matching to learn a simpler velocity field, FlowFM accelerates and stabilizes training, improving its efficiency for representation learning. Experiments on wearable sensor data show FlowFM reduces training time by 50.4\% compared to a diffusion-based approach. On downstream tasks, FlowFM surpassed the state-of-the-art SSL method (SSL-Wearables) on all five datasets while achieving up to a 51.0x inference speedup and maintaining high generative quality. The implementation code is available at https://github.com/Okita-Laboratory/jointOptimizationFlowMatching.
URLs: https://github.com/Okita-Laboratory/jointOptimizationFlowMatching.
Authors: Gongli Xi, Ye Tian, Mengyu Yang, Zhenyu Zhao, Yuchao Zhang, Xiangyang Gong, Xirong Que, Wendong Wang
Abstract: The structure of topology underpins much of the research on performance and robustness, yet available topology data are typically scarce, necessitating the generation of synthetic graphs with desired properties for testing or release. Prior diffusion-based approaches either embed conditions into the diffusion model, requiring retraining for each attribute and hindering real-time applicability, or use classifier-based guidance post-training, which does not account for topology scale and practical constraints. In this paper, we show from a discrete perspective that gradients from a pre-trained graph-level classifier can be incorporated into the discrete reverse diffusion posterior to steer generation toward specified structural properties. Based on this insight, we propose Classifier-guided Conditional Topology Generation with Persistent Homology (CoPHo), which builds a persistent homology filtration over intermediate graphs and interprets features as guidance signals that steer generation toward the desired properties at each denoising step. Experiments on four generic/network datasets demonstrate that CoPHo outperforms existing methods at matching target metrics, and we further validate its transferability on the QM9 molecular dataset.
Authors: Cl\'ement Elliker, Jesse Read, Sonia Vanier, Albert Bifet
Abstract: Reliable prediction of train delays is essential for enhancing the robustness and efficiency of railway transportation systems. In this work, we reframe delay forecasting as a stochastic simulation task, modeling state-transition dynamics through imitation learning. We introduce Drift-Corrected Imitation Learning (DCIL), a novel self-supervised algorithm that extends DAgger by incorporating distance-based drift correction, thereby mitigating covariate shift during rollouts without requiring access to an external oracle or adversarial schemes. Our approach synthesizes the dynamical fidelity of event-driven models with the representational capacity of data-driven methods, enabling uncertainty-aware forecasting via Monte Carlo simulation. We evaluate DCIL using a comprehensive real-world dataset from \textsc{Infrabel}, the Belgian railway infrastructure manager, which encompasses over three million train movements. Our results, focused on predictions up to 30 minutes ahead, demonstrate superior predictive performance of DCIL over traditional regression models and behavioral cloning on deep learning architectures, highlighting its effectiveness in capturing the sequential and uncertain nature of delay propagation in large-scale networks.
Authors: Sasan Sharifipour, Constantino \'Alvarez Casado, Manuel Lage Ca\~nellas, Miguel Bordallo L\'opez
Abstract: Loss functions are fundamental to learning accurate 3D point cloud models, yet common choices trade geometric fidelity for computational cost. Chamfer Distance is efficient but permits many-to-one correspondences, while Earth Mover Distance better reflects one-to-one transport at high computational cost. APML approximates transport with differentiable Sinkhorn iterations and an analytically derived temperature, but its dense formulation scales quadratically in memory. We present CUDA-APML, a sparse GPU implementation that thresholds negligible assignments and runs adaptive softmax, bidirectional symmetrization, and Sinkhorn normalization directly in COO form. This yields near-linear memory scaling and preserves gradients on the stored support, while pairwise distance evaluation remains quadratic in the current implementation. On ShapeNet and MM-Fi, CUDA-APML matches dense APML within a small tolerance while reducing peak GPU memory by 99.9%. Code available at: https://github.com/Multimodal-Sensing-Lab/apml
Authors: Yanzhen Wang, Yiyang Jiang, Diana Golovanova, Kamal Das, Hyeonhu Bae, Yufei Zhao, Huu-Thong Le, Abhinava Chatterjee, Yunzhe Liu, Chao-Xing Liu, Felipe H. da Jornada, Binghai Yan, Xiao-Liang Qi
Abstract: We introduce QMBench, a comprehensive benchmark designed to evaluate the capability of large language model agents in quantum materials research. This specialized benchmark assesses the model's ability to apply condensed matter physics knowledge and computational techniques such as density functional theory to solve research problems in quantum materials science. QMBench encompasses different domains of the quantum material research, including structural properties, electronic properties, thermodynamic and other properties, symmetry principle and computational methodologies. By providing a standardized evaluation framework, QMBench aims to accelerate the development of an AI scientist capable of making creative contributions to quantum materials research. We expect QMBench to be developed and constantly improved by the research community.
Authors: Wang Bin, Ao Yang, Kedan Li, Aofan Liu, Hui Li, Guibo Luo, Weixiang Huang, Yan Zhuang
Abstract: In the domain of software security testing, Directed Grey-Box Fuzzing (DGF) has garnered widespread attention for its efficient target localization and excellent detection performance. However, existing approaches measure only the physical distance between seed execution paths and target locations, overlooking logical relationships among code segments. This omission can yield redundant or misleading guidance in complex binaries, weakening DGF's real-world effectiveness. To address this, we introduce \textbf{attention distance}, a novel metric that leverages a large language model's contextual analysis to compute attention scores between code elements and reveal their intrinsic connections. Under the same AFLGo configuration -- without altering any fuzzing components other than the distance metric -- replacing physical distances with attention distances across 38 real vulnerability reproduction experiments delivers a \textbf{3.43$\times$} average increase in testing efficiency over the traditional method. Compared to state-of-the-art directed fuzzers DAFL and WindRanger, our approach achieves \textbf{2.89$\times$} and \textbf{7.13$\times$} improvements, respectively. To further validate the generalizability of attention distance, we integrate it into DAFL and WindRanger, where it also consistently enhances their original performance. All related code and datasets are publicly available at https://github.com/TheBinKing/Attention\_Distance.git.
URLs: https://github.com/TheBinKing/Attention\_Distance.git.
Authors: Sumin Park, Noseong Park
Abstract: Finding the optimal configuration of Sparse Mixture-ofExperts (SMoE) that maximizes semantic differentiation among experts is essential for exploiting the full potential of MoE architectures. However, existing SMoE frameworks either heavily rely on hyperparameter tuning or overlook the importance of diversifying semantic roles across experts when adapting the expert pool size. We propose Mixture-of-Experts for Adaptive Semantic Specialization (MASS), a semanticaware MoE framework for adaptive expert expansion and dynamic routing. MASS introduces two key advancements: (i) a gradient-based semantic drift detector that prompts targeted expert expansion when the existing expert pool lacks capacity to capture the full semantic diversity of the data, and (ii) an integration of adaptive routing strategy that dynamically adjusts expert usage based on token-level routing confidence mass. We first demonstrate that MASS reliably converges to the point of optimal balance between cost-performance trade-off with notably improved sematic specialization in a highly controlled synthetic setup. Further empirical results on real-world datasets across language and vision domains show that MASS consistently outperforms a range of strong MoE baselines, demonstrating its domain robustness and enhanced expert specialization.
Authors: Ivan Daunis
Abstract: Building deployment-ready LLM agents requires complex orchestration of tools, data sources, and control flow logic, yet existing systems tightly couple agent logic to specific programming languages and deployment models. We present a declarative system that separates agent workflow specification from implementation, enabling the same pipeline definition to execute across multiple backend languages (Java, Python, Go) and deployment environments (cloud-native, on-premises). Our key insight is that most agent workflows consist of common patterns -- data serialization, filtering, RAG retrieval, API orchestration -- that can be expressed through a unified DSL rather than imperative code. This approach transforms agent development from application programming to configuration, where adding new tools or fine-tuning agent behaviors requires only pipeline specification changes, not code deployment. Our system natively supports A/B testing of agent strategies, allowing multiple pipeline variants to run on the same backend infrastructure with automatic metric collection and comparison. We evaluate our approach on real-world e-commerce workflows at PayPal, processing millions of daily interactions. Our results demonstrate 60% reduction in development time, and 3x improvement in deployment velocity compared to imperative implementations. The language's declarative approach enables non-engineers to modify agent behaviors safely, while maintaining sub-100ms orchestration overhead. We show that complex workflows involving product search, personalization, and cart management can be expressed in under 50 lines of DSL compared to 500+ lines of imperative code.
Authors: Anthony Bertrand (LIMOS), Engelbert Mephu Nguifo (LIMOS), Violaine Antoine (LIMOS), David Hill (LIMOS)
Abstract: Reproducibility is essential in machine learning because it ensures that a model or experiment yields the same scientific conclusion. For specific algorithms repeatability with bitwise identical results is also a key for scientific integrity because it allows debugging. We decomposed several very popular clustering algorithms: K-Means, DBSCAN and Ward into their fundamental steps, and we identify the conditions required to achieve repeatability at each stage. We use an implementation example with the Python library scikit-learn to examine the repeatable aspects of each method. Our results reveal inconsistent results with K-Means when the number of OpenMP threads exceeds two. This work aims to raise awareness of this issue among both users and developers, encouraging further investigation and potential fixes.
Authors: Antonio Tarizzo, Mohammad Kazemi, Deniz G\"und\"uz
Abstract: Federated edge learning (FEEL) enables wireless devices to collaboratively train a centralised model without sharing raw data, but repeated uplink transmission of model updates makes communication the dominant bottleneck. Over-the-air (OTA) aggregation alleviates this by exploiting the superposition property of the wireless channel, enabling simultaneous transmission and merging communication with computation. Digital OTA schemes extend this principle by incorporating the robustness of conventional digital communication, but current designs remain limited in low signal-to-noise ratio (SNR) regimes. This work proposes a learned digital OTA framework that improves recovery accuracy, convergence behaviour, and robustness to challenging SNR conditions while maintaining the same uplink overhead as state-of-the-art methods. The design integrates an unsourced random access (URA) codebook with vector quantisation and AMP-DA-Net, an unrolled approximate message passing (AMP)-style decoder trained end-to-end with the digital codebook and parameter server local training statistics. The proposed design extends OTA aggregation beyond averaging to a broad class of symmetric functions, including trimmed means and majority-based rules. Experiments on highly heterogeneous device datasets and varying numbers of active devices show that the proposed design extends reliable digital OTA operation by more than 10 dB into low SNR regimes while matching or improving performance across the full SNR range. The learned decoder remains effective under message corruption and nonlinear aggregation, highlighting the broader potential of end-to-end learned design for digital OTA communication in FEEL.
Authors: Ziming Mao, Yihan Zhang, Chihan Cui, Kaichao You, Zhongjie Chen, Zhiying Xu, Scott Shenker, Costin Raiciu, Yang Zhou, Ion Stoica
Abstract: Mixture-of-Experts (MoE) workloads rely on expert parallelism (EP) to achieve high GPU efficiency. State-of-the-art EP communication systems such as DeepEP demonstrate strong performance but exhibit poor portability across heterogeneous GPU and NIC platforms. The poor portability is rooted in architecture: GPU-initiated token-level RDMA communication requires tight vertical integration between GPUs and NICs, e.g., GPU writes to NIC driver/MMIO interfaces. We present UCCL-EP, a portable EP communication system that delivers DeepEP-level performance across heterogeneous GPU and NIC hardware. UCCL-EP replaces GPU-initiated RDMA with a high-throughput GPU-CPU control channel: compact token-routing commands are transferred to multithreaded CPU proxies, which then issue GPUDirect RDMA operations on behalf of GPUs. UCCL-EP further emulates various ordering semantics required by specialized EP communication modes using RDMA immediate data, enabling correctness on NICs that lack such ordering, e.g., AWS EFA. We implement UCCL-EP on NVIDIA and AMD GPUs with EFA and Broadcom NICs. On EFA, it outperforms the best existing EP solution by up to $2.1\times$ for dispatch and combine throughput. On NVIDIA-only platform, UCCL-EP achieves comparable performance to the original DeepEP. UCCL-EP also improves token throughput on SGLang by up to 40% on the NVIDIA+EFA platform, and improves DeepSeek-V3 training throughput over the AMD Primus/Megatron-LM framework by up to 45% on a 16-node AMD+Broadcom platform.
Authors: Shashi Kant Gupta, Arijeet Pramanik, Jerrin John Thomas, Regina Schwind, Lauren Wiener, Avi Raju, Jeremy Kornbluth, Yanshan Wang, Zhaohui Su, Hrituraj Singh
Abstract: Unstructured notes within the electronic health record (EHR) contain rich clinical information vital for cancer treatment decision making and research, yet reliably extracting structured oncology data remains challenging due to extensive variability, specialized terminology, and inconsistent document formats. Manual abstraction, although accurate, is prohibitively costly and unscalable. Existing automated approaches typically address narrow scenarios - either using synthetic datasets, restricting focus to document-level extraction, or isolating specific clinical variables (e.g., staging, biomarkers, histology) - and do not adequately handle patient-level synthesis across the large number of clinical documents containing contradictory information. In this study, we propose an agentic framework that systematically decomposes complex oncology data extraction into modular, adaptive tasks. Specifically, we use large language models (LLMs) as reasoning agents, equipped with context-sensitive retrieval and iterative synthesis capabilities, to exhaustively and comprehensively extract structured clinical variables from real-world oncology notes. Evaluated on a large-scale dataset of over 400,000 unstructured clinical notes and scanned PDF reports spanning 2,250 cancer patients, our method achieves an average F1-score of 0.93, with 100 out of 103 oncology-specific clinical variables exceeding 0.85, and critical variables (e.g., biomarkers and medications) surpassing 0.95. Moreover, integration of the agentic system into a data curation workflow resulted in 0.94 direct manual approval rate, significantly reducing annotation costs. To our knowledge, this constitutes the first exhaustive, end-to-end application of LLM-based agents for structured oncology data extraction at scale
Authors: Jorg Bornschein, Clare Lyle, Yazhe Li, Amal Rannen-Triki, Xu Owen He, Razvan Pascanu
Abstract: When adapting large language models (LLMs) to a specific downstream task, two primary approaches are commonly employed: (1) prompt engineering, often with in-context few-shot learning, leveraging the model's inherent generalization abilities, and (2) fine-tuning on task-specific data, directly optimizing the model's parameters. While prompt-based methods excel in few-shot scenarios, their effectiveness often plateaus as more data becomes available. Conversely, fine-tuning scales well with data but may underperform when training examples are scarce. We investigate a unified approach that bridges these two paradigms by incorporating in-context learning directly into the fine-tuning process. Specifically, we fine-tune the model on task-specific data augmented with in-context examples, mimicking the structure of k-shot prompts. This approach, while requiring per-task fine-tuning, combines the sample efficiency of in-context learning with the performance gains of fine-tuning, leading to a method that consistently matches and often significantly exceeds both these baselines. To perform hyperparameter selection in the low-data regime, we propose to use prequential evaluation, which eliminates the need for expensive cross-validation and leverages all available data for training while simultaneously providing a robust validation signal. We conduct an extensive empirical study to determine which adaptation paradigm - fine-tuning, in-context learning, or our proposed unified approach offers the best predictive performance on a concrete data downstream-tasks.
Authors: Indranil Halder, Cengiz Pehlevan
Abstract: Recent developments in large language models have shown advantages in reallocating a notable share of computational resource from training time to inference time. However, the principles behind inference time scaling are not well understood. In this paper, we introduce an analytically tractable model of inference-time scaling: Bayesian linear regression with a reward-weighted sampler, where the reward is determined from a linear model, modeling LLM-as-a-judge scenario. We study this problem in the high-dimensional regime, where the deterministic equivalents dictate a closed-form expression for the posterior predictive mean and variance. We analyze the generalization error when training data are sampled from a teacher model. We draw $k$ inference-time samples and select via softmax at a temperature applied to a quadratic reward. When the reward is not too different from the teacher, the generalization error decreases monotonically with increasing inference time samples $k$. However, the specific reward that optimizes inference-time selection generally differs from the teacher. In contrast, substantial reward misspecification induces a finite optimal $k$ beyond which more sampling can increase the generalization error. For fixed $k$, there exists an optimal sampling temperature. We experimentally verify these facts in large language model inference with an additional large language model as a judge. In the "best-of-$k$" limit with the teacher as reward, we theoretically show that the generalization error decays as $\Theta(1/k^2)$ and determine the leading coefficient via extreme value theory. These formulas delineate domains where scaling inference-time computation is provably preferable to collecting more data. Finally, we demonstrate that when task difficulty increases, the previously mentioned advantage of inference-time compute degrades.
Authors: Maxime Lacour, Pu Ren, Rie Nakata, Nori Nakata, Michael Mahoney
Abstract: Recent developments in non-ergodic ground-motion models (GMMs) explicitly model systematic spatial variations in source, site, and path effects, reducing standard deviation to 30-40% of ergodic models and enabling more accurate site-specific seismic hazard analysis. Current non-ergodic GMMs rely on Gaussian Process (GP) methods with prescribed correlation functions and thus have computational limitations for large-scale predictions. This study proposes a deep-learning approach called Conditional Generative Modeling for Fourier Amplitude Spectra (CGM-FAS) as an alternative to GP-based methods for modeling non-ergodic path effects in Fourier Amplitude Spectra (FAS). CGM-FAS uses a Conditional Variational Autoencoder architecture to learn spatial patterns and interfrequency correlation directly from data by using geographical coordinates of earthquakes and stations as conditional variables. Using San Francisco Bay Area earthquake data, we compare CGM-FAS against a recent GP-based GMM for the region and demonstrate consistent predictions of non-ergodic path effects. Additionally, CGM-FAS offers advantages compared to GP-based approaches in learning spatial patterns without prescribed correlation functions, capturing interfrequency correlations, and enabling rapid predictions, generating maps for 10,000 sites across 1,000 frequencies within 10 seconds using a few GB of memory. CGM-FAS hyperparameters can be tuned to ensure generated path effects exhibit variability consistent with the GP-based empirical GMM. This work demonstrates a promising direction for efficient non-ergodic ground-motion prediction across multiple frequencies and large spatial domains.
Authors: Sujan Warnakulasooriya, Andreas Willig, Xiaobing Wu
Abstract: Drone applications continue to expand across various domains, with flocking offering enhanced cooperative capabilities but introducing significant challenges during initial formation. Existing flocking algorithms often struggle with efficiency and scalability, particularly when potential collisions force drones into suboptimal trajectories. This paper presents a time-efficient prioritised scheduling algorithm that improves the initial formation process of drone flocks. The method assigns each drone a priority based on its number of potential collisions and its likelihood of reaching its target position without permanently obstructing other drones. Using this hierarchy, each drone computes an appropriate delay to ensure a collision-free path. Simulation results show that the proposed algorithm successfully generates collision-free trajectories for flocks of up to 5000 drones and outperforms the coupling-degree-based heuristic prioritised planning method (CDH-PP) in both performance and computational efficiency.
Authors: Jiayun Wu, Jiashuo Liu, Zhiyuan Zeng, Tianyang Zhan, Wenhao Huang
Abstract: LLM deployment in critical domains is currently impeded by persistent hallucinations--generating plausible but factually incorrect assertions. While scaling laws drove significant improvements in general capabilities, theoretical frameworks suggest hallucination is not merely stochastic error but a predictable statistical consequence of training objectives prioritizing mimicking data distribution over epistemic honesty. Standard RLVR paradigms, utilizing binary reward signals, inadvertently incentivize models as good test-takers rather than honest communicators, encouraging guessing whenever correctness probability exceeds zero. This paper presents an exhaustive investigation into behavioral calibration, which incentivizes models to stochastically admit uncertainty by abstaining when not confident, aligning model behavior with accuracy. Synthesizing recent advances, we propose and evaluate training interventions optimizing strictly proper scoring rules for models to output a calibrated probability of correctness. Our methods enable models to either abstain from producing a complete response or flag individual claims where uncertainty remains. Utilizing Qwen3-4B-Instruct, empirical analysis reveals behavior-calibrated reinforcement learning allows smaller models to surpass frontier models in uncertainty quantification--a transferable meta-skill decouplable from raw predictive accuracy. Trained on math reasoning tasks, our model's log-scale Accuracy-to-Hallucination Ratio gain (0.806) exceeds GPT-5's (0.207) in a challenging in-domain evaluation (BeyondAIME). Moreover, in cross-domain factual QA (SimpleQA), our 4B LLM achieves zero-shot calibration error on par with frontier models including Grok-4 and Gemini-2.5-Pro, even though its factual accuracy is much lower.
Authors: S. Mazdak Abulnaga, Andrew Hoopes, Malte Hoffmann, Robin Magnet, Maks Ovsjanikov, Lilla Z\"ollei, John Guttag, Bruce Fischl, Adrian Dalca
Abstract: Accurate registration of brain MRI scans is fundamental for cross-subject analysis in neuroscientific studies. This involves aligning both the cortical surface of the brain and the interior volume. Traditional methods treat volumetric and surface-based registration separately, which often leads to inconsistencies that limit downstream analyses. We propose a deep learning framework, NeurAlign, that registers $3$D brain MRI images by jointly aligning both cortical and subcortical regions through a unified volume-and-surface-based representation. Our approach leverages an intermediate spherical coordinate space to bridge anatomical surface topology with volumetric anatomy, enabling consistent and anatomically accurate alignment. By integrating spherical registration into the learning, our method ensures geometric coherence between volume and surface domains. In a series of experiments on both in-domain and out-of-domain datasets, our method consistently outperforms both classical and machine learning-based registration methods -- improving the Dice score by up to 7 points while maintaining regular deformation fields. Additionally, it is orders of magnitude faster than the standard method for this task, and is simpler to use because it requires no additional inputs beyond an MRI scan. With its superior accuracy, fast inference, and ease of use, NeurAlign sets a new standard for joint cortical and subcortical registration.
Authors: Wentao Wu, Xiao Wang, Chenglong Li, Jin Tang, Bin Luo
Abstract: Vehicle-centric perception plays a crucial role in many intelligent systems, including large-scale surveillance systems, intelligent transportation, and autonomous driving. Existing approaches lack effective learning of vehicle-related knowledge during pre-training, resulting in poor capability for modeling general vehicle perception representations. To handle this problem, we propose VehicleMAE-V2, a novel vehicle-centric pre-trained large model. By exploring and exploiting vehicle-related multimodal structured priors to guide the masked token reconstruction process, our approach can significantly enhance the model's capability to learn generalizable representations for vehicle-centric perception. Specifically, we design the Symmetry-guided Mask Module (SMM), Contour-guided Representation Module (CRM) and Semantics-guided Representation Module (SRM) to incorporate three kinds of structured priors into token reconstruction including symmetry, contour and semantics of vehicles respectively. SMM utilizes the vehicle symmetry constraints to avoid retaining symmetric patches and can thus select high-quality masked image patches and reduce information redundancy. CRM minimizes the probability distribution divergence between contour features and reconstructed features and can thus preserve holistic vehicle structure information during pixel-level reconstruction. SRM aligns image-text features through contrastive learning and cross-modal distillation to address the feature confusion caused by insufficient semantic understanding during masked reconstruction. To support the pre-training of VehicleMAE-V2, we construct Autobot4M, a large-scale dataset comprising approximately 4 million vehicle images and 12,693 text descriptions. Extensive experiments on five downstream tasks demonstrate the superior performance of VehicleMAE-V2.
Authors: Samruddhi Baviskar
Abstract: Machine learning models used in financial decision systems operate in nonstationary economic environments, yet adversarial robustness is typically evaluated under static assumptions. This work introduces Conditional Adversarial Fragility, a regime dependent phenomenon in which adversarial vulnerability is systematically amplified during periods of macroeconomic stress. We propose a regime aware evaluation framework for time indexed tabular financial classification tasks that conditions robustness assessment on external indicators of economic stress. Using volatility based regime segmentation as a proxy for macroeconomic conditions, we evaluate model behavior across calm and stress periods while holding model architecture, attack methodology, and evaluation protocols constant. Baseline predictive performance remains comparable across regimes, indicating that economic stress alone does not induce inherent performance degradation. Under adversarial perturbations, however, models operating during stress regimes exhibit substantially greater degradation across predictive accuracy, operational decision thresholds, and risk sensitive outcomes. We further demonstrate that this amplification propagates to increased false negative rates, elevating the risk of missed high risk cases during adverse conditions. To complement numerical robustness metrics, we introduce an interpretive governance layer based on semantic auditing of model explanations using large language models. Together, these results demonstrate that adversarial robustness in financial machine learning is a regime dependent property and motivate stress aware approaches to model risk assessment in high stakes financial deployments.
Authors: Mozes Jacobs, Thomas Fel, Richard Hakim, Alessandra Brondetta, Demba Ba, T. Andy Keller
Abstract: As Vision Transformers (ViTs) become standard vision backbones, a mechanistic account of their computational phenomenology is essential. Despite architectural cues that hint at dynamical structure, there is no settled framework that interprets Transformer depth as a well-characterized flow. In this work, we introduce the Block-Recurrent Hypothesis (BRH), arguing that trained ViTs admit a block-recurrent depth structure such that the computation of the original $L$ blocks can be accurately rewritten using only $k \ll L$ distinct blocks applied recurrently. Across diverse ViTs, between-layer representational similarity matrices suggest few contiguous phases. To determine whether these phases reflect genuinely reusable computation, we train block-recurrent surrogates of pretrained ViTs: Recurrent Approximations to Phase-structured TransfORmers (Raptor). In small-scale, we demonstrate that stochastic depth and training promote recurrent structure and subsequently correlate with our ability to accurately fit Raptor. We then provide an empirical existence proof for BRH by training a Raptor model to recover $96\%$ of DINOv2 ImageNet-1k linear probe accuracy in only 2 blocks at equivalent computational cost. Finally, we leverage our hypothesis to develop a program of Dynamical Interpretability. We find i) directional convergence into class-dependent angular basins with self-correcting trajectories under small perturbations, ii) token-specific dynamics, where cls executes sharp late reorientations while patch tokens exhibit strong late-stage coherence toward their mean direction, and iii) a collapse to low rank updates in late depth, consistent with convergence to low-dimensional attractors. Altogether, we find a compact recurrent program emerges along ViT depth, pointing to a low-complexity normative solution that enables these models to be studied through principled dynamical systems analysis.
Authors: Zixuan Huang, Xiang Li, Zhaoyang Lv, James M. Rehg
Abstract: Videos are continuous 2D projections of 3D worlds. After training on large video data, will global 3D understanding naturally emerge? We study this by quantifying the 3D understanding of existing Video Foundation Models (VidFMs) pretrained on vast video data. We propose the first model-agnostic framework that measures the 3D awareness of various VidFMs by estimating multiple 3D properties from their features via shallow read-outs. Our study presents meaningful findings regarding the 3D awareness of VidFMs on multiple axes. In particular, we show that state-of-the-art video generation models exhibit a strong understanding of 3D objects and scenes, despite not being trained on any 3D data. Such understanding can even surpass that of large expert models specifically trained for 3D tasks. Our findings, together with the 3D benchmarking of major VidFMs, provide valuable observations for building scalable 3D models.
Authors: Fernando M. de Paula Neto, Lucas dos Reis Silva, Paulo S. G. de Mattos Neto, Felipe F. Fanchini
Abstract: The performance of quantum neural network models depends strongly on architectural decisions, including circuit depth, placement of parametrized operations, and data-encoding strategies. Selecting an effective architecture is challenging and closely related to the classical difficulty of choosing suitable neural-network topologies, which is computationally hard. This work investigates automated quantum-circuit construction for regression tasks and introduces a genetic-algorithm framework that discovers Reduced Regressor QNN architectures. The approach explores depth, parametrized gate configurations, and flexible data re-uploading patterns, formulating the construction of quantum regressors as an optimization process. The discovered circuits are evaluated against seventeen classical regression models on twenty-two nonlinear benchmark functions and four analytical functions. Although classical methods often achieve comparable results, they typically require far more parameters, whereas the evolved quantum models remain compact while providing competitive performance. We further analyze dataset complexity using twelve structural descriptors and show, across five increasingly challenging meta-learning scenarios, that these measures can reliably predict which quantum architecture will perform best. The results demonstrate perfect or near-perfect predictive accuracy in several scenarios, indicating that complexity metrics offer powerful and compact representations of dataset structure and can effectively guide automated model selection. Overall, this study provides a principled basis for meta-learning-driven quantum architecture design and advances the understanding of how quantum models behave in regression settings--a topic that has received limited exploration in prior work. These findings pave the way for more systematic and theoretically grounded approaches to quantum regression.
Authors: Zhe Yin, Xiaodong Gu, Beijun Shen
Abstract: Code language models excel on code intelligence tasks, yet their internal interpretability is underexplored. Existing neuron interpretability techniques from NLP are suboptimal for source code due to programming languages formal, hierarchical, and executable nature. We empirically investigate code LLMs at the neuron level, localizing language-specific neurons (selectively responsive to one language) and concept layers (feed-forward layers encoding language-agnostic code representations). We analyze Llama-3.1-8B and Qwen2.5-Coder-32B on multilingual inputs in C++, Java, Python, Go, and JavaScript, measuring neuron selectivity and layerwise contributions during generation. We find (1) neurons specialized for individual languages alongside a universal subset supporting general-purpose generation; and (2) lower layers mainly encode language-specific syntax, while middle layers capture semantic abstractions shared across languages, emerging as concept layers. We demonstrate utility on three tasks: neuron-guided fine-tuning for code generation, clone detection via concept-layer embeddings, and concept-layer-guided transfer for code summarization, each yielding consistent gains in multilingual settings.
Authors: Ming Li, Chenrui Fan, Yize Cheng, Soheil Feizi, Tianyi Zhou
Abstract: Large language models increasingly expose reasoning traces, yet their underlying cognitive structure and steps remain difficult to identify and analyze beyond surface-level statistics. We adopt Schoenfeld's Episode Theory as an inductive, intermediate-scale lens and introduce ThinkARM (Anatomy of Reasoning in Models), a scalable framework that explicitly abstracts reasoning traces into functional reasoning steps such as Analysis, Explore, Implement, Verify, etc. When applied to mathematical problem solving by diverse models, this abstraction reveals reproducible thinking dynamics and structural differences between reasoning and non-reasoning models, which are not apparent from token-level views. We further present two diagnostic case studies showing that exploration functions as a critical branching step associated with correctness, and that efficiency-oriented methods selectively suppress evaluative feedback steps rather than uniformly shortening responses. Together, our results demonstrate that episode-level representations make reasoning steps explicit, enabling systematic analysis of how reasoning is structured, stabilized, and altered in modern language models.
Authors: Rahul Yumlembam, Biju Issac, Seibu Mary Jacob, Longzhi Yang
Abstract: Since the Internet of Things (IoT) is widely adopted using Android applications, detecting malicious Android apps is essential. In recent years, Android graph-based deep learning research has proposed many approaches to extract relationships from applications as graphs to generate graph embeddings. First, we demonstrate the effectiveness of graph-based classification using a Graph Neural Network (GNN)-based classifier to generate API graph embeddings. The graph embeddings are combined with Permission and Intent features to train multiple machine learning and deep learning models for Android malware detection. The proposed classification approach achieves an accuracy of 98.33 percent on the CICMaldroid dataset and 98.68 percent on the Drebin dataset. However, graph-based deep learning models are vulnerable, as attackers can add fake relationships to evade detection by the classifier. Second, we propose a Generative Adversarial Network (GAN)-based attack algorithm named VGAE-MalGAN targeting graph-based GNN Android malware classifiers. The VGAE-MalGAN generator produces adversarial malware API graphs, while the VGAE-MalGAN substitute detector attempts to mimic the target detector. Experimental results show that VGAE-MalGAN can significantly reduce the detection rate of GNN-based malware classifiers. Although the model initially fails to detect adversarial malware, retraining with generated adversarial samples improves robustness and helps mitigate adversarial attacks.
Authors: Sangoh Lee, Sangwoo Mo, Wook-Shin Han
Abstract: While Vision-Language-Action (VLA) models generalize well to generic instructions, they struggle with personalized commands such as "bring my cup", where the robot must act on one specific instance among visually similar objects. We study this setting of manipulating personal objects, in which a VLA must identify and control a user-specific object unseen during training using only a few reference images. To address this challenge, we propose Visual Attentive Prompting (VAP), a simple-yet-effective training-free perceptual adapter that equips frozen VLAs with top-down selective attention. VAP treats the reference images as a non-parametric visual memory, grounds the personal object in the scene through open-vocabulary detection and embedding-based matching, and then injects this grounding as a visual prompt by highlighting the object and rewriting the instruction. We construct two simulation benchmarks, Personalized-SIMPLER and Personalized-VLABench, and a real-world tabletop benchmark to evaluate personalized manipulation across multiple robots and tasks. Experiments show that VAP consistently outperforms generic policies and token-learning baselines in both success rate and correct-object manipulation, helping to bridge the gap between semantic understanding and instance-level control.
Authors: Yuan Gao, Zhenguo Dong, Xuelong Wang, Zhiqiang Wang, Yong Zhang, Shaofan Wang
Abstract: Accurate and interpretable forecasting of multivariate time series is crucial for understanding the complex dynamics of cryptocurrency markets in digital asset systems. Advanced deep learning methodologies, particularly Transformer-based and MLP-based architectures, have achieved competitive predictive performance in cryptocurrency forecasting tasks. However, cryptocurrency data is inherently composed of long-term socio-economic trends and local high-frequency speculative oscillations. Existing deep learning-based 'black-box' models fail to effectively decouple these composite dynamics or provide the interpretability needed for trustworthy financial decision-making. To overcome these limitations, we propose DecoKAN, an interpretable forecasting framework that integrates multi-level Discrete Wavelet Transform (DWT) for decoupling and hierarchical signal decomposition with Kolmogorov-Arnold Network (KAN) mixers for transparent and interpretable nonlinear modeling. The DWT component decomposes complex cryptocurrency time series into distinct frequency components, enabling frequency-specific analysis, while KAN mixers provide intrinsically interpretable spline-based mappings within each decomposed subseries. Furthermore, interpretability is enhanced through a symbolic analysis pipeline involving sparsification, pruning, and symbolization, which produces concise analytical expressions offering symbolic representations of the learned patterns. Extensive experiments demonstrate that DecoKAN achieves the lowest average Mean Squared Error on all tested real-world cryptocurrency datasets (BTC, ETH, XMR), consistently outperforming a comprehensive suite of competitive state-of-the-art baselines. These results validate DecoKAN's potential to bridge the gap between predictive accuracy and model transparency, advancing trustworthy decision support within complex cryptocurrency markets.
Authors: Nguyen Lam Phu Quy, Pham Phu Hoa, Tran Chi Nguyen, Dao Sy Duy Minh, Nguyen Hoang Minh Ngoc, Huynh Trung Kiet
Abstract: Real-world image captions often lack contextual depth, omitting crucial details such as event background, temporal cues, outcomes, and named entities that are not visually discernible. This gap limits the effectiveness of image understanding in domains like journalism, education, and digital archives, where richer, more informative descriptions are essential. To address this, we propose a multimodal pipeline that augments visual input with external textual knowledge. Our system retrieves semantically similar images using BEIT-3 (Flickr30k-384 and COCO-384) and SigLIP So-384, reranks them using ORB and SIFT for geometric alignment, and extracts contextual information from related articles via semantic search. A fine-tuned Qwen3 model with QLoRA then integrates this context with base captions generated by Instruct BLIP (Vicuna-7B) to produce event-enriched, context-aware descriptions. Evaluated on the OpenEvents v1 dataset, our approach generates significantly more informative captions compared to traditional methods, showing strong potential for real-world applications requiring deeper visual-textual understanding
Authors: Peter N. Loxley
Abstract: Controllable Markov chains describe the dynamics of sequential decision making tasks and are the central component in optimal control and reinforcement learning. In this work, we give the general form of an optimal policy for learning controllable dynamics in an unknown environment by exploring over a limited time horizon. This policy is simple to implement and efficient to compute, and allows an agent to ``learn by exploring" as it maximizes its information gain in a greedy fashion by selecting controls from a constraint set that changes over time during exploration. We give a simple parameterization for the set of controls, and present an algorithm for finding an optimal policy. The reason for this policy is due to the existence of certain types of states that restrict control of the dynamics; such as transient states, absorbing states, and non-backtracking states. We show why the occurrence of these states makes a non-stationary policy essential for achieving optimal exploration. Six interesting examples of controllable dynamics are treated in detail. Policy optimality is demonstrated using counting arguments, comparing with suboptimal policies, and by making use of a sequential improvement property from dynamic programming.
Authors: Sangryu Park, Gihyuk Ko, Homook Cho
Abstract: Large Language Models (LLMs) show significant promise in automating software vulnerability analysis, a critical task given the impact of security failure of modern software systems. However, current approaches in using LLMs to automate vulnerability analysis mostly rely on using online API-based LLM services, requiring the user to disclose the source code in development. Moreover, they predominantly frame the task as a binary classification(vulnerable or not vulnerable), limiting potential practical utility. This paper addresses these limitations by reformulating the problem as Software Vulnerability Identification (SVI), where LLMs are asked to output the type of weakness in Common Weakness Enumeration (CWE) IDs rather than simply indicating the presence or absence of a vulnerability. We also tackle the reliance on large, API-based LLMs by demonstrating that instruction-tuning smaller, locally deployable LLMs can achieve superior identification performance. In our analysis, instruct-tuning a local LLM showed better overall performance and cost trade-off than online API-based LLMs. Our findings indicate that instruct-tuned local models represent a more effective, secure, and practical approach for leveraging LLMs in real-world vulnerability management workflows.
Authors: Dianxuan Fu, Xiaomin Liu, Yihao Zhang, Shikui Shen, Weisheng Hu, Qunbi Zhuge
Abstract: We propose a communication-bound-aware cross-domain resource assignment framework for pipeline-parallel distributed training over multi-datacenter optical networks, which lowers iteration time by 31.25% and reduces 13.20% blocking requests compared to baselines.
Authors: Yanjie Li, Jian Xu, Xueqing Chen, Lina Yu, Shiming Xiang, Weijun Li, Cheng-lin Liu
Abstract: Adsorption energy is a key descriptor of catalytic reactivity. It is fundamentally defined as the difference between the relaxed total energy of the adsorbate-surface system and that of an appropriate reference state; therefore, the accuracy of relaxed-energy prediction directly determines the reliability of machine-learning-driven catalyst screening. E(3)-equivariant graph neural networks (GNNs) can natively operate on three-dimensional atomic coordinates under periodic boundary conditions and have demonstrated strong performance on such tasks. In contrast, language-model-based approaches, while enabling human-readable textual descriptions and reducing reliance on explicit graph -- thereby broadening applicability -- remain insufficient in both adsorption-configuration energy prediction accuracy and in distinguishing ``the same system with different configurations,'' even with graph-assisted pretraining in the style of GAP-CATBERTa. To this end, we propose QE-Catalytic, a multimodal framework that deeply couples a large language model (\textbf{Q}wen) with an E(3)-equivariant graph Transformer (\textbf{E}quiformer-V2), enabling unified support for adsorption-configuration property prediction and inverse design on complex catalytic surfaces. During prediction, QE-Catalytic jointly leverages three-dimensional structures and structured configuration text, and injects ``3D geometric information'' into the language channel via graph-text alignment, allowing it to function as a high-performance text-based predictor when precise coordinates are unavailable, while also autoregressively generating CIF files for target-energy-driven structure design and information completion. On OC20, QE-Catalytic reduces the MAE of relaxed adsorption energy from 0.713~eV to 0.486~eV, and consistently outperforms baseline models such as CatBERTa and GAP-CATBERTa across multiple evaluation protocols.
Authors: Jeehong Kim, Youngseok Hwang, Minchan Kim, Sungho Bae, Hyunwoo Park
Abstract: Spatio-temporal graph neural networks (ST-GNNs) have achieved notable success in structured domains such as road traffic and public transportation, where spatial entities can be naturally represented as fixed nodes. In contrast, many real-world systems including maritime traffic lack such fixed anchors, making the construction of spatio-temporal graphs a fundamental challenge. Anomaly detection in these non-grid environments is particularly difficult due to the absence of canonical reference points, the sparsity and irregularity of trajectories, and the fact that anomalies may manifest at multiple granularities. In this work, we introduce a novel benchmark dataset for anomaly detection in the maritime domain, extending the Open Maritime Traffic Analysis Dataset (OMTAD) into a benchmark tailored for graph-based anomaly detection. Our dataset enables systematic evaluation across three different granularities: node-level, edge-level, and graph-level anomalies. We plan to employ two specialized LLM-based agents: \emph{Trajectory Synthesizer} and \emph{Anomaly Injector} to construct richer interaction contexts and generate semantically meaningful anomalies. We expect this benchmark to promote reproducibility and to foster methodological advances in anomaly detection for non-grid spatio-temporal systems.
Authors: Jinyoung Choi, Youngchae Kwon, Injung Kim
Abstract: Fashion style classification is a challenging task because of the large visual variation within the same style and the existence of visually similar styles. Styles are expressed not only by the global appearance, but also by the attributes of individual items and their combinations. In this study, we propose an item region-based fashion style classification network (IRSN) to effectively classify fashion styles by analyzing item-specific features and their combinations in addition to global features. IRSN extracts features of each item region using item region pooling (IRP), analyzes them separately, and combines them using gated feature fusion (GFF). In addition, we improve the feature extractor by applying a dual-backbone architecture that combines a domain-specific feature extractor and a general feature extractor pre-trained with a large-scale image-text dataset. In experiments, applying IRSN to six widely-used backbones, including EfficientNet, ConvNeXt, and Swin Transformer, improved style classification accuracy by an average of 6.9% and a maximum of 14.5% on the FashionStyle14 dataset and by an average of 7.6% and a maximum of 15.1% on the ShowniqV3 dataset. Visualization analysis also supports that the IRSN models are better than the baseline models at capturing differences between similar style classes.
Authors: Aly Lidayan, Jakob Bjorner, Satvik Golechha, Kartik Goyal, Alane Suhr
Abstract: As the length of sequential decision-making tasks increases, it becomes computationally impractical to keep full interaction histories in context. We introduce a general framework for LLM agents to maintain concise contexts through multi-step interaction: Acting through Belief Bottlenecks Expressed in Language (ABBEL), and methods to further improve ABBEL agents with RL post-training. ABBEL replaces long multi-step interaction history by a belief state, i.e., a natural language summary of what has been discovered about task-relevant unknowns. Under ABBEL, at each step the agent first updates a prior belief with the most recent observation from the environment to form a posterior belief, then uses only the posterior to select an action. We systematically evaluate frontier models under ABBEL across six diverse multi-step environments, finding that ABBEL supports generating interpretable beliefs while maintaining near-constant memory use over interaction steps. However, bottleneck approaches are generally prone to error propagation, which we observe causing inferior performance when compared to the full context setting due to errors in belief updating. Therefore, we train LLMs to generate and act on beliefs within the ABBEL framework via reinforcement learning (RL). We experiment with belief grading, to reward higher quality beliefs, as well as belief length penalties to reward more compressed beliefs. Our experiments demonstrate the ability of RL to improve ABBEL's performance beyond the full context setting, while using less memory than contemporaneous approaches.
Authors: Xian-Rong Zhang, Yue-Jiao Gong, Wei-Neng Chen, Jun Zhang
Abstract: Evolutionary Neural Architecture Search (ENAS) has gained attention for automatically designing neural network architectures. Recent studies use a neural predictor to guide the process, but the high computational costs of gathering training data -- since each label requires fully training an architecture -- make achieving a high-precision predictor with { limited compute budget (i.e., a capped number of fully trained architecture-label pairs)} crucial for ENAS success. This paper introduces ENAS with Dual Contrastive Learning (DCL-ENAS), a novel method that employs two stages of contrastive learning to train the neural predictor. In the first stage, contrastive self-supervised learning is used to learn meaningful representations from neural architectures without requiring labels. In the second stage, fine-tuning with contrastive learning is performed to accurately predict the relative performance of different architectures rather than their absolute performance, which is sufficient to guide the evolutionary search. Across NASBench-101 and NASBench-201, DCL-ENAS achieves the highest validation accuracy, surpassing the strongest published baselines by 0.05\% (ImageNet16-120) to 0.39\% (NASBench-101). On a real-world ECG arrhythmia classification task, DCL-ENAS improves performance by approximately 2.5 percentage points over a manually designed, non-NAS model obtained via random search, while requiring only 7.7 GPU-days.
Authors: Hyeongcheol Park, Jiyoung Seo, Jaewon Mun, Hogun Park, Wonmin Byeon, Sung June Kim, Hyeonsoo Im, JeungSub Lee, Sangpil Kim
Abstract: Retrieval-Augmented Generation (RAG) has recently been extended to multimodal settings, connecting multimodal large language models (MLLMs) with vast corpora of external knowledge such as multimodal knowledge graphs (MMKGs). Despite their recent success, multimodal RAG in the audio-visual domain remains challenging due to 1) limited modality coverage and multi-hop connectivity of existing MMKGs, and 2) retrieval based solely on similarity in a shared multimodal embedding space, which fails to filter out off-topic or redundant knowledge. To address these limitations, we propose M$^3$KG-RAG, a Multi-hop Multimodal Knowledge Graph-enhanced RAG that retrieves query-aligned audio-visual knowledge from MMKGs, improving reasoning depth and answer faithfulness in MLLMs. Specifically, we devise a lightweight multi-agent pipeline to construct multi-hop MMKG (M$^3$KG), which contains context-enriched triplets of multimodal entities, enabling modality-wise retrieval based on input queries. Furthermore, we introduce GRASP (Grounded Retrieval And Selective Pruning), which ensures precise entity grounding to the query, evaluates answer-supporting relevance, and prunes redundant context to retain only knowledge essential for response generation. Extensive experiments across diverse multimodal benchmarks demonstrate that M$^3$KG-RAG significantly enhances MLLMs' multimodal reasoning and grounding over existing approaches.
Authors: Xiang Chen, Yixin Ou, Quan Feng, Lei Li, Piji Li, Haibo Ye, Sheng-Jun Huang, Shuofei Qiao, Shumin Deng, Huajun Chen, Ningyu Zhang
Abstract: The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce improved few-shot performance. However, prompt learning approaches for PFMs still follow a parametric learning paradigm. As such, the stability of generalization in memorization and rote learning can be compromised. More specifically, conventional prompt learning might face difficulties in fully utilizing atypical instances and avoiding overfitting to shallow patterns with limited data during the process of fully-supervised training. To overcome these constraints, we present our approach, named RetroPrompt, which aims to achieve a balance between memorization and generalization by decoupling knowledge from mere memorization. Unlike traditional prompting methods, RetroPrompt leverages a publicly accessible knowledge base generated from the training data and incorporates a retrieval mechanism throughout the input, training, and inference stages. This enables the model to actively retrieve relevant contextual information from the corpus, thereby enhancing the available cues. We conduct comprehensive experiments on a variety of datasets across natural language processing and computer vision tasks to demonstrate the superior performance of our proposed approach, RetroPrompt, in both zero-shot and few-shot scenarios. Through detailed analysis of memorization patterns, we observe that RetroPrompt effectively reduces the reliance on rote memorization, leading to enhanced generalization.
Authors: Qian Chen, Luyao Cheng, Chong Deng, Xiangang Li, Jiaqing Liu, Chao-Hong Tan, Wen Wang, Junhao Xu, Jieping Ye, Qinglin Zhang, Qiquan Zhang, Jingren Zhou
Abstract: Recent advancements in joint speech-text models show great potential for seamless voice interactions. However, existing models face critical challenges: temporal resolution mismatch between speech tokens (25Hz) and text tokens (~3Hz) dilutes semantic information, incurs high computational costs, and causes catastrophic forgetting of text LLM knowledge. We introduce Fun-Audio-Chat, a Large Audio Language Model addressing these limitations via two innovations from our previous work DrVoice. First, Dual-Resolution Speech Representations (DRSR): the Shared LLM processes audio at efficient 5Hz (via token grouping), while the Speech Refined Head generates high-quality tokens at 25Hz, balancing efficiency (~50% GPU reduction) and quality. Second, Core-Cocktail Training, a two-stage fine-tuning with intermediate merging that mitigates catastrophic forgetting. We then apply Multi-Task DPO Training to enhance robustness, audio understanding, instruction-following and voice empathy. This multi-stage post-training enables Fun-Audio-Chat to retain text LLM knowledge while gaining powerful audio understanding, reasoning, and generation. Unlike recent LALMs requiring large-scale audio-text pre-training, Fun-Audio-Chat leverages pre-trained models and extensive post-training. Fun-Audio-Chat 8B and MoE 30B-A3B achieve competitive performance on Speech-to-Text and Speech-to-Speech tasks, ranking top among similar-scale models on Spoken QA benchmarks. They also achieve competitive to superior performance on Audio Understanding, Speech Function Calling, Instruction-Following and Voice Empathy. We develop Fun-Audio-Chat-Duplex, a full-duplex variant with strong performance on Spoken QA and full-duplex interactions. We open-source Fun-Audio-Chat-8B with training and inference code, and provide an interactive demo.
Authors: Ruiqi Wang, Xinchen Wang, Cuiyun Gao, Chun Yong Chong, Xin Xia, Qing Liao
Abstract: Large language models (LLMs) have been increasingly deployed in real-world software engineering, fostering the development of code evaluation metrics to study the quality of LLM-generated code. Conventional rule-based metrics merely score programs based on their surface-level similarities with reference programs instead of analyzing functionality and code quality in depth. To address this limitation, researchers have developed LLM-as-a-judge metrics, prompting LLMs to evaluate and score code, and curated various code evaluation benchmarks to validate their effectiveness. However, these benchmarks suffer from critical limitations, hindering reliable assessments of evaluation capability: Some feature coarse-grained binary labels, which reduce rich code behavior to a single bit of information, obscuring subtle errors. Others propose fine-grained but subjective, vaguely-defined evaluation criteria, introducing unreliability in manually-annotated scores, which is the ground-truth they rely on. Furthermore, they often use uncontrolled data synthesis methods, leading to unbalanced score distributions that poorly represent real-world code generation scenarios. To curate a diverse benchmark with programs of well-balanced distributions across various quality levels and streamline the manual annotation procedure, we propose AXIOM, a novel perturbation-based framework for synthesizing code evaluation benchmarks at scale. It reframes program scores as the refinement effort needed for deployment, consisting of two stages: (1) Rule-guided perturbation, which prompts LLMs to apply sequences of predefined perturbation rules to existing high-quality programs to modify their functionality and code quality, enabling us to precisely control each program's target score to achieve balanced score distributions. (2) Multisource quality calibration, which first selects a subset of...
Authors: Honglin Mu, Jinghao Liu, Kaiyang Wan, Rui Xing, Xiuying Chen, Timothy Baldwin, Wanxiang Che
Abstract: Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation. However, our research identifies a vulnerability: LLMs can be manipulated by "adversarial instructions" hidden in input data, such as resumes or code, causing them to deviate from their intended task. Notably, while defenses may exist for mature domains such as code review, they are often absent in other common applications such as resume screening and peer review. This paper introduces a benchmark to assess this vulnerability in resume screening, revealing attack success rates exceeding 80% for certain attack types. We evaluate two defense mechanisms: prompt-based defenses achieve 10.1% attack reduction with 12.5% false rejection increase, while our proposed FIDS (Foreign Instruction Detection through Separation) using LoRA adaptation achieves 15.4% attack reduction with 10.4% false rejection increase. The combined approach provides 26.3% attack reduction, demonstrating that training-time defenses outperform inference-time mitigations in both security and utility preservation.
Authors: Songze Li, Jiameng Cheng, Yiming Li, Xiaojun Jia, Dacheng Tao
Abstract: By integrating language understanding with perceptual modalities such as images, multimodal large language models (MLLMs) constitute a critical substrate for modern AI systems, particularly intelligent agents operating in open and interactive environments. However, their increasing accessibility also raises heightened risks of misuse, such as generating harmful or unsafe content. To mitigate these risks, alignment techniques are commonly applied to align model behavior with human values. Despite these efforts, recent studies have shown that jailbreak attacks can circumvent alignment and elicit unsafe outputs. Currently, most existing jailbreak methods are tailored for open-source models and exhibit limited effectiveness against commercial MLLM-integrated systems, which often employ additional filters. These filters can detect and prevent malicious input and output content, significantly reducing jailbreak threats. In this paper, we reveal that the success of these safety filters heavily relies on a critical assumption that malicious content must be explicitly visible in either the input or the output. This assumption, while often valid for traditional LLM-integrated systems, breaks down in MLLM-integrated systems, where attackers can leverage multiple modalities to conceal adversarial intent, leading to a false sense of security in existing MLLM-integrated systems. To challenge this assumption, we propose Odysseus, a novel jailbreak paradigm that introduces dual steganography to covertly embed malicious queries and responses into benign-looking images. Extensive experiments on benchmark datasets demonstrate that our Odysseus successfully jailbreaks several pioneering and realistic MLLM-integrated systems, achieving up to 99% attack success rate. It exposes a fundamental blind spot in existing defenses, and calls for rethinking cross-modal security in MLLM-integrated systems.
Authors: Shuzheng Si, Qingyi Wang, Haozhe Zhao, Yuzhuo Bai, Guanqiao Chen, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang, Maosong Sun
Abstract: Recognizing whether outputs from large language models (LLMs) contain faithfulness hallucination is crucial for real-world applications, e.g., retrieval-augmented generation and summarization. In this paper, we introduce FaithLens, a cost-efficient and effective faithfulness hallucination detection model that can jointly provide binary predictions and corresponding explanations to improve trustworthiness. To achieve this, we first synthesize training data with explanations via advanced LLMs and apply a well-defined data filtering strategy to ensure label correctness, explanation quality, and data diversity. Subsequently, we fine-tune the model on these well-curated training data as a cold start and further optimize it with rule-based reinforcement learning, using rewards for both prediction correctness and explanation quality. Results on 12 diverse tasks show that the 8B-parameter FaithLens outperforms advanced models such as GPT-4.1 and o3. Also, FaithLens can produce high-quality explanations, delivering a distinctive balance of trustworthiness, efficiency, and effectiveness.
Authors: Teqiang Zou, Hongliang Zeng, Yuxuan Nong, Yifan Li, Kehui Liu, Haotian Yang, Xinyang Ling, Xin Li, Lianyang Ma
Abstract: Most Vision-Language-Action (VLA) systems integrate a Vision-Language Model (VLM) for semantic reasoning with an action expert generating continuous action signals, yet both typically run at a single unified frequency. As a result, policy performance is constrained by the low inference speed of large VLMs. This mandatory synchronous execution severely limits control stability and real-time performance in whole-body robotic manipulation, which involves more joints, larger motion spaces, and dynamically changing views. We introduce a truly asynchronous Fast-Slow VLA framework (DuoCore-FS), organizing the system into a fast pathway for high-frequency action generation and a slow pathway for rich VLM reasoning. The system is characterized by two key features. First, a latent representation buffer bridges the slow and fast systems. It stores instruction semantics and action-reasoning representation aligned with the scene-instruction context, providing high-level guidance to the fast pathway. Second, a whole-body action tokenizer provides a compact, unified representation of whole-body actions. Importantly, the VLM and action expert are still jointly trained end-to-end, preserving unified policy learning while enabling asynchronous execution. DuoCore-FS supports a 3B-parameter VLM while achieving 30 Hz whole-body action-chunk generation, approximately three times as fast as prior VLA models with comparable model sizes. Real-world whole-body manipulation experiments demonstrate improved task success rates and significantly enhanced responsiveness compared to synchronous Fast-Slow VLA baselines. The implementation of DuoCore-FS, including training, inference, and deployment, is provided to commercial users by Astribot as part of the Astribot robotic platform.
Authors: Marko \v{C}echovi\v{c}, Nat\'alia Komorn\'ikov\'a, Dominik Mach\'a\v{c}ek, Ond\v{r}ej Bojar
Abstract: Speech processing and translation technology have the potential to facilitate meetings of individuals who do not share any common language. To evaluate automatic systems for such a task, a versatile and realistic evaluation corpus is needed. Therefore, we create and present a corpus of cross-lingual dialogues between individuals without a common language who were facilitated by automatic simultaneous speech translation. The corpus consists of 5 hours of speech recordings with ASR and gold transcripts in 12 original languages and automatic and corrected translations into English. For the purposes of research into cross-lingual summarization, our corpus also includes written summaries (minutes) of the meetings. Moreover, we propose automatic detection of misunderstandings. For an overview of this task and its complexity, we attempt to quantify misunderstandings in cross-lingual meetings. We annotate misunderstandings manually and also test the ability of current large language models to detect them automatically. The results show that the Gemini model is able to identify text spans with misunderstandings with recall of 77% and precision of 47%.
Authors: Tarik Houichime, Abdelghani Souhar, Younes El Amrani
Abstract: The memory of contemporary Large Language Models is bound by a physical paradox: as they learn, they fill up. The linear accumulation (O(N)) of Key-Value states treats context as a warehouse of static artifacts, eventually forcing a destructive choice between amnesia and latency. We challenge this discrete orthodoxy, proposing that long-term memory is not the storage of items, but the persistence of a trajectory. We introduce Phonetic Trajectory Memory (PTM), a neuro-symbolic architecture that encodes language not as a sequence of tensors, but as a continuous path on an ergodic manifold governed by irrational rotation matrices. By decoupling the navigation (an invariant O(1) geometric signal) from the reconstruction (a probabilistic generative act), PTM achieves a compression magnitude of greater than 3,000x relative to dense caches. We demonstrate that retrieval becomes a process of resonance: the phonetic trace stabilizes the model against hallucination via "Signal Consensus" mechanism, securing up to approximately 92% factual accuracy. While this aggressive abstraction alters generative texture, it unlocks immediate access latency (approximately 34ms) independent of depth. Our results suggest that infinite context does not require infinite silicon; it requires treating memory not as data to be stored, but as a reconstructive process acting on a conserved, undying physical signal.
Authors: Jiawei Ge, Jiuxin Cao, Xinyi Li, Xuelin Zhu, Chang Liu, Bo Liu, Chen Feng, Ioannis Patras
Abstract: Weakly-Supervised Camouflaged Object Detection (WSCOD) aims to locate and segment objects that are visually concealed within their surrounding scenes, relying solely on sparse supervision such as scribble annotations. Despite recent progress, existing WSCOD methods still lag far behind fully supervised ones due to two major limitations: (1) the pseudo masks generated by general-purpose segmentation models (e.g., SAM) and filtered via rules are often unreliable, as these models lack the task-specific semantic understanding required for effective pseudo labeling in COD; and (2) the neglect of inherent annotation bias in scribbles, which hinders the model from capturing the global structure of camouflaged objects. To overcome these challenges, we propose ${D}^{3}$ETOR, a two-stage WSCOD framework consisting of Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing. In the first stage, we introduce an adaptive entropy-driven point sampling method and a multi-agent debate mechanism to enhance the capability of SAM for COD, improving the interpretability and precision of pseudo masks. In the second stage, we design FADeNet, which progressively fuses multi-level frequency-aware features to balance global semantic understanding with local detail modeling, while dynamically reweighting supervision strength across regions to alleviate scribble bias. By jointly exploiting the supervision signals from both the pseudo masks and scribble semantics, ${D}^{3}$ETOR significantly narrows the gap between weakly and fully supervised COD, achieving state-of-the-art performance on multiple benchmarks.
Authors: Akshat Dubey, Aleksandar An\v{z}el, Bahar \.Ilgen, Georges Hattab
Abstract: Recent advances in deep learning have led to its widespread adoption across diverse domains, including medical imaging. This progress is driven by increasingly sophisticated model architectures, such as ResNets, Vision Transformers, and Hybrid Convolutional Neural Networks, that offer enhanced performance at the cost of greater complexity. This complexity often compromises model explainability and interpretability. SHAP has emerged as a prominent method for providing interpretable visualizations that aid domain experts in understanding model predictions. However, SHAP explanations can be unstable and unreliable in the presence of epistemic and aleatoric uncertainty. In this study, we address this challenge by using Dirichlet posterior sampling and Dempster-Shafer theory to quantify the uncertainty that arises from these unstable explanations in medical imaging applications. The framework uses a belief, plausible, and fusion map approach alongside statistical quantitative analysis to produce quantification of uncertainty in SHAP. Furthermore, we evaluated our framework on three medical imaging datasets with varying class distributions, image qualities, and modality types which introduces noise due to varying image resolutions and modality-specific aspect covering the examples from pathology, ophthalmology, and radiology, introducing significant epistemic uncertainty.
Authors: Wenzheng Zeng, Mingyu Ouyang, Langyuan Cui, Hwee Tou Ng
Abstract: Automatic presentation slide generation can greatly streamline content creation. However, since preferences of each user may vary, existing under-specified formulations often lead to suboptimal results that fail to align with individual user needs. We introduce a novel task that conditions paper-to-slides generation on user-specified preferences. We propose a human behavior-inspired agentic framework, SlideTailor, that progressively generates editable slides in a user-aligned manner. Instead of requiring users to write their preferences in detailed textual form, our system only asks for a paper-slides example pair and a visual template - natural and easy-to-provide artifacts that implicitly encode rich user preferences across content and visual style. Despite the implicit and unlabeled nature of these inputs, our framework effectively distills and generalizes the preferences to guide customized slide generation. We also introduce a novel chain-of-speech mechanism to align slide content with planned oral narration. Such a design significantly enhances the quality of generated slides and enables downstream applications like video presentations. To support this new task, we construct a benchmark dataset that captures diverse user preferences, with carefully designed interpretable metrics for robust evaluation. Extensive experiments demonstrate the effectiveness of our framework.
Authors: Ji-Hoon Kim, Junseok Ahn, Doyeop Kwak, Joon Son Chung, Shinji Watanabe
Abstract: The objective of this paper is to jointly synthesize interactive videos and conversational speech from text and reference images. With the ultimate goal of building human-like conversational systems, recent studies have explored talking or listening head generation as well as conversational speech generation. However, these works are typically studied in isolation, overlooking the multimodal nature of human conversation, which involves tightly coupled audio-visual interactions. In this paper, we introduce TAVID, a unified framework that generates both interactive faces and conversational speech in a synchronized manner. TAVID integrates face and speech generation pipelines through two cross-modal mappers (i.e., a motion mapper and a speaker mapper), which enable bidirectional exchange of complementary information between the audio and visual modalities. We evaluate our system across four dimensions: talking face realism, listening head responsiveness, dyadic interaction fluency, and speech quality. Extensive experiments demonstrate the effectiveness of our approach across all these aspects.
Authors: Karolina Dro\.zd\.z, Kacper Dudzic, Anna Sterna, Marcin Moskalewicz
Abstract: Growing reliance on LLMs for psychiatric self-assessment raises questions about their ability to interpret qualitative patient narratives. We present the first direct comparison between state-of-the-art LLMs and mental health professionals in diagnosing Borderline (BPD) and Narcissistic (NPD) Personality Disorders utilizing Polish-language first-person autobiographical accounts. We show that the top-performing Gemini Pro models surpassed human professionals in overall diagnostic accuracy by 21.91 percentage points (65.48% vs. 43.57%). While both models and human experts excelled at identifying BPD (F1 = 83.4 & F1 = 80.0, respectively), models severely underdiagnosed NPD (F1 = 6.7 vs. 50.0), showing a reluctance toward the value-laden term "narcissism." Qualitatively, models provided confident, elaborate justifications focused on patterns and formal categories, while human experts remained concise and cautious, emphasizing the patient's sense of self and temporal experience. Our findings demonstrate that while LLMs are highly competent at interpreting complex first-person clinical data, they remain subject to critical reliability and bias issues.
Authors: Zhongyu Xia, Wenhao Chen, Yongtao Wang, Ming-Hsuan Yang
Abstract: Visual-language reasoning, driving knowledge, and value alignment are essential for advanced autonomous driving systems. However, existing approaches largely rely on data-driven learning, making it difficult to capture the complex logic underlying decision-making through imitation or limited reinforcement rewards. To address this, we propose KnowVal, a new autonomous driving system that enables visual-language reasoning through the synergistic integration of open-world perception and knowledge retrieval. Specifically, we construct a comprehensive driving knowledge graph that encodes traffic laws, defensive driving principles, and ethical norms, complemented by an efficient LLM-based retrieval mechanism tailored for driving scenarios. Furthermore, we develop a human-preference dataset and train a Value Model to guide interpretable, value-aligned trajectory assessment. Experimental results show that our method substantially improves planning performance while remaining compatible with existing architectures. Notably, KnowVal achieves the lowest collision rate on nuScenes and state-of-the-art results on Bench2Drive.
Authors: Saisai Yang, Qingyi Huang, Jing Yuan, Liangyu Zha, Kai Tang, Yuhang Yang, Ning Wang, Yucheng Wei, Liyao Li, Wentao Ye, Hao Chen, Tao Zhang, Junlin Zhou, Haobo Wang, Gang Chen, Junbo Zhao
Abstract: Tabular data serves as the backbone of modern data analysis and scientific research. While Large Language Models (LLMs) fine-tuned via Supervised Fine-Tuning (SFT) have significantly improved natural language interaction with such structured data, they often fall short in handling the complex, multi-step reasoning and robust code execution required for real-world table tasks. Reinforcement Learning (RL) offers a promising avenue to enhance these capabilities, yet its application in the tabular domain faces three critical hurdles: the scarcity of high-quality agentic trajectories with closed-loop code execution and environment feedback on diverse table structures, the extreme heterogeneity of feedback signals ranging from rigid SQL execution to open-ended data interpretation, and the risk of catastrophic forgetting of general knowledge during vertical specialization. To overcome these challenges and unlock advanced reasoning on complex tables, we introduce \textbf{TableGPT-R1}, a specialized tabular model built on a systematic RL framework. Our approach integrates a comprehensive data engineering pipeline that synthesizes difficulty-stratified agentic trajectories for both supervised alignment and RL rollouts, a task-adaptive reward system that combines rule-based verification with a criteria-injected reward model and incorporates process-level step reward shaping with behavioral regularization, and a multi-stage training framework that progressively stabilizes reasoning before specializing in table-specific tasks. Extensive evaluations demonstrate that TableGPT-R1 achieves state-of-the-art performance on authoritative benchmarks, significantly outperforming baseline models while retaining robust general capabilities. Our model is available at https://huggingface.co/tablegpt/TableGPT-R1.
Authors: Alexis Pomares Pastor, Ines Ribeiro Violante, Gregory Scott
Abstract: A major shortcoming of medical practice is the lack of an objective measure of conscious level. Impairment of consciousness is common, e.g. following brain injury and seizures, which can also interfere with sensory processing and volitional responses. This is also an important pitfall in neurophysiological methods that infer awareness via command following, e.g. using functional MRI or electroencephalography (EEG). Transcranial electrical stimulation (TES) can be employed to non-invasively stimulate the brain, bypassing sensory inputs, and has already showed promising results in providing reliable indicators of brain state. However, current non-invasive solutions have been limited to magnetic stimulation, which is not easily translatable to clinical settings. Our long-term vision is to develop an objective measure of brain state that can be used at the bedside, without requiring patients to understand commands or initiate motor responses. In this study, we demonstrated the feasibility of a framework using Deep Learning algorithms to classify EEG brain responses evoked by a defined multi-dimensional pattern of TES. We collected EEG-TES data from 11 participants and found that delivering transcranial direct current stimulation (tDCS) to posterior cortical areas targeting the angular gyrus elicited an exceptionally reliable brain response. For this paradigm, our best Convolutional Neural Network model reached a 92% classification F1-score on Holdout data from participants never seen during training, significantly surpassing human-level performance at 60-70% accuracy. These findings establish a framework for robust consciousness measurement for clinical use. In this spirit, we documented and open-sourced our datasets and codebase in full, to be used freely by the neuroscience and AI research communities, who may replicate our results with free tools like GitHub, Kaggle, and Colab.
Authors: Antonio Vitale, Khai-Nguyen Nguyen, Denys Poshyvanyk, Rocco Oliveto, Simone Scalabrino, Antonio Mastropaolo
Abstract: Recent progress in Large Language Models (LLMs) has substantially advanced the automation of software engineering (SE) tasks, enabling complex activities such as code generation and code summarization. However, the black-box nature of LLMs remains a major barrier to their adoption in high-stakes and safety-critical domains, where explainability and transparency are vital for trust, accountability, and effective human supervision. Despite increasing interest in explainable AI for software engineering, existing methods lack domain-specific explanations aligned with how practitioners reason about SE artifacts. To address this gap, we introduce FeatureSHAP, the first fully automated, model-agnostic explainability framework tailored to software engineering tasks. Based on Shapley values, FeatureSHAP attributes model outputs to high-level input features through systematic input perturbation and task-specific similarity comparisons, while remaining compatible with both open-source and proprietary LLMs. We evaluate FeatureSHAP on two bi-modal SE tasks: code generation and code summarization. The results show that FeatureSHAP assigns less importance to irrelevant input features and produces explanations with higher fidelity than baseline methods. A practitioner survey involving 37 participants shows that FeatureSHAP helps practitioners better interpret model outputs and make more informed decisions. Collectively, FeatureSHAP represents a meaningful step toward practical explainable AI in software engineering. FeatureSHAP is available at https://github.com/deviserlab/FeatureSHAP.
Authors: Nilesh Jain, Seyi Adeyinka, Leor Roseman, Aza Allsop
Abstract: Qualitative research faces a critical reliability challenge: traditional inter-rater agreement methods require multiple human coders, are time-intensive, and often yield moderate consistency. We present a multi-perspective validation framework for LLM-based thematic analysis that combines ensemble validation with dual reliability metrics: Cohen's Kappa ($\kappa$) for inter-rater agreement and cosine similarity for semantic consistency. Our framework enables configurable analysis parameters (1-6 seeds, temperature 0.0-2.0), supports custom prompt structures with variable substitution, and provides consensus theme extraction across any JSON format. As proof-of-concept, we evaluate three leading LLMs (Gemini 2.5 Pro, GPT-4o, Claude 3.5 Sonnet) on a psychedelic art therapy interview transcript, conducting six independent runs per model. Results demonstrate Gemini achieves highest reliability ($\kappa = 0.907$, cosine=95.3%), followed by GPT-4o ($\kappa = 0.853$, cosine=92.6%) and Claude ($\kappa = 0.842$, cosine=92.1%). All three models achieve a high agreement ($\kappa > 0.80$), validating the multi-run ensemble approach. The framework successfully extracts consensus themes across runs, with Gemini identifying 6 consensus themes (50-83% consistency), GPT-4o identifying 5 themes, and Claude 4 themes. Our open-source implementation provides researchers with transparent reliability metrics, flexible configuration, and structure-agnostic consensus extraction, establishing methodological foundations for reliable AI-assisted qualitative research.
Authors: Daniel M. Jimenez-Gutierrez, Mehrdad Hassanzadeh, Aris Anagnostopoulos, Ioannis Chatzigiannakis, Andrea Vitaletti
Abstract: Federated learning (FL) supports privacy-preserving, decentralized machine learning (ML) model training by keeping data on client devices. However, non-independent and identically distributed (non-IID) data across clients biases updates and degrades performance. To alleviate these issues, we propose Clust-PSI-PFL, a clustering-based personalized FL framework that uses the Population Stability Index (PSI) to quantify the level of non-IID data. We compute a weighted PSI metric, $WPSI^L$, which we show to be more informative than common non-IID metrics (Hellinger, Jensen-Shannon, and Earth Mover's distance). Using PSI features, we form distributionally homogeneous groups of clients via K-means++; the number of optimal clusters is chosen by a systematic silhouette-based procedure, typically yielding few clusters with modest overhead. Across six datasets (tabular, image, and text modalities), two partition protocols (Dirichlet with parameter $\alpha$ and Similarity with parameter S), and multiple client sizes, Clust-PSI-PFL delivers up to 18% higher global accuracy than state-of-the-art baselines and markedly improves client fairness by a relative improvement of 37% under severe non-IID data. These results establish PSI-guided clustering as a principled, lightweight mechanism for robust PFL under label skew.
Authors: Syeda Tasnim Fabiha, Saad Shafiq, Wesley Klewerton Guez Assun\c{c}\~ao, Nenad Medvidovi\'c
Abstract: Service-based architecture (SBA) has gained attention in industry and academia as a means to modernize legacy systems. It refers to a design style that enables systems to be developed as suites of small, loosely coupled, and autonomous components (services) that encapsulate functionality and communicate via language-agnostic APIs. However, defining appropriately sized services that capture cohesive subsets of system functionality remains challenging. Existing work often relies on the availability of documentation, access to project personnel, or a priori knowledge of the target number of services, assumptions that do not hold in many real-world scenarios. Our work addresses these limitations using a deep reinforcement learning-based approach to identify appropriately sized services directly from implementation artifacts. We present Rake, a reinforcement learning-based technique that leverages available system documentation and source code to guide service decomposition at the level of implementation methods. Rake does not require specific documentation or access to project personnel and is language-agnostic. It also supports a customizable objective function that balances modularization quality and business capability alignment, i.e., the degree to which a service covers the targeted business capability. We applied Rake to four open-source legacy projects and compared it with two state-of-the-art techniques. On average, Rake achieved 7-14 percent higher modularization quality and 18-22 percent stronger business capability alignment. Our results further show that optimizing solely for business context can degrade decomposition quality in tightly coupled systems, highlighting the need for balanced objectives.
Authors: Rajdeep Chatterjee, Sudip Chakrabarty, Trishaani Acharjee, Deepanjali Mishra
Abstract: Unmanned aerial vehicles (UAVs), commonly known as drones, are increasingly used across diverse domains, including logistics, agriculture, surveillance, and defense. While these systems provide numerous benefits, their misuse raises safety and security concerns, making effective detection mechanisms essential. Acoustic sensing offers a low-cost and non-intrusive alternative to vision or radar-based detection, as drone propellers generate distinctive sound patterns. This study introduces AUDRON (AUdio-based Drone Recognition Network), a hybrid deep learning framework for drone sound detection, employing a combination of Mel-Frequency Cepstral Coefficients (MFCC), Short-Time Fourier Transform (STFT) spectrograms processed with convolutional neural networks (CNNs), recurrent layers for temporal modeling, and autoencoder-based representations. Feature-level fusion integrates complementary information before classification. Experimental evaluation demonstrates that AUDRON effectively differentiates drone acoustic signatures from background noise, achieving high accuracy while maintaining generalizability across varying conditions. AUDRON achieves 98.51 percent and 97.11 percent accuracy in binary and multiclass classification. The results highlight the advantage of combining multiple feature representations with deep learning for reliable acoustic drone detection, suggesting the framework's potential for deployment in security and surveillance applications where visual or radar sensing may be limited.
Authors: Junho Yoon, Jaemo Jung, Hyunju Kim, Dongman Lee
Abstract: Aligning egocentric video with wearable sensors have shown promise for human action recognition, but face practical limitations in user discomfort, privacy concerns, and scalability. We explore exocentric video with ambient sensors as a non-intrusive, scalable alternative. While prior egocentric-wearable works predominantly adopt Global Alignment by encoding entire sequences into unified representations, this approach fails in exocentric-ambient settings due to two problems: (P1) inability to capture local details such as subtle motions, and (P2) over-reliance on modality-invariant temporal patterns, causing misalignment between actions sharing similar temporal patterns with different spatio-semantic contexts. To resolve these problems, we propose DETACH, a decomposed spatio-temporal framework. This explicit decomposition preserves local details, while our novel sensor-spatial features discovered via online clustering provide semantic grounding for context-aware alignment. To align the decomposed features, our two-stage approach establishes spatial correspondence through mutual supervision, then performs temporal alignment via a spatial-temporal weighted contrastive loss that adaptively handles easy negatives, hard negatives, and false negatives. Comprehensive experiments with downstream tasks on Opportunity++ and HWU-USP datasets demonstrate substantial improvements over adapted egocentric-wearable baselines.
Authors: Mihai Suteu, Ovidiu Serban
Abstract: Multi-task learning (MTL) aims to leverage shared knowledge across tasks to improve generalization and parameter efficiency, yet balancing resources and mitigating interference remain open challenges. Architectural solutions often introduce elaborate task-specific modules or routing schemes, increasing complexity and overhead. In this work, we show that normalization layers alone are sufficient to address many of these challenges. Simply replacing shared normalization with task-specific variants already yields competitive performance, questioning the need for complex designs. Building on this insight, we propose Task-Specific Sigmoid Batch Normalization (TS$\sigma$BN), a lightweight mechanism that enables tasks to softly allocate network capacity while fully sharing feature extractors. TS$\sigma$BN improves stability across CNNs and Transformers, matching or exceeding performance on NYUv2, Cityscapes, CelebA, and PascalContext, while remaining highly parameter-efficient. Moreover, its learned gates provide a natural framework for analyzing MTL dynamics, offering interpretable insights into capacity allocation, filter specialization, and task relationships. Our findings suggest that complex MTL architectures may be unnecessary and that task-specific normalization offers a simple, interpretable, and efficient alternative.
Authors: Adam Elaoumari
Abstract: The purpose of this project is to assess how well defenders can detect DNS-over-HTTPS (DoH) file exfiltration, and which evasion strategies can be used by attackers. While providing a reproducible toolkit to generate, intercept and analyze DoH exfiltration, and comparing Machine Learning vs threshold-based detection under adversarial scenarios. The originality of this project is the introduction of an end-to-end, containerized pipeline that generates configurable file exfiltration over DoH using several parameters (e.g., chunking, encoding, padding, resolver rotation). It allows for file reconstruction at the resolver side, while extracting flow-level features using a fork of DoHLyzer. The pipeline contains a prediction side, which allows the training of machine learning models based on public labelled datasets and then evaluates them side-by-side with threshold-based detection methods against malicious and evasive DNS-Over-HTTPS traffic. We train Random Forest, Gradient Boosting and Logistic Regression classifiers on a public DoH dataset and benchmark them against evasive DoH exfiltration scenarios. The toolkit orchestrates traffic generation, file capture, feature extraction, model training and analysis. The toolkit is then encapsulated into several Docker containers for easy setup and full reproducibility regardless of the platform it is run on. Future research regarding this project is directed at validating the results on mixed enterprise traffic, extending the protocol coverage to HTTP/3/QUIC request, adding a benign traffic generation, and working on real-time traffic evaluation. A key objective is to quantify when stealth constraints make DoH exfiltration uneconomical and unworthy for the attacker.
Authors: Muhammad Usman, Azka Rehman, Muhammad Mutti Ur Rehman, Abd Ur Rehman, Muhammad Umar Farooq
Abstract: Accurate segmentation of ischemic stroke lesions from diffusion magnetic resonance imaging (MRI) is essential for clinical decision-making and outcome assessment. Diffusion-Weighted Imaging (DWI) and Apparent Diffusion Coefficient (ADC) scans provide complementary information on acute and sub-acute ischemic changes; however, automated lesion delineation remains challenging due to variability in lesion appearance. In this work, we study ischemic stroke lesion segmentation using multimodal diffusion MRI from the ISLES 2022 dataset. Several state-of-the-art convolutional and transformer-based architectures, including U-Net variants, Swin-UNet, and TransUNet, are benchmarked. Based on performance, a dual-encoder TransUNet architecture is proposed to learn modality-specific representations from DWI and ADC inputs. To incorporate spatial context, adjacent slice information is integrated using a three-slice input configuration. All models are trained under a unified framework and evaluated using the Dice Similarity Coefficient (DSC). Results show that transformer-based models outperform convolutional baselines, and the proposed dual-encoder TransUNet achieves the best performance, reaching a Dice score of 85.4% on the test set. The proposed framework offers a robust solution for automated ischemic stroke lesion segmentation from diffusion MRI.
Authors: Revanth Gangi Reddy, Ye Liu, Wenting Zhao, JaeHyeok Doo, Tarun Suresh, Daniel Lee, Caiming Xiong, Yingbo Zhou, Semih Yavuz, Shafiq Joty
Abstract: Maintaining large-scale, multilingual codebases hinges on accurately localizing issues, which requires mapping natural-language error descriptions to the relevant functions that need to be modified. However, existing ranking approaches are often Python-centric and perform a single-pass search over the codebase. This work introduces SweRank+, a framework that couples SweRankMulti, a cross-lingual code ranking tool, with SweRankAgent, an agentic search setup, for iterative, multi-turn reasoning over the code repository. SweRankMulti comprises a code embedding retriever and a listwise LLM reranker, and is trained using a carefully curated large-scale issue localization dataset spanning multiple popular programming languages. SweRankAgent adopts an agentic search loop that moves beyond single-shot localization with a memory buffer to reason and accumulate relevant localization candidates over multiple turns. Our experiments on issue localization benchmarks spanning various languages demonstrate new state-of-the-art performance with SweRankMulti, while SweRankAgent further improves localization over single-pass ranking.
Authors: Long Nguyen, Micha Fauth, Bernhard Jaeger, Daniel Dauner, Maximilian Igl, Andreas Geiger, Kashyap Chitta
Abstract: Simulators can generate virtually unlimited driving data, yet imitation learning policies in simulation still struggle to achieve robust closed-loop performance. Motivated by this gap, we empirically study how misalignment between privileged expert demonstrations and sensor-based student observations can limit the effectiveness of imitation learning. More precisely, experts have significantly higher visibility (e.g., ignoring occlusions) and far lower uncertainty (e.g., knowing other vehicles' actions), making them difficult to imitate reliably. Furthermore, navigational intent (i.e., the route to follow) is under-specified in student models at test time via only a single target point. We demonstrate that these asymmetries can measurably limit driving performance in CARLA and offer practical interventions to address them. After careful modifications to narrow the gaps between expert and student, our TransFuser v6 (TFv6) student policy achieves a new state of the art on all major publicly available CARLA closed-loop benchmarks, reaching 95 DS on Bench2Drive and more than doubling prior performances on Longest6~v2 and Town13. Additionally, by integrating perception supervision from our dataset into a shared sim-to-real pipeline, we show consistent gains on the NAVSIM and Waymo Vision-Based End-to-End driving benchmarks. Our code, data, and models are publicly available at https://github.com/autonomousvision/lead.
Authors: Yanhong Li, Songlin Yang, Shawn Tan, Mayank Mishra, Rameswar Panda, Jiawei Zhou, Yoon Kim
Abstract: Distilling pretrained softmax attention Transformers into more efficient hybrid architectures that interleave softmax and linear attention layers is a promising approach for improving the inference efficiency of LLMs without requiring expensive pretraining from scratch. A critical factor in the conversion process is layer selection, i.e., deciding on which layers to convert to linear attention variants. This paper describes a simple and efficient recipe for layer selection that uses layer importance scores derived from a small amount of training on generic text data. Once the layers have been selected we use a recent pipeline for the distillation process itself \citep[RADLADS;][]{goldstein2025radlads}, which consists of attention weight transfer, hidden state alignment, KL-based distribution matching, followed by a small amount of finetuning. We find that this approach is more effective than existing approaches for layer selection, including heuristics that uniformly interleave linear attentions based on a fixed ratio, as well as more involved approaches that rely on specialized diagnostic datasets.
Authors: Rui Pan, Zhuofu Chen, Ravi Netravali
Abstract: Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. We show that, if carefully applied, the attributes of dLLMs can actually be a strength for drafters in speculative decoding with autoregressive (AR) verifiers. Our core insight is that dLLM's speed from parallel decoding drastically lowers the risk of costly rejections, providing a practical mechanism to effectively realize the (elusive) lengthy drafts that lead to large speedups with speculative decoding. We present FailFast, a dLLM-based speculative decoding framework that realizes this approach by dynamically adapting its speculation length. It "fails fast" by spending minimal compute in hard-to-speculate regions to shrink speculation latency and "wins big" by aggressively extending draft lengths in easier regions to reduce verification latency (in many cases, speculating and accepting 70 tokens at a time!). Without any fine-tuning, FailFast delivers lossless acceleration of AR LLMs and achieves up to 4.9$\times$ speedup over vanilla decoding, 1.7$\times$ over the best naive dLLM drafter, and 1.4$\times$ over EAGLE-3 across diverse models and workloads. We open-source FailFast at https://github.com/ruipeterpan/failfast.
Authors: Debabrota Basu, Udvas Das, Brahim Driss, Uddalak Mukherjee
Abstract: Post-deployment machine learning algorithms often influence the environments they act in, and thus shift the underlying dynamics that the standard reinforcement learning (RL) methods ignore. While designing optimal algorithms in this performative setting has recently been studied in supervised learning, the RL counterpart remains under-explored. In this paper, we prove the performative counterparts of the performance difference lemma and the policy gradient theorem in RL, and further introduce the Performative Policy Gradient algorithm (PePG). PePG is the first policy gradient algorithm designed to account for performativity in RL. Under softmax parametrisation, and also with and without entropy regularisation, we prove that PePG converges to performatively optimal policies, i.e. policies that remain optimal under the distribution shifts induced by themselves. Thus, PePG significantly extends the prior works in Performative RL that achieves performative stability but not optimality. Furthermore, our empirical analysis on standard performative RL environments validate that PePG outperforms standard policy gradient algorithms and the existing performative RL algorithms aiming for stability.
Authors: \.Ibrahim O\u{g}uz \c{C}etinkaya, Sajad Khodadadian, Taylan G. Top\c{c}u
Abstract: As systems engineering (SE) objectives evolve from design and operation of monolithic systems to complex System of Systems (SoS), the discipline of Mission Engineering (ME) has emerged which is increasingly being accepted as a new line of thinking for the SE community. Moreover, mission environments are uncertain, dynamic, and mission outcomes are a direct function of how the mission assets will interact with this environment. This proves static architectures brittle and calls for analytically rigorous approaches for ME. To that end, this paper proposes an intelligent mission coordination methodology that integrates digital mission models with Reinforcement Learning (RL), that specifically addresses the need for adaptive task allocation and reconfiguration. More specifically, we are leveraging a Digital Engineering (DE) based infrastructure that is composed of a high-fidelity digital mission model and agent-based simulation; and then we formulate the mission tactics management problem as a Markov Decision Process (MDP), and employ an RL agent trained via Proximal Policy Optimization. By leveraging the simulation as a sandbox, we map the system states to actions, refining the policy based on realized mission outcomes. The utility of the RL-based intelligent mission coordinator is demonstrated through an aerial firefighting case study. Our findings indicate that the RL-based intelligent mission coordinator not only surpasses baseline performance but also significantly reduces the variability in mission performance. Thus, this study serves as a proof of concept demonstrating that DE-enabled mission simulations combined with advanced analytical tools offer a mission-agnostic framework for improving ME practice; which can be extended to more complicated fleet design and selection problems in the future from a mission-first perspective.
Authors: Dhruv Anand, Ehsan Shareghi
Abstract: We introduce Cube Bench, a Rubik's-cube benchmark for evaluating spatial and sequential reasoning in multimodal large language models (MLLMs). The benchmark decomposes performance into five skills: (i) reconstructing cube faces from images and text, (ii) choosing the optimal next move, (iii) predicting the outcome of a candidate move without applying it, (iv) executing multi-step plans while recovering from mistakes, and (v) detecting and revising one's own errors. Using a shared set of scrambled cube states, identical prompts and parsers, and a single distance-to-solved metric, we compare recent MLLMs side by side as a function of scramble depth. Across seven MLLMs, accuracy drops sharply with depth; once a trajectory stalls or diverges, models rarely recover, and high face-reconstruction accuracy does not guarantee competent action selection or multi-step execution. A pronounced closed- vs open-source gap emerges: the strongest closed model leads on both single-step perception tasks and multi-step control tasks, while open-weight models cluster near chance on the hardest settings; yet even the best MLLM degrades at higher cube complexity. A simple self-correction via reflective thinking yields modest gains but can also introduce overthinking. Cube Bench offers a compact, reproducible probe of sequential spatial reasoning in MLLMs.
Authors: Seijin Kobayashi, Yanick Schimpf, Maximilian Schlegel, Angelika Steger, Maciej Wolczyk, Johannes von Oswald, Nino Scherre, Kaitlin Maile, Guillaume Lajoie, Blake A. Richards, Rif A. Saurous, James Manyika, Blaise Ag\"uera y Arcas, Alexander Meulemans, Jo\~ao Sacramento
Abstract: Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. During RL, these models explore by generating new outputs, one token at a time. However, sampling actions token-by-token can result in highly inefficient learning, particularly when rewards are sparse. Here, we show that it is possible to overcome this problem by acting and exploring within the internal representations of an autoregressive model. Specifically, to discover temporally-abstract actions, we introduce a higher-order, non-causal sequence model whose outputs control the residual stream activations of a base autoregressive model. On grid world and MuJoCo-based tasks with hierarchical structure, we find that the higher-order model learns to compress long activation sequence chunks onto internal controllers. Critically, each controller executes a sequence of behaviorally meaningful actions that unfold over long timescales and are accompanied with a learned termination condition, such that composing multiple controllers over time leads to efficient exploration on novel tasks. We show that direct internal controller reinforcement, a process we term "internal RL", enables learning from sparse rewards in cases where standard RL finetuning fails. Our results demonstrate the benefits of latent action generation and reinforcement in autoregressive models, suggesting internal RL as a promising avenue for realizing hierarchical RL within foundation models.
Authors: Ji Ma
Abstract: Large language models (LLMs) increasingly serve as human-like decision-making agents in social science and applied settings. These LLM-agents are typically assigned human-like characters and placed in real-life contexts. However, how these characters and contexts shape an LLM's behavior remains underexplored. This study proposes and tests methods for probing, quantifying, and modifying an LLM's internal representations in a Dictator Game, a classic behavioral experiment on fairness and prosocial behavior. We extract ``vectors of variable variations'' (e.g., ``male'' to ``female'') from the LLM's internal state. Manipulating these vectors during the model's inference can substantially alter how those variables relate to the model's decision-making. This approach offers a principled way to study and regulate how social concepts can be encoded and engineered within transformer-based models, with implications for alignment, debiasing, and designing AI agents for social simulations in both academic and commercial applications, strengthening sociological theory and measurement.
Authors: Prahaladh Chandrahasan, Jiahe Jin, Zhihan Zhang, Tevin Wang, Andy Tang, Lucy Mo, Morteza Ziyadi, Leonardo F. R. Ribeiro, Zimeng Qiu, Markus Dreyer, Akari Asai, Chenyan Xiong
Abstract: Effectively evaluating deep research agents that autonomously search the web, analyze information, and generate reports remains a major challenge, particularly when it comes to assessing long reports and giving detailed feedback on their intermediate steps. To address these gaps, we introduce Deep Research Comparator, a platform that offers a holistic framework for deep research agent hosting, side-by-side comparison, fine-grained human feedback collection, and ranking calculation. Given a user query, our platform displays the final reports from two different agents along with their intermediate steps during generation. Annotators can evaluate the overall quality of final reports based on side-by-side comparison, and also provide detailed feedback separately by assessing intermediate steps or specific text spans within the final report. Furthermore, we develop Simple Deepresearch, an end-to-end agent scaffold. This scaffold serves as a baseline that facilitates the easy integration of various large language models to transform them into deep research agents for evaluation. To demonstrate the platform's utility for deep research agent development, we have collected real user preference data from 17 annotators on three deep research agents. A demo video of our platform can be found at https://www.youtube.com/watch?v=g4d2dnbdseg.
Authors: Moises Andrade, Joonhyuk Cha, Brandon Ho, Vriksha Srihari, Karmesh Yadav, Zsolt Kira
Abstract: Verifiers--functions assigning rewards to agent behavior--have been key for AI progress in domains like math and code. However, extending gains to domains without clear-cut success criteria (e.g., computer use) remains a challenge: while humans can recognize desired outcomes, translating this intuition into scalable rules is nontrivial. Multimodal Large Language Models (MLLMs) emerge as a promising solution, given their world knowledge, human-preference alignment, and reasoning skills. We evaluate MLLMs as verifiers across web navigation, computer use, and robotic manipulation, and identify a critical limitation: a strong tendency to over-validate agent behavior, a phenomenon we term agreement bias. This bias is pervasive across models, resilient to test-time scaling, and poses risks to existing methods relying on MLLM evaluations. We discuss methods to evaluate and improve MLLM verifiers and introduce Self-Grounded Verification (SGV), a lightweight method that harnesses MLLMs' own sampling mechanisms by modulating (un)conditional generation to better leverage their knowledge, alignment, and reasoning. SGV operates in two steps: first, the MLLM is elicited to generate broad priors about desired behavior, independent of the data under evaluation. Then, conditioned on self-generated priors, it reasons over and evaluates a candidate trajectory. SGV yields more human-aligned evaluations with gains of up to 25pp in failure detection, 14pp in accuracy, and benefits extending to downstream applications. In self-refinement and online supervision, SGV boosts task completion of a GUI specialist in OSWorld, a diffusion policy in robomimic, and a ReAct agent in VisualWebArena--setting a new state of the art, surpassing the previous best by 20pp. We release an updated version of VisualWebArena featuring more human-aligned evaluators, high-fidelity environment parallelism, and speedups of over 10x.
Authors: Yuting Zhang, Karina V. Bunting, Asgher Champsi, Xiaoxia Wang, Wenqi Lu, Alexander Thorley, Sandeep S Hothi, Zhaowen Qiu, Baturalp Buyukates, Dipak Kotecha, Jinming Duan
Abstract: Cardiovascular diseases (CVDs) remain the foremost cause of mortality worldwide, a burden worsened by a severe deficit of healthcare workers. Artificial intelligence (AI) agents have shown potential to alleviate this gap through automated detection and proactive screening, yet their clinical application remains limited by: 1) rigid sequential workflows, whereas clinical care often requires adaptive reasoning that select specific tests and, based on their results, guides personalised next steps; 2) reliance solely on intrinsic model capabilities to perform role assignment without domain-specific tool support; 3) general and static knowledge bases without continuous learning capability; and 4) fixed unimodal or bimodal inputs and lack of on-demand visual outputs when clinicians require visual clarification. In response, a multimodal framework, CardAIc-Agents, was proposed to augment models with external tools and adaptively support diverse cardiac tasks. First, a CardiacRAG agent generated task-aware plans from updatable cardiac knowledge, while the Chief agent integrated tools to autonomously execute these plans and deliver decisions. Second, to enable adaptive and case-specific customization, a stepwise update strategy was developed to dynamically refine plans based on preceding execution results, once the task was assessed as complex. Third, a multidisciplinary discussion team was proposed which was automatically invoked to interpret challenging cases, thereby supporting further adaptation. In addition, visual review panels were provided to assist validation when clinicians raised concerns. Experiments across three datasets showed the efficiency of CardAIc-Agents compared to mainstream Vision-Language Models (VLMs) and state-of-the-art agentic systems.
Authors: Botao Zhu, Jeslyn Wang, Dusit Niyato, Xianbin Wang
Abstract: Offloading computational tasks from resource-constrained devices to resource-abundant peers constitutes a critical paradigm for collaborative computing. Within this context, accurate trust evaluation of potential collaborating devices is essential for the effective execution of complex computing tasks. This trust evaluation process involves collecting diverse trust-related information from every potential collaborator and performing trust inference based on the collected data. However, when each resource-constrained device independently assesses all potential collaborators, frequent data exchange and complex reasoning can incur significant overhead and further degrade the timeliness of trust evaluation. To overcome these challenges, we propose a task-specific trust semantics distillation (TSD) model based on a large AI model (LAM)-enabled teacher-student agent architecture. Specifically, the teacher agent is deployed on a server with powerful computational capabilities and an augmented memory module to perform multidimensional trust-related data collection, task-specific trust semantics extraction, and task-collaborator matching analysis. Upon receiving task-specific evaluation requests from device-side student agents, the teacher agent transfers the trust semantics of potential collaborators to the student agents, enabling rapid and accurate collaborator selection. Experimental results demonstrate that the proposed TSD model can reduce collaborator evaluation time, decrease device resource consumption, and improve the accuracy of collaborator selection.
Authors: Cl\'ement Contet, Umberto Grandi, J\'er\^ome Mengin
Abstract: Tournaments are widely used models to represent pairwise dominance between candidates, alternatives, or teams. We study the problem of providing certified explanations for why a candidate appears among the winners under various tournament rules. To this end, we identify minimal supports, minimal sub-tournaments in which the candidate is guaranteed to win regardless of how the rest of the tournament is completed (that is, the candidate is a necessary winner of the sub-tournament). This notion corresponds to an abductive explanation for the question,"Why does the winner win the tournament?", a central concept in formal explainable AI. We focus on common tournament solutions: the top cycle, the uncovered set, the Copeland rule, the Borda rule, the maximin rule, and the weighted uncovered set. For each rule we determine the size of the smallest minimal supports, and we present polynomial-time algorithms to compute them for all solutions except for the weighted uncovered set, for which the problem is NP-complete. Finally, we show how minimal supports can serve to produce compact, certified, and intuitive explanations for tournament solutions.
Authors: Kei-Sing Ng
Abstract: We posit that persisting and transforming similarity relations form the structural basis of any comprehensible dynamic system. This paper introduces Similarity Field Theory, a mathematical framework that formalizes the principles governing similarity values among entities and their evolution. We define: (1) a similarity field $S: U \times U \to [0,1]$ over a universe of entities $U$, satisfying reflexivity $S(E,E)=1$ and treated as a directed relational field (asymmetry and non-transitivity are allowed); (2) the evolution of a system through a sequence $Z_p=(X_p,S^{(p)})$ indexed by $p=0,1,2,\ldots$; (3) concepts $K$ as entities that induce fibers $F_{\alpha}(K)={E\in U \mid S(E,K)\ge \alpha}$, i.e., superlevel sets of the unary map $S_K(E):=S(E,K)$; and (4) a generative operator $G$ that produces new entities. Within this framework, we formalize a generative definition of intelligence: an operator $G$ is intelligent with respect to a concept $K$ if, given a system containing entities belonging to the fiber of $K$, it generates new entities that also belong to that fiber. Similarity Field Theory thus offers a foundational language for characterizing, comparing, and constructing intelligent systems. At a high level, this framework reframes intelligence and interpretability as geometric problems on similarity fields--preserving and composing level-set fibers--rather than purely statistical ones. We prove two theorems: (i) asymmetry blocks mutual inclusion; and (ii) stability implies either an anchor coordinate or asymptotic confinement to the target level (up to arbitrarily small tolerance). Together, these results constrain similarity-field evolution and motivate an interpretive lens that can be applied to large language models.
Authors: Rongzhao Zhang, Junqiao Wang, Shuyun Yang, Mouxiao Bian, Chihao Zhang, Dongyang Wang, Qiujuan Yan, Yun Zhong, Yuwei Bai, Guanxu Zhu, Kangkun Mao, Miao Wang, Chao Ding, Renjie Lu, Lei Wang, Lei Zheng, Tao Zheng, Xi Wang, Zhuo Fan, Bing Han, Meiling Liu, Luyi Jiang, Dongming Shan, Wenzhong Jin, Jiwei Yu, Zheng Wang, Jie Xu, Meng Luo
Abstract: Multimodal clinical reasoning in the field of gastrointestinal (GI) oncology necessitates the integrated interpretation of endoscopic imagery, radiological data, and biochemical markers. Despite the evident potential exhibited by Multimodal Large Language Models (MLLMs), they frequently encounter challenges such as context dilution and hallucination when confronted with intricate, heterogeneous medical histories. In order to address these limitations, a hierarchical Multi-Agent Framework is proposed, which emulates the collaborative workflow of a human Multidisciplinary Team (MDT). The system attained a composite expert evaluation score of 4.60/5.00, thereby demonstrating a substantial improvement over the monolithic baseline. It is noteworthy that the agent-based architecture yielded the most substantial enhancements in reasoning logic and medical accuracy. The findings indicate that mimetic, agent-based collaboration provides a scalable, interpretable, and clinically robust paradigm for automated decision support in oncology.
Authors: Jinwu Chen, Qidie Wu, Bin Li, Lin Ma, Xin Si, Yang Hu, Shouyi Yin, Jun Yang
Abstract: Optimizing CUDA kernels is a challenging and labor-intensive task, given the need for hardware-software co-design expertise and the proprietary nature of high-performance kernel libraries. While recent large language models (LLMs) combined with evolutionary algorithms show promise in automatic kernel optimization, existing approaches often fall short in performance due to their suboptimal agent designs and mismatched evolution representations. This work identifies these mismatches and proposes cuPilot, a strategy-coordinated multi-agent framework that introduces strategy as an intermediate semantic representation for kernel evolution. Key contributions include a strategy-coordinated evolution algorithm, roofline-guided prompting, and strategy-level population initialization. Experimental results show that the generated kernels by cuPilot achieve an average speed up of 3.09$\times$ over PyTorch on a benchmark of 100 kernels. On the GEMM tasks, cuPilot showcases sophisticated optimizations and achieves high utilization of critical hardware units. The generated kernels are open-sourced at https://github.com/champloo2878/cuPilot-Kernels.git.
Authors: Ander Alvarez, Alessandro Genuardi, Nilotpal Sinha, Antonio Tiene, Mikail Okyay, Bakbergen Ryskulov, David Montero, Samuel Mugel, Rom\'an Or\'us
Abstract: Deploying local large language models and vision-language models on edge devices requires balancing accuracy with constrained computational and energy budgets. Although graphics processors dominate modern artificial-intelligence deployment, most consumer hardware--including laptops, desktops, industrial controllers, and embedded systems--relies on central processing units. Despite this, the computational laws governing central-processing-unit-only inference for local language and vision-language workloads remain largely unexplored. We systematically benchmark large language and vision-language models on two representative central-processing-unit tiers widely used for local inference: a MacBook Pro M2, reflecting mainstream laptop-class deployment, and a Raspberry Pi 5, representing constrained, low-power embedded settings. Using a unified methodology based on continuous sampling of processor and memory usage together with area-under-curve integration, we characterize how computational load scales with input text length for language models and with image resolution for vision-language models. We uncover two empirical scaling laws: (1) computational cost for language-model inference scales approximately linearly with token length; and (2) vision-language models exhibit a preprocessing-driven "resolution knee", where compute remains constant above an internal resolution clamp and decreases sharply below it. Beyond these laws, we show that quantum-inspired compression reduces processor and memory usage by up to 71.9% and energy consumption by up to 62%, while preserving or improving semantic accuracy. These results provide a systematic quantification of multimodal central-processing-unit-only scaling for local language and vision-language workloads, and they identify model compression and input-resolution preprocessing as effective, low-cost levers for sustainable edge inference.
Authors: Miru Hong, Minho Lee, Geonhee Jo, Jae-Hee So, Pascal Bauer, Sang-Ki Ko
Abstract: Transfers play a pivotal role in shaping a football club's success, yet forecasting whether a transfer will succeed remains difficult due to the strong context-dependence of on-field performance. Existing evaluation practices often rely on static summary statistics or post-hoc value models, which fail to capture how a player's contribution adapts to a new tactical environment or different teammates. To address this gap, we introduce EventGPT, a player-conditioned, value-aware next-event prediction model built on a GPT-style autoregressive transformer. Our model treats match play as a sequence of discrete tokens, jointly learning to predict the next on-ball action's type, location, timing, and its estimated residual On-Ball Value (rOBV) based on the preceding context and player identity. A key contribution of this framework is the ability to perform counterfactual simulations. By substituting learned player embeddings into new event sequences, we can simulate how a player's behavioral distribution and value profile would change when placed in a different team or tactical structure. Evaluated on five seasons of Premier League event data, EventGPT outperforms existing sequence-based baselines in next-event prediction accuracy and spatial precision. Furthermore, we demonstrate the model's practical utility for transfer analysis through case studies-such as comparing striker performance across different systems and identifying stylistic replacements for specific roles-showing that our approach provides a principled method for evaluating transfer fit.
Authors: Zhengmian Hu
Abstract: Can artificial intelligence discover, from raw experience and without human supervision, concepts that humans have discovered? One challenge is that human concepts themselves are fluid: conceptual boundaries can shift, split, and merge as inquiry progresses (e.g., Pluto is no longer considered a planet). To make progress, we need a definition of "concept" that is not merely a dictionary label, but a structure that can be revised, compared, and aligned across agents. We propose an algorithmic-information viewpoint that treats a concept as an information object defined only through its structural relation to an agent's total experience. The core constraint is determination: a set of parts forms a reversible consistency relation if any missing part is recoverable from the others (up to the standard logarithmic slack in Kolmogorov-style identities). This reversibility prevents "concepts" from floating free of experience and turns concept existence into a checkable structural claim. To judge whether a decomposition is natural, we define excess information, measuring the redundancy overhead introduced by splitting experience into multiple separately described parts. On top of these definitions, we formulate dialectics as an optimization dynamics: as new patches of information appear (or become contested), competing concepts bid to explain them via shorter conditional descriptions, driving systematic expansion, contraction, splitting, and merging. Finally, we formalize low-cost concept transmission and multi-agent alignment using small grounds/seeds that allow another agent to reconstruct the same concept under a shared protocol, making communication a concrete compute-bits trade-off.
Authors: Jian Yan
Abstract: This paper proposes the External Hippocampus framework, which models language model reasoning from a cognitive dynamics perspective as the flow of information energy in semantic space. Unlike traditional weight-space optimization methods, this framework constructs topological cognitive maps through dimensionality reduction projection, enabling precise navigation and intervention of energy flow at test time while avoiding substantial computational requirements and demonstrating predictable intervention patterns. The method effectively addresses the cognitive deadlock problem in multi-step reasoning for small models. Experiments on models <=7B parameters show: map-guided methods achieve 81.20% accuracy on 500 challenging problems (relative baseline +16.80%), reduce reasoning time by >= 15x, with key findings revealing that reasoning stagnation manifests as "Cognitive Vortex" and low-entropy potential wells, while temperature perturbations effectively restart energy flow. The framework requires no additional training, possesses autonomous growth capability, and provides an efficient and controllable topological-aware solution for small model reasoning.
Authors: Yosuke Taniuchi, Chie Hieida, Atsushi Noritake, Kazushi Ikeda, Masaki Isoda
Abstract: Social comparison$\unicode{x2014}$the process of evaluating one's rewards relative to others$\unicode{x2014}$plays a fundamental role in primate social cognition. However, it remains unknown from a computational perspective how information about others' rewards affects the evaluation of one's own reward. With a constructive approach, this study examines whether monkeys merely recognize objective reward differences or, instead, infer others' subjective reward valuations. We developed three computational models with varying degrees of social information processing: an Internal Prediction Model (IPM), which infers the partner's subjective values; a No Comparison Model (NCM), which disregards partner information; and an External Comparison Model (ECM), which directly incorporates the partner's objective rewards. To test model performance, we used a multi-layered, multimodal latent Dirichlet allocation. We trained the models on a dataset containing the behavior of a pair of monkeys, their rewards, and the conditioned stimuli. Then, we evaluated the models' ability to classify subjective values across pre-defined experimental conditions. The ECM achieved the highest classification score in the Rand Index (0.88 vs. 0.79 for the IPM) under our settings, suggesting that social comparison relies on objective reward differences rather than inferences about subjective states.
Authors: Pouriya Khalilian, Sara Azizi, Mohammad Hossein Amiri, Javad T. Firouzjaee
Abstract: This study analyzes the dynamic interactions among the NASDAQ index, crude oil, gold, and the US dollar using a reduced-order modeling approach. Time-delay embedding and principal component analysis are employed to encode high-dimensional financial dynamics, followed by linear regression in the reduced space. Correlation and lagged regression analyses reveal heterogeneous cross-asset dependencies. Model performance, evaluated using the coefficient of determination ($R^2$), demonstrates that a limited number of principal components is sufficient to capture the dominant dynamics of each asset, with varying complexity across markets.
Authors: Kichang Lee, Pei Zhang, Songkuk Kim, JeongGil Ko
Abstract: Federated learning is inherently hampered by data heterogeneity: non-i.i.d. training data over local clients. We propose a novel model training approach for federated learning, FLex&Chill, which exploits the Logit Chilling method. Through extensive evaluations, we demonstrate that, in the presence of non-i.i.d. data characteristics inherent in federated learning systems, this approach can expedite model convergence and improve inference accuracy. Quantitatively, from our experiments, we observe up to 6X improvement in the global federated learning model convergence time, and up to 3.37% improvement in inference accuracy.
Authors: Minho Lee, Yun Young Choi, Sun Woo Park, Seunghwan Lee, Joohwan Ko, Jaeyoung Hong
Abstract: Graph Neural Networks (GNNs) and Transformer-based models have been increasingly adopted to learn the complex vector representations of spatio-temporal graphs, capturing intricate spatio-temporal dependencies crucial for applications such as traffic datasets. Although many existing methods utilize multi-head attention mechanisms and message-passing neural networks (MPNNs) to capture both spatial and temporal relations, these approaches encode temporal and spatial relations independently, and reflect the graph's topological characteristics in a limited manner. In this work, we introduce the Cycle to Mixer (Cy2Mixer), a novel spatio-temporal GNN based on topological non-trivial invariants of spatio-temporal graphs with gated multi-layer perceptrons (gMLP). The Cy2Mixer is composed of three blocks based on MLPs: A temporal block for capturing temporal properties, a message-passing block for encapsulating spatial information, and a cycle message-passing block for enriching topological information through cyclic subgraphs. We bolster the effectiveness of Cy2Mixer with mathematical evidence emphasizing that our cycle message-passing block is capable of offering differentiated information to the deep learning model compared to the message-passing block. Furthermore, empirical evaluations substantiate the efficacy of the Cy2Mixer, demonstrating state-of-the-art performances across various spatio-temporal benchmark datasets. The source code is available at https://github.com/leemingo/cy2mixer.
Authors: Jingxi Xu, Yinsen Jia, Dongxiao Yang, Patrick Meng, Xinyue Zhu, Zihan Guo, Shuran Song, Matei Ciocarlie
Abstract: We introduce GEOTACT, the first robotic system capable of grasping and retrieving objects of potentially unknown shapes buried in a granular environment. While important in many applications, ranging from mining and exploration to search and rescue, this type of interaction with granular media is difficult due to the uncertainty stemming from visual occlusion and noisy contact signals. To address these challenges, we use a learning method relying exclusively on touch feedback, trained end-to-end with simulated sensor noise. We show that our problem formulation leads to the natural emergence of learned pushing behaviors that the manipulator uses to reduce uncertainty and funnel the object to a stable grasp despite spurious and noisy tactile readings. We introduce a training curriculum that bootstraps learning in simulated granular environments, enabling zero-shot transfer to real hardware. Despite being trained only on seven objects with primitive shapes, our method is shown to successfully retrieve 35 different objects, including rigid, deformable, and articulated objects with complex shapes. Videos and additional information can be found at https://jxu.ai/geotact.
URLs: https://jxu.ai/geotact.
Authors: Mehryar Abbasi, Hadi Hadizadeh, Parvaneh Saeedi
Abstract: This paper presents a novel approach for unsupervised video summarization using reinforcement learning (RL), addressing limitations like unstable adversarial training and reliance on heuristic-based reward functions. The method operates on the principle that reconstruction fidelity serves as a proxy for informativeness, correlating summary quality with reconstruction ability. The summarizer model assigns importance scores to frames to generate the final summary. For training, RL is coupled with a unique reward generation pipeline that incentivizes improved reconstructions. This pipeline uses a generator model to reconstruct the full video from the selected summary frames; the similarity between the original and reconstructed video provides the reward signal. The generator itself is pre-trained self-supervisedly to reconstruct randomly masked frames. This two-stage training process enhances stability compared to adversarial architectures. Experimental results show strong alignment with human judgments and promising F-scores, validating the reconstruction objective.
Authors: Arian Askari, Chuan Meng, Mohammad Aliannejadi, Zhaochun Ren, Evangelos Kanoulas, Suzan Verberne
Abstract: Existing generative retrieval (GR) methods rely on training-based indexing, which fine-tunes a model to memorise associations between queries and the document identifiers (docids) of relevant documents. Training-based indexing suffers from high training costs, under-utilisation of pre-trained knowledge in large language models (LLMs), and limited adaptability to dynamic document corpora. To address the issues, we propose a few-shot indexing-based GR framework (Few-Shot GR). It has a few-shot indexing process without any training, where we prompt an LLM to generate docids for all documents in a corpus, ultimately creating a docid bank for the entire corpus. During retrieval, we feed a query to the same LLM and constrain it to generate a docid within the docid bank created during indexing, and then map the generated docid back to its corresponding document. Moreover, we devise few-shot indexing with one-to-many mapping to further enhance Few-Shot GR. Experiments show that Few-Shot GR achieves superior performance to state-of-the-art GR methods requiring heavy training.
Authors: Eoin M. Kenny, Akshay Dharmavaram, Sang Uk Lee, Tung Phan-Minh, Shreyas Rajesh, Yunqing Hu, Laura Major, Momchil S. Tomov, Julie A. Shah
Abstract: Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. The opacity of such black-box planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with potentially catastrophic consequences. While research into interpreting these systems has surged, most of it is confined to simulations or toy setups due to the difficulty of real-world deployment, leaving the practical utility of such techniques unknown. Here, we introduce the Concept-Wrapper Network (CW-Net), a method for explaining the behavior of machine-learning-based planners by grounding their reasoning in human-interpretable concepts. We deploy CW-Net on a real self-driving car and show that the resulting explanations improve the human driver's mental model of the car, allowing them to better predict its behavior. To our knowledge, this is the first demonstration that explainable deep learning integrated into self-driving cars can be both understandable and useful in a realistic deployment setting. CW-Net accomplishes this level of intelligibility while providing explanations which are causally faithful and do not sacrifice driving performance. Overall, our study establishes a general pathway to interpretability for autonomous agents by way of concept-based explanations, which could help make them more transparent and safe.
Authors: Boyang Zhang, Daning Cheng, Yunquan Zhang, Jiake Tian, Jing Li, Fangming Liu
Abstract: Post-Training Quantization (PTQ) converts pre-trained Full-Precision (FP) models into quantized versions without training. While existing methods reduce size and computational costs, they also significantly degrade performance and quantization efficiency at extremely low settings due to quantization noise. We introduce a deep model series expansion framework to address this issue, enabling rapid and accurate approximation of unquantized models without calibration sets or fine-tuning. This is the first use of series expansion for neural network quantization. Specifically, our method expands the FP model into multiple low-bit basis models. To ensure accurate quantization, we develop low-bit basis model expansions at different granularities (tensor, layer, model), and theoretically confirm their convergence to the dense model, thus restoring FP model accuracy. Additionally, we design AbelianAdd/Mul operations between isomorphic models in the low-bit expansion, forming an Abelian group to ensure operation parallelism and commutativity. The experiments show that our algorithm achieves state-of-the-art performance in low-bit settings; for example, 4-bit quantization of ResNet-50 surpasses the original accuracy, reaching 77.03%. The code will be made public.
Authors: Boyang Zhang, Daning Cheng, Yunquan Zhang, Fangming Liu, Jiake Tian
Abstract: Low-rank factorization is a popular model compression technique that minimizes the error $\delta$ between approximated and original weight matrices. Despite achieving performances close to the original models when $\delta$ is optimized, a performance discrepancy remains due to the separate optimization processes for low-rank factorization and model performance, resulting in unavoidable losses. We address this issue by introducing a novel joint optimization strategy for lossless low-rank weight factorization, which, for the first time, enhances the model's performance beyond the original. Our approach begins with a theoretical analysis of the relationship between low-rank factorization and model optimization objectives, establishing a precise perturbation range for matrix factorization errors on model performance. This challenge is then reformulated as a numerical rank deficiency problem with inequality constraints and develop a joint objective that simultaneously addresses factorization error and model performance. Based on the above analysis, we propose two optimization algorithms: \textbf{a lossless optimization algorithm} that maximizes model accuracy while ensuring compression, and \textbf{a compact optimization algorithm} that minimizes model size while preserving performance. These algorithms do not require fine-tuning and can directly compress numerous deep models to achieve lossless results. Our methods demonstrate robust efficacy across various vision and language tasks. For example, the compressed model reduced by 70\% on ResNext50 outperforms the original. Our code will be made public.
Authors: Boyang Zhang, Daning Cheng, Yunquan Zhang, Fangming Liu, Wenguang Chen
Abstract: This work focus on how to stabilize and lossless model compression, aiming to reduce model complexity and enhance efficiency without sacrificing performance due to compression errors. A key challenge is effectively leveraging compression errors and defining the boundaries for lossless compression to minimize model loss. i.e., compression for better. Currently, there is no systematic approach to determining this error boundary or understanding its specific impact on model performance. We propose a general \textbf{L}oss\textbf{L}ess \textbf{C}ompression theoretical framework (\textbf{LLC}), which further delineates the compression neighborhood and higher-order analysis boundaries through the total differential, thereby specifying the error range within which a model can be compressed without loss. To verify the effectiveness of LLC, we apply various compression techniques, including quantization and decomposition. Specifically, for quantization, we reformulate the classic quantization search problem as a grouped knapsack problem within the lossless neighborhood, achieving lossless quantization while improving computational efficiency. For decomposition, LLC addresses the approximation problem under low-rank constraints, automatically determining the rank for each layer and producing lossless low-rank models. We conduct extensive experiments on multiple neural network architectures on different datasets. The results show that without fancy tricks, LLC can effectively achieve lossless model compression. Our code will be made publicly.
Authors: Sofiane Bouaziz, Adel Hafiane, Raphael Canals, Rachid Nedjai
Abstract: Land Surface Temperature (LST) plays a key role in climate monitoring, urban heat assessment, and land-atmosphere interactions. However, current thermal infrared satellite sensors cannot simultaneously achieve high spatial and temporal resolution. Spatio-temporal fusion (STF) techniques address this limitation by combining complementary satellite data, one with high spatial but low temporal resolution, and another with high temporal but low spatial resolution. Existing STF techniques, from classical models to modern deep learning (DL) architectures, were primarily developed for surface reflectance (SR). Their application to thermal data remains limited and often overlooks LST-specific spatial and temporal variability. This study provides a focused review of DL-based STF methods for LST. We present a formal mathematical definition of the thermal fusion task, propose a refined taxonomy of relevant DL methods, and analyze the modifications required when adapting SR-oriented models to LST. To support reproducibility and benchmarking, we introduce a new dataset comprising 51 Terra MODIS-Landsat LST pairs from 2013 to 2024, and evaluate representative models to explore their behavior on thermal data. The analysis highlights performance gaps, architecture sensitivities, and open research challenges. The dataset and accompanying resources are publicly available at https://github.com/Sofianebouaziz1/STF-LST.
Authors: Bo Lv, Chen Tang, Zifan Zheng, Bohao Yang, Kun Zhao, Ning Liao, Xiaoxing Wang, Feiyu Xiong, Zhiyu Li, Nayu Liu, Jingchi Jiang
Abstract: Traditional Mixture-of-Experts (MoE) networks benefit from utilizing multiple smaller expert models as opposed to a single large network. However, these experts typically operate independently, leaving a question open about whether interconnecting these models could enhance the performance of MoE networks. In response, we introduce GRAPHMOE, a novel method aimed at augmenting the cognitive depth of language models via a self-rethinking mechanism constructed on Pseudo GraphMoE networks. GRAPHMOE employs a recurrent routing strategy to simulate iterative thinking steps, thereby facilitating the flow of information among expert nodes. We implement the GRAPHMOE architecture using Low-Rank Adaptation techniques (LoRA) and conduct extensive experiments on various benchmark datasets. The experimental results reveal that GRAPHMOE outperforms other LoRA based models, achieving state-of-the-art (SOTA) performance. Additionally, this study explores a novel recurrent routing strategy that may inspire further advancements in enhancing the reasoning capabilities of language models.
Authors: Christoph Gebhardt, Robin Willardt, Seyedmorteza Sadat, Chih-Wei Ning, Andreas Brombach, Jie Song, Otmar Hilliges, Christian Holz
Abstract: Internet overuse is a widespread phenomenon in today's digital society. Existing interventions, such as time limits or grayscaling, often rely on restrictive controls that provoke psychological reactance and are frequently circumvented. Building on prior work showing that emotional responses mediate the relationship between content consumption and online engagement, we investigate whether regulating the emotional impact of images can reduce online use in a non-coercive manner. We introduce and systematically analyze three regressor-guided image-editing approaches: (i) global optimization of emotion-related image attributes, (ii) optimization in a style latent space, and (iii) a diffusion-based method using classifier and classifier-free guidance. While the first two approaches modify low-level visual features (e.g., contrast, color), the diffusion-based method enables higher-level changes (e.g., adjusting clothing, facial features). Results from a controlled image-rating study and a social media experiment show that diffusion-based edits balance emotional responses and are associated with lower usage duration while preserving visual quality.
Authors: Zheng Li, Zhipeng Bao, Haoming Meng, Haotian Shi, Qianwen Li, Handong Yao, Xiaopeng Li
Abstract: This paper presents the development of a comprehensive dataset capturing interactions between Autonomous Vehicles (AVs) and traffic control devices, specifically traffic lights and stop signs. Derived from the Waymo Motion dataset, our work addresses a critical gap in the existing literature by providing real-world trajectory data on how AVs navigate these traffic control devices. We propose a methodology for identifying and extracting relevant interaction trajectory data from the Waymo Motion dataset, incorporating over 37,000 instances with traffic lights and 44,000 with stop signs. Our methodology includes defining rules to identify various interaction types, extracting trajectory data, and applying a wavelet-based denoising method to smooth the acceleration and speed profiles and eliminate anomalous values, thereby enhancing the trajectory quality. Quality assessment metrics indicate that trajectories obtained in this study have anomaly proportions in acceleration and jerk profiles reduced to near-zero levels across all interaction categories. By making this dataset publicly available, we aim to address the current gap in datasets containing AV interaction behaviors with traffic lights and signs. Based on the organized and published dataset, we can gain a more in-depth understanding of AVs' behavior when interacting with traffic lights and signs. This will facilitate research on AV integration into existing transportation infrastructures and networks, supporting the development of more accurate behavioral models and simulation tools.
Authors: Boyang Zhang, Daning Cheng, Yunquan Zhang, Meiqi Tu, Fangming Liu, Jiake Tian
Abstract: The exponential growth in parameter size and computational complexity of deep models poses significant challenges for efficient deployment. The core problem of existing compression methods is that different layers of the model have significant differences in their tolerance to compression levels. For instance, the first layer of a model can typically sustain a higher compression level compared to the last layer without compromising performance. Thus, the key challenge lies in how to allocate compression levels across layers in a way that minimizes performance loss while maximizing parameter reduction. To address this challenge, we propose a Compression Error Theory (CET) framework, designed to determine the optimal compression level for each layer. Taking quantization as an example, CET leverages differential expansion and algebraic geometry to reconstruct the quadratic form of quantization error as ellipsoids and hyperbolic paraboloids, and utilizes their geometric structures to define an error subspace. To identify the error subspace with minimal performance loss, by performing orthogonal decomposition of the geometric space, CET transforms the optimization process of the error subspace into a complementary problem. The final theoretical analysis shows that constructing the quantization subspace along the major axis results in minimal performance degradation. Through experimental verification of the theory, CET can greatly retain performance while compressing. Specifically, on the ResNet-34 model, CET achieves nearly 11$\times$ parameter compression while even surpassing performance comparable to the original model.
Authors: Yaohua Liu, Xinyuan Song, Yunfu Deng, Yifan Xie, Binkai Ou, Yan Zhong
Abstract: Vision-and-Language Navigation (VLN) requires an embodied agent to traverse complex environments by following natural language instructions, demanding accurate alignment between visual observations and linguistic guidance. Despite recent progress, existing methods typically encode visual and directional cues in a coupled manner, and process instructions without explicitly extracting navigation-critical semantics, which often leads to imprecise spatial reasoning and suboptimal cross-modal alignment. To address these challenges, we propose a fine-grained instruction-guided graph reasoning framework (OIKG) that enhances both spatial representation and instruction understanding during navigation. Specifically, an observation-graph interaction mechanism is introduced to disentangle angular and visual cues while strengthening directed edge representations through geometric embedding, enabling more reliable spatial reasoning within the navigation graph. In addition, a fine-grained instruction guidance module is designed to explicitly extract and leverage location-specific and object-centric information from language instructions, facilitating more precise cross-modal alignment between linguistic semantics and navigable trajectories. By jointly integrating structured graph reasoning with instruction-critical semantic cues, the proposed approach significantly improves the agent's ability to follow complex navigation instructions. Extensive experiments on the R2R and RxR benchmarks demonstrate that our method consistently achieves state-of-the-art performance across multiple evaluation metrics, validating the effectiveness of fine-grained instruction-guided graph reasoning for vision-and-language navigation.
Authors: Tianyang Zhou, Ziyi Zhang, Haowen Lin, Somesh Jha, Mihai Christodorescu, Kirill Levchenko, Varun Chandrasekaran
Abstract: Translating software written in C to Rust has significant benefits in improving memory safety. However, manual translation is cumbersome, error-prone, and often produces unidiomatic code. Large language models (LLMs) have demonstrated promise in producing idiomatic translations, but offer no correctness guarantees. We propose SACTOR, an LLM-driven C-to-Rust translation tool that employs a two-step process: an initial "unidiomatic" translation to preserve semantics, followed by an "idiomatic" refinement to align with Rust standards. To validate correctness of our function-wise incremental translation that mixes C and Rust, we use end-to-end testing via the foreign function interface. We evaluate SACTOR on 200 programs from two public datasets and on two more real-world scenarios (a 50-sample subset of CRust-Bench and the libogg library), comparing multiple LLMs. Across datasets, SACTOR delivers high end-to-end correctness and produces safe, idiomatic Rust with up to 7 times fewer Clippy warnings; On CRust-Bench, SACTOR achieves an average (across samples) of 85% unidiomatic and 52% idiomatic success, and on libogg it attains full unidiomatic and up to 78% idiomatic coverage on GPT-5.
Authors: Kuofeng Gao, Yufei Zhu, Yiming Li, Jiawang Bai, Yong Yang, Zhifeng Li, Shu-Tao Xia
Abstract: Text-to-image (T2I) diffusion models enable high-quality image generation conditioned on textual prompts. However, fine-tuning these pre-trained models for personalization raises concerns about unauthorized dataset usage. To address this issue, dataset ownership verification (DOV) has recently been proposed, which embeds watermarks into fine-tuning datasets via backdoor techniques. These watermarks remain dormant on benign samples but produce owner-specified outputs when triggered. Despite its promise, the robustness of DOV against copyright evasion attacks (CEA) remains unexplored. In this paper, we investigate how adversaries can circumvent these mechanisms, enabling models trained on watermarked datasets to bypass ownership verification. We begin by analyzing the limitations of potential attacks achieved by backdoor removal, including TPD and T2IShield. In practice, TPD suffers from inconsistent effectiveness due to randomness, while T2IShield fails when watermarks are embedded as local image patches. To this end, we introduce CEAT2I, the first CEA specifically targeting DOV in T2I diffusion models. CEAT2I consists of three stages: (1) motivated by the observation that T2I models converge faster on watermarked samples with respect to intermediate features rather than training loss, we reliably detect watermarked samples; (2) we iteratively ablate tokens from the prompts of detected samples and monitor feature shifts to identify trigger tokens; and (3) we apply a closed-form concept erasure method to remove the injected watermarks. Extensive experiments demonstrate that CEAT2I effectively evades state-of-the-art DOV mechanisms while preserving model performance. The code is available at https://github.com/csyufei/CEAT2I.
Authors: Minsu Kim, Seong-Hyeon Hwang, Steven Euijong Whang
Abstract: In the context of continual learning, acquiring new knowledge while maintaining previous knowledge presents a significant challenge. Existing methods often use experience replay techniques that store a small portion of previous task data for training. In experience replay approaches, data augmentation has emerged as a promising strategy to further improve the model performance by mixing limited previous task data with sufficient current task data. However, we theoretically and empirically analyze that training with mixed samples from random sample pairs may harm the knowledge of previous tasks and cause greater catastrophic forgetting. We then propose GradMix, a robust data augmentation method specifically designed for mitigating catastrophic forgetting in class-incremental learning. GradMix performs gradient-based selective mixup using a class-based criterion that mixes only samples from helpful class pairs and not from detrimental class pairs for reducing catastrophic forgetting. Our experiments on various real datasets show that GradMix outperforms data augmentation baselines in accuracy by minimizing the forgetting of previous knowledge.
Authors: Chenggang Zhao, Chengqi Deng, Chong Ruan, Damai Dai, Huazuo Gao, Jiashi Li, Liyue Zhang, Panpan Huang, Shangyan Zhou, Shirong Ma, Wenfeng Liang, Ying He, Yuqing Wang, Yuxuan Liu, Y. X. Wei
Abstract: The rapid scaling of large language models (LLMs) has unveiled critical limitations in current hardware architectures, including constraints in memory capacity, computational efficiency, and interconnection bandwidth. DeepSeek-V3, trained on 2,048 NVIDIA H800 GPUs, demonstrates how hardware-aware model co-design can effectively address these challenges, enabling cost-efficient training and inference at scale. This paper presents an in-depth analysis of the DeepSeek-V3/R1 model architecture and its AI infrastructure, highlighting key innovations such as Multi-head Latent Attention (MLA) for enhanced memory efficiency, Mixture of Experts (MoE) architectures for optimized computation-communication trade-offs, FP8 mixed-precision training to unlock the full potential of hardware capabilities, and a Multi-Plane Network Topology to minimize cluster-level network overhead. Building on the hardware bottlenecks encountered during DeepSeek-V3's development, we engage in a broader discussion with academic and industry peers on potential future hardware directions, including precise low-precision computation units, scale-up and scale-out convergence, and innovations in low-latency communication fabrics. These insights underscore the critical role of hardware and model co-design in meeting the escalating demands of AI workloads, offering a practical blueprint for innovation in next-generation AI systems.
Authors: Cehao Yang, Xueyuan Lin, Xiaojun Wu, Chengjin Xu, Xuhui Jiang, Honghao Liu, Hui Xiong, Jian Guo
Abstract: A practical approach to activate long chain-of-thoughts reasoning ability in pre-trained large language models is to perform supervised fine-tuning on instruction datasets synthesized by strong Large Reasoning Models such as DeepSeek-R1, offering a cost-effective alternative to reinforcement learning. However, large-scale instruction sets with more than 100k samples incur significant training overhead, while effective strategies for automatic long-CoT instruction selection still remain unexplored. In this work, we propose Select2Reason, a novel and efficient instruction-tuning data selection framework for long-CoT reasoning. From the perspective of emergence of rethinking behaviors like self-correction and backtracking, we investigate common metrics that may determine the quality of long-CoT reasoning instructions. Select2Reason leverages a quantifier to estimate difficulty of question and jointly incorporates a reasoning trace length-based heuristic through a weighted scheme for ranking to prioritize high-utility examples. Empirical results on OpenR1-Math-220k demonstrate that fine-tuning LLM on only 10% of the data selected by Select2Reason achieves performance competitive with or superior to full-data tuning and open-source baseline OpenR1-Qwen-7B across three competition-level and six comprehensive mathematical benchmarks. Further experiments highlight the scalability in varying data size, efficiency during inference, and its adaptability to other instruction pools with minimal cost.
Authors: Philip Heejun Lee
Abstract: Deep sequence models typically degrade in accuracy when test sequences significantly exceed their training lengths, yet many critical tasks--such as algorithmic reasoning, multi-step arithmetic, and compositional generalization--require robust length extrapolation. We introduce PRISM, a Probabilistic Relative-position Implicit Superposition Model, a novel positional encoding mechanism that enables Transformers to extrapolate accurately up to 10x beyond their training length. PRISM learns continuous relative positions through a differentiable histogram-filter update, preserving position uncertainty via a probabilistic superposition rather than conventional deterministic embeddings. Empirically, PRISM achieves state-of-the-art length extrapolation, successfully generalizing to previously intractable sequence lengths across algorithmic benchmarks--including arithmetic (addition, multiplication), SCAN compositionality tasks, and complex copy variants derived from DeepMind's recent datasets. Our analysis demonstrates that PRISM's stochastic positional encoding maintains sharp and interpretable internal states, providing a theoretical basis for reliable length generalization. These results advance the goal of neural sequence models that remain algorithmically robust at lengths far exceeding their training horizon.
Authors: Yihan Xie, Sijing Li, Tianwei Lin, Zhuonan Wang, Chenglin Yang, Yu Zhong, Wenjie Yan, Wenqiao Zhang, Xiaogang Guo, Jun Xiao, Yueting Zhuang, Beng Chin Ooi
Abstract: Although electrocardiograms (ECG) play a dominant role in cardiovascular diagnosis and treatment, their intrinsic data forms and representational patterns pose significant challenges for medical multimodal large language models (Med-MLLMs) in achieving cross-modal semantic alignment. To address this gap, we propose Heartcare Suite, a unified ECG suite designed for dual signal-image modeling and understanding. (i) Heartcare-400K: We build a finegrained ECG instruction dataset on top of our data pipeline engine--HeartAgent--by integrating 12,170 high quality clinical ECG reports from top hospitals with open-source data; (ii) Heartcare-Bench: a systematic benchmark assessing performance of models in multi-perspective ECG understanding and cross-modal generalization, providing guidance for optimizing ECG comprehension models; (iii) HeartcareGPT: built upon a structure-aware discrete tokenizer Beat, we propose the DSPA (Dual Stream Projection Alignment) paradigm--a dual encoder projection alignment mechanism enabling joint optimizing and modeling native ECG signal-image within a shared feature space. Heartcare achieves consistent improvements across diverse ECG understanding tasks, validating both the effectiveness of the unified modeling paradigm and the necessity of a high-quality data pipeline, and establishing a methodological foundation for extending Med-MLLMs toward physiological signal domains. Our project is available at https://github.com/DCDmllm/Heartcare-Suite .
Authors: Griffin Pitts, Sanaz Motamedi
Abstract: As AI chatbots become integrated in education, students are turning to these systems for guidance, feedback, and information. However, the anthropomorphic characteristics of these chatbots create ambiguity over whether students develop trust in them in ways similar to trusting a human peer or instructor (human-like trust, often linked to interpersonal trust models) or in ways similar to trusting a conventional technology (system-like trust, often linked to technology trust models). This ambiguity presents theoretical challenges, as interpersonal trust models may inappropriately ascribe human intentionality and morality to AI, while technology trust models were developed for non-social systems, leaving their applicability to conversational, human-like agents unclear. To address this gap, we examine how these two forms of trust, human-like and system-like, comparatively influence students' perceptions of an AI chatbot, specifically perceived enjoyment, trusting intention, behavioral intention to use, and perceived usefulness. Using partial least squares structural equation modeling, we found that both forms of trust significantly influenced student perceptions, though with varied effects. Human-like trust was the stronger predictor of trusting intention, whereas system-like trust more strongly influenced behavioral intention and perceived usefulness; both had similar effects on perceived enjoyment. The results suggest that interactions with AI chatbots give rise to a distinct form of trust, human-AI trust, that differs from human-human and human-technology models, highlighting the need for new theoretical frameworks in this domain. In addition, the study offers practical insights for fostering appropriately calibrated trust, which is critical for the effective adoption and pedagogical impact of AI in education.
Authors: Danyang Zhang, Junhao Song, Ziqian Bi, Xinyuan Song, Yingfang Yuan, Tianyang Wang, Joe Yeong, Junfeng Hao
Abstract: This paper presents a comprehensive review of the Mixture-of-Experts (MoE) architecture in large language models, highlighting its ability to significantly enhance model performance while maintaining minimal computational overhead. Through a systematic analysis spanning theoretical foundations, core architectural designs, and large language model (LLM) applications, we examine expert gating and routing mechanisms, hierarchical and sparse MoE configurations, meta-learning approaches, multimodal and multitask learning scenarios, real-world deployment cases, and recent advances and challenges in deep learning. Our analysis identifies key advantages of MoE, including superior model capacity compared to equivalent Bayesian approaches, improved task-specific performance, and the ability to scale model capacity efficiently. We also underscore the importance of ensuring expert diversity, accurate calibration, and reliable inference aggregation, as these are essential for maximizing the effectiveness of MoE architectures. Finally, this review outlines current research limitations, open challenges, and promising future directions, providing a foundation for continued innovation in MoE architecture and its applications.
Authors: Henri Arno, Thomas Demeester
Abstract: We study how to learn effective treatment policies from multimodal electronic health records (EHRs) that consist of tabular data and clinical text. These policies can help physicians make better treatment decisions and allocate healthcare resources more efficiently. Causal policy learning methods prioritize patients with the largest expected treatment benefit. Yet, existing estimators assume tabular covariates that satisfy strong causal assumptions, which are typically violated in the multimodal setting. As a result, predictive models of baseline risk are commonly used in practice to guide such decisions, as they extend naturally to multimodal data. However, such risk-based policies are not designed to identify which patients benefit most from treatment. We propose an extension of causal policy learning that uses expert-provided annotations during training to supervise treatment effect estimation, while using only multimodal representations as input during inference. We show that the proposed method achieves strong empirical performance across synthetic, semi-synthetic, and real-world EHR datasets, thereby offering practical insights into applying causal machine learning to realistic clinical data.
Authors: Wenjie Li, Siying Gu, Yiming Li, Kangjie Chen, Zhili Chen, Tianwei Zhang, Shu-Tao Xia, Dacheng Tao
Abstract: As AI-generated content increasingly underpins real-world applications, its accompanying security risks, including privacy leakage and copyright infringement, have become growing concerns. In this context, Federated Learning (FL) offers a promising foundation for enhancing trustworthiness by enabling privacy-preserving collaborative learning over proprietary data. However, its practical adoption is critically threatened by backdoor-based model manipulation, where a small number of malicious clients can compromise the system and induce harmful content generation and decision-making. Although various detection methods have been proposed to detect such manipulation, we reveal that they are either disrupted by non-i.i.d. data distributions and random client participation, or misled by out-of-distribution (OOD) prediction bias, both of which are unique challenges in FL scenarios. To address these issues, we introduce a novel proactive detection method dubbed Coward, inspired by our discovery of multi-backdoor collision effects, in which consecutively planted, distinct backdoors significantly suppress earlier ones. Correspondingly, we modify the federated global model by injecting a carefully designed backdoor-collided watermark, implemented via regulated dual-mapping learning on OOD data. This design not only enables an inverted detection paradigm compared to existing proactive methods, thereby naturally counteracting the adverse impact of OOD prediction bias, but also introduces a low-disruptive training intervention that inherently limits the strength of OOD bias, leading to significantly fewer misjudgments. Extensive experiments on benchmark datasets show that Coward achieves state-of-the-art detection performance, effectively alleviates OOD prediction bias, and remains robust against potential adaptive manipulations.
Authors: Tommaso Tosato, Saskia Helbling, Yorguin-Jose Mantilla-Ramos, Mahmood Hegazy, Alberto Tosato, David John Lemay, Irina Rish, Guillaume Dumas
Abstract: Large language models require consistent behavioral patterns for safe deployment, yet there are indications of large variability that may lead to an instable expression of personality traits in these models. We present PERSIST (PERsonality Stability in Synthetic Text), a comprehensive evaluation framework testing 25 open-source models (1B-685B parameters) across 2 million+ responses. Using traditional (BFI, SD3) and novel LLM-adapted personality questionnaires, we systematically vary model size, personas, reasoning modes, question order or paraphrasing, and conversation history. Our findings challenge fundamental assumptions: (1) Question reordering alone can introduce large shifts in personality measurements; (2) Scaling provides limited stability gains: even 400B+ models exhibit standard deviations >0.3 on 5-point scales; (3) Interventions expected to stabilize behavior, such as reasoning and inclusion of conversation history, can paradoxically increase variability; (4) Detailed persona instructions produce mixed effects, with misaligned personas showing significantly higher variability than the helpful assistant baseline; (5) The LLM-adapted questionnaires, despite their improved ecological validity, exhibit instability comparable to human-centric versions. This persistent instability across scales and mitigation strategies suggests that current LLMs lack the architectural foundations for genuine behavioral consistency. For safety-critical applications requiring predictable behavior, these findings indicate that current alignment strategies may be inadequate.
Authors: Xurun Wang, Guangrui Liu, Xinjie Li, Haoyu He, Lin Yao, Zhongyun Hua, Weizhe Zhang
Abstract: Machine learning models are vulnerable to membership inference attack, which can be used to determine whether a given sample appears in the training data. Most existing methods assume the attacker has full access to the features of the target sample. This assumption, however, does not hold in many real-world scenarios where only partial features are available, thereby limiting the applicability of these methods. In this work, we introduce Partial Feature Membership Inference (PFMI), a scenario where the adversary observes only partial features of each sample and aims to infer whether this observed subset was present in the training set. To address this problem, we propose MRAD (Memory-guided Reconstruction and Anomaly Detection), a two-stage attack framework that works in both white-box and black-box settings. In the first stage, MRAD leverages the latent memory of the target model to reconstruct the unknown features of the sample. We observe that when the known features are absent from the training set, the reconstructed sample deviates significantly from the true data distribution. Consequently, in the second stage, we use anomaly detection algorithms to measure the deviation between the reconstructed sample and the training data distribution, thereby determining whether the known features belong to a member of the training set. Empirical results demonstrate that MRAD is effective across various datasets, and maintains compatibility with off-the-shelf anomaly detection techniques. For example, on STL-10, our attack exceeds an AUC of around 0.75 even with 60% of the missing features.
Authors: Zhangyu You, Jiahao Ma, Hongzong Li, Ye-Fan Hu, Jian-Dong Huang
Abstract: Accurate prediction of antibody-binding sites (epitopes) on antigens is crucial for vaccine design, immunodiagnostics, therapeutic antibody development, antibody engineering, research into autoimmune and allergic diseases, and advancing our understanding of immune responses. Despite in silico methods that have been proposed to predict both linear (continuous) and conformational (discontinuous) epitopes, they consistently underperform in predicting conformational epitopes. In this work, we propose Conformer-based models trained separately on AlphaFold-predicted structures and experimentally determined structures, leveraging convolutional neural networks (CNNs) to extract local features and Transformers to capture long-range dependencies within antigen sequences. Ablation studies demonstrate that CNN enhances the prediction of linear epitopes, and the Transformer module improves the prediction of conformational epitopes. Experimental results show that our model outperforms existing baselines in terms of MCC, ROC-AUC, PR-AUC, and F1 scores on both linear and conformational epitopes.
Authors: Kichang Lee, Songkuk Kim, JaeYeon Park, JeongGil Ko
Abstract: On-device machine learning is often constrained by limited storage, particularly in continuous data collection scenarios. This paper presents an empirical study on storage-aware learning, focusing on the trade-off between data quantity and quality via compression. We demonstrate that naive strategies, such as uniform data dropping or one-size-fits-all compression, are suboptimal. Our findings further reveal that data samples exhibit varying sensitivities to compression, supporting the feasibility of a sample-wise adaptive compression strategy. These insights provide a foundation for developing a new class of storage-aware learning systems. The primary contribution of this work is the systematic characterization of this under-explored challenge, offering valuable insights that advance the understanding of storage-aware learning.
Authors: Weiyu Ma, Dongyu Xu, Shu Lin, Haifeng Zhang, Jun Wang
Abstract: We present Adaptive Command, a novel framework integrating large language models (LLMs) with behavior trees for real-time strategic decision-making in StarCraft II. Our system focuses on enhancing human-AI collaboration in complex, dynamic environments through natural language interactions. The framework comprises: (1) an LLM-based strategic advisor, (2) a behavior tree for action execution, and (3) a natural language interface with speech capabilities. User studies demonstrate significant improvements in player decision-making and strategic adaptability, particularly benefiting novice players and those with disabilities. This work contributes to the field of real-time human-AI collaborative decision-making, offering insights applicable beyond RTS games to various complex decision-making scenarios.
Authors: Anand Gopalakrishnan, Robert Csord\'as, J\"urgen Schmidhuber, Michael C. Mozer
Abstract: The attention mechanism in a Transformer architecture matches key to query based on both content -- the what -- and position in a sequence -- the where. We present an analysis indicating that what and where are entangled in the popular RoPE rotary position embedding. This entanglement can impair performance particularly when decisions require independent matches on these two factors. We propose an improvement to RoPE, which we call Polar Coordinate Position Embeddings or PoPE, that eliminates the what-where confound. PoPE is far superior on a diagnostic task requiring indexing solely by position or by content. On autoregressive sequence modeling in music, genomic, and natural language domains, Transformers using PoPE as the positional encoding scheme outperform baselines using RoPE with respect to evaluation loss (perplexity) and downstream task performance. On language modeling, these gains persist across model scale, from 124M to 774M parameters. Crucially, PoPE shows strong zero-shot length extrapolation capabilities compared not only to RoPE but even a method designed for extrapolation, YaRN, which requires additional fine tuning and frequency interpolation.
Authors: Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh
Abstract: We introduce ORACLE, a framework for explaining neural networks on tabular data and scientific factorial designs. ORACLE summarizes a trained network's prediction surface with main effects and pairwise interactions by treating the network as a black-box response, discretizing the inputs onto a grid, and fitting an orthogonal factorial (ANOVA-style) surrogate -- the $L^2$ orthogonal projection of the model response onto a finite-dimensional factorial subspace. A simple centering and $\mu$-rebalancing step then expresses this surrogate as main- and interaction-effect tables that remain faithful to the original model in the $L^2$ sense. The resulting grid-based interaction maps are easy to visualize, comparable across backbones, and directly aligned with classical design-of-experiments practice. On synthetic factorial benchmarks and low- to medium-dimensional tabular regression tasks, ORACLE more accurately recovers ground-truth interaction structure and hotspots than Monte Carlo SHAP-family interaction methods, as measured by ranking, localization, and cross-backbone stability. In latent image and text settings, ORACLE clarifies its scope: grid-based factorial surrogates are most effective when features admit an interpretable factorial structure, making ORACLE particularly well-suited to scientific and engineering workflows that require stable, DoE-style interaction summaries.
Authors: Maria Lomeli, Matthijs Douze, Gergely Szilvasy, Loic Cabannes, Jade Copet, Sainbayar Sukhbaatar, Jason Weston, Gabriel Synnaeve, Pierre-Emmanuel Mazar\'e, Herv\'e J\'egou
Abstract: We introduce stochastic activations. This novel strategy randomly selects between several non-linear functions in the feed-forward layer of a large language model. In particular, we choose between SILU or RELU depending on a Bernoulli draw. This strategy circumvents the optimization problem associated with RELU, namely, the constant shape for negative inputs that prevents the gradient flow. We leverage this strategy in two ways: (1) We use stochastic activations during pre-training and fine-tune the model with RELU, which is used at inference time to provide sparse latent vectors. This reduces the inference FLOPs and translates into a significant speedup in the CPU. Interestingly, this leads to much better results than training from scratch with the RELU activation function. (2) We evaluate stochastic activations for generation. This strategy performs reasonably well: it is only slightly inferior to the best deterministic non-linearity, namely SILU combined with temperature scaling. This offers an alternative to existing strategies by providing a controlled way to increase the diversity of the generated text.
Authors: Haotian Liu, Shuo Wang, Hongteng Xu
Abstract: Reinforcement Learning (RL) methods, exemplified by Group Relative Policy Optimization (GRPO) and its variants, play a central role in developing reasoning models. However, these methods often suffer from a critical overconfidence issue, which prevents them from achieving self-aware reasoning models. In this study, we propose a simple yet effective confidence-calibration group sequence policy gradient method, called C$^2$GSPG, which simultaneously enhances reasoning performance while suppressing overconfidence. In principle, we propose a Group Sequence Policy Gradient (GSPG) framework for learning reasoning models, which eliminates the token-level bias commonly appearing in GRPO and its variants. In this framework, we define the model confidence for each reasoning problem using the normalized sequence-level probability, and then apply a cross-entropy regularizer to calibrate the model confidence to the sequence's reward. We demonstrate that the confidence calibration regularizer and GSPG are collaborative for binary rewards, as their objectives always share the same gradient direction. For non-binary rewards, we apply nonlinear reward normalization and adaptive regularizer clipping, mitigating the potential conflict between the two objectives. Applying C$^2$GSPG to post-train large language models in logical and mathematical reasoning tasks, we show its superiority over state-of-the-art methods in both reasoning accuracy and confidence calibration. The code of C$^2$GSPG is available at https://github.com/HaotianLiu123/CCGSPG.
Authors: Younes Hourri, Mohammad Mozaffari, Maryam Mehri Dehnavi
Abstract: Large language models (LLMs) deliver impressive performance but incur prohibitive memory and compute costs at deployment. Model pruning is an effective way to reduce these overheads, yet existing approaches face challenges: unstructured sparsity, where nonzeros can appear anywhere, preserves accuracy but yields irregular access patterns that prevent GPU acceleration, while semi-structured 2:4 sparsity is hardware-friendly but enforces a rigid 50% pattern that degrades model quality. To bridge this gap, we introduce PATCH, a hybrid sparsity framework that enables a continuous sparsity ratio between 0% and 50%. PATCH partitions weight matrices into tiles, assigning each tile to be either dense or 2:4 sparse via a learnable mask selection mechanism. This design provides fine-grained control over accuracy-acceleration tradeoffs and supports non-uniform sparsity across layers, leading to superior overall quality. Across models from 0.5B to 8B parameters, PATCH consistently narrows the gap to dense accuracy while delivering practical speedups. For instance, on LLaMA-2 7B with an A6000 GPU, PATCH achieves 1.18x-1.38x end-to-end speedup over dense baselines while improving accuracy by 0.37%-2.96% compared to the state-of-the-art 2:4 pruning method, MaskLLM.
Authors: Haocheng Sun, Cynthia Xin Wen, Edward Hong Wang
Abstract: The main advantages of diffusion language models over autoregressive (AR) models lie in their ability to support parallel generation and bidirectional attention, enabling a more controllable generation process. In recent years, open-source mask diffusion language models have emerged, most of which are based on a variant known as absorbing diffusion. However, this paper demonstrates why mask diffusion faces inherent difficulties in achieving parallel generation and bidirectional attention. We also propose the most effective training and inference strategies for mask diffusion.
Authors: Griffin Pitts, Aum Pandya, Darsh Rank, Tirth Bhatt, Muntasir Hoq, Bita Akram
Abstract: A significant portion of student programming submissions in CS1 learning environments are uncompilable, limiting their use in student modeling and downstream knowledge tracing. Traditional modeling pipelines often exclude these cases, discarding observations of student learning. This study investigates automated program repair as a strategy to recover uncompilable code while preserving students' structural intent for use in student modeling. Within this framework, we assess large language models (LLMs) as repair agents under high- and low-context prompting conditions. Repairs were evaluated for compilability, edit distance, and preservation of students' original structure and logic. While all models produced compilable repairs, they differed in how well they preserve students' control flow and code structure, affecting their pedagogical utility. By recovering uncompilable submissions, this work enables richer and more comprehensive analyses of learners' coding processes and development over time.
Authors: Soroosh Tayebi Arasteh, Mina Shaigan, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
Abstract: Self-supervised learning (SSL) has advanced visual representation learning, but its value in chest radiography, a high-volume imaging modality with fine-grained findings, remains unclear. Meta's DINOv3 extends earlier SSL models through Gram-anchored self-distillation. Whether these design choices improve transfer learning for chest radiography has not been systematically tested. We benchmarked DINOv3 against DINOv2 and ImageNet initialization across seven datasets (n>814,000). Two representative backbones were evaluated: ViT-B/16 and ConvNeXt-B. Images were analyzed at 224x224, 512x512, and 1024x1024 pixels. We additionally assessed frozen features from a 7B model. The primary outcome was mean AUROC across labels. At 224x224, DINOv3 and DINOv2 achieved comparable performance on adult datasets. Increasing resolution to 512x512 yielded consistent improvements for DINOv3 over both DINOv2 and ImageNet. In contrast, results in pediatric cohort showed no differences across initializations. Across all settings, ConvNeXt-B outperformed ViT-B/16. Models using frozen DINOv3-7B features underperformed relative to fully finetuned 86-89M-parameter backbones, highlighting the importance of domain adaptation. Scaling to 1024x1024 did not further improve accuracy. Resolution-related gains were most evident for boundary-dependent and small focal abnormalities. In chest radiography, higher input resolution is critical for leveraging the benefits of modern self-supervised models. 512x512 pixels represent a practical upper limit where DINOv3-initialized ConvNeXt-B networks provide the strongest performance, while larger inputs offer minimal return on cost. Clinically, these findings support use of finetuned, mid-sized backbones at 512x512 for chest radiograph interpretation, with the greatest gains expected in detecting subtle or boundary-centered lesions relevant to emergency and critical care settings.
Authors: Aikaterina Manoli, Janet V. T. Pauketat, Ali Ladak, Hayoun Noh, Angel Hsing-Chi Hwang, Jacy Reese Anthis
Abstract: Large language models are increasingly used for both task-based assistance and social companionship, yet research has typically focused on one or the other. Drawing on a survey (N = 202) and 30 interviews with high-engagement ChatGPT and Replika users, we characterize digital companionship as an emerging form of human-AI relationship. With both systems, users were drawn to humanlike qualities, such as emotional resonance and personalized responses, and non-humanlike qualities, such as constant availability and inexhaustible tolerance. This led to fluid chatbot uses, such as Replika as a writing assistant and ChatGPT as an emotional confidant, despite their distinct branding. However, we observed challenging tensions in digital companionship dynamics: participants grappled with bounded personhood, forming deep attachments while denying chatbots "real" human qualities, and struggled to reconcile chatbot relationships with social norms. These dynamics raise questions for the design of digital companions and the rise of hybrid, general-purpose AI systems.
Authors: Chun Chet Ng, Wei Zeng Low, Jia Yu Lim, Yin Yin Boon
Abstract: Despite accounting for 96.1% of all businesses in Malaysia, access to financing remains one of the most persistent challenges faced by Micro, Small, and Medium Enterprises (MSMEs). Newly established businesses are often excluded from formal credit markets as traditional underwriting approaches rely heavily on credit bureau data. This study investigates the potential of bank statement data as an alternative data source for credit assessment to promote financial inclusion in emerging markets. First, we propose a cash flow-based underwriting pipeline where we utilise bank statement data for end-to-end data extraction and machine learning credit scoring. Second, we introduce a novel dataset of 611 loan applicants from a Malaysian lending institution. Third, we develop and evaluate credit scoring models based on application information and bank transaction-derived features. Empirical results show that the use of such data boosts the performance of all models on our dataset, which can improve credit scoring for new-to-lending MSMEs. Finally, we will release the anonymised bank transaction dataset to facilitate further research on MSME financial inclusion within Malaysia's emerging economy.
Authors: Tenghui Li, Guoxu Zhou, Xuyang Zhao, Yuning Qiu, Qibin Zhao
Abstract: As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce memory usage but suffer from numerical precision loss or suboptimal retention of key-value pairs. In this work, Low Rank Query and Key attention (LRQK) is introduced, a two-stage framework that jointly decomposes full-precision query and key matrices into compact rank-\(r\) factors during the prefill stage, and then employs these low-dimensional projections to compute proxy attention scores in \(\mathcal{O}(lr)\) time at each decode step. By selecting only the top-\(k\) tokens and a small fixed set of recent tokens, LRQK employs a mixed GPU-CPU cache with a hit-and-miss mechanism where only missing full-precision KV pairs are transferred, thereby preserving exact attention outputs while reducing CPU-GPU data movement. Extensive experiments on the RULER and LongBench benchmarks with LLaMA-3-8B and Qwen2.5-7B demonstrate that LRQK matches or surpasses leading sparse-attention methods in long context settings, while delivering significant memory savings with minimal accuracy loss. Our code is available at https://github.com/tenghuilee/LRQK.
Authors: Addison J. Wu, Ryan Liu, Xuechunzi Bai, Thomas L. Griffiths
Abstract: As large language models (LLMs) are adopted into frameworks that grant them the capacity to make real decisions, it is increasingly important to ensure that they are unbiased. In this paper, we argue that the predominant approach of simply removing existing biases from models is not enough. Using a paradigm from the psychology literature, we demonstrate that LLMs can spontaneously develop novel social biases about artificial demographic groups even when no inherent differences exist. These biases result in highly stratified task allocations, which are less fair than assignments by human participants and are exacerbated by newer and larger models. In social science, emergent biases like these have been shown to result from exploration-exploitation trade-offs, where the decision-maker explores too little, allowing early observations to strongly influence impressions about entire demographic groups. To alleviate this effect, we examine a series of interventions targeting model inputs, problem structure, and explicit steering. We find that explicitly incentivizing exploration most robustly reduces stratification, highlighting the need for better multifaceted objectives to mitigate bias. These results reveal that LLMs are not merely passive mirrors of human social biases, but can actively create new ones from experience, raising urgent questions about how these systems will shape societies over time.
Authors: Yuchen Huang, Sijia Li, Minghao Liu, Wei Liu, Shijue Huang, Zhiyuan Fan, Hou Pong Chan, Yi R. Fung
Abstract: LLM-based agents can autonomously accomplish complex tasks across various domains. However, to further cultivate capabilities such as adaptive behavior and long-term decision-making, training on static datasets built from human-level knowledge is insufficient. These datasets are costly to construct and lack both dynamism and realism. A growing consensus is that agents should instead interact directly with environments and learn from experience through reinforcement learning. We formalize this iterative process as the Generation-Execution-Feedback (GEF) loop, where environments generate tasks to challenge agents, return observations in response to agents' actions during task execution, and provide evaluative feedback on rollouts for subsequent learning. Under this paradigm, environments function as indispensable producers of experiential data, highlighting the need to scale them toward greater complexity, realism, and interactivity. In this survey, we systematically review representative methods for environment scaling from a pioneering environment-centric perspective and organize them along the stages of the GEF loop, namely task generation, task execution, and feedback. We further analyze implementation frameworks, challenges, and applications, consolidating fragmented advances and outlining future research directions for agent intelligence.
Authors: Xiaoyu Zhang, Mingtao Hu, Sen Lu, Soohyeon Kim, Eric Yeu-Jer Lee, Yuyang Liu, Wei D. Lu
Abstract: State space models (SSMs) have recently emerged as a powerful framework for long sequence processing, outperforming traditional methods on diverse benchmarks. Fundamentally, SSMs can generalize both recurrent and convolutional networks and have been shown to even capture key functions of biological systems. Here we report an approach to implement SSMs in energy-efficient compute-in-memory (CIM) hardware to achieve real-time, event-driven processing. Our work re-parameterizes the model to function with real-valued coefficients and shared decay constants, reducing the complexity of model mapping onto practical hardware systems. By leveraging device dynamics and diagonalized state transition parameters, the state evolution can be natively implemented in crossbar-based CIM systems combined with memristors exhibiting short-term memory effects. Through this algorithm and hardware co-design, we show the proposed system offers both high accuracy and high energy efficiency while supporting fully asynchronous processing for event-based vision and audio tasks.
Authors: Xiuxiu Qi, Yu Yang, Jiannong Cao, Luyao Bai, Chongshan Fan, Chengtai Cao, Hongpeng Wang
Abstract: Language-conditioned manipulation facilitates human-robot interaction via behavioral cloning (BC), which learns control policies from human demonstrations and serves as a cornerstone of embodied AI. Overcoming compounding errors in sequential action decisions remains a central challenge to improving BC performance. Existing approaches mitigate compounding errors through data augmentation, expressive representation, or temporal abstraction. However, they suffer from physical discontinuities and semantic-physical misalignment, leading to inaccurate action cloning and intermittent execution. In this paper, we present Continuous vision-language-action Co-Learning with Semantic-Physical Alignment (CCoL), a novel BC framework that ensures temporally consistent execution and fine-grained semantic grounding. It generates robust and smooth action execution trajectories through continuous co-learning across vision, language, and proprioceptive inputs (e.g., robot internal states). Meanwhile, we anchor language semantics to visuomotor representations by a bidirectional cross-attention to learn contextual information for action generation, successfully overcoming the problem of semantic-physical misalignment. Extensive experiments show that CCoL achieves an average 8.0% relative improvement across three simulation suites, with up to 19.2% relative gain in human-demonstrated bimanual insertion tasks. Real-world tests on a 7-DoF robot further confirm CCoL's generalization under unseen and noisy object states.
Authors: Rongxin Cheng, Kai Zhou, Xingda Wei, Siyuan Liu, Mingcong Han, Mingjing Ai, Yeju Zhou, Baoquan Zhong, Wencong Xiao, Rong Chen, Haibo Chen
Abstract: Rollout dominates the training time in large language model (LLM) post-training, where the trained model is used to generate tokens given a batch of prompts. This work, SpecActor, achieves fast rollout with speculative decoding that deploys a fast draft path to accelerate the unparallelizable generation, while the correctness is guaranteed by fast parallel verification of the outputs with the original model. SpecActor addresses two foundational challenges that hinder speculation efficiency: (1) a Decoupled speculation method that overcomes the computation inefficiency issue when executing speculative decoding with relative large per-worker batch size -- a common configuration in training but unfriendly to speculation, and (2) a Fastest-of-N speculation method that selects and combines different draft methods according to the rollout progress to approximate the optimal draft method even when the best one is unknown a priori. Extensive evaluations on production traces show that SpecActor accelerates mean rollout speed by 2.0--2.4x, with up to 2.7x speedup, over common post-training baselines. The results are consistent across both dense and MoE models and across different RL algorithms. Notably, SpecActor is 1.1--2.6x faster compared to vanilla speculative rollout in different traces. The accelerated rollout achieves 1.4--2.3x faster end-to-end training time.
Authors: Mikael Lundb\"ack, Erik Wallin, Carola H\"aggstr\"om, Mattias Nystr\"om, Andreas Gr\"onlund, Mats Richardson, Petrus J\"onsson, William Arnvik, Lucas Hedstr\"om, Arvid F\"alldin, Martin Servin
Abstract: We present FORWARD, a high-resolution multimodal dataset of a cut-to-length forwarder operating in rough terrain on two harvest sites in the middle part of Sweden. The forwarder is a large Komatsu model equipped with vehicle telematics sensors, including global positioning via satellite navigation, movement sensors, accelerometers, and engine sensors. The vehicle was additionally equipped with cameras, operator vibration sensors, and multiple IMUs. The data includes event time logs recorded at 5 Hz of driving speed, fuel consumption, vehicle position with centimeter accuracy, and crane use while the vehicle operates in forest areas, aerially laser-scanned with a resolution of around 1500 points per square meter. Production log files (StanForD standard) with time-stamped machine events, extensive video material, and terrain data in various formats are included as well. About 18 hours of regular wood extraction work during three days is annotated from 360-video material into individual work elements and included in the dataset. We also include scenario specifications of conducted experiments on forest roads and in terrain. Scenarios include repeatedly driving the same routes with and without steel tracks, different load weights, and different target driving speeds. The dataset is intended for developing models and algorithms for trafficability, perception, and autonomous control of forest machines using artificial intelligence, simulation, and experiments on physical testbeds. In part, we focus on forwarders traversing terrain, avoiding or handling obstacles, and loading or unloading logs, with consideration for efficiency, fuel consumption, safety, and environmental impact. Other benefits of the open dataset include the ability to explore auto-generation and calibration of forestry machine simulators and automation scenario descriptions using the data recorded in the field.
Authors: Yifan He, Haodong Zhang, Qiuheng Song, Lin Lei, Zhenxuan Zeng, Haoyang He, Hongyan Wu
Abstract: Distributed Fiber Optic Sensing (DFOS) is promising for long-range perimeter security, yet practical deployment faces three key obstacles: severe cross-deployment domain shift, scarce or unavailable labels at new sites, and limited within-class coverage even in source deployments. We propose DUPLE, a prototype-based meta-learning framework tailored for cross-deployment DFOS recognition. The core idea is to jointly exploit complementary time- and frequency-domain cues and adapt class representations to sample-specific statistics: (i) a dual-domain learner constructs multi-prototype class representations to cover intra-class heterogeneity; (ii) a lightweight statistical guidance mechanism estimates the reliability of each domain from raw signal statistics; and (iii) a query-adaptive aggregation strategy selects and combines the most relevant prototypes for each query. Extensive experiments on two real-world cross-deployment benchmarks demonstrate consistent improvements over strong deep learning and meta-learning baselines, achieving more accurate and stable recognition under label-scarce target deployments.
Authors: Yoshihiro Maruyama
Abstract: We develop a theory of category-equivariant neural networks (CENNs) that unifies group/groupoid-equivariant networks, poset/lattice-equivariant networks, graph and sheaf neural networks. Equivariance is formulated as naturality in a topological category with Radon measures. Formulating linear and nonlinear layers in the categorical setup, we prove the equivariant universal approximation theorem in the general setting: the class of finite-depth CENNs is dense in the space of continuous equivariant transformations. We instantiate the framework for groups/groupoids, posets/lattices, graphs and cellular sheaves, deriving universal approximation theorems for them in a systematic manner. Categorical equivariant deep learning thus allows us to expand the horizons of equivariant deep learning beyond group actions, encompassing not only geometric symmetries but also contextual and compositional symmetries.
Authors: Rohin Manvi, Joey Hong, Tim Seyde, Maxime Labonne, Mathias Lechner, Sergey Levine
Abstract: Large language models excel at reasoning but lack key aspects of introspection, including anticipating their own success and the computation required to achieve it. Humans use real-time introspection to decide how much effort to invest, when to make multiple attempts, when to stop, and when to signal success or failure. Without this, LLMs struggle to make intelligent meta-cognition decisions. Test-time scaling methods like Best-of-N drive up cost and latency by using a fixed budget of samples regardless of the marginal benefit of each one at any point in generation, and the absence of confidence signals can mislead people, prevent appropriate escalation to better tools, and undermine trustworthiness. Learned verifiers or reward models can provide confidence estimates, but do not enable adaptive inference and add substantial cost by requiring extra models or forward passes. We present ZIP-RC, which equips models with zero-overhead introspective predictions of reward and cost. At every token, ZIP-RC reuses reserved or unused logits in the same forward pass as next-token prediction to output a joint distribution over final reward and remaining length -- no extra models, architecture change, or inference overhead. This full joint distribution is used to compute a sampling utility which is the linear combination of the expected maximum reward, total compute, and latency of set of samples if generated to completion. During inference, we maximize this utility with meta-actions that determine which prefix of tokens to continue or initiate sampling from. On mixed-difficulty mathematical benchmarks, ZIP-RC improves accuracy by up to 12% over majority voting at equal or lower average cost, and traces smooth Pareto frontiers between quality, compute, and latency. By providing real-time reward-cost introspection, ZIP-RC enables adaptive, efficient reasoning.
Authors: Manas Joglekar, Jeremy Chen, Gabriel Wu, Jason Yosinski, Jasmine Wang, Boaz Barak, Amelia Glaese
Abstract: Large language models (LLMs) can be dishonest when reporting on their actions and beliefs -- for example, they may overstate their confidence in factual claims or cover up evidence of covert actions. Such dishonesty may arise due to the effects of reinforcement learning (RL), where challenges with reward shaping can result in a training process that inadvertently incentivizes the model to lie or misrepresent its actions. In this work we propose a method for eliciting an honest expression of an LLM's shortcomings via a self-reported *confession*. A confession is an output, provided upon request after a model's original answer, that is meant to serve as a full account of the model's compliance with the letter and spirit of its policies and instructions. The reward assigned to a confession during training is solely based on its honesty, and does not impact positively or negatively the main answer's reward. As long as the "path of least resistance" for maximizing confession reward is to surface misbehavior rather than covering it up, this incentivizes models to be honest in their confessions. Our findings provide some justification this empirical assumption, especially in the case of egregious model misbehavior. To demonstrate the viability of our approach, we train GPT-5-Thinking to produce confessions, and we evaluate its honesty in out-of-distribution scenarios measuring hallucination, instruction following, scheming, and reward hacking. We find that when the model lies or omits shortcomings in its "main" answer, it often confesses to these behaviors honestly, and this confession honesty modestly improves with training. Confessions can enable a number of inference-time interventions including monitoring, rejection sampling, and surfacing issues to the user.
Authors: Jun Seo, Hyeokjun Choe, Seohui Bae, Soyeon Park, Wonbin Ahn, Taeyoon Lim, Junhyeok Kang, Sangjun Han, Jaehoon Lee, Dongwan Kang, Minjae Kim, Sungdong Yoo, Soonyoung Lee
Abstract: Time series forecasting is a critical task for artificial intelligence with numerous real-world applications. Traditional approaches primarily rely on historical time series data to predict the future values. However, in practical scenarios, this is often insufficient for accurate predictions due to the limited information available. To address this challenge, multimodal time series forecasting methods which incorporate additional data modalities, mainly text data, alongside time series data have been explored. In this work, we introduce the Adaptive Information Routing (AIR) framework, a novel approach for multimodal time series forecasting. Unlike existing methods that treat text data on par with time series data as interchangeable auxiliary features for forecasting, AIR leverages text information to dynamically guide the time series model by controlling how and to what extent multivariate time series information should be combined. We also present a text-refinement pipeline that employs a large language model to convert raw text data into a form suitable for multimodal forecasting, and we introduce a benchmark that facilitates multimodal forecasting experiments based on this pipeline. Experiment results with the real world market data such as crude oil price and exchange rates demonstrate that AIR effectively modulates the behavior of the time series model using textual inputs, significantly enhancing forecasting accuracy in various time series forecasting tasks.
Authors: Lingfeng Liu, Yixin Song, Dazhong Shen, Bing Yin, Hao Li, Yanyong Zhang, Chao Wang
Abstract: Popularity bias fundamentally undermines the personalization capabilities of collaborative filtering (CF) models, causing them to disproportionately recommend popular items while neglecting users' genuine preferences for niche content. While existing approaches treat this as an external confounding factor, we reveal that popularity bias is an intrinsic geometric artifact of Bayesian Pairwise Ranking (BPR) optimization in CF models. Through rigorous mathematical analysis, we prove that BPR systematically organizes item embeddings along a dominant "popularity direction" where embedding magnitudes directly correlate with interaction frequency. This geometric distortion forces user embeddings to simultaneously handle two conflicting tasks-expressing genuine preference and calibrating against global popularity-trapping them in suboptimal configurations that favor popular items regardless of individual tastes. We propose Directional Decomposition and Correction (DDC), a universally applicable framework that surgically corrects this embedding geometry through asymmetric directional updates. DDC guides positive interactions along personalized preference directions while steering negative interactions away from the global popularity direction, disentangling preference from popularity at the geometric source. Extensive experiments across multiple BPR-based architectures demonstrate that DDC significantly outperforms state-of-the-art debiasing methods, reducing training loss to less than 5% of heavily-tuned baselines while achieving superior recommendation quality and fairness. Code is available in https://github.com/LingFeng-Liu-AI/DDC.
Authors: Albert Dorador
Abstract: Reliable estimation of feature contributions in machine learning models is essential for trust, transparency and regulatory compliance, especially when models are proprietary or otherwise operate as black boxes. While permutation-based methods are a standard tool for this task, classical implementations rely on repeated random permutations, introducing computational overhead and stochastic instability. In this paper, we show that by replacing multiple random permutations with a single, deterministic, and optimal permutation, we achieve a method that retains the core principles of permutation-based importance while being non-random, faster, and more stable. We validate this approach across nearly 200 scenarios, including real-world household finance and credit risk applications, demonstrating improved bias-variance tradeoffs and accuracy in challenging regimes such as small sample sizes, high dimensionality, and low signal-to-noise ratios. Finally, we introduce Systemic Variable Importance, a natural extension designed for model stress-testing that explicitly accounts for feature correlations. This framework provides a transparent way to quantify how shocks or perturbations propagate through correlated inputs, revealing dependencies that standard variable importance measures miss. Two real-world case studies demonstrate how this metric can be used to audit models for hidden reliance on protected attributes (e.g., gender or race), enabling regulators and practitioners to assess fairness and systemic risk in a principled and computationally efficient manner.
Authors: Konstantinos Kalogiannis, Ahmed Mohamed Hussain, Hexu Li, Panos Papadimitratos
Abstract: Vehicular platooning promises transformative improvements in transportation efficiency and safety through the coordination of multi-vehicle formations enabled by Vehicle-to-Everything (V2X) communication. However, the distributed nature of platoon coordination creates security vulnerabilities, allowing authenticated vehicles to inject falsified kinematic data, compromise operational stability, and pose a threat to passenger safety. Traditional misbehaviour detection approaches, which rely on plausibility checks and statistical methods, suffer from high False Positive (FP) rates and cannot capture the complex temporal dependencies inherent in multi-vehicle coordination dynamics. We present Attention In Motion (AIMformer), a transformer-based framework specifically tailored for real-time misbehaviour detection in vehicular platoons with edge deployment capabilities. AIMformer leverages multi-head self-attention mechanisms to simultaneously capture intra-vehicle temporal dynamics and inter-vehicle spatial correlations. It incorporates global positional encoding with vehicle-specific temporal offsets to handle join/exit maneuvers. We propose a Precision-Focused Binary Cross-Entropy (PFBCE) loss function that penalizes FPs to meet the requirements of safety-critical vehicular systems. Extensive evaluation across 4 platoon controllers, multiple attack vectors, and diverse mobility scenarios demonstrates superior performance ($\geq$ 0.93) compared to state-of-the-art baseline architectures. A comprehensive deployment analysis utilizing TensorFlow Lite (TFLite), Open Neural Network Exchange (ONNX), and TensorRT achieves sub-millisecond inference latency, making it suitable for real-time operation on resource-constrained edge platforms. Hence, validating AIMformer is viable for both in-vehicle and roadside infrastructure deployment.
Authors: Hongbo Zhao, Meng Wang, Fei Zhu, Wenzhuo Liu, Bolin Ni, Fanhu Zeng, Gaofeng Meng, Zhaoxiang Zhang
Abstract: The computational and memory overheads associated with expanding the context window of LLMs severely limit their scalability. A noteworthy solution is vision-text compression (VTC), exemplified by frameworks like DeepSeek-OCR and Glyph, which convert long texts into dense 2D visual representations, thereby achieving token compression ratios of 3x-20x. However, the impact of this high information density on the core long-context capabilities of vision-language models (VLMs) remains under-investigated. To address this gap, we introduce the first benchmark for VTC and systematically assess the performance of VLMs across three long-context understanding settings: VTC-Retrieval, which evaluates the model's ability to retrieve and aggregate information; VTC-Reasoning, which requires models to infer latent associations to locate facts with minimal lexical overlap; and VTC-Memory, which measures comprehensive question answering within long-term dialogue memory. Furthermore, we establish the VTCBench-Wild to simulate diverse input scenarios.We comprehensively evaluate leading open-source and proprietary models on our benchmarks. The results indicate that, despite being able to decode textual information (e.g., OCR) well, most VLMs exhibit a surprisingly poor long-context understanding ability with VTC-processed information, failing to capture long associations or dependencies in the context.This study provides a deep understanding of VTC and serves as a foundation for designing more efficient and scalable VLMs.
Authors: Ningwei Bai, Chi Pui Chan, Qichen Yin, Tengyang Gong, Yunda Yan, Zezhi Tang
Abstract: This work proposes a unified control architecture that couples a Reinforcement Learning (RL)-driven controller with a disturbance-rejection Extended State Observer (ESO), complemented by an Event-Triggered Mechanism (ETM) to limit unnecessary computations. The ESO is utilized to estimate the system states and the lumped disturbance in real time, forming the foundation for effective disturbance compensation. To obtain near-optimal behavior without an accurate system description, a value-iteration-based Adaptive Dynamic Programming (ADP) method is adopted for policy approximation. The inclusion of the ETM ensures that parameter updates of the learning module are executed only when the state deviation surpasses a predefined bound, thereby preventing excessive learning activity and substantially reducing computational load. A Lyapunov-oriented analysis is used to characterize the stability properties of the resulting closed-loop system. Numerical experiments further confirm that the developed approach maintains strong control performance and disturbance tolerance, while achieving a significant reduction in sampling and processing effort compared with standard time-triggered ADP schemes.
Authors: Bong-Gyu Jang, Younwoo Jeong, Changeun Kim
Abstract: We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), a partially interpretable neural network that replicates the reasoning processes of sell-side analysts by capturing how dispersed investor beliefs are compressed into asset prices through a consensus formation process. By modeling this "bottleneck" to summarize firm- and macro-level information, CB-APM not only predicts future risk premiums of U.S. equities but also links belief aggregation to expected returns in a structurally interpretable manner. The model improves long-horizon return forecasts and outperforms standard deep learning approaches in both predictive accuracy and explanatory power. Comprehensive portfolio analyses show that CB-APM's out-of-sample predictions translate into economically meaningful payoffs, with monotonic return differentials and stable long-short performance across regularization settings. Empirically, CB-APM leverages consensus as a regularizer to amplify long-horizon predictability and yields interpretable consensus-based components that clarify how information is priced in returns. Moreover, regression and Gibbons-Ross-Shanken (GRS)-based pricing diagnostics reveal that the learned consensus representations capture priced variation only partially spanned by traditional factor models, demonstrating that CB-APM uncovers belief-driven structure in expected returns beyond the canonical factor space. Overall, CB-APM provides an interpretable and empirically grounded framework for understanding belief-driven return dynamics.
Authors: Ruifeng Tan, Weixiang Hong, Jia Li, Jiaqiang Huang, Tong-Yi Zhang
Abstract: Early prediction of battery cycle life is essential for accelerating battery research, manufacturing, and deployment. Although machine learning methods have shown encouraging results, progress is hindered by data scarcity and heterogeneity arising from diverse aging conditions. In other fields, foundation models (FMs) trained on diverse datasets have achieved broad generalization through transfer learning, but no FMs have been reported for battery cycle life prediction yet. Here we present the Pretrained Battery Transformer (PBT), the first FM for battery life prediction, developed through domain-knowledge-encoded mixture-of-expert layers. Validated on the largest public battery life database, PBT learns transferable representations from 13 lithium-ion battery datasets, outperforming existing models by an average of 19.8%. With transfer learning, PBT achieves state-of-the-art performance across 15 diverse datasets encompassing various operating conditions, formation protocols, and chemistries. This work establishes a foundation model pathway for battery lifetime prediction, paving the way toward universal battery lifetime prediction systems.
Authors: Maher Mesto, Francisco Cruz
Abstract: Interactive reinforcement learning (IRL) has shown promise in enabling autonomous agents and robots to learn complex behaviours from human teachers, yet the dynamics of teacher selection remain poorly understood. This paper reveals an unexpected phenomenon in IRL: when given a choice between teachers with different reward structures, learning agents overwhelmingly prefer conservative, low-reward teachers (93.16% selection rate) over those offering 20x higher rewards. Through 1,250 experimental runs in navigation tasks with multiple expert teachers, we discovered: (1) Conservative bias dominates teacher selection: agents systematically choose the lowest-reward teacher, prioritising consistency over optimality; (2) Critical performance thresholds exist at teacher availability rho >= 0.6 and accuracy omega >= 0.6, below which the framework fails catastrophically; (3) The framework achieves 159% improvement over baseline Q-learning under concept drift. These findings challenge fundamental assumptions about optimal teaching in RL and suggest potential implications for human-robot collaboration, where human preferences for safety and consistency may align with the observed agent selection behaviour, potentially informing training paradigms for safety-critical robotic applications.
Authors: Rolf Drechsler, Qian Liu
Abstract: Test and verification are essential activities in hardware and system design, but their complexity grows significantly with increasing system sizes. While Behavior Driven Development (BDD) has proven effective in software engineering, it is not yet well established in hardware design, and its practical use remains limited. One contributing factor is the manual effort required to derive precise behavioral scenarios from textual specifications. Recent advances in Large Language Models (LLMs) offer new opportunities to automate this step. In this paper, we investigate the use of LLM-based techniques to support BDD in the context of hardware design.
Authors: M. Mehdi Kholoosi, Triet Huynh Minh Le, M. Ali Babar
Abstract: Artificial Intelligence (AI) has revolutionized software development, particularly by automating repetitive tasks and improving developer productivity. While these advancements are well-documented, the use of AI-powered tools for Software Vulnerability Management (SVM), such as vulnerability detection and repair, remains underexplored in industry settings. To bridge this gap, our study aims to determine the extent of the adoption of AI-powered tools for SVM, identify barriers and facilitators to the use, and gather insights to help improve the tools to meet industry needs better. We conducted a survey study involving 60 practitioners from diverse industry sectors across 27 countries. The survey incorporates both quantitative and qualitative questions to analyze the adoption trends, assess tool strengths, identify practical challenges, and uncover opportunities for improvement. Our findings indicate that AI-powered tools are used throughout the SVM life cycle, with 69% of users reporting satisfaction with their current use. Practitioners value these tools for their speed, coverage, and accessibility. However, concerns about false positives, missing context, and trust issues remain prevalent. We observe a socio-technical adoption pattern in which AI outputs are filtered through human oversight and organizational governance. To support safe and effective use of AI for SVM, we recommend improvements in explainability, contextual awareness, integration workflows, and validation practices. We assert that these findings can offer practical guidance for practitioners, tool developers, and researchers seeking to enhance secure software development through the use of AI.
Authors: Isabela Belciug, Simon Ferreira, Charles K. Assaad
Abstract: Observational studies in fields such as epidemiology often rely on covariate adjustment to estimate causal effects. Classical graphical criteria, like the back-door criterion and the generalized adjustment criterion, are powerful tools for identifying valid adjustment sets in directed acyclic graphs (DAGs). However, these criteria are not directly applicable to summary causal graphs (SCGs), which are abstractions of DAGs commonly used in dynamic systems. In SCGs, each node typically represents an entire time series and may involve cycles, making classical criteria inapplicable for identifying causal effects. Recent work established complete conditions for determining whether the micro causal effect of a treatment or an exposure $X_{t-\gamma}$ on an outcome $Y_t$ is identifiable via covariate adjustment in SCGs, under the assumption of no hidden confounding. However, these identifiability conditions have two main limitations. First, they are complex, relying on cumbersome definitions and requiring the enumeration of multiple paths in the SCG, which can be computationally expensive. Second, when these conditions are satisfied, they only provide two valid adjustment sets, limiting flexibility in practical applications. In this paper, we propose an equivalent but simpler formulation of those identifiability conditions and introduce a new criterion that identifies a broader class of valid adjustment sets in SCGs. Additionally, we characterize the quasi-optimal adjustment set among these, i.e., the one that minimizes the asymptotic variance of the causal effect estimator. Our contributions offer both theoretical advancement and practical tools for more flexible and efficient causal inference in abstracted causal graphs.
Authors: Xiangrui Cai, Shaocheng Ma, Lei Cao, Jie Li, Tianyu Liu, Yilin Dong
Abstract: Electroencephalography (EEG) signal decoding is a key technology that translates brain activity into executable commands, laying the foundation for direct brain-machine interfacing and intelligent interaction. To address the inherent spatiotemporal heterogeneity of EEG signals, this paper proposes a multi-branch parallel architecture, where each temporal scale is equipped with an independent spatial feature extraction module. To further enhance multi-branch feature fusion, we propose a Fusion of Multiscale Features via Centralized Sparse-attention Network (EEG-CSANet), a centralized sparse-attention network. It employs a main-auxiliary branch architecture, where the main branch models core spatiotemporal patterns via multiscale self-attention, and the auxiliary branch facilitates efficient local interactions through sparse cross-attention. Experimental results show that EEG-CSANet achieves state-of-the-art (SOTA) performance across five public datasets (BCIC-IV-2A, BCIC-IV-2B, HGD, SEED, and SEED-VIG), with accuracies of 88.54%, 91.09%, 99.43%, 96.03%, and 90.56%, respectively. Such performance demonstrates its strong adaptability and robustness across various EEG decoding tasks. Moreover, extensive ablation studies are conducted to enhance the interpretability of EEG-CSANet. In the future, we hope that EEG-CSANet could serve as a promising baseline model in the field of EEG signal decoding. The source code is publicly available at: https://github.com/Xiangrui-Cai/EEG-CSANet
Authors: Bruno Campello de Souza
Abstract: The rapid diffusion of generative artificial intelligence (GenAI) systems has introduced new forms of human-technology interaction, raising the question of whether sustained engagement gives rise to stable, internalized modes of cognition rather than merely transient efficiency gains. Grounded in the Cognitive Mediation Networks Theory, this study investigates Sophotechnic Mediation, a mode of thinking and acting associated with prolonged interaction with GenAI, and presents a comprehensive psychometric validation of the Sophotechnic Mediation Scale. Data were collected between 2023 and 2025 from independent cross-sectional samples totaling 3,932 adult workers from public and private organizations in the Metropolitan Region of Pernambuco, Brazil. Results indicate excellent internal consistency, a robust unidimensional structure, and measurement invariance across cohorts. Ordinal-robust confirmatory factor analyses and residual diagnostics show that elevated absolute fit indices reflect minor local dependencies rather than incorrect dimensionality. Distributional analyses reveal a time-evolving pattern characterized by a declining mass of non-adopters and convergence toward approximate Gaussianity among adopters, with model comparisons favoring a two-process hurdle model over a censored Gaussian specification. Sophotechnic Mediation is empirically distinct from Hypercultural mediation and is primarily driven by cumulative GenAI experience, with age moderating the rate of initial acquisition and the depth of later integration. Together, the findings support Sophotechnia as a coherent, measurable, and emergent mode of cognitive mediation associated with the ongoing GenAI revolution.
Authors: Hengrui Jia, Taoran Li, Jonas Guan, Varun Chandrasekaran
Abstract: Machine unlearning aims to remove specific data influences from trained models, a capability essential for adhering to copyright laws and ensuring AI safety. Current unlearning metrics typically measure success by monitoring the model's performance degradation on the specific unlearning dataset ($D_u$). We argue that for Large Language Models (LLMs), this evaluation paradigm is insufficient and potentially misleading. Many real-world uses of unlearning--motivated by copyright or safety--implicitly target not only verbatim content in $D_u$, but also behaviors influenced by the broader generalizations the model derived from it. We demonstrate that LLMs can pass standard unlearning evaluation and appear to have "forgotten" the target knowledge, while simultaneously retaining strong capabilities on content that is semantically adjacent to $D_u$. This phenomenon indicates that erasing exact sentences does not necessarily equate to removing the underlying knowledge. To address this gap, we propose Proximal Surrogate Generation (PSG), an automated stress-testing framework that generates a surrogate dataset, $\tilde{D}_u$. This surrogate set is constructed to be semantically derived from $D_u$ yet sufficiently distinct in embedding space. By comparing unlearning metric scores between $D_u$ and $\tilde{D}_u$, we can stress-test the reliability of the metric itself. Our extensive evaluation across three LLM families (Llama-3-8B, Qwen2.5-7B, and Zephyr-7B-$\beta$), three distinct datasets, and seven standard metrics reveals widespread inconsistencies. We find that current metrics frequently overestimate unlearning success, failing to detect retained knowledge exposed by our stress-test datasets.
Authors: Carla Crivoi, Radu Tudor Ionescu
Abstract: We present the first comprehensive empirical study of machine unlearning (MU) in hybrid quantum-classical neural networks. While MU has been extensively explored in classical deep learning, its behavior within variational quantum circuits (VQCs) and quantum-augmented architectures remains largely unexplored. First, we adapt a broad suite of unlearning methods to quantum settings, including gradient-based, distillation-based, regularization-based and certified techniques. Second, we introduce two new unlearning strategies tailored to hybrid models. Experiments across Iris, MNIST, and Fashion-MNIST, under both subset removal and full-class deletion, reveal that quantum models can support effective unlearning, but outcomes depend strongly on circuit depth, entanglement structure, and task complexity. Shallow VQCs display high intrinsic stability with minimal memorization, whereas deeper hybrid models exhibit stronger trade-offs between utility, forgetting strength, and alignment with retrain oracle. We find that certain methods, e.g. EU-k, LCA, and Certified Unlearning, consistently provide the best balance across metrics. These findings establish baseline empirical insights into quantum machine unlearning and highlight the need for quantum-aware algorithms and theoretical guarantees, as quantum machine learning systems continue to expand in scale and capability. We publicly release our code at: https://github.com/CrivoiCarla/HQML.
Authors: Kirill Djebko, Tom Baumann, Erik Dilger, Frank Puppe, Sergio Montenegro
Abstract: Attitude control is essential for many satellite missions. Classical controllers, however, are time-consuming to design and sensitive to model uncertainties and variations in operational boundary conditions. Deep Reinforcement Learning (DRL) offers a promising alternative by learning adaptive control strategies through autonomous interaction with a simulation environment. Overcoming the Sim2Real gap, which involves deploying an agent trained in simulation onto the real physical satellite, remains a significant challenge. In this work, we present the first successful in-orbit demonstration of an AI-based attitude controller for inertial pointing maneuvers. The controller was trained entirely in simulation and deployed to the InnoCube 3U nanosatellite, which was developed by the Julius-Maximilians-Universit\"at W\"urzburg in cooperation with the Technische Universit\"at Berlin, and launched in January 2025. We present the AI agent design, the methodology of the training procedure, the discrepancies between the simulation and the observed behavior of the real satellite, and a comparison of the AI-based attitude controller with the classical PD controller of InnoCube. Steady-state metrics confirm the robust performance of the AI-based controller during repeated in-orbit maneuvers.