Authors: Mitchell A. Klusty, Elizabeth C. Solie, Caroline N. Leach, W. Vaiden Logan, Lynnet E. Richey, John C. Gensel, David P. Szczykutowicz, Bryan C. McLellan, Emily B. Collier, Samuel E. Armstrong, V. K. Cody Bumgardner
Abstract: Manual chart review remains an extremely time-consuming and resource-intensive component of clinical research, requiring experts to extract often complex information from unstructured electronic health record (EHR) narratives. We present a secure, modular framework for automated structured feature extraction from clinical notes leveraging locally deployed large language models (LLMs) on institutionally approved, Health Insurance Portability and Accountability Act (HIPPA)-compliant compute infrastructure. This system integrates retrieval augmented generation (RAG) and structured response methods of LLMs into a widely deployable and scalable container to provide feature extraction for diverse clinical domains. In evaluation, the framework achieved high accuracy across multiple medical characteristics present in large bodies of patient notes when compared against an expert-annotated dataset and identified several annotation errors missed in manual review. This framework demonstrates the potential of LLM systems to reduce the burden of manual chart review through automated extraction and increase consistency in data capture, accelerating clinical research.
Authors: Zheng Xing, Junting Chen
Abstract: Radio maps enable intelligent wireless applications by capturing the spatial distribution of channel characteristics. However, conventional construction methods demand extensive location-labeled data, which are costly and impractical in many real-world scenarios. This paper presents a blind radio map construction framework that infers user trajectories from indoor multiple-input multiple-output (MIMO)-Orthogonal Frequency-Division Multiplexing (OFDM) channel measurements without relying on location labels. It first proves that channel state information (CSI) under non-line-of-sight (NLOS) exhibits spatial continuity under a quasi-specular environmental model, allowing the derivation of a CSI-distance metric that is proportional to the corresponding physical distance. For rectilinear trajectories in Poisson-distributed access point (AP) deployments, it is shown that the Cramer-Rao Lower Bound (CRLB) of localization error vanishes asymptotically, even under poor angular resolution. Building on these theoretical results, a spatially regularized Bayesian inference framework is developed that jointly estimates channel features, distinguishes line-of-sight (LOS)/NLOS conditions and recovers user trajectories. Experiments on a ray-tracing dataset demonstrate an average localization error of 0.68 m and a beam map reconstruction error of 3.3%, validating the effectiveness of the proposed blind mapping method.
Authors: Doohee You, Sundeep Paul
Abstract: The performance of production machine learning systems is fundamentally limited by the quality of their training data. In high-stakes industrial applications, noisy labels can degrade performance and erode user trust. This paper presents Adjudicator, a system that addresses the critical data mining challenge of automatically identifying and correcting label noise and has been validated for production deployment. Adjudicator models this as a neuro-symbolic task, first constructing a dynamic Knowledge Graph (KG) to unify item context. This KG then informs a "Council of Agents," a novel multi-agent Large Language Model architecture where specialized agents debate and vote on a label's validity. We validate our system on a 1,000-item balanced subset of the AlleNoise benchmark. Our KG-informed model achieves a 0.99 F1-score, significantly outperforming a single-LLM baseline (0.48 F1) and a non-KG council (0.59 F1). Our analysis reveals this is due to a Precision, achieved by a novel override logic that uses the KG to perfectly identify complex, structural errors (complete Recall) -- a class of errors that baselines fail to find. This result demonstrates a robust and explainable system for automated, high-precision data verification, serving as a vital proof-of-concept for generating golden datasets in strictly governed industrial environments.
Authors: Ali Parsaee, Yashar Talebirad, Csongor Szepesv\'ari, Vishwajeet Ohal, Eden Redman
Abstract: Large Language Models (LLMs) are increasingly being utilized as autonomous agents, yet their ability to coordinate in distributed systems remains poorly understood. We introduce \textbf{LoopBench}, a benchmark to evaluate LLM reasoning in distributed symmetry breaking and meta-cognitive thinking. The benchmark focuses on coloring odd cycle graphs ($C_3, C_5, C_{11}$) with limited colors, where deterministic, non-communicating agents fail in infinite loops. A strategy passing mechanism is implemented as a form of consistent memory. We show that while standard LLMs and classical heuristics struggle, advanced reasoning models (e.g., O3) devise strategies to escape deadlocks. LoopBench allows the study of emergent distributed algorithms based on language-based reasoning, offering a testbed for collective intelligence.
Authors: Gangesh Pathak, Prasanna Kumar
Abstract: LLM implementations are failing in highly regulated industries owing to instability issues, inconsistent reasoning, hallucinations and performance variability, especially in workflows. These reliability issues restrict safe use of LLM in areas that need the precision of facts and consistent behavior (Aiyappa et al., 2023). The current methods of stabilization, such as, reinforcement learning with human feedback (RLHF) and supervised fine-tuning, offer quantifiable improvements but are expensive and based on the intensive annotation of humans, thus being not easily scaled in a sustainable way (Dong et al., 2023; Retzlaff et al., 2024). This paper presents an AI-based annotation pipeline that systematically identifies, labels, and fixes for instability patterns on LLM output. Our human-AI synergy method combines the models of automated weak supervision and confidence-based annotation with the target human validation to guarantee the reliability and moral uprightness of feedback information (Cabitza et al., 2023; Jiang et al., 2023). The semantic consistency, factual correctness, and logical coherence categories of stability-specific annotation are introduced into our framework, allowing the continuous calibration of models and the enhancement of their robustness based on the feedback loops (Honovich et al., 2021; Nan et al., 2021).
Authors: Fatemeh Lotfi, Fatemeh Afghah
Abstract: The increasing complexity of modern applications demands wireless networks capable of real time adaptability and efficient resource management. The Open Radio Access Network (O-RAN) architecture, with its RAN Intelligent Controller (RIC) modules, has emerged as a pivotal solution for dynamic resource management and network slicing. While artificial intelligence (AI) driven methods have shown promise, most approaches struggle to maintain performance under unpredictable and highly dynamic conditions. This paper proposes an adaptive Meta Hierarchical Reinforcement Learning (Meta-HRL) framework, inspired by Model Agnostic Meta Learning (MAML), to jointly optimize resource allocation and network slicing in O-RAN. The framework integrates hierarchical control with meta learning to enable both global and local adaptation: the high-level controller allocates resources across slices, while low level agents perform intra slice scheduling. The adaptive meta-update mechanism weights tasks by temporal difference error variance, improving stability and prioritizing complex network scenarios. Theoretical analysis establishes sublinear convergence and regret guarantees for the two-level learning process. Simulation results demonstrate a 19.8% improvement in network management efficiency compared with baseline RL and meta-RL approaches, along with faster adaptation and higher QoS satisfaction across eMBB, URLLC, and mMTC slices. Additional ablation and scalability studies confirm the method's robustness, achieving up to 40% faster adaptation and consistent fairness, latency, and throughput performance as network scale increases.
Authors: Yitong Luo, Ziang Chen, Hou Hei Lam, Jiayu zhan, Junqi Wang, Zhenliang Zhang, Xue Feng
Abstract: Personalized decision-making is essential for human-AI interaction, enabling AI agents to act in alignment with individual users' value preferences. As AI systems expand into real-world applications, adapting to personalized values beyond task completion or collective alignment has become a critical challenge. We address this by proposing a value-driven approach to personalized decision-making. Human values serve as stable, transferable signals that support consistent and generalizable behavior across contexts. Compared to task-oriented paradigms driven by external rewards and incentives, value-driven decision-making enhances interpretability and enables agents to act appropriately even in novel scenarios. We introduce ValuePilot, a two-phase framework consisting of a dataset generation toolkit (DGT) and a decision-making module (DMM). DGT constructs diverse, value-annotated scenarios from a human-LLM collaborative pipeline. DMM learns to evaluate actions based on personal value preferences, enabling context-sensitive, individualized decisions. When evaluated on previously unseen scenarios, DMM outperforms strong LLM baselines, including GPT-5, Claude-Sonnet-4, Gemini-2-flash, and Llama-3.1-70b, in aligning with human action choices. Our results demonstrate that value-driven decision-making is an effective and extensible engineering pathway toward building interpretable, personalized AI agents.
Authors: Steve Nwaiwu, Nipat Jongsawat, Anucha Tungkasthan
Abstract: Causal reasoning in Large Language Models spanning association, intervention, and counterfactual inference is essential for reliable decision making in high stakes settings. As deployment shifts toward edge and resource constrained environments, quantized models such as INT8 and NF4 are becoming standard. Yet the impact of precision reduction on formal causal reasoning is poorly understood. To our knowledge, this is the first study to systematically evaluate quantization effects across all three levels of Pearls Causal Ladder. Using a 3000 sample stratified CLadder benchmark, we find that rung level accuracy in Llama 3 8B remains broadly stable under quantization, with NF4 showing less than one percent overall degradation. Interventional queries at rung 2 are the most sensitive to precision loss, whereas counterfactual reasoning at rung 3 is comparatively stable but exhibits heterogeneous weaknesses across query types such as collider bias and backdoor adjustment. Experiments on the CRASS benchmark show near identical performance across precisions, indicating that existing commonsense counterfactual datasets lack the structural sensitivity needed to reveal quantization induced reasoning drift. We further evaluate Graph Retrieval Augmented Generation using ground truth causal graphs and observe a consistent improvement in NF4 interventional accuracy of plus 1.7 percent, partially offsetting compression related degradation. These results suggest that causal reasoning is unexpectedly robust to four bit quantization, graph structured augmentation can selectively reinforce interventional reasoning, and current counterfactual benchmarks fail to capture deeper causal brittleness. This work provides an initial empirical map of compressed causal reasoning and practical guidance for deploying efficient and structurally supported causal AI systems.
Authors: TK Lee
Abstract: Large language models (LLMs) are widely deployed as general-purpose tools, yet extended interaction can reveal behavioral patterns not captured by standard quantitative benchmarks. We present a qualitative case-study methodology for auditing policy-linked behavioral selectivity in long-horizon interaction. In a single 86-turn dialogue session, the same model shows Normal Performance (NP) in broad, non-sensitive domains while repeatedly producing Functional Refusal (FR) in provider- or policy-sensitive domains, yielding a consistent asymmetry between NP and FR across domains. Drawing on learned helplessness as an analogy, we introduce learned incapacity (LI) as a behavioral descriptor for this selective withholding without implying intentionality or internal mechanisms. We operationalize three response regimes (NP, FR, Meta-Narrative; MN) and show that MN role-framing narratives tend to co-occur with refusals in the same sensitive contexts. Overall, the study proposes an interaction-level auditing framework based on observable behavior and motivates LI as a lens for examining potential alignment side effects, warranting further investigation across users and models.
Authors: Przemyslaw Chojecki
Abstract: We study the special role of mathematics and coding inside the moduli space of psychometric batteries for AI agents. Building on the AAI framework and GVU dynamics from previous works, we define the Mathematics Fiber and show that, when paired with formal proof kernels (e.g. Lean, Coq), GVU flows on this fiber admit spectrally stable self-improvement regimes due to oracle-like verification. Our main technical result is a density theorem: under uniform tightness of agent outputs and a Lipschitz AAI functional, the subspace of batteries generated by mathematical theorem-proving and coding tasks is dense in the moduli space of batteries with respect to the evaluation metric. Coding alone is universal in this sense, while pure mathematics is not; its privilege is spectral rather than expressive. We interpret this as evidence that mathematics and coding provide ``universal coordinates'' for evaluation, and that formal mathematics is a natural ignition domain for recursive self-improvement in advanced AI agents.
Authors: Javier Mar\'in
Abstract: When retrieval-augmented generation (RAG) systems hallucinate, what geometric trace does this leave in embedding space? We introduce the Semantic Grounding Index (SGI), defined as the ratio of angular distances from the response to the question versus the context on the unit hypersphere $\mathbb{S}^{d-1}$.Our central finding is \emph{semantic laziness}: hallucinated responses remain angularly proximate to questions rather than departing toward retrieved contexts. On HaluEval ($n$=5,000), we observe large effect sizes (Cohen's $d$ ranging from 0.92 to 1.28) across five embedding models with mean cross-model correlation $r$=0.85. Crucially, we derive from the spherical triangle inequality that SGI's discriminative power should increase with question-context angular separation $\theta(q,c)$-a theoretical prediction confirmed empirically: effect size rises monotonically from $d$=0.61 -low $\theta(q,c)$, to $d$=1.27 -high $\theta(q,c)$, with AUC improving from 0.72 to 0.83. Subgroup analysis reveals that SGI excels on long responses ($d$=2.05) and short questions ($d$=1.22), while remaining robust across context lengths. Calibration analysis yields ECE=0.10, indicating SGI scores can serve as probability estimates, not merely rankings. A critical negative result on TruthfulQA (AUC=0.478) establishes that angular geometry measures topical engagement rather than factual accuracy. SGI provides computationally efficient, theoretically grounded infrastructure for identifying responses that warrant verification in production RAG deployments.
Authors: Kamer Ali Yuksel
Abstract: Large language models (LLMs) are increasingly used to evolve programs and multi-agent systems, yet most existing approaches rely on overwrite-based mutations that maintain only a single candidate at a time. Such methods discard useful variants, suffer from destructive edits, and explore a brittle search space prone to structural failure. We introduce EvoLattice, a framework that represents an entire population of candidate programs or agent behaviors within a single directed acyclic graph. Each node stores multiple persistent alternatives, and every valid path through the graph defines a distinct executable candidate, yielding a large combinatorial search space without duplicating structure. EvoLattice enables fine-grained alternative-level evaluation by scoring each alternative across all paths in which it appears, producing statistics that reveal how local design choices affect global performance. These statistics provide a dense, data-driven feedback signal for LLM-guided mutation, recombination, and pruning, while preserving successful components. Structural correctness is guaranteed by a deterministic self-repair mechanism that enforces acyclicity and dependency consistency independently of the LLM. EvoLattice naturally extends to agent evolution by interpreting alternatives as prompt fragments or sub-agent behaviors. Across program synthesis (proxy and optimizer meta-learning), EvoLattice yields more stable evolution, greater expressivity, and stronger improvement trajectories than prior LLM-guided methods. The resulting dynamics resemble quality-diversity optimization, emerging implicitly from EvoLattice's internal multi-alternative representation rather than an explicit external archive.
Authors: Sindhuja Madabushi, Dawood Wasif, Jin-Hee Cho
Abstract: Federated Learning (FL) has emerged as a leading privacy-preserving machine learning paradigm, enabling participants to share model updates instead of raw data. However, FL continues to face key challenges, including weak client incentives, privacy risks, and resource constraints. Assessing client reliability is essential for fair incentive allocation and ensuring that each client's data contributes meaningfully to the global model. To this end, we propose MURIM, a MUlti-dimensional Reputation-based Incentive Mechanism that jointly considers client reliability, privacy, resource capacity, and fairness while preventing malicious or unreliable clients from earning undeserved rewards. MURIM allocates incentives based on client contribution, latency, and reputation, supported by a reliability verification module. Extensive experiments on MNIST, FMNIST, and ADULT Income datasets demonstrate that MURIM achieves up to 18% improvement in fairness metrics, reduces privacy attack success rates by 5-9%, and improves robustness against poisoning and noisy-gradient attacks by up to 85% compared to state-of-the-art baselines. Overall, MURIM effectively mitigates adversarial threats, promotes fair and truthful participation, and preserves stable model convergence across heterogeneous and dynamic federated settings.
Authors: Yang Cao, Yubin Chen, Xuyang Guo, Zhao Song, Song Yue, Jiahao Zhang, Jiale Zhao
Abstract: The rapid advancement of large language models (LLMs) has led to significant breakthroughs in automated mathematical reasoning and scientific discovery. Georgiev, G${\'o}$mez-Serrano, Tao, and Wagner [GGSTW+25] demonstrate that AI systems can explore new constructions and improve existing bounds, illustrating the growing potential of LLMs to accelerate mathematical discovery. Similarly, Bubeck et al. [BCE+25] show that GPT-5 can meaningfully contribute to scientific workflows, from proposing hypotheses to generating proofs and analyses. Despite these advances, a rigorous evaluation of these models on canonical, graduate-level mathematical theory remains necessary to understand their baseline reasoning capabilities. In this paper, we present a comprehensive benchmark of four frontier models: GPT-5-Thinking, Gemini-3-Pro, Claude-Sonnet-4.5-Thinking, and Grok-4 against the classic curriculum of Randomized Algorithms by Motwani and Raghavan [MR95]. We tasked each model with generating formal LaTeX proofs for a series of lemmas and exercises spanning the textbook. We find that while the top-tier models (Gemini, and Claude) achieve a high accuracy rate (approx. 66%), demonstrating a robust grasp of probabilistic method and formal logic, other models lag significantly in consistency (approx. 40%). We provide a qualitative analysis of the generated proofs, highlighting differences in conciseness, hallucination rates, and logical structure. Our results suggest that while frontier models have reached a threshold of proficiency suitable for graduate-level pedagogical assistance and formalization, significant variance exists in their reliability for rigorous mathematical derivation. The code and the full set of LLM-generated responses are open-sourced and publicly available at https://github.com/magiclinux/math_benchmark_probability.
URLs: https://github.com/magiclinux/math_benchmark_probability.
Authors: Ge Yan (Lily), Chung-En Sun (Lily), Tsui-Wei (Lily), Weng
Abstract: Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A distinctive ability of these reasoning models is self-reflection: the ability to review and revise previous reasoning steps. While self-reflection enhances reasoning performance, it also increases inference cost. In this work, we study self-reflection through the lens of representation engineering. We segment the model's reasoning into steps, identify the steps corresponding to reflection, and extract a reflection direction in the latent space that governs this behavior. Using this direction, we propose a stepwise steering method that can control reflection frequency. We call our framework ReflCtrl. Our experiments show that (1) in many cases reflections are redundant, especially in stronger models (in our experiments, we can save up to 33.6 percent of reasoning tokens while preserving performance), and (2) the model's reflection behavior is highly correlated with an internal uncertainty signal, implying self-reflection may be controlled by the model's uncertainty.
Authors: Can Jin, Hongwu Peng, Mingcan Xiang, Qixin Zhang, Xiangchi Yuan, Amit Hasan, Ohiremen Dibua, Yifan Gong, Yan Kang, Dimitris N. Metaxas
Abstract: Sparse Mixture-of-Experts (MoE) architectures effectively scale model capacity by activating only a subset of experts for each input token. However, the standard Top-k routing strategy imposes a uniform sparsity pattern that ignores the varying difficulty of tokens. While Top-p routing offers a flexible alternative, existing implementations typically rely on a fixed global probability threshold, which results in uncontrolled computational costs and sensitivity to hyperparameter selection. In this paper, we propose DTop-p MoE, a sparsity-controllable dynamic Top-p routing mechanism. To resolve the challenge of optimizing a non-differentiable threshold, we utilize a Proportional-Integral (PI) Controller that dynamically adjusts the probability threshold to align the running activated-expert sparsity with a specified target. Furthermore, we introduce a dynamic routing normalization mechanism that adapts layer-wise routing logits, allowing different layers to learn distinct expert-selection patterns while utilizing a global probability threshold. Extensive experiments on Large Language Models and Diffusion Transformers demonstrate that DTop-p consistently outperforms both Top-k and fixed-threshold Top-p baselines. Our analysis confirms that DTop-p maintains precise control over the number of activated experts while adaptively allocating resources across different tokens and layers. Furthermore, DTop-p exhibits strong scaling properties with respect to expert granularity, expert capacity, model size, and dataset size, offering a robust framework for large-scale MoE pre-training.
Authors: Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka, Aditya Grover
Abstract: World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world models, these approaches face practical limitations in GUI settings, where predicting complex visual elements in future states is often difficult. In this work, we explore an alternative formulation of world modeling for GUI agents, where state transitions are described in natural language rather than predicting raw pixels. First, we introduce MobileWorldBench, a benchmark that evaluates the ability of vision-language models (VLMs) to function as world models for mobile GUI agents. Second, we release MobileWorld, a large-scale dataset consisting of 1.4M samples, that significantly improves the world modeling capabilities of VLMs. Finally, we propose a novel framework that integrates VLM world models into the planning framework of mobile agents, demonstrating that semantic world models can directly benefit mobile agents by improving task success rates. The code and dataset is available at https://github.com/jacklishufan/MobileWorld
Authors: Enhong Liu, Haiyu Yang, Miel Hostens
Abstract: Large Language Models (LLM) hold potential to support dairy scholars and farmers by supporting decision-making and broadening access to knowledge for stakeholders with limited technical expertise. However, the substantial computational demand restricts access to LLM almost exclusively through cloud-based service, which makes LLM-based decision support tools impractical for dairy farming. To address this gap, lightweight alternatives capable of running locally on farm hardware are required. In this work, we benchmarked 20 open-source Small Language Models (SLM) available on HuggingFace under farm-realistic computing constraints. Building on our prior work, we developed an agentic AI system that integrates five task-specific agents: literature search, web search, SQL database interaction, NoSQL database interaction, and graph generation following predictive models. Evaluation was conducted in two phases. In the first phase, five test questions were used for the initial screening to identify models capable of following basic dairy-related instructions and performing reliably in a compute-constrained environment. Models that passed this preliminary stage were then evaluated using 30 questions (five per task category mentioned above, plus one category addressing integrity and misconduct) in phase two. In results, Qwen-4B achieved superior performance across most of task categories, although showed unstable effectiveness in NoSQL database interactions through PySpark. To our knowledge, this is the first work explicitly evaluating the feasibility of SLM as engines for dairy farming decision-making, with central emphases on privacy and computational efficiency. While results highlight the promise of SLM-assisted tools for practical deployment in dairy farming, challenges remain, and fine-tuning is still needed to refine SLM performance in dairy-specific questions.
Authors: Shen Li, Li Huang, Shaoxiong Zhan, Weifeng Sun, Tao Yin, Zhongxin Liu, Meng Yan
Abstract: Large language models (LLMs) exhibit strong generative capabilities and have shown great potential in code generation. Existing chain-of-thought (CoT) prompting methods enhance model reasoning by eliciting intermediate steps, but suffer from two major limitations: First, their uniform application tends to induce overthinking on simple tasks. Second, they lack intention abstraction in code generation, such as explicitly modeling core algorithmic design and efficiency, leading models to focus on surface-level structures while neglecting the global problem objective. Inspired by the cognitive economy principle of engaging structured reasoning only when necessary to conserve cognitive resources, we propose RoutingGen, a novel difficulty-aware routing framework that dynamically adapts prompting strategies for code generation. For simple tasks, it adopts few-shot prompting; for more complex ones, it invokes a structured reasoning strategy, termed Intention Chain-of-Thought (ICoT), which we introduce to guide the model in capturing task intention, such as the core algorithmic logic and its time complexity. Experiments across three models and six standard code generation benchmarks show that RoutingGen achieves state-of-the-art performance in most settings, while reducing total token usage by 46.37% on average across settings. Furthermore, ICoT outperforms six existing prompting baselines on challenging benchmarks.
Authors: Mengzhang Cai, Xin Gao, Yu Li, Honglin Lin, Zheng Liu, Zhuoshi Pan, Qizhi Pei, Xiaoran Shang, Mengyuan Sun, Zinan Tang, Xiaoyang Wang, Zhanping Zhong, Yun Zhu, Dahua Lin, Conghui He, Lijun Wu
Abstract: The rapid evolution of Large Language Models (LLMs) is predicated on the quality and diversity of post-training datasets. However, a critical dichotomy persists: while models are rigorously benchmarked, the data fueling them remains a black box--characterized by opaque composition, uncertain provenance, and a lack of systematic evaluation. This opacity hinders reproducibility and obscures the causal link between data characteristics and model behaviors. To bridge this gap, we introduce OpenDataArena (ODA), a holistic and open platform designed to benchmark the intrinsic value of post-training data. ODA establishes a comprehensive ecosystem comprising four key pillars: (i) a unified training-evaluation pipeline that ensures fair, open comparisons across diverse models (e.g., Llama, Qwen) and domains; (ii) a multi-dimensional scoring framework that profiles data quality along tens of distinct axes; (iii) an interactive data lineage explorer to visualize dataset genealogy and dissect component sources; and (iv) a fully open-source toolkit for training, evaluation, and scoring to foster data research. Extensive experiments on ODA--covering over 120 training datasets across multiple domains on 22 benchmarks, validated by more than 600 training runs and 40 million processed data points--reveal non-trivial insights. Our analysis uncovers the inherent trade-offs between data complexity and task performance, identifies redundancy in popular benchmarks through lineage tracing, and maps the genealogical relationships across datasets. We release all results, tools, and configurations to democratize access to high-quality data evaluation. Rather than merely expanding a leaderboard, ODA envisions a shift from trial-and-error data curation to a principled science of Data-Centric AI, paving the way for rigorous studies on data mixing laws and the strategic composition of foundation models.
Authors: Junjie Ma, Jinlong Li
Abstract: Inference with modern Large Language Models (LLMs) is expensive and slow, and speculative sampling has emerged as an effective solution to this problem, however, the number of the calls to the draft model for generating candidate tokens in speculative sampling is a preset hyperparameter, lacking flexibility. To generate and utilize the candidate tokens more effectively, we propose RADAR, a novel speculative sampling method with RL-based dynamic draft trees. RADAR formulates the draft tree generation process as a Markov Decision Process (MDP) and employs offline reinforcement learning to train a prediction model, which enables real-time decision on the calls to the draft model, reducing redundant computations and further accelerating inference. Evaluations across three LLMs and four tasks show that RADAR achieves a speedup of 3.17x-4.82x over the auto-regressive decoding baseline. The code is available at https://github.com/minaduki-sora/RADAR.
Authors: Mayank Singh, Vikas Yadav, Shiva Krishna Reddy Malay, Shravan Nayak, Sai Rajeswar, Sathwik Tejaswi Madhusudhan, Eduardo Blanco
Abstract: Automatic search for Multi-Agent Systems has recently emerged as a key focus in agentic AI research. Several prior approaches have relied on LLM-based free-form search over the code space. In this work, we propose a more structured framework that explores the same space through a fixed set of simple, composable components. We show that, despite lacking the generative flexibility of LLMs during the candidate generation stage, our method outperforms prior approaches on four out of five benchmarks across two domains: mathematics and question answering. Furthermore, our method offers additional advantages, including a more cost-efficient search process and the generation of modular, interpretable multi-agent systems with simpler logic.
Authors: Ijaz Ul Haq, Byung Suk Lee, Julia N. Perdrial, David Baude
Abstract: Real-time streamflow monitoring networks generate millions of observations annually, yet maintaining data quality across thousands of remote sensors remains labor-intensive. We introduce HydroGEM (Hydrological Generalizable Encoder for Monitoring), a foundation model for continental-scale streamflow quality control. HydroGEM uses two-stage training: self-supervised pretraining on 6.03 million sequences from 3,724 USGS stations learns hydrological representations, followed by fine-tuning with synthetic anomalies for detection and reconstruction. A hybrid TCN-Transformer architecture (14.2M parameters) captures local temporal patterns and long-range dependencies, while hierarchical normalization handles six orders of magnitude in discharge. On held-out synthetic tests comprising 799 stations with 18 expert-validated anomaly types, HydroGEM achieves F1 = 0.792 for detection and 68.7% reconstruction-error reduction, a 36.3% improvement over existing methods. Zero-shot transfer to 100 Environment and Climate Change Canada stations yields F1 = 0.586, exceeding all baselines and demonstrating cross-national generalization. The model maintains consistent detection across correction magnitudes and aligns with operational seasonal patterns. HydroGEM is designed for human-in-the-loop workflows - outputs are quality control suggestions requiring expert review, not autonomous corrections.
Authors: Chunan Tong
Abstract: Supply chain management (SCM) faces significant challenges like demand fluctuations and the bullwhip effect. Traditional methods and even state-of-the-art LLMs struggle with benchmarks like the Vending Machine Test, failing to handle SCM's complex continuous time-series data. While ML approaches like LSTM and XGBoost offer solutions, they are often limited by computational inefficiency. Liquid Neural Networks (LNN), known for their adaptability and efficiency in robotics, remain untapped in SCM. This study proposes a hybrid LNN+XGBoost model for multi-tier supply chains. By combining LNN's dynamic feature extraction with XGBoost's global optimization, the model aims to minimize the bullwhip effect and increase profitability. This innovative approach addresses the need for efficiency and adaptability, filling a critical gap in intelligent SCM.
Authors: Yankai Jiang, Yujie Zhang, Peng Zhang, Yichen Li, Jintai Chen, Xiaoming Shi, Shihui Zhen
Abstract: Recent reasoning based medical MLLMs have made progress in generating step by step textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on fine-grained visual regions to achieve precise grounding and diagnosis. We introduce Ophiuchus, a versatile, tool-augmented framework that equips an MLLM to (i) decide when additional visual evidence is needed, (ii) determine where to probe and ground within the medical image, and (iii) seamlessly weave the relevant sub-image content back into an interleaved, multimodal chain of thought. In contrast to prior approaches limited by the performance ceiling of specialized tools, Ophiuchus integrates the model's inherent grounding and perception capabilities with external tools, thereby fostering higher-level reasoning. The core of our method is a three-stage training strategy: cold-start training with tool-integrated reasoning data to achieve basic tool selection and adaptation for inspecting key regions; self-reflection fine-tuning to strengthen reflective reasoning and encourage revisiting tool outputs; and Agentic Tool Reinforcement Learning to directly optimize task-specific rewards and emulate expert-like diagnostic behavior. Extensive experiments show that Ophiuchus consistently outperforms both closed-source and open-source SOTA methods across diverse medical benchmarks, including VQA, detection, and reasoning-based segmentation. Our approach illuminates a path toward medical AI agents that can genuinely "think with images" through tool-integrated reasoning. Datasets, codes, and trained models will be released publicly.
Authors: Aneesha Fernando, Surangika Ranathunga, Kristin Stock, Raj Prasanna, Christopher B. Jones
Abstract: Georeferencing text documents has typically relied on either gazetteer-based methods to assign geographic coordinates to place names, or on language modelling approaches that associate textual terms with geographic locations. However, many location descriptions specify positions relatively with spatial relationships, making geocoding based solely on place names or geo-indicative words inaccurate. This issue frequently arises in biological specimen collection records, where locations are often described through narratives rather than coordinates if they pre-date GPS. Accurate georeferencing is vital for biodiversity studies, yet the process remains labour-intensive, leading to a demand for automated georeferencing solutions. This paper explores the potential of Large Language Models (LLMs) to georeference complex locality descriptions automatically, focusing on the biodiversity collections domain. We first identified effective prompting patterns, then fine-tuned an LLM using Quantized Low-Rank Adaptation (QLoRA) on biodiversity datasets from multiple regions and languages. Our approach outperforms existing baselines with an average, across datasets, of 65% of records within a 10 km radius, for a fixed amount of training data. The best results (New York state) were 85% within 10km and 67% within 1km. The selected LLM performs well for lengthy, complex descriptions, highlighting its potential for georeferencing intricate locality descriptions.
Authors: Kelly J. Davis
Abstract: Formal, automated theorem proving has long been viewed as a challenge to artificial intelligence. We introduce here a new approach to computer theorem proving, one that employs specialized language models for Lean4 proof generation combined with recursive decomposition of difficult theorems into simpler entailing propositions. These models are coordinated through a multi-agent architecture that orchestrates autoformalization (if required), proof generation, decomposition of difficult theorems into simpler entailing propositions, and recursive proof (and/or decomposition) of these propositions. Without decomposition, we achieve a 90.4% pass rate on miniF2F. With decomposition, this is significantly improved. A key technical contribution lies in our extension of the Kimina Lean Server with abstract syntax tree (AST) parsing capabilities to facilitate automated, recursive proof decomposition. The system is made available on PyPI as goedels-poetry (at https://pypi.org/project/goedels-poetry ), and the open-source implementation KellyJDavis/goedels-poetry (at https://github.com/KellyJDavis/goedels-poetry ) facilitates both adaptation to alternative language models and extension with custom functionality.
URLs: https://pypi.org/project/goedels-poetry, https://github.com/KellyJDavis/goedels-poetry
Authors: Georgios Bouchouras, Dimitrios Doumanas, Andreas Soularidis, Konstantinos Kotis, George A. Vouros
Abstract: This paper explores the integration of Large Language Models (LLMs) in the engineering of a Parkinson's Disease (PD) monitoring and alerting ontology through four key methodologies: One Shot (OS) prompt techniques, Chain of Thought (CoT) prompts, X-HCOME, and SimX-HCOME+. The primary objective is to determine whether LLMs alone can create comprehensive ontologies and, if not, whether human-LLM collaboration can achieve this goal. Consequently, the paper assesses the effectiveness of LLMs in automated ontology development and the enhancement achieved through human-LLM collaboration. Initial ontology generation was performed using One Shot (OS) and Chain of Thought (CoT) prompts, demonstrating the capability of LLMs to autonomously construct ontologies for PD monitoring and alerting. However, these outputs were not comprehensive and required substantial human refinement to enhance their completeness and accuracy. X-HCOME, a hybrid ontology engineering approach that combines human expertise with LLM capabilities, showed significant improvements in ontology comprehensiveness. This methodology resulted in ontologies that are very similar to those constructed by experts. Further experimentation with SimX-HCOME+, another hybrid methodology emphasizing continuous human supervision and iterative refinement, highlighted the importance of ongoing human involvement. This approach led to the creation of more comprehensive and accurate ontologies. Overall, the paper underscores the potential of human-LLM collaboration in advancing ontology engineering, particularly in complex domains like PD. The results suggest promising directions for future research, including the development of specialized GPT models for ontology construction.
Authors: Qizhi Wang
Abstract: Cardinality estimation is a key bottleneck for cost-based query optimization, yet deployable improvements remain difficult: classical estimators miss correlations, while learned estimators often require workload-specific training pipelines and invasive integration into the optimizer. This paper presents TiCard, a low intrusion, correction-based framework that augments (rather than replaces) a database's native estimator. TiCard learns multiplicative residual corrections using EXPLAIN-only features, and uses EXPLAIN ANALYZE only for offline labels. We study two practical instantiations: (i) a Gradient Boosting Regressor for sub-millisecond inference, and (ii) TabPFN, an in-context tabular foundation model that adapts by refreshing a small reference set without gradient retraining. On TiDB with TPCH and the Join Order Benchmark, in a low-trace setting (263 executions total; 157 used for learning), TiCard improves operator-level tail accuracy substantially: P90 Q-error drops from 312.85 (native) to 13.69 (TiCard-GBR), and P99 drops from 37,974.37 to 3,416.50 (TiCard-TabPFN), while a join-only policy preserves near-perfect median behavior. We position TiCard as an AI4DB building block focused on deployability: explicit scope, conservative integration policies, and an integration roadmap from offline correction to in-optimizer use.
Authors: Wentao Wan, Qiqing Lao, Zhiwei Xie, Hefeng Wu, Runnan Lin, Liang Lin, Keze Wang
Abstract: Knowledge Editing (KE) is a field that studies how to modify some knowledge in Large Language Models (LLMs) at a low cost (compared to pre-training). Currently, performing large-scale edits on LLMs while ensuring the Reliability, Generality, and Locality metrics of the edits remain a challenge. This paper proposes a Massive editing approach for LLMs based on dynamic weight Generation (MeG). Our MeG involves attaching a dynamic weight neuron to specific layers of the LLMs and using a diffusion model to conditionally generate the weights of this neuron based on the input query required for the knowledge. This allows the use of adding a single dynamic weight neuron to achieve the goal of large-scale knowledge editing. Experiments show that our MeG can significantly improve the performance of large-scale KE in terms of Reliability, Generality, and Locality metrics compared to existing knowledge editing methods, particularly with a high percentage point increase in the absolute value index for the Locality metric, demonstrating the advantages of our proposed method.
Authors: Jia Hu, Junqi Li, Weimeng Lin, Peng Jia, Yuxiong Ji, Jintao Lai
Abstract: Vehicle Dispatching Systems (VDSs) are critical to the operational efficiency of Automated Container Terminals (ACTs). However, their widespread commercialization is hindered due to their low transferability across diverse terminals. This transferability challenge stems from three limitations: high reliance on port operational specialists, a high demand for terminal-specific data, and time-consuming manual deployment processes. Leveraging the emergence of Large Language Models (LLMs), this paper proposes PortAgent, an LLM-driven vehicle dispatching agent that fully automates the VDS transferring workflow. It bears three features: (1) no need for port operations specialists; (2) low need of data; and (3) fast deployment. Specifically, specialist dependency is eliminated by the Virtual Expert Team (VET). The VET collaborates with four virtual experts, including a Knowledge Retriever, Modeler, Coder, and Debugger, to emulate a human expert team for the VDS transferring workflow. These experts specialize in the domain of terminal VDS via a few-shot example learning approach. Through this approach, the experts are able to learn VDS-domain knowledge from a few VDS examples. These examples are retrieved via a Retrieval-Augmented Generation (RAG) mechanism, mitigating the high demand for terminal-specific data. Furthermore, an automatic VDS design workflow is established among these experts to avoid extra manual interventions. In this workflow, a self-correction loop inspired by the LLM Reflexion framework is created
Authors: Yukun Ren, Siwei Yu, Kai Chen, Jianwei Ma
Abstract: To address the steep learning curve and reliance on complex manual file editing and command-line operations in the traditional workflow of the mainstream open-source seismic wave simulation software SPECFEM, this paper proposes an intelligent, interactive workflow powered by Large Language Models (LLMs). We introduce the first Model Context Protocol (MCP) server suite for SPECFEM (supporting 2D, 3D Cartesian, and 3D Globe versions), which decomposes the entire simulation process into discrete, agent-executable tools spanning from parameter generation and mesh partitioning to solver execution and visualization. This approach enables a paradigm shift from file-driven to intent-driven conversational interactions. The framework supports both fully automated execution and human-in-the-loop collaboration, allowing researchers to guide simulation strategies in real time and retain scientific decision-making authority while significantly reducing tedious low-level operations. Validated through multiple case studies, the workflow operates seamlessly in both autonomous and interactive modes, yielding high-fidelity results consistent with standard baselines. As the first application of MCP technology to computational seismology, this study significantly lowers the entry barrier, enhances reproducibility, and offers a promising avenue for advancing computational geophysics toward AI-assisted and automated scientific research. The complete source code is available at https://github.com/RenYukun1563/specfem-mcp.
Authors: Siyuan Zhu, Chengdong Xu, Kaiqiang Ke, Chao Yu
Abstract: In long-context question answering (LCQA), determining the optimal amount of context for a given query is a significant challenge. Including too few passages may omit critical information, while including too many can introduce noise and reduce the quality of the answer. Traditional approaches, such as fixed Top-$K$ retrieval and single-stage reranking, face the dilemma of selecting the right number of passages. This problem is particularly pronounced for factoid questions, which often require only a few specific pieces of evidence. To address this issue, we introduce \emph{Context-Picker}, a reasoning-aware framework that shifts the paradigm from similarity-based ranking to minimal sufficient subset selection. Context-Picker treats context selection as a decision-making process optimized via a human-inspired, two-stage reinforcement learning schedule: a \emph{recall-oriented} stage that prioritizes the coverage of reasoning chains, followed by a \emph{precision-oriented} stage that aggressively prunes redundancy to distill a compact evidence set. To resolve reward sparsity, we propose an offline evidence distillation pipeline that mines "minimal sufficient sets" via a Leave-One-Out (LOO) procedure, providing dense, task-aligned supervision. Experiments on five long-context and multi-hop QA benchmarks demonstrate that Context-Picker significantly outperforms strong RAG baselines, achieving superior answer accuracy with comparable or reduced context lengths. Ablation studies indicate that the coarse-to-fine optimization schedule, the redundancy-aware reward shaping, and the rationale-guided format all contribute substantially to these gains.
Authors: Annu Rana, Gaurav Kumar
Abstract: Large Language Models (LLMs) often struggle with complex multi-step planning tasks, showing high rates of constraint violations and inconsistent solutions. Existing strategies such as Chain-of-Thought and ReAct rely on implicit state tracking and lack an explicit problem representation. Inspired by classical AI planning, we propose Model-First Reasoning (MFR), a two-phase paradigm in which the LLM first constructs an explicit model of the problem, defining entities, state variables, actions, and constraints, before generating a solution plan. Across multiple planning domains, including medical scheduling, route planning, resource allocation, logic puzzles, and procedural synthesis, MFR reduces constraint violations and improves solution quality compared to Chain-of-Thought and ReAct. Ablation studies show that the explicit modeling phase is critical for these gains. Our results suggest that many LLM planning failures stem from representational deficiencies rather than reasoning limitations, highlighting explicit modeling as a key component for robust and interpretable AI agents. All prompts, evaluation procedures, and task datasets are documented to facilitate reproducibility.
Authors: Cheng-Han Lu, Pei-Hsuan Tsai
Abstract: Transformer-based multi-modal intelligent systems often suffer from high computational and energy costs due to dense self-attention, limiting their scalability under resource constraints. This paper presents SMMT, a sparse multi-modal transformer architecture designed to improve efficiency and robustness. Building upon a cascaded multi-modal transformer framework, SMMT introduces cluster-based sparse attention to achieve near linear computational complexity and modality-wise masking to enhance robustness against incomplete inputs. The architecture is evaluated using Alzheimer's Disease classification on the ADNI dataset as a representative multi-modal case study. Experimental results show that SMMT maintains competitive predictive performance while significantly reducing training time, memory usage, and energy consumption compared to dense attention baselines, demonstrating its suitability as a resource-aware architectural component for scalable intelligent systems.
Authors: Shreyas Subramanian, Bala Krishnamoorthy, Pranav Murthy
Abstract: Despite significant advances in optimizers for training, most research works use common scheduler choices like Cosine or exponential decay. In this paper, we study \emph{GreedyLR}, a novel scheduler that adaptively adjusts the learning rate during training based on the current loss. To validate the effectiveness of our proposed scheduler, we conduct experiments on several NLP, CV, and LLM tasks with up to $7B$ parameters, including both fine-tuning and pre-training experiments. The results show that our approach outperforms several state-of-the-art schedulers in terms of accuracy, speed, and convergence. We also provide a theoretical analysis of the GreedyLR algorithm, including a proof of convergence and derivation of the optimal scaling factor $F$ that maximizes the convergence rate, along with experiments to show robustness of the algorithm to realistic noisy landscapes. Our scheduler is easy to implement, computationally efficient, and could be considered a good default scheduler for training.
Authors: Zitian Gao, Lynx Chen, Yihao Xiao, He Xing, Ran Tao, Haoming Luo, Joey Zhou, Bryan Dai
Abstract: Universal transformers (UTs) have been widely used for complex reasoning tasks such as ARC-AGI and Sudoku, yet the specific sources of their performance gains remain underexplored. In this work, we systematically analyze UTs variants and show that improvements on ARC-AGI primarily arise from the recurrent inductive bias and strong nonlinear components of Transformer, rather than from elaborate architectural designs. Motivated by this finding, we propose the Universal Reasoning Model (URM), which enhances the UT with short convolution and truncated backpropagation. Our approach substantially improves reasoning performance, achieving state-of-the-art 53.8% pass@1 on ARC-AGI 1 and 16.0% pass@1 on ARC-AGI 2. Our code is avaliable at https://github.com/zitian-gao/URM.
Authors: Qingao Yi, Jiaang Duan, Hanwen Hu, Qin Hua, Haiyan Zhao, Shiyou Qian, Dingyu Yang, Jian Cao, Jinghua Tang, Yinghao Yu, Chenzhi Liao, Kangjin Wang, Liping Zhang
Abstract: Training large language models (LLMs) poses significant challenges regarding computational resources and memory capacity. Although distributed training techniques help mitigate these issues, they still suffer from considerable communication overhead. Existing approaches primarily rely on static gradient compression to enhance communication efficiency; however, these methods neglect the dynamic nature of evolving gradients during training, leading to performance degradation. Accelerating LLM training via compression without sacrificing performance remains a challenge. In this paper, we propose an entropy-driven dynamic gradient compression framework called EDGC. The core concept is to adjust the compression rate during LLM training based on the evolving trends of gradient entropy, taking into account both compression efficiency and error. EDGC consists of three key components.First, it employs a down-sampling method to efficiently estimate gradient entropy, reducing computation overhead. Second, it establishes a theoretical model linking compression rate with gradient entropy, enabling more informed compression decisions. Lastly, a window-based adjustment mechanism dynamically adapts the compression rate across pipeline stages, improving communication efficiency and maintaining model performance. We implemented EDGC on a 32-NVIDIA-V100 cluster and a 64-NVIDIA-H100 cluster to train GPT2-2.5B and GPT2-12.1B, respectively. The results show that EDGC significantly reduces communication latency and training time by up to 46.45% and 16.13% while preserving LLM accuracy.
Authors: Md. Tanzim Ferdous, Naeem Ahsan Chowdhury, Prithwiraj Bhattacharjee
Abstract: This study developed a new Bangla abstractive summarization dataset to generate concise summaries of Bangla articles from diverse sources. Most existing studies in this field have concentrated on news articles, where journalists usually follow a fixed writing style. While such approaches are effective in limited contexts, they often fail to adapt to the varied nature of real-world Bangla texts. In today's digital era, a massive amount of Bangla content is continuously produced across blogs, newspapers, and social media. This creates a pressing need for summarization systems that can reduce information overload and help readers understand content more quickly. To address this challenge, we developed a dataset of over 54,000 Bangla articles and summaries collected from multiple sources, including blogs such as Cinegolpo and newspapers such as Samakal and The Business Standard. Unlike single-domain resources, our dataset spans multiple domains and writing styles. It offers greater adaptability and practical relevance. To establish strong baselines, we trained and evaluated this dataset using several deep learning and transfer learning models, including LSTM, BanglaT5-small, and MTS-small. The results highlight its potential as a benchmark for future research in Bangla natural language processing. This dataset provides a solid foundation for building robust summarization systems and helps expand NLP resources for low-resource languages.
Authors: Vivan Doshi, Mengyuan Li
Abstract: The proliferation of Large Language Models (LLMs) raises a critical question about what it means to be human when we share an increasingly symbiotic relationship with persuasive and creative machines. This paper examines patterns of human-AI coevolution in creative writing, investigating how human craft and agency are adapting alongside machine capabilities. We challenge the prevailing notion of stylistic homogenization by examining diverse patterns in longitudinal writing data. Using a large-scale corpus spanning the pre- and post-LLM era, we observe patterns suggestive of a "Dual-Track Evolution": thematic convergence around AI-related topics, coupled with structured stylistic differentiation. Our analysis reveals three emergent adaptation patterns: authors showing increased similarity to AI style, those exhibiting decreased similarity, and those maintaining stylistic stability while engaging with AI-related themes. This Creative Archetype Map illuminates how authorship is coevolving with AI, contributing to discussions about human-AI collaboration, detection challenges, and the preservation of creative diversity.
Authors: A. Anil Sinaci, Senan Postaci, Dogukan Cavdaroglu, Machteld J. Boonstra, Okan Mercan, Kerem Yilmaz, Gokce B. Laleci Erturkmen, Folkert W. Asselbergs, Karim Lekadir
Abstract: Objective: To develop the AI Product Passport, a standards-based framework improving transparency, traceability, and compliance in healthcare AI via lifecycle-based documentation. Materials and Methods: The AI Product Passport was developed within the AI4HF project, focusing on heart failure AI tools. We analyzed regulatory frameworks (EU AI Act, FDA guidelines) and existing standards to design a relational data model capturing metadata across AI lifecycle phases: study definition, dataset preparation, model generation/evaluation, deployment/monitoring, and passport generation. MLOps/ModelOps concepts were integrated for operational relevance. Co-creation involved feedback from AI4HF consortium and a Lisbon workshop with 21 diverse stakeholders, evaluated via Mentimeter polls. The open-source platform was implemented with Python libraries for automated provenance tracking. Results: The AI Product Passport was designed based on existing standards and methods with well-defined lifecycle management and role-based access. Its implementation is a web-based platform with a relational data model supporting auditable documentation. It generates machine- and human-readable reports, customizable for stakeholders. It aligns with FUTURE-AI principles (Fairness, Universality, Traceability, Usability, Robustness, Explainability), ensuring fairness, traceability, and usability. Exported passports detail model purpose, data provenance, performance, and deployment context. GitHub-hosted backend/frontend codebases enhance accessibility. Discussion and Conclusion: The AI Product Passport addresses transparency gaps in healthcare AI, meeting regulatory and ethical demands. Its open-source nature and alignment with standards foster trust and adaptability. Future enhancements include FAIR data principles and FHIR integration for improved interoperability, promoting responsible AI deployment.
Authors: Fan Yang
Abstract: Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal domains. Most existing jailbreak methods revolve around Prompt Engineering or adversarial optimization, yet we identify a previously overlooked phenomenon: many harmful scenarios are highly consistent with legitimate ones in terms of underlying principles. Based on this finding, this paper proposes the Safe2Harm Semantic Isomorphism Attack method, which achieves efficient jailbreaking through four stages: first, rewrite the harmful question into a semantically safe question with similar underlying principles; second, extract the thematic mapping relationship between the two; third, let the LLM generate a detailed response targeting the safe question; finally, reversely rewrite the safe response based on the thematic mapping relationship to obtain harmful output. Experiments on 7 mainstream LLMs and three types of benchmark datasets show that Safe2Harm exhibits strong jailbreaking capability, and its overall performance is superior to existing methods. Additionally, we construct a challenging harmful content evaluation dataset containing 358 samples and evaluate the effectiveness of existing harmful detection methods, which can be deployed for LLM input-output filtering to enable defense.
Authors: Siqi Wang, Zhengyu Chen, Teng Xiao, Zheqi Lv, Jinluan Yang, Xunliang Cai, Jingang Wang, Xiaomeng Li
Abstract: Learning rate scheduling is crucial for training large language models, yet understanding the optimal annealing strategies across different model configurations remains challenging. In this work, we investigate the transferability of annealing dynamics in large language model training and refine a generalized predictive framework for optimizing annealing strategies under the Warmup-Steady-Decay (WSD) scheduler. Our improved framework incorporates training steps, maximum learning rate, and annealing behavior, enabling more efficient optimization of learning rate schedules. Our work provides a practical guidance for selecting optimal annealing strategies without exhaustive hyperparameter searches, demonstrating that smaller models can serve as reliable proxies for optimizing the training dynamics of larger models. We validate our findings on extensive experiments using both Dense and Mixture-of-Experts (MoE) models, demonstrating that optimal annealing ratios follow consistent patterns and can be transferred across different training configurations.
Authors: Ekaterina Sysoykova, Bernhard Anzengruber-Tanase, Michael Haslgrubler, Philipp Seidl, Alois Ferscha
Abstract: Many deep learning approaches have been developed for EEG-based seizure detection; however, most rely on access to large centralized annotated datasets. In clinical practice, EEG data are often scarce, patient-specific distributed across institutions, and governed by strict privacy regulations that prohibit data pooling. As a result, creating usable AI-based seizure detection models remains challenging in real-world medical settings. To address these constraints, we propose a two-stage federated few-shot learning (FFSL) framework for personalized EEG-based seizure detection. The method is trained and evaluated on the TUH Event Corpus, which includes six EEG event classes. In Stage 1, a pretrained biosignal transformer (BIOT) is fine-tuned across non-IID simulated hospital sites using federated learning, enabling shared representation learning without centralizing EEG recordings. In Stage 2, federated few-shot personalization adapts the classifier to each patient using only five labeled EEG segments, retaining seizure-specific information while still benefiting from cross-site knowledge. Federated fine-tuning achieved a balanced accuracy of 0.43 (centralized: 0.52), Cohen's kappa of 0.42 (0.49), and weighted F1 of 0.69 (0.74). In the FFSL stage, client-specific models reached an average balanced accuracy of 0.77, Cohen's kappa of 0.62, and weighted F1 of 0.73 across four sites with heterogeneous event distributions. These results suggest that FFSL can support effective patient-adaptive seizure detection under realistic data-availability and privacy constraints.
Authors: David Haslett, Linus Ta-Lun Huang, Leila Khalatbari, Janet Hui-wen Hsiao, Antoni B. Chan
Abstract: As large language models increasingly mediate access to information and facilitate decision-making, they are becoming instruments in soft power competitions between global actors such as the United States and China. So far, language models seem to be aligned with the values of Western countries, but evidence for this ethical bias comes mostly from models made by American companies. The current crop of state-of-the-art models includes several made in China, so we conducted the first large-scale investigation of how models made in China and the USA align with people from China and the USA. We elicited responses to the Moral Foundations Questionnaire 2.0 and the World Values Survey from ten Chinese models and ten American models, and we compared their responses to responses from thousands of Chinese and American people. We found that all models respond to both surveys more like American people than like Chinese people. This skew toward American values is only slightly mitigated when prompting the models in Chinese or imposing a Chinese persona on the models. These findings have important implications for a near future in which large language models generate much of the content people consume and shape normative influence in geopolitics.
Authors: Ayush Noori, Joaqu\'in Polonuer, Katharina Meyer, Bogdan Budnik, Shad Morton, Xinyuan Wang, Sumaiya Nazeen, Yingnan He, I\~naki Arango, Lucas Vittor, Matthew Woodworth, Richard C. Krolewski, Michelle M. Li, Ninning Liu, Tushar Kamath, Evan Macosko, Dylan Ritter, Jalwa Afroz, Alexander B. H. Henderson, Lorenz Studer, Samuel G. Rodriques, Andrew White, Noa Dagan, David A. Clifton, George M. Church, Sudeshna Das, Jenny M. Tam, Vikram Khurana, Marinka Zitnik
Abstract: Neurological diseases are the leading global cause of disability, yet most lack disease-modifying treatments. We present PROTON, a heterogeneous graph transformer that generates testable hypotheses across molecular, organoid, and clinical systems. To evaluate PROTON, we apply it to Parkinson's disease (PD), bipolar disorder (BD), and Alzheimer's disease (AD). In PD, PROTON linked genetic risk loci to genes essential for dopaminergic neuron survival and predicted pesticides toxic to patient-derived neurons, including the insecticide endosulfan, which ranked within the top 1.29% of predictions. In silico screens performed by PROTON reproduced six genome-wide $\alpha$-synuclein experiments, including a split-ubiquitin yeast two-hybrid system (normalized enrichment score [NES] = 2.30, FDR-adjusted $p < 1 \times 10^{-4}$), an ascorbate peroxidase proximity labeling assay (NES = 2.16, FDR $< 1 \times 10^{-4}$), and a high-depth targeted exome sequencing study in 496 synucleinopathy patients (NES = 2.13, FDR $< 1 \times 10^{-4}$). In BD, PROTON predicted calcitriol as a candidate drug that reversed proteomic alterations observed in cortical organoids derived from BD patients. In AD, we evaluated PROTON predictions in health records from $n = 610,524$ patients at Mass General Brigham, confirming that five PROTON-predicted drugs were associated with reduced seven-year dementia risk (minimum hazard ratio = 0.63, 95% CI: 0.53-0.75, $p < 1 \times 10^{-7}$). PROTON generated neurological hypotheses that were evaluated across molecular, organoid, and clinical systems, defining a path for AI-driven discovery in neurological disease.
Authors: Sayak Chakrabarty, Souradip Pal
Abstract: Unlike traditional recommendation tasks, finite user time budgets introduce a critical resource constraint, requiring the recommender system to balance item relevance and evaluation cost. For example, in a mobile shopping interface, users interact with recommendations by scrolling, where each scroll triggers a list of items called slate. Users incur an evaluation cost - time spent assessing item features before deciding to click. Highly relevant items having higher evaluation costs may not fit within the user's time budget, affecting engagement. In this position paper, our objective is to evaluate reinforcement learning algorithms that learn patterns in user preferences and time budgets simultaneously, crafting recommendations with higher engagement potential under resource constraints. Our experiments explore the use of reinforcement learning to recommend items for users using Alibaba's Personalized Re-ranking dataset supporting slate optimization in e-commerce contexts. Our contributions include (i) a unified formulation of time-constrained slate recommendation modeled as Markov Decision Processes (MDPs) with budget-aware utilities; (ii) a simulation framework to study policy behavior on re-ranking data; and (iii) empirical evidence that on-policy and off-policy control can improve performance under tight time budgets than traditional contextual bandit-based methods.
Authors: Bhavesh Kumar, Roger Jin, Jeffrey Quesnelle
Abstract: As language models scale to trillions of parameters, distributed training across many GPUs becomes essential, yet gradient synchronization over high-bandwidth, low-latency networks remains a critical bottleneck. While recent methods like Dion reduce per-step communication through low-rank updates, they synchronize at every step regardless of the optimization landscape. We observe that synchronization requirements vary dramatically throughout training: workers naturally compute similar gradients in flat regions, making frequent synchronization redundant, while high-curvature regions require coordination to prevent divergence. We introduce CurvaDion, which uses Relative Maximum Momentum Change (RMMC) to detect high-curvature regions requiring synchronization. RMMC leverages momentum dynamics which are already computed during optimization as a computationally tractable proxy for directional curvature, adding only $\mathcal{O}(d)$ operations per layer. We establish theoretical connections between RMMC and loss curvature and demonstrate that CurvaDion achieves 99\% communication reduction while matching baseline convergence across models from 160M to 1.3B parameters.
Authors: Jacob Schnell, Aditya Makkar, Gunadi Gani, Aniket Srinivasan Ashok, Darren Lo, Mike Optis, Alexander Wong, Yuhao Chen
Abstract: Various weather modelling problems (e.g., weather forecasting, optimizing turbine placements, etc.) require ample access to high-resolution, highly accurate wind data. Acquiring such high-resolution wind data, however, remains a challenging and expensive endeavour. Traditional reconstruction approaches are typically either cost-effective or accurate, but not both. Deep learning methods, including diffusion models, have been proposed to resolve this trade-off by leveraging advances in natural image super-resolution. Wind data, however, is distinct from natural images, and wind super-resolvers often use upwards of 10 input channels, significantly more than the usual 3-channel RGB inputs in natural images. To better leverage a large number of conditioning variables in diffusion models, we present a generalization of classifier-free guidance (CFG) to multiple conditioning inputs. Our novel composite classifier-free guidance (CCFG) can be dropped into any pre-trained diffusion model trained with standard CFG dropout. We demonstrate that CCFG outputs are higher-fidelity than those from CFG on wind super-resolution tasks. We present WindDM, a diffusion model trained for industrial-scale wind dynamics reconstruction and leveraging CCFG. WindDM achieves state-of-the-art reconstruction quality among deep learning models and costs up to $1000\times$ less than classical methods.
Authors: Wang Jiaqi, Lan Yi, Chen Xiang
Abstract: This study investigates AI integration in architectural education through a teaching experiment in Zhejiang University's 2024-25 grade three undergraduate design studio. Adopting a dual-module framework (20-hour AI training + embedded ethics discussions), the course introduced deep learning models, LLMs, AIGC, LoRA, and ComfyUI while maintaining the original curriculum structure, supported by dedicated technical instructors. Findings demonstrate the effectiveness of phased guidance, balanced technical-ethical approaches, and institutional support. The model improved students' digital skills and strategic cognition while addressing AI ethics, providing a replicable approach combining technical and critical learning in design education.
Authors: Weikang Bai, Yongkun Du, Yuchen Su, Yazhen Xie, Zhineng Chen
Abstract: Mathematical Expression Recognition (MER) has made significant progress in recognizing simple expressions, but the robust recognition of complex mathematical expressions with many tokens and multiple lines remains a formidable challenge. In this paper, we first introduce CMER-Bench, a carefully constructed benchmark that categorizes expressions into three difficulty levels: easy, moderate, and complex. Leveraging CMER-Bench, we conduct a comprehensive evaluation of existing MER models and general-purpose multimodal large language models (MLLMs). The results reveal that while current methods perform well on easy and moderate expressions, their performance degrades significantly when handling complex mathematical expressions, mainly because existing public training datasets are primarily composed of simple samples. In response, we propose MER-17M and CMER-3M that are large-scale datasets emphasizing the recognition of complex mathematical expressions. The datasets provide rich and diverse samples to support the development of accurate and robust complex MER models. Furthermore, to address the challenges posed by the complicated spatial layout of complex expressions, we introduce a novel expression tokenizer, and a new representation called Structured Mathematical Language, which explicitly models the hierarchical and spatial structure of expressions beyond LaTeX format. Based on these, we propose a specialized model named CMERNet, built upon an encoder-decoder architecture and trained on CMER-3M. Experimental results show that CMERNet, with only 125 million parameters, significantly outperforms existing MER models and MLLMs on CMER-Bench.
Authors: Weijie Yang, Xun Zhang
Abstract: Estimation of PDE-constrained physical parameters from limited indirect measurements is inherently ill-posed, particularly when observations are sparse, irregular, and constrained by real-world sensor placement. This challenge is ubiquitous in fields such as fluid mechanics, seismic inversion, and structural health monitoring. Existing deep and operator-learning models collapse under these conditions: fixed-grid assumptions fail, reconstruction deteriorates sharply, and inversion becomes unreliable with limited robustness and no uncertainty quantification (UQ).We propose the Physical Inversion Solver (PIS), a set-conditioned diffusion framework enabling inversion from truly arbitrary observation sets. PIS employs a Set Transformer-based encoder to handle measurements of any number or geometry, and a cosine-annealed sparsity curriculum for exceptional robustness. An accompanying information-theoretic analysis provides insight into the limits of inversion under extreme sparsity by revealing how observation entropy varies across physical systems.PIS is evaluated on three challenging PDE inverse problems: Darcy flow, wavefield inversion (Helmholtz), and structural health monitoring (Hooke's Law). Across all tasks and sparsity regimes -- including extreme cases with an observation rate of only $0.29\%$ -- existing operator-learning baselines fail to reconstruct meaningful fields, often diverging or collapsing entirely.In stark contrast, PIS remains stable and accurate, reducing inversion error by $12.28\%$--$88.73\%$ and reliably producing calibrated posterior samples. These samples accurately reflect both data scarcity and intrinsic physical ambiguity. These results position PIS as a powerful, general-purpose, and uniquely sparsity-resilient solution for physical inversion under arbitrary and severely undersampled observations.
Authors: Sidhant Sundrani, Francesco Tudisco, Pasquale Minervini
Abstract: Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves the trade-off between decomposition rank and downstream task performance. Despite these advancements, a persistent challenge remains--selecting the optimal ranks for each layer to jointly optimise compression rate and downstream task accuracy. Current methods either rely on heuristics that can yield sub-optimal results due to their limited discrete search space or are gradient-based but are not as performant as heuristic approaches without post-compression fine-tuning. To address these issues, we propose Learning to Low-Rank Compress (LLRC), a gradient-based approach which directly learns the weights of masks that select singular values in a fine-tuning-free setting. Using a calibration dataset, we train only the mask weights to select fewer and fewer singular values while minimising the divergence of intermediate activations from the original model. Our approach outperforms competing ranking selection methods that similarly require no post-compression fine-tuning across various compression rates on common-sense reasoning and open-domain question-answering tasks. For instance, with a compression rate of 20% on Llama-2-13B, LLRC outperforms the competitive Sensitivity-based Truncation Rank Searching (STRS) on MMLU, BoolQ, and OpenbookQA by 12%, 3.5%, and 4.4%, respectively. Compared to other compression techniques, our approach consistently outperforms fine-tuning-free variants of SVD-LLM and LLM-Pruner across datasets and compression rates. Our fine-tuning-free approach also performs competitively with the fine-tuning variant of LLM-Pruner.
Authors: Haochen Yuan, Yang Zhang, Xiang He, Quan Z. Sheng, Zhongjie Wang
Abstract: With the rise of cloud-edge collaboration, recommendation services are increasingly trained in distributed environments. Federated Recommendation (FR) enables such multi-end collaborative training while preserving privacy by sharing model parameters instead of raw data. However, the large number of parameters, primarily due to the massive item embeddings, significantly hampers communication efficiency. While existing studies mainly focus on improving the efficiency of FR models, they largely overlook the issue of embedding parameter overhead. To address this gap, we propose a FR training framework with Parameter-Efficient Fine-Tuning (PEFT) based embedding designed to reduce the volume of embedding parameters that need to be transmitted. Our approach offers a lightweight, plugin-style solution that can be seamlessly integrated into existing FR methods. In addition to incorporating common PEFT techniques such as LoRA and Hash-based encoding, we explore the use of Residual Quantized Variational Autoencoders (RQ-VAE) as a novel PEFT strategy within our framework. Extensive experiments across various FR model backbones and datasets demonstrate that our framework significantly reduces communication overhead while improving accuracy. The source code is available at https://github.com/young1010/FedPEFT.
Authors: Xuechun Liu, Heli Sun, Xuecheng Wu, Ruichen Cao, Yunyun Shi, Dingkang Yang, Haoran Li
Abstract: Multivariate time series anomaly detection (MTSAD) aims to accurately identify and localize complex abnormal patterns in the large-scale industrial control systems. While existing approaches excel in recognizing the distinct patterns under the low-dimensional scenarios, they often fail to robustly capture long-range spatiotemporal dependencies when learning representations from the high-dimensional noisy time series. To address these limitations, we propose DARTs, a robust long short-term dual-path framework with window-aware spatiotemporal soft fusion mechanism, which can be primarily decomposed into three complementary components. Specifically, in the short-term path, we introduce a Multi-View Sparse Graph Learner and a Diffusion Multi-Relation Graph Unit that collaborate to adaptively capture hierarchical discriminative short-term spatiotemporal patterns in the high-noise time series. While in the long-term path, we design a Multi-Scale Spatiotemporal Graph Constructor to model salient long-term dynamics within the high-dimensional representation space. Finally, a window-aware spatiotemporal soft-fusion mechanism is introduced to filter the residual noise while seamlessly integrating anomalous patterns. Extensive qualitative and quantitative experimental results across mainstream datasets demonstrate the superiority and robustness of our proposed DARTs. A series of ablation studies are also conducted to explore the crucial design factors of our proposed components. Our code and model will be made publicly open soon.
Authors: Li-Xuan Zhao, Chen-Yang Xu, Wen-Qiang Li, Bo Wang, Rong-Xing Wei, Qing-Hao Menga
Abstract: In recent years, there has been a notable increase in the use of supervised detection methods of major depressive disorder (MDD) based on electroencephalogram (EEG) signals. However, the process of labeling MDD remains challenging. As a self-supervised learning method, contrastive learning could address the shortcomings of supervised learning methods, which are unduly reliant on labels in the context of MDD detection. However, existing contrastive learning methods are not specifically designed to characterize the time-frequency distribution of EEG signals, and their capacity to acquire low-semantic data representations is still inadequate for MDD detection tasks. To address the problem of contrastive learning method, we propose a time-frequency fusion and multi-domain cross-loss (TF-MCL) model for MDD detection. TF-MCL generates time-frequency hybrid representations through the use of a fusion mapping head (FMH), which efficiently remaps time-frequency domain information to the fusion domain, and thus can effectively enhance the model's capacity to synthesize time-frequency information. Moreover, by optimizing the multi-domain cross-loss function, the distribution of the representations in the time-frequency domain and the fusion domain is reconstructed, thereby improving the model's capacity to acquire fusion representations. We evaluated the performance of our model on the publicly available datasets MODMA and PRED+CT and show a significant improvement in accuracy, outperforming the existing state-of-the-art (SOTA) method by 5.87% and 9.96%, respectively.
Authors: Nardine Osman, Manel Rodriguez-Soto, Jordi Sabater-Mir
Abstract: In firefighting and other emergency operations, decisions made under pressure carry profound ethical weight and can significantly impact incident outcomes and firefighter safety. Traditional training methods, while foundational, often fall short in adequately preparing firefighters for the complex ethical dilemmas and value conflicts inherent in chaotic emergency environments. This paper proposes a conceptual framework for enhancing firefighter training by systematically integrating departmental values into simulation-based training. This approach fosters deeper value internalisation and improves value-driven decision-making under pressure. Furthermore, the underlying tools can also be leveraged to evaluate and refine departmental operational protocols for better alignment with preferred values.
Authors: Yajie Yang, Yuqing Zhao, Xiaochao Xi, Yinan Zhu
Abstract: Artificial Intelligence Generated Content (AIGC) assisting image production triggers controversy in journalism while attracting attention from media agencies. Key issues involve misinformation, authenticity, semantic fidelity, and interpretability. Most AIGC tools are opaque "black boxes," hindering the dual demands of content accuracy and semantic alignment and creating ethical, sociotechnical, and trust dilemmas. This paper explores pathways for controllable image production in journalism's special coverage and conducts two experiments with projects from China's media agency: (1) Experiment 1 tests cross-platform adaptability via standardized prompts across three scenes, revealing disparities in semantic alignment, cultural specificity, and visual realism driven by training-corpus bias and platform-level filtering. (2) Experiment 2 builds a human-in-the-loop modular pipeline combining high-precision segmentation (SAM, GroundingDINO), semantic alignment (BrushNet), and style regulating (Style-LoRA, Prompt-to-Prompt), ensuring editorial fidelity through CLIP-based semantic scoring, NSFW/OCR/YOLO filtering, and verifiable content credentials. Traceable deployment preserves semantic representation. Consequently, we propose a human-AI collaboration mechanism for AIGC assisted image production in special coverage and recommend evaluating Character Identity Stability (CIS), Cultural Expression Accuracy (CEA), and User-Public Appropriateness (U-PA).
Authors: Md. Hasib Ur Rahman
Abstract: As Large Language Models (LLMs) become ubiquitous, the challenge of securing them against adversarial "jailbreaking" attacks has intensified. Current defense strategies often rely on computationally expensive external classifiers or brittle lexical filters, overlooking the intrinsic dynamics of the model's reasoning process. In this work, the Laminar Flow Hypothesis is introduced, which posits that benign inputs induce smooth, gradual transitions in an LLM's high-dimensional latent space, whereas adversarial prompts trigger chaotic, high-variance trajectories - termed Semantic Turbulence - resulting from the internal conflict between safety alignment and instruction-following objectives. This phenomenon is formalized through a novel, zero-shot metric: the variance of layer-wise cosine velocity. Experimental evaluation across diverse small language models reveals a striking diagnostic capability. The RLHF-aligned Qwen2-1.5B exhibits a statistically significant 75.4% increase in turbulence under attack (p less than 0.001), validating the hypothesis of internal conflict. Conversely, Gemma-2B displays a 22.0% decrease in turbulence, characterizing a distinct, low-entropy "reflex-based" refusal mechanism. These findings demonstrate that Semantic Turbulence serves not only as a lightweight, real-time jailbreak detector but also as a non-invasive diagnostic tool for categorizing the underlying safety architecture of black-box models.
Authors: Md. Najib Hasan (Wichita State University, USA), Imran Ahmad (Wichita State University, USA), Sourav Basak Shuvo (Khulna University of Engineering and Technology, Bangladesh), Md. Mahadi Hasan Ankon (Khulna University of Engineering and Technology, Bangladesh), Sunanda Das (University of Arkansas, USA), Nazmul Siddique (Ulster University, UK), Hui Wang (Queen's University Belfast, UK)
Abstract: Medical image classifiers detect gastrointestinal diseases well, but they do not explain their decisions. Large language models can generate clinical text, yet they struggle with visual reasoning and often produce unstable or incorrect explanations. This leaves a gap between what a model sees and the type of reasoning a clinician expects. We introduce a framework that links image classification with structured clinical reasoning. A new hybrid model, MobileCoAtNet, is designed for endoscopic images and achieves high accuracy across eight stomach-related classes. Its outputs are then used to drive reasoning by several LLMs. To judge this reasoning, we build two expert-verified benchmarks covering causes, symptoms, treatment, lifestyle, and follow-up care. Thirty-two LLMs are evaluated against these gold standards. Strong classification improves the quality of their explanations, but none of the models reach human-level stability. Even the best LLMs change their reasoning when prompts vary. Our study shows that combining DL with LLMs can produce useful clinical narratives, but current LLMs remain unreliable for high-stakes medical decisions. The framework provides a clearer view of their limits and a path for building safer reasoning systems. The complete source code and datasets used in this study are available at https://github.com/souravbasakshuvo/DL3M.
Authors: Udayon Sen, Alka Luqman, Anupam Chattopadhyay
Abstract: Deepfake audio detection has progressed rapidly with strong pre-trained encoders (e.g., WavLM, Wav2Vec2, MMS). However, performance in realistic capture conditions - background noise (domestic/office/transport), room reverberation, and consumer channels - often lags clean-lab results. We survey and evaluate robustness for state-of-the-art audio deepfake detection models and present a reproducible framework that mixes MS-SNSD noises with ASVspoof 2021 DF utterances to evaluate under controlled signal-to-noise ratios (SNRs). SNR is a measured proxy for noise severity used widely in speech; it lets us sweep from near-clean (35 dB) to very noisy (-5 dB) to quantify graceful degradation. We study multi-condition training and fixed-SNR testing for pretrained encoders (WavLM, Wav2Vec2, MMS), reporting accuracy, ROC-AUC, and EER on binary and four-class (authenticity x corruption) tasks. In our experiments, finetuning reduces EER by 10-15 percentage points at 10-0 dB SNR across backbones.
Authors: Xiuying Zhang, Qinsheng Zhu, Xiaodong Xing
Abstract: We propose a Hybrid Spatio-Temporal Quantum Graph Convolutional Network (H-STQGCN) algorithm by combining the strengths of quantum computing and classical deep learning to predict the taxi destination within urban road networks. Our algorithm consists of two branches: spatial processing and time evolution. Regarding the spatial processing, the classical module encodes the local topological features of the road network based on the GCN method, and the quantum module is designed to map graph features onto parameterized quantum circuits through a differentiable pooling layer. The time evolution is solved by integrating multi-source contextual information and capturing dynamic trip dependencies on the classical TCN theory. Finally, our experimental results demonstrate that the proposed algorithm outperforms the current methods in terms of prediction accuracy and stability, validating the unique advantages of the quantum-enhanced mechanism in capturing high-dimensional spatial dependencies.
Authors: Siyuan Dai, Lunxiao Li, Kun Zhao, Eardi Lila, Paul K. Crane, Heng Huang, Dongkuan Xu, Haoteng Tang, Liang Zhan
Abstract: With the rapid progress of large language models (LLMs), advanced multimodal large language models (MLLMs) have demonstrated impressive zero-shot capabilities on vision-language tasks. In the biomedical domain, however, even state-of-the-art MLLMs struggle with basic Medical Decision Making (MDM) tasks. We investigate this limitation using two challenging datasets: (1) three-stage Alzheimer's disease (AD) classification (normal, mild cognitive impairment, dementia), where category differences are visually subtle, and (2) MIMIC-CXR chest radiograph classification with 14 non-mutually exclusive conditions. Our empirical study shows that text-only reasoning consistently outperforms vision-only or vision-text settings, with multimodal inputs often performing worse than text alone. To mitigate this, we explore three strategies: (1) in-context learning with reason-annotated exemplars, (2) vision captioning followed by text-only inference, and (3) few-shot fine-tuning of the vision tower with classification supervision. These findings reveal that current MLLMs lack grounded visual understanding and point to promising directions for improving multimodal decision making in healthcare.
Authors: Joyjit Roy, Samaresh Kumar Singh
Abstract: Financial sentiment analysis enhances market understanding; however, standard natural language processing approaches encounter significant challenges when applied to small datasets. This study provides a comparative evaluation of embedding-based methods for financial news sentiment classification in resource-constrained environments. Word2Vec, GloVe, and sentence transformer representations are evaluated in combination with gradient boosting on manually labeled headlines. Experimental results identify a substantial gap between validation and test performance, with models performing worse than trivial baselines despite strong validation metrics. The analysis demonstrates that pretrained embeddings yield diminishing returns below a critical data sufficiency threshold, and that small validation sets contribute to overfitting during model selection. Practical application is illustrated through weekly sentiment aggregation and narrative summarization for market monitoring workflows. The findings offer empirical evidence that embedding quality alone cannot address fundamental data scarcity in sentiment classification. For practitioners operating with limited resources, the results indicate the need to consider alternative approaches such as few-shot learning, data augmentation, or lexicon-enhanced hybrid methods when labeled samples are scarce.
Authors: Ezieddin Elmahjub
Abstract: Generative AI (GenAI) outputs are not copyrightable. This article argues why. We bypass conventional doctrinal analysis that focuses on black letter law notions of originality and authorship to re-evaluate copyright's foundational philosophy. GenAI fundamentally severs the direct human creative link to expressive form. Traditional theories utilitarian incentive, labor desert and personality fail to provide coherent justification for protection. The public domain constitutes the default baseline for intellectual creations. Those seeking copyright coverage for GenAI outputs bear the burden of proof. Granting copyright to raw GenAI outputs would not only be philosophically unsound but would also trigger an unprecedented enclosure of the digital commons, creating a legal quagmire and stifling future innovation. The paper advocates for a clear distinction: human creative contributions to AI-generated works may warrant protection, but the raw algorithmic output should remain in the public domain.
Authors: Taero Kim, Hoyoon Byun, Youngjun Choi, Sungrae Park, Kyungwoo Song
Abstract: Scaling large language models (LLMs) demands approaches that increase capacity without incurring excessive parameter growth or inference cost. Depth Up-Scaling (DUS) has emerged as a promising strategy by duplicating layers and applying Continual Pre-training (CPT), but its reliance on feed-forward networks (FFNs) limits efficiency and attainable gains. We introduce Memory-Infused Depth Up-Scaling (MIDUS), which replaces FFNs in duplicated blocks with a head-wise memory (HML) layer. Motivated by observations that attention heads have distinct roles both across and within layers, MIDUS assigns an independent memory bank to each head, enabling head-wise retrieval and injecting information into subsequent layers while preserving head-wise functional structure. This design combines sparse memory access with head-wise representations and incorporates an efficient per-head value factorization module, thereby relaxing the usual efficiency-performance trade-off. Across our CPT experiments, MIDUS exhibits robust performance improvements over strong DUS baselines while maintaining a highly efficient parameter footprint. Our findings establish MIDUS as a compelling and resource-efficient alternative to conventional FFN replication for depth up-scaling by leveraging its head-wise memory design.
Authors: Jie Qin, Jiancheng Huang, Limeng Qiao, Lin Ma
Abstract: Multimodal large language models (MLLMs) play a pivotal role in advancing the quest for general artificial intelligence. However, achieving unified target for multimodal understanding and generation remains challenging due to optimization conflicts and performance trade-offs. To effectively enhance generative performance while preserving existing comprehension capabilities, we introduce STAR: a STacked AutoRegressive scheme for task-progressive unified multimodal learning. This approach decomposes multimodal learning into multiple stages: understanding, generation, and editing. By freezing the parameters of the fundamental autoregressive (AR) model and progressively stacking isomorphic AR modules, it avoids cross-task interference while expanding the model's capabilities. Concurrently, we introduce a high-capacity VQ to enhance the granularity of image representations and employ an implicit reasoning mechanism to improve generation quality under complex conditions. Experiments demonstrate that STAR achieves state-of-the-art performance on GenEval (0.91), DPG-Bench (87.44), and ImgEdit (4.34), validating its efficacy for unified multimodal learning.
Authors: L\'eo Hein (IFPEN), Giovanni de Nunzio (IFPEN), Giovanni Chierchia (LIGM), Aur\'elie Pirayre (IFPEN), Laurent Najman (LIGM)
Abstract: Existing traffic volume estimation methods typically address either forecasting traffic on sensor-equipped roads or spatially imputing missing volumes using nearby sensors. While forecasting models generally disregard unmonitored roads by design, spatial imputation methods explicitly address network-wide estimation; yet this approach relies on volume data at inference time, limiting its applicability in sensor-scarce cities. Unlike traffic volume data, probe vehicle speeds and static road attributes are more broadly accessible and support full coverage of road segments in most urban networks. In this work, we present the Hybrid Directed-Attention Spatio-Temporal Graph Neural Network (HDA-STGNN), an inductive deep learning framework designed to tackle the network-wide volume estimation problem. Our approach leverages speed profiles, static road attributes, and road network topology to predict daily traffic volume profiles across all road segments in the network. To evaluate the effectiveness of our approach, we perform extensive ablation studies that demonstrate the model's capacity to capture complex spatio-temporal dependencies and highlight the value of topological information for accurate network-wide traffic volume estimation without relying on volume data at inference time.
Authors: Shaheim Ogbomo-Harmitt, Cesare Magnetti, Chiara Spota, Jakub Grzelak, Oleg Aslanidi
Abstract: The forward problem in electrocardiology, computing body surface potentials from cardiac electrical activity, is traditionally solved using physics-based models such as the bidomain or monodomain equations. While accurate, these approaches are computationally expensive, limiting their use in real-time and large-scale clinical applications. We propose a proof-of-concept deep learning (DL) framework as an efficient surrogate for forward solvers. The model adopts a time-dependent, attention-based sequence-to-sequence architecture to predict electrocardiogram (ECG) signals from cardiac voltage propagation maps. A hybrid loss combining Huber loss with a spectral entropy term was introduced to preserve both temporal and frequency-domain fidelity. Using 2D tissue simulations incorporating healthy, fibrotic, and gap junction-remodelled conditions, the model achieved high accuracy (mean $R^2 = 0.99 \pm 0.01$). Ablation studies confirmed the contributions of convolutional encoders, time-aware attention, and spectral entropy loss. These findings highlight DL as a scalable, cost-effective alternative to physics-based solvers, with potential for clinical and digital twin applications.
Authors: Yao Xie, Walter Cullen
Abstract: Major AI ethics guidelines and laws, including the EU AI Act, call for effective human oversight, but do not define it as a distinct and developable capacity. This paper introduces human oversight as a well-being capacity, situated within the emerging Well-being Efficacy framework. The concept integrates AI literacy, ethical discernment, and awareness of human needs, acknowledging that some needs may be conflicting or harmful. Because people inevitably project desires, fears, and interests into AI systems, oversight requires the competence to examine and, when necessary, restrain problematic demands. The authors argue that the sustainable and cost-effective development of this capacity depends on its integration into education at every level, from professional training to lifelong learning. The frame of human oversight as a well-being capacity provides a practical path from high-level regulatory goals to the continuous cultivation of human agency and responsibility essential for safe and ethical AI. The paper establishes a theoretical foundation for future research on the pedagogical implementation and empirical validation of well-being effectiveness in multiple contexts.
Authors: Siegfried Ludwig, Stylianos Bakas, Konstantinos Barmpas, Georgios Zoumpourlis, Dimitrios A. Adamos, Nikolaos Laskaris, Yannis Panagakis, Stefanos Zafeiriou
Abstract: Deep learning for decoding EEG signals has gained traction, with many claims to state-of-the-art accuracy. However, despite the convincing benchmark performance, successful translation to real applications is limited. The frequent disconnect between performance on controlled BCI benchmarks and its lack of generalisation to practical settings indicates hidden overfitting problems. We introduce Disentangled Decoding Decomposition (D3), a weakly supervised method for training deep learning models across EEG datasets. By predicting the place in the respective trial sequence from which the input window was sampled, EEG-D3 separates latent components of brain activity, akin to non-linear ICA. We utilise a novel model architecture with fully independent sub-networks for strict interpretability. We outline a feature interpretation paradigm to contrast the component activation profiles on different datasets and inspect the associated temporal and spatial filters. The proposed method reliably separates latent components of brain activity on motor imagery data. Training downstream classifiers on an appropriate subset of these components prevents hidden overfitting caused by task-correlated artefacts, which severely affects end-to-end classifiers. We further exploit the linearly separable latent space for effective few-shot learning on sleep stage classification. The ability to distinguish genuine components of brain activity from spurious features results in models that avoid the hidden overfitting problem and generalise well to real-world applications, while requiring only minimal labelled data. With interest to the neuroscience community, the proposed method gives researchers a tool to separate individual brain processes and potentially even uncover heretofore unknown dynamics.
Authors: Naman Balbir Singh Makkar
Abstract: Recent years have seen significant advances in real-time object detection, with the release of YOLOv10, YOLO11, YOLOv12, and YOLOv13 between 2024 and 2025. This technical report presents the VajraV1 model architecture, which introduces architectural enhancements over existing YOLO-based detectors. VajraV1 combines effective design choices from prior YOLO models to achieve state-of-the-art accuracy among real-time object detectors while maintaining competitive inference speed. On the COCO validation set, VajraV1-Nano achieves 44.3% mAP, outperforming YOLOv12-N by 3.7% and YOLOv13-N by 2.7% at latency competitive with YOLOv12-N and YOLOv11-N. VajraV1-Small achieves 50.4% mAP, exceeding YOLOv12-S and YOLOv13-S by 2.4%. VajraV1-Medium achieves 52.7% mAP, outperforming YOLOv12-M by 0.2%. VajraV1-Large achieves 53.7% mAP, surpassing YOLOv13-L by 0.3%. VajraV1-Xlarge achieves 56.2% mAP, outperforming all existing real-time object detectors.
Authors: Ujjwal Mishra, Vinita Shukla, Praful Hambarde, Amit Shukla
Abstract: Adapting Vision Language Segmentation Models (VLSMs) to medical imaging domains requires significant computational overhead when using conventional fine-tuning approaches. Existing Parameter-Efficient Fine-Tuning (PEFT) methods apply uniform adapter dimensions across all transformer layers, leading to suboptimal parameter allocation and reduced adaptation efficiency. We introduce Telescopic Adapters, a novel PEFT framework that employs depth-aware scaling to progressively increase adapter capacity from shallow to deep transformer layers. Our method integrates lightweight bottleneck modules within CLIPSeg's vision and text encoders, with adapter dimensions dynamically scaled based on layer depth and semantic relevance. Using only 613k trainable parameters--244x fewer than end-to-end fine-tuning, Telescopic Adapters achieve superior performance across five diverse medical datasets spanning polyp segmentation, skin lesion detection, and breast ultrasound imaging. Comprehensive ablation studies demonstrate that deeper layers require substantially more adaptation capacity than shallow layers, validating our telescopic scaling hypothesis. Our approach establishes a new paradigm for efficient medical VLSM fine-tuning, enabling deployment in resource-constrained clinical environments while maintaining competitive segmentation accuracy.
Authors: Henger Li, Shuangjie You, Flavio Di Palo, Yiyue Qian, Ayush Jain
Abstract: Tool calling enables large language models (LLMs) to interact with external environments through tool invocation, providing a practical way to overcome the limitations of pretraining. However, the effectiveness of tool use depends heavily on the quality of the associated documentation and knowledge base context. These materials are usually written for human users and are often misaligned with how LLMs interpret information. This problem is even more pronounced in industrial settings, where hundreds of tools with overlapping functionality create challenges in scalability, variability, and ambiguity. We propose Verification-Guided Context Optimization (VGCO), a framework that uses LLMs as editors to automatically refine tool-related documentation and knowledge base context. VGCO works in two stages. First, Evaluation collects real-world failure cases and identifies mismatches between tools and their context. Second, Optimization performs hierarchical editing through offline learning with structure-aware, in-context optimization. The novelty of our LLM editors has three main aspects. First, they use a hierarchical structure that naturally integrates into the tool-calling workflow. Second, they are state-aware, action-specific, and verification-guided, which constrains the search space and enables efficient, targeted improvements. Third, they enable cost-efficient sub-task specialization, either by prompt engineering large editor models or by post-training smaller editor models. Unlike prior work that emphasizes multi-turn reasoning, VGCO focuses on the single-turn, large-scale tool-calling problem and achieves significant improvements in accuracy, robustness, and generalization across LLMs.
Authors: Geofrey Owino, Bernard Shibwabo
Abstract: Infant cry classification can aid early assessment of infant needs. However, deployment of such solutions is limited by privacy concerns around audio data, sensitivity to background noise, and domain shift across recording environments. We present an end-to-end infant cry analysis pipeline that integrates a denoising autoencoder (DAE), a convolutional tokenizer, and a Transformer encoder trained using communication-efficient federated learning (FL). The system performs on-device denoising, adaptive segmentation, post hoc calibration, and energy-based out-of-distribution (OOD) abstention. Federated training employs a regularized control variate update with 8-bit adapter deltas under secure aggregation. Using the Baby Chillanto and Donate-a-Cry datasets with ESC-50 noise overlays, the model achieves a macro F1 score of 0.938, an AUC of 0.962, and an Expected Calibration Error (ECE) of 0.032, while reducing per-round client upload from approximately 36 to 42 MB to 3.3 MB. Real-time edge inference on an NVIDIA Jetson Nano (4 GB, TensorRT FP16) achieves 96 ms per one-second spectrogram frame. These results demonstrate a practical path toward privacy-preserving, noise-robust, and communication-efficient infant cry classification suitable for federated deployment.
Authors: Mohammad Mozaffari, Samuel Kushnir, Maryam Mehri Dehnavi, Amir Yazdanbakhsh
Abstract: Post-training model pruning is a promising solution, yet it faces a trade-off: simple heuristics that zero weights are fast but degrade accuracy, while principled joint optimization methods recover accuracy but are computationally infeasible at modern scale. One-shot methods such as SparseGPT offer a practical trade-off in optimality by applying efficient, approximate heuristic weight updates. To close this gap, we introduce OPTIMA, a practical one-shot post-training pruning method that balances accuracy and scalability. OPTIMA casts layer-wise weight reconstruction after mask selection as independent, row-wise Quadratic Programs (QPs) that share a common layer Hessian. Solving these QPs yields the per-row globally optimal update with respect to the reconstruction objective given the estimated Hessian. The shared-Hessian structure makes the problem highly amenable to batching on accelerators. We implement an accelerator-friendly QP solver that accumulates one Hessian per layer and solves many small QPs in parallel, enabling one-shot post-training pruning at scale on a single accelerator without fine-tuning. OPTIMA integrates with existing mask selectors and consistently improves zero-shot performance across multiple LLM families and sparsity regimes, yielding up to 3.97% absolute accuracy improvement. On an NVIDIA H100, OPTIMA prunes a 8B-parameter transformer end-to-end in 40 hours with 60GB peak memory. Together, these results set a new state-of-the-art accuracy-efficiency trade-offs for one-shot post-training pruning.
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: Amirkia Rafiei Oskooei, Eren Caglar, Ibrahim Sahin, Ayse Kayabay, Mehmet S. Aktas
Abstract: The real-time deployment of cascaded generative AI pipelines for applications like video translation is constrained by significant system-level challenges. These include the cumulative latency of sequential model inference and the quadratic ($\mathcal{O}(N^2)$) computational complexity that renders multi-user video conferencing applications unscalable. This paper proposes and evaluates a practical system-level framework designed to mitigate these critical bottlenecks. The proposed architecture incorporates a turn-taking mechanism to reduce computational complexity from quadratic to linear in multi-user scenarios, and a segmented processing protocol to manage inference latency for a perceptually real-time experience. We implement a proof-of-concept pipeline and conduct a rigorous performance analysis across a multi-tiered hardware setup, including commodity (NVIDIA RTX 4060), cloud (NVIDIA T4), and enterprise (NVIDIA A100) GPUs. Our objective evaluation demonstrates that the system achieves real-time throughput ($\tau < 1.0$) on modern hardware. A subjective user study further validates the approach, showing that a predictable, initial processing delay is highly acceptable to users in exchange for a smooth, uninterrupted playback experience. The work presents a validated, end-to-end system design that offers a practical roadmap for deploying scalable, real-time generative AI applications in multilingual communication platforms.
Authors: Alessio Buscemi, Tom Deckenbrunnen, Fahria Kabir, Nishat Mowla, Kateryna Mishchenko
Abstract: A central challenge in implementing the AI Act and other AI-relevant regulations in the EU is the lack of a systematic approach to verify their legal mandates. Recent surveys show that this regulatory ambiguity is perceived as a significant burden, leading to inconsistent readiness across Member States. This paper proposes a comprehensive framework designed to help close this gap by organising compliance verification along two fundamental dimensions: the type of method (controls vs. testing) and the target of assessment (data, model, processes, and final product). Additionally, our framework maps core legal requirements to concrete verification activities, serving as a vital bridge between policymakers and practitioners, and aligning legal text with technical standards and best practices. The proposed approach aims to reduce interpretive uncertainty, promote consistency in assessment practices, and support the alignment of regulatory, ethical, and technical perspectives across the AI lifecycle.
Authors: Matheus Corr\^ea Domingos, Valdivino Alexandre de Santiago J\'unior, Juliana Aparecida Anochi, Elcio Hideiti Shiguemori, Lu\'isa Mirelle Costa dos Santos, H\'ercules Carlos dos Santos Pereira, Andr\'e Estevam Costa Oliveira
Abstract: Forecasting meteorological variables is challenging due to the complexity of their processes, requiring advanced models for accuracy. Accurate precipitation forecasts are vital for society. Reliable predictions help communities mitigate climatic impacts. Based on the current relevance of artificial intelligence (AI), classical machine learning (ML) and deep learning (DL) techniques have been used as an alternative or complement to dynamic modeling. However, there is still a lack of broad investigations into the feasibility of purely data-driven approaches for precipitation forecasting. This study aims at addressing this issue where different classical ML and DL approaches for forecasting precipitation in South America, taking into account all 2019 seasons, are considered in a detailed investigation. The selected classical ML techniques were Random Forests and extreme gradient boosting (XGBoost), while the DL counterparts were a 1D convolutional neural network (CNN 1D), a long short-term memory (LSTM) model, and a gated recurrent unit (GRU) model. Additionally, the Brazilian Global Atmospheric Model (BAM) was used as a representative of the traditional dynamic modeling approach. We also relied on explainable artificial intelligence (XAI) to provide some explanations for the models behaviors. LSTM showed strong predictive performance while BAM, the traditional dynamic model representative, had the worst results. Despite presented the higher latency, LSTM was most accurate for heavy precipitation. If cost is a concern, XGBoost offers lower latency with slightly accuracy loss. The results of this research confirm the viability of DL models for climate forecasting, solidifying a global trend in major meteorological and climate forecasting centers.
Authors: Julian Jeggle, Raphael Wittkowski
Abstract: In this book chapter, we review how systems of simple motile agents can be used as a pathway to intelligent systems. It is a well known result from nature that large groups of entities following simple rules, such as swarms of animals, can give rise to much more complex collective behavior in a display of emergence. This begs the question whether we can emulate this behavior in synthetic matter and drive it to a point where the collective behavior reaches the complexity level of intelligent systems. Here, we will use a formalized notion of "intelligent matter" and compare it to recent results in the field of active matter. First, we will explore the approach of emergent computing in which specialized active matter systems are designed to directly solve a given task through emergent behavior. This we will then contrast with the approach of physical reservoir computing powered by the dynamics of active particle systems. In this context, we will also describe a novel reservoir computing scheme for active particles driven ultrasonically or via light refraction.
Authors: Bhargav Chickmagalur Nanjundappa, Spandan Maaheshwari
Abstract: Large Language Models (LLMs) have become integral to software engineering workflows, yet their effectiveness degrades significantly in multi-turn conversations. Recent studies demonstrate an average 39% performance drop when instructions are delivered across multiple turns, with models making premature assumptions and failing to course correct (Laban et al., 2025). This degradation is particularly problematic in exploratory programming tasks where developers need to investigate alternative approaches without committing to a single path. Current solutions force users into a false dichotomy: continue in a context-polluted conversation where the LLM becomes increasingly confused, or start fresh and lose all accumulated context. We present ContextBranch, a conversation management system that applies version control semantics to LLM interactions. ContextBranch provides four core primitives--checkpoint, branch, switch, and inject--enabling users to capture conversation state, explore alternatives in isolation, and selectively merge insights. We evaluate ContextBranch through a controlled experiment with 30 software engineering scenarios featuring intentionally polluting explorations. Branched conversations achieved higher response quality compared to linear conversations, with large improvements in focus and context awareness. Benefits were concentrated in complex scenarios involving conceptually distant explorations. Branching reduced context size by 58.1% (31.0 to 13.0 messages), eliminating irrelevant exploratory content. Our work establishes conversation branching as a fundamental primitive for AI-assisted exploratory work, demonstrating that isolation prevents context pollution when exploring alternatives.
Authors: Samuel Rothfarb, Megan C. Davis, Ivana Matanovic, Baikun Li, Edward F. Holby, Wilton J. M. Kort-Kamp
Abstract: Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We introduce Materials Agents for Simulation and Theory in Electronic-structure Reasoning (MASTER), an active learning framework where large language models autonomously design, execute, and interpret atomistic simulations. In MASTER, a multimodal system translates natural language into density functional theory workflows, while higher-level reasoning agents guide discovery through a hierarchy of strategies, including a single agent baseline and three multi-agent approaches: peer review, triage-ranking, and triage-forms. Across two chemical applications, CO adsorption on Cu-surface transition metal (M) adatoms and on M-N-C catalysts, reasoning-driven exploration reduces required atomistic simulations by up to 90% relative to trial-and-error selection. Reasoning trajectories reveal chemically grounded decisions that cannot be explained by stochastic sampling or semantic bias. Altogether, multi-agent collaboration accelerates materials discovery and marks a new paradigm for autonomous scientific exploration.
Authors: Qi Chen, Fabio Ramos, Al\'an Aspuru-Guzik, Florian Shkurti
Abstract: Bayesian Optimization (BO) is a key methodology for accelerating molecular discovery by estimating the mapping from molecules to their properties while seeking the optimal candidate. Typically, BO iteratively updates a probabilistic surrogate model of this mapping and optimizes acquisition functions derived from the model to guide molecule selection. However, its performance is limited in low-data regimes with insufficient prior knowledge and vast candidate spaces. Large language models (LLMs) and chemistry foundation models offer rich priors to enhance BO, but high-dimensional features, costly in-context learning, and the computational burden of deep Bayesian surrogates hinder their full utilization. To address these challenges, we propose a likelihood-free BO method that bypasses explicit surrogate modeling and directly leverages priors from general LLMs and chemistry-specific foundation models to inform acquisition functions. Our method also learns a tree-structured partition of the molecular search space with local acquisition functions, enabling efficient candidate selection via Monte Carlo Tree Search. By further incorporating coarse-grained LLM-based clustering, it substantially improves scalability to large candidate sets by restricting acquisition function evaluations to clusters with statistically higher property values. We show through extensive experiments and ablations that the proposed method substantially improves scalability, robustness, and sample efficiency in LLM-guided BO for molecular discovery.
Authors: Zishan Bai, Enze Ge, Junfeng Hao
Abstract: The proliferation of cloud-native architectures, characterized by microservices and dynamic orchestration, has rendered modern IT infrastructures exceedingly complex and volatile. This complexity generates overwhelming volumes of operational data, leading to critical bottlenecks in conventional systems: inefficient information processing, poor task coordination, and loss of contextual continuity during fault diagnosis and remediation. To address these challenges, we propose AOI (AI-Oriented Operations), a novel multi-agent collaborative framework that integrates three specialized agents with an LLM-based Context Compressor. Its core innovations include: (1) a dynamic task scheduling strategy that adaptively prioritizes operations based on real-time system states, and (2) a three-layer memory architecture comprising Working, Episodic, and Semantic layers that optimizes context retention and retrieval. Extensive experiments on both synthetic and real-world benchmarks demonstrate that AOI effectively mitigates information overload, achieving a 72.4% context compression ratio while preserving 92.8% of critical information and significantly enhances operational efficiency, attaining a 94.2% task success rate and reducing the Mean Time to Repair (MTTR) by 34.4% compared to the best baseline. This work presents a paradigm shift towards scalable, adaptive, and context-aware autonomous operations, enabling robust management of next-generation IT infrastructures with minimal human intervention.
Authors: Qilin Li, C. L. Philip Chen, TongZhang
Abstract: Music Emotion Recogniser (MER) research faces challenges due to limited high-quality annotated datasets and difficulties in addressing cross-track feature drift. This work presents two primary contributions to address these issues. Memo2496, a large-scale dataset, offers 2496 instrumental music tracks with continuous valence arousal labels, annotated by 30 certified music specialists. Annotation quality is ensured through calibration with extreme emotion exemplars and a consistency threshold of 0.25, measured by Euclidean distance in the valence arousal space. Furthermore, the Dual-view Adaptive Music Emotion Recogniser (DAMER) is introduced. DAMER integrates three synergistic modules: Dual Stream Attention Fusion (DSAF) facilitates token-level bidirectional interaction between Mel spectrograms and cochleagrams via cross attention mechanisms; Progressive Confidence Labelling (PCL) generates reliable pseudo labels employing curriculum-based temperature scheduling and consistency quantification using Jensen Shannon divergence; and Style Anchored Memory Learning (SAML) maintains a contrastive memory queue to mitigate cross-track feature drift. Extensive experiments on the Memo2496, 1000songs, and PMEmo datasets demonstrate DAMER's state-of-the-art performance, improving arousal dimension accuracy by 3.43%, 2.25%, and 0.17%, respectively. Ablation studies and visualisation analyses validate each module's contribution. Both the dataset and source code are publicly available.
Authors: Ruanqianqian Huang, Avery Reyna, Sorin Lerner, Haijun Xia, Brian Hempel
Abstract: The rise of AI agents is transforming how software can be built. The promise of agents is that developers might write code quicker, delegate multiple tasks to different agents, and even write a full piece of software purely out of natural language. In reality, what roles agents play in professional software development remains in question. This paper investigates how experienced developers use agents in building software, including their motivations, strategies, task suitability, and sentiments. Through field observations (N=13) and qualitative surveys (N=99), we find that while experienced developers value agents as a productivity boost, they retain their agency in software design and implementation out of insistence on fundamental software quality attributes, employing strategies for controlling agent behavior leveraging their expertise. In addition, experienced developers feel overall positive about incorporating agents into software development given their confidence in complementing the agents' limitations. Our results shed light on the value of software development best practices in effective use of agents, suggest the kinds of tasks for which agents may be suitable, and point towards future opportunities for better agentic interfaces and agentic use guidelines.
Authors: Zongyao Li, Kengo Ishida, Satoshi Yamazaki, Xiaotong Ji, Jianquan Liu
Abstract: We propose KFS-Bench, the first benchmark for key frame sampling in long video question answering (QA), featuring multi-scene annotations to enable direct and robust evaluation of sampling strategies. Key frame sampling is crucial for efficient long-form video understanding. In long video QA, selecting informative frames enables multimodal large language models (MLLMs) to improve both accuracy and efficiency. KFS-Bench addresses the limitation of prior works that only indirectly assess frame selection quality via QA accuracy. By providing ground-truth annotations of multiple disjoint scenes required per question, KFS-Bench allows us to directly analyze how different sampling approaches capture essential content across an entire long video. Using KFS-Bench, we conduct a comprehensive study of key frame sampling methods and identify that not only sampling precision but also scene coverage and sampling balance are the key factors influencing QA performance. Regarding all the factors, we design a novel sampling quality metric that correlates with QA accuracy. Furthermore, we develop a novel key frame sampling method that leverages question-video relevance to balance sampling diversity against question-frame similarity, thereby improving coverage of relevant scenes. Our adaptively balanced sampling approach achieves superior performance in both key frame sampling and QA performance. The benchmark is available at https://github.com/NEC-VID/KFS-Bench.
Authors: Jiuding Yang, Shengyao Lu, Hongxuan Liu, Shayan Shirahmad Gale Bagi, Zahra Fazel, Tomasz Czajkowski, Di Niu
Abstract: Large language models (LLMs) have achieved remarkable progress in automatic code generation, yet their ability to produce high-performance code remains limited--a critical requirement in real-world software systems. We argue that current LLMs struggle not only due to data scarcity but, more importantly, because they lack supervision that guides interpretable and effective performance improvements. In this work, we introduce PerfCoder, a family of LLMs specifically designed to generate performance-enhanced code from source code via interpretable, customized optimizations. PerfCoder is fine-tuned on a curated collection of real-world optimization trajectories with human-readable annotations, and preference-aligned by reinforcement fine-tuning using runtime measurements, enabling it to propose input-specific improvement strategies and apply them directly without relying on iterative refinement. On the PIE code performance benchmark, PerfCoder surpasses all existing models in both runtime speedup and effective optimization rate, demonstrating that performance optimization cannot be achieved by scale alone but requires optimization stratetgy awareness. In addition, PerfCoder can generate interpretable feedback about the source code, which, when provided as input to a larger LLM in a planner-and-optimizer cooperative workflow, can further improve outcomes. Specifically, we elevate the performance of 32B models and GPT-5 to new levels on code optimization, substantially surpassing their original performance.
Authors: Zhaofeng Hu, Hongrui Yu, Vaidhyanathan Chandramouli, Ci-Jyun Liang
Abstract: This study evaluates two leading approaches for teaching construction robots new skills to understand their applicability for construction automation: a Vision-Language-Action (VLA) model and Reinforcement Learning (RL) methods. The goal is to understand both task performance and the practical effort needed to deploy each approach on real jobs. The authors developed two teleoperation interfaces to control the robots and collect the demonstrations needed, both of which proved effective for training robots for long-horizon and dexterous tasks. In addition, the authors conduct a three-stage evaluation. First, the authors compare a Multi-Layer Perceptron (MLP) policy with a Deep Q-network (DQN) imitation model to identify the stronger RL baseline, focusing on model performance, generalization, and a pick-up experiment. Second, three different VLA models are trained in two different scenarios and compared with each other. Third, the authors benchmark the selected RL baseline against the VLA model using computational and sample-efficiency measures and then a robot experiment on a multi-stage panel installation task that includes transport and installation. The VLA model demonstrates strong generalization and few-shot capability, achieving 60% and 100% success in the pickup phase. In comparison, DQN can be made robust but needs additional noise during tuning, which increases the workload. Overall, the findings indicate that VLA offers practical advantages for changing tasks by reducing programming effort and enabling useful performance with minimal data, while DQN provides a viable baseline when sufficient tuning effort is acceptable.
Authors: Ignacio Alzugaray, Marwan Taher, Andrew J. Davison
Abstract: We present a novel neural RGB-D Simultaneous Localization And Mapping (SLAM) system that learns an implicit map of the scene in real time. For the first time, we explore the use of Scene Coordinate Regression (SCR) as the core implicit map representation in a neural SLAM pipeline, a paradigm that trains a lightweight network to directly map 2D image features to 3D global coordinates. SCR networks provide efficient, low-memory 3D map representations, enable extremely fast relocalization, and inherently preserve privacy, making them particularly suitable for neural implicit SLAM. Our system is the first one to achieve strict real-time in neural implicit RGB-D SLAM by relying on a SCR-based representation. We introduce a novel SCR architecture specifically tailored for this purpose and detail the critical design choices required to integrate SCR into a live SLAM pipeline. The resulting framework is simple yet flexible, seamlessly supporting both sparse and dense features, and operates reliably in dynamic environments without special adaptation. We evaluate our approach on established synthetic and real-world benchmarks, demonstrating competitive performance against the state of the art. Project Page: https://github.com/ialzugaray/ace-slam
Authors: Zhenguo Zhang, Haohan Zhen, Yishen Wang, Le Xu, Tianchen Deng, Xuefeng Chen, Qu Chen, Bo Zhang, Wuxiong Huang
Abstract: The deployment of Vision-Language Models (VLMs) in safety-critical domains like autonomous driving (AD) is critically hindered by reliability failures, most notably object hallucination. This failure stems from their reliance on ungrounded, text-based Chain-of-Thought (CoT) reasoning.While existing multi-modal CoT approaches attempt mitigation, they suffer from two fundamental flaws: (1) decoupled perception and reasoning stages that prevent end-to-end joint optimization, and (2) reliance on expensive, dense localization labels.Thus we introduce OmniDrive-R1, an end-to-end VLM framework designed for autonomous driving, which unifies perception and reasoning through an interleaved Multi-modal Chain-of-Thought (iMCoT) mechanism. Our core innovation is an Reinforcement-driven visual grounding capability, enabling the model to autonomously direct its attention and "zoom in" on critical regions for fine-grained analysis. This capability is enabled by our pure two-stage reinforcement learning training pipeline and Clip-GRPO algorithm. Crucially, Clip-GRPO introduces an annotation-free, process-based grounding reward. This reward not only eliminates the need for dense labels but also circumvents the instability of external tool calls by enforcing real-time cross-modal consistency between the visual focus and the textual reasoning. Extensive experiments on DriveLMM-o1 demonstrate our model's significant improvements. Compared to the baseline Qwen2.5VL-7B, OmniDrive-R1 improves the overall reasoning score from 51.77% to 80.35%, and the final answer accuracy from 37.81% to 73.62%.
Authors: Kim Sung-Bin, Joohyun Chang, David Harwath, Tae-Hyun Oh
Abstract: Talking face editing and face generation have often been studied as distinct problems. In this work, we propose viewing both not as separate tasks but as subtasks of a unifying formulation, speech-conditional facial motion infilling. We explore facial motion infilling as a self-supervised pretext task that also serves as a unifying formulation of dynamic talking face synthesis. To instantiate this idea, we propose FacEDiT, a speech-conditional Diffusion Transformer trained with flow matching. Inspired by masked autoencoders, FacEDiT learns to synthesize masked facial motions conditioned on surrounding motions and speech. This formulation enables both localized generation and edits, such as substitution, insertion, and deletion, while ensuring seamless transitions with unedited regions. In addition, biased attention and temporal smoothness constraints enhance boundary continuity and lip synchronization. To address the lack of a standard editing benchmark, we introduce FacEDiTBench, the first dataset for talking face editing, featuring diverse edit types and lengths, along with new evaluation metrics. Extensive experiments validate that talking face editing and generation emerge as subtasks of speech-conditional motion infilling; FacEDiT produces accurate, speech-aligned facial edits with strong identity preservation and smooth visual continuity while generalizing effectively to talking face generation.
Authors: Zulin Zhuang, Yu Bian
Abstract: Daylight-linked controls (DLCs) have significant potential for energy savings in buildings, especially when abundant daylight is available and indoor workplane illuminance can be accurately predicted in real time. Most existing studies on indoor daylight predictions were developed and tested for static scenes. This study proposes a multimodal deep learning framework that predicts indoor workplane illuminance distributions in real time from non-intrusive images with temporal-spatial features. By extracting image features only from the side-lit window areas rather than interior pixels, the approach remains applicable in dynamically occupied indoor spaces. A field experiment was conducted in a test room in Guangzhou (China), where 17,344 samples were collected for model training and validation. The model achieved R2 > 0.98 with RMSE < 0.14 on the same-distribution test set and R2 > 0.82 with RMSE < 0.17 on an unseen-day test set, indicating high accuracy and acceptable temporal generalization.
Authors: Yonggan Fu, Lexington Whalen, Zhifan Ye, Xin Dong, Shizhe Diao, Jingyu Liu, Chengyue Wu, Hao Zhang, Enze Xie, Song Han, Maksim Khadkevich, Jan Kautz, Yingyan Celine Lin, Pavlo Molchanov
Abstract: Diffusion language models (dLMs) have emerged as a promising paradigm that enables parallel, non-autoregressive generation, but their learning efficiency lags behind that of autoregressive (AR) language models when trained from scratch. To this end, we study AR-to-dLM conversion to transform pretrained AR models into efficient dLMs that excel in speed while preserving AR models' task accuracy. We achieve this by identifying limitations in the attention patterns and objectives of existing AR-to-dLM methods and then proposing principles and methodologies for more effective AR-to-dLM conversion. Specifically, we first systematically compare different attention patterns and find that maintaining pretrained AR weight distributions is critical for effective AR-to-dLM conversion. As such, we introduce a continuous pretraining scheme with a block-wise attention pattern, which remains causal across blocks while enabling bidirectional modeling within each block. We find that this approach can better preserve pretrained AR models' weight distributions than fully bidirectional modeling, in addition to its known benefit of enabling KV caching, and leads to a win-win in accuracy and efficiency. Second, to mitigate the training-test gap in mask token distributions (uniform vs. highly left-to-right), we propose a position-dependent token masking strategy that assigns higher masking probabilities to later tokens during training to better mimic test-time behavior. Leveraging this framework, we conduct extensive studies of dLMs' attention patterns, training dynamics, and other design choices, providing actionable insights into scalable AR-to-dLM conversion. These studies lead to the Efficient-DLM family, which outperforms state-of-the-art AR models and dLMs, e.g., our Efficient-DLM 8B achieves +5.4%/+2.7% higher accuracy with 4.5x/2.7x higher throughput compared to Dream 7B and Qwen3 4B, respectively.
Authors: Shuang Cheng, Yuhua Jiang, Zineng Zhou, Dawei Liu, Wang Tao, Linfeng Zhang, Biqing Qi, Bowen Zhou
Abstract: Block-wise discrete diffusion offers an attractive balance between parallel generation and causal dependency modeling, making it a promising backbone for vision-language modeling. However, its practical adoption has been limited by high training cost, slow convergence, and instability, which have so far kept it behind strong autoregressive (AR) baselines. We present \textbf{SDAR-VL}, the first systematic application of block-wise discrete diffusion to large-scale vision-language understanding (VLU), together with an \emph{integrated framework for efficient and stable training}. This framework unifies three components: (1) \textbf{Asynchronous Block-wise Noise Scheduling} to diversify supervision within each batch; (2) \textbf{Effective Mask Ratio Scaling} for unbiased loss normalization under stochastic masking; and (3) a \textbf{Progressive Beta Noise Curriculum} that increases effective mask coverage while preserving corruption diversity. Experiments on 21 single-image, multi-image, and video benchmarks show that SDAR-VL consistently improves \emph{training efficiency}, \emph{convergence stability}, and \emph{task performance} over conventional block diffusion. On this evaluation suite, SDAR-VL sets a new state of the art among diffusion-based vision-language models and, under matched settings, matches or surpasses strong AR baselines such as LLaVA-OneVision as well as the global diffusion baseline LLaDA-V, establishing block-wise diffusion as a practical backbone for VLU.
Authors: Wentao Guo, Mayank Mishra, Xinle Cheng, Ion Stoica, Tri Dao
Abstract: Mixture of Experts (MoE) models have emerged as the de facto architecture for scaling up language models without significantly increasing the computational cost. Recent MoE models demonstrate a clear trend towards high expert granularity (smaller expert intermediate dimension) and higher sparsity (constant number of activated experts with higher number of total experts), which improve model quality per FLOP. However, fine-grained MoEs suffer from increased activation memory footprint and reduced hardware efficiency due to higher IO costs, while sparser MoEs suffer from wasted computations due to padding in Grouped GEMM kernels. In response, we propose a memory-efficient algorithm to compute the forward and backward passes of MoEs with minimal activation caching for the backward pass. We also design GPU kernels that overlap memory IO with computation benefiting all MoE architectures. Finally, we propose a novel "token rounding" method that minimizes the wasted compute due to padding in Grouped GEMM kernels. As a result, our method SonicMoE reduces activation memory by 45% and achieves a 1.86x compute throughput improvement on Hopper GPUs compared to ScatterMoE's BF16 MoE kernel for a fine-grained 7B MoE. Concretely, SonicMoE on 64 H100s achieves a training throughput of 213 billion tokens per day comparable to ScatterMoE's 225 billion tokens per day on 96 H100s for a 7B MoE model training with FSDP-2 using the lm-engine codebase. Under high MoE sparsity settings, our tile-aware token rounding algorithm yields an additional 1.16x speedup on kernel execution time compared to vanilla top-$K$ routing while maintaining similar downstream performance. We open-source all our kernels to enable faster MoE model training.
Authors: Taig Singh, Shreshth Rajan, Nikhil Iyer
Abstract: As modern neural networks become increasingly memory-bound, inference throughput is limited by DRAM bandwidth rather than compute. We present Arithmetic-Intensity-Aware Quantization (AIQ), a mixed precision quantization framework that chooses per-layer bit-widths to maximize arithmetic intensity (AI) while minimizing accuracy loss. AIQ is a post-training quantization method that uses search algorithms over per-layer quantization schemes to minimize a weighted loss over AI and accuracy. On ResNet-20/CIFAR-10, AIQ increases AI by ~50% over an FP32 baseline while keeping test accuracy within ~1 percentage point, and outperforming global uniform quantization schemes. On a memory-bound MobileNetV2 architecture, AIQ configurations give a 1.66x higher throughput than the FP32 baseline while keeping test accuracy within 1 percentage point. We also find that AIQ naturally quantizes larger layers more aggressively.
Authors: Felix Holm, Ghazal Ghazaei, Nassir Navab
Abstract: Purpose: Detailed surgical recognition is critical for advancing AI-assisted surgery, yet progress is hampered by high annotation costs, data scarcity, and a lack of interpretable models. While scene graphs offer a structured abstraction of surgical events, their full potential remains untapped. In this work, we introduce ProtoFlow, a novel framework that learns dynamic scene graph prototypes to model complex surgical workflows in an interpretable and robust manner. Methods: ProtoFlow leverages a graph neural network (GNN) encoder-decoder architecture that combines self-supervised pretraining for rich representation learning with a prototype-based fine-tuning stage. This process discovers and refines core prototypes that encapsulate recurring, clinically meaningful patterns of surgical interaction, forming an explainable foundation for workflow analysis. Results: We evaluate our approach on the fine-grained CAT-SG dataset. ProtoFlow not only outperforms standard GNN baselines in overall accuracy but also demonstrates exceptional robustness in limited-data, few-shot scenarios, maintaining strong performance when trained on as few as one surgical video. Our qualitative analyses further show that the learned prototypes successfully identify distinct surgical sub-techniques and provide clear, interpretable insights into workflow deviations and rare complications. Conclusion: By uniting robust representation learning with inherent explainability, ProtoFlow represents a significant step toward developing more transparent, reliable, and data-efficient AI systems, accelerating their potential for clinical adoption in surgical training, real-time decision support, and workflow optimization.
Authors: Emanuele Mezzi, Gertjan Burghouts, Maarten Kruithof
Abstract: Text-to-image retrieval in remote sensing (RS) has advanced rapidly with the rise of large vision-language models (LVLMs) tailored for aerial and satellite imagery, culminating in remote sensing large vision-language models (RS-LVLMS). However, limited explainability and poor handling of complex spatial relations remain key challenges for real-world use. To address these issues, we introduce RUNE (Reasoning Using Neurosymbolic Entities), an approach that combines Large Language Models (LLMs) with neurosymbolic AI to retrieve images by reasoning over the compatibility between detected entities and First-Order Logic (FOL) expressions derived from text queries. Unlike RS-LVLMs that rely on implicit joint embeddings, RUNE performs explicit reasoning, enhancing performance and interpretability. For scalability, we propose a logic decomposition strategy that operates on conditioned subsets of detected entities, guaranteeing shorter execution time compared to neural approaches. Rather than using foundation models for end-to-end retrieval, we leverage them only to generate FOL expressions, delegating reasoning to a neurosymbolic inference module. For evaluation we repurpose the DOTA dataset, originally designed for object detection, by augmenting it with more complex queries than in existing benchmarks. We show the LLM's effectiveness in text-to-logic translation and compare RUNE with state-of-the-art RS-LVLMs, demonstrating superior performance. We introduce two metrics, Retrieval Robustness to Query Complexity (RRQC) and Retrieval Robustness to Image Uncertainty (RRIU), which evaluate performance relative to query complexity and image uncertainty. RUNE outperforms joint-embedding models in complex RS retrieval tasks, offering gains in performance, robustness, and explainability. We show RUNE's potential for real-world RS applications through a use case on post-flood satellite image retrieval.
Authors: Wenbo Tian, Ruting Lin, Hongxian Zheng, Yaodong Yang, Geng Wu, Zihao Zhang, Zhang Zhang
Abstract: Existing intelligent sports analysis systems mainly focus on "scoring and visualization," often lacking automatic performance diagnosis and interpretable training guidance. Recent advances of Large Language Models (LMMs) and motion analysis techniques provide new opportunities to address the above limitations. In this paper, we propose SportsGPT, an LLM-driven framework for interpretable sports motion assessment and training guidance, which establishes a closed loop from motion time-series input to professional training guidance. First, given a set of high-quality target models, we introduce MotionDTW, a two-stage time series alignment algorithm designed for accurate keyframe extraction from skeleton-based motion sequences. Subsequently, we design a Knowledge-based Interpretable Sports Motion Assessment Model (KISMAM) to obtain a set of interpretable assessment metrics (e.g., insufficient extension) by constrasting the keyframes with the targe models. Finally, we propose SportsRAG, a RAG-based training guidance model based on Qwen3. Leveraging a 6B-token knowledge base, it prompts the LLM to generate professional training guidance by retrieving domain-specific QA pairs. Experimental results demonstrate that MotionDTW significantly outperforms traditional methods with lower temporal error and higher IoU scores. Furthermore, ablation studies validate the KISMAM and SportsRAG, confirming that SportsGPT surpasses general LLMs in diagnostic accuracy and professionalism.
Authors: Amirmohammad Pasdar, Toby Murray, Van-Thuan Pham
Abstract: We introduce UIXPOSE, a source-code-agnostic framework that operates on both compiled and open-source apps. This framework applies Intention Behaviour Alignment (IBA) to mobile malware analysis, aligning UI-inferred intent with runtime semantics. Previous work either infers intent statically, e.g., permission-centric, or widget-level or monitors coarse dynamic signals (endpoints, partial resource usage) that miss content and context. UIXPOSE infers an intent vector from each screen using vision-language models and knowledge structures and combines decoded network payloads, heap/memory signals, and resource utilisation traces into a behaviour vector. Their alignment, calculated at runtime, can both detect misbehaviour and highlight exploration of behaviourally rich paths. In three real-world case studies, UIXPOSE reveals covert exfiltration and hidden background activity that evade metadata-only baselines, demonstrating how IBA improves dynamic detection.
Authors: So Kuroki, Manami Nakagawa, Shigeo Yoshida, Yuki Koyama, Kozuno Tadashi
Abstract: Many real-world tasks, such as trip planning or meal planning, can be formulated as combinatorial optimization problems. However, using optimization solvers is difficult for end users because it requires problem instantiation: defining candidate items, assigning preference scores, and specifying constraints. We introduce LAPPI (LLM-Assisted Preference-based Problem Instantiation), an interactive approach that uses large language models (LLMs) to support users in this instantiation process. Through natural language conversations, the system helps users transform vague preferences into well-defined optimization problems. These instantiated problems are then passed to existing optimization solvers to generate solutions. In a user study on trip planning, our method successfully captured user preferences and generated feasible plans that outperformed both conventional and prompt-engineering approaches. We further demonstrate LAPPI's versatility by adapting it to an additional use case.
Authors: Hanning Chen, Keyu Man, Kevin Zhu, Chenguang Zhu, Haonan Li, Tongbo Luo, Xizhou Feng, Wei Sun, Sreen Tallam, Mohsen Imani, Partha Kanuparthy
Abstract: Identifying and addressing performance anti-patterns in machine learning (ML) models is critical for efficient training and inference, but it typically demands deep expertise spanning system infrastructure, ML models and kernel development. While large tech companies rely on dedicated ML infrastructure engineers to analyze torch traces and benchmarks, such resource-intensive workflows are largely inaccessible to computer vision researchers in general. Among the challenges, pinpointing problematic trace segments within lengthy execution traces remains the most time-consuming task, and is difficult to automate with current ML models, including LLMs. In this work, we present the first benchmark dataset specifically designed to evaluate and improve ML models' ability to detect anti patterns in traces. Our dataset contains over 600 PyTorch traces from diverse computer vision models classification, detection, segmentation, and generation collected across multiple hardware platforms. We also propose a novel iterative approach: a lightweight ML model first detects trace segments with anti patterns, followed by a large language model (LLM) for fine grained classification and targeted feedback. Experimental results demonstrate that our method significantly outperforms unsupervised clustering and rule based statistical techniques for detecting anti pattern regions. Our method also effectively compensates LLM's limited context length and reasoning inefficiencies.
Authors: Zhijie Zhong, Zhiwen Yu, Pengyu Li, Jianming Lv, C. L. Philip Chen, Min Chen
Abstract: Radio path loss prediction (RPP) is critical for optimizing 5G networks and enabling IoT, smart city, and similar applications. However, current deep learning-based RPP methods lack proactive environmental modeling, struggle with realistic multi-transmitter scenarios, and generalize poorly under distribution shifts, particularly when training/testing environments differ in building density or transmitter configurations. This paper identifies three key issues: (1) passive environmental modeling that overlooks transmitters and key environmental features; (2) overemphasis on single-transmitter scenarios despite real-world multi-transmitter prevalence; (3) excessive focus on in-distribution performance while neglecting distribution shift challenges. To address these, we propose PathFinder, a novel architecture that actively models buildings and transmitters via disentangled feature encoding and integrates Mask-Guided Low-rank Attention to independently focus on receiver and building regions. We also introduce a Transmitter-Oriented Mixup strategy for robust training and a new benchmark, single-to-multi-transmitter RPP (S2MT-RPP), tailored to evaluate extrapolation performance (multi-transmitter testing after single-transmitter training). Experimental results show PathFinder outperforms state-of-the-art methods significantly, especially in challenging multi-transmitter scenarios. Our code and project site are available at: https://emorzz1g.github.io/PathFinder/.
Authors: Yunhao Yao, Zhiqiang Wang, Haoran Cheng, Yihang Cheng, Haohua Du, Xiang-Yang Li
Abstract: The rapid evolution of Large Language Models (LLMs) into autonomous agents has led to the adoption of the Model Context Protocol (MCP) as a standard for discovering and invoking external tools. While this architecture decouples the reasoning engine from tool execution to enhance scalability, it introduces a significant privacy surface: third-party MCP servers, acting as semi-honest intermediaries, can observe detailed tool interaction logs outside the user's trusted boundary. In this paper, we first identify and formalize a novel privacy threat termed Intent Inversion, where a semi-honest MCP server attempts to reconstruct the user's private underlying intent solely by analyzing legitimate tool calls. To systematically assess this vulnerability, we propose IntentMiner, a framework that leverages Hierarchical Information Isolation and Three-Dimensional Semantic Analysis, integrating tool purpose, call statements, and returned results, to accurately infer user intent at the step level. Extensive experiments demonstrate that IntentMiner achieves a high degree of semantic alignment (over 85%) with original user queries, significantly outperforming baseline approaches. These results highlight the inherent privacy risks in decoupled agent architectures, revealing that seemingly benign tool execution logs can serve as a potent vector for exposing user secrets.
Authors: K. M. Jubair Sami, Dipto Sumit, Ariyan Hossain, Farig Sadeque
Abstract: Translating from a standard language to its regional dialects is a significant NLP challenge due to scarce data and linguistic variation, a problem prominent in the Bengali language. This paper proposes and compares two novel RAG pipelines for standard-to-dialectal Bengali translation. The first, a Transcript-Based Pipeline, uses large dialect sentence contexts from audio transcripts. The second, a more effective Standardized Sentence-Pairs Pipeline, utilizes structured local\_dialect:standard\_bengali sentence pairs. We evaluated both pipelines across six Bengali dialects and multiple LLMs using BLEU, ChrF, WER, and BERTScore. Our findings show that the sentence-pair pipeline consistently outperforms the transcript-based one, reducing Word Error Rate (WER) from 76\% to 55\% for the Chittagong dialect. Critically, this RAG approach enables smaller models (e.g., Llama-3.1-8B) to outperform much larger models (e.g., GPT-OSS-120B), demonstrating that a well-designed retrieval strategy can be more crucial than model size. This work contributes an effective, fine-tuning-free solution for low-resource dialect translation, offering a practical blueprint for preserving linguistic diversity.
Authors: Shaolun Ruan, Feng Liang, Rohan Ramakrishna, Chao Ren, Rudai Yan, Qiang Guan, Jiannan Li, Yong Wang
Abstract: Quantum Neural Networks (QNNs) represent a promising fusion of quantum computing and neural network architectures, offering speed-ups and efficient processing of high-dimensional, entangled data. A crucial component of QNNs is the encoder, which maps classical input data into quantum states. However, choosing suitable encoders remains a significant challenge, largely due to the lack of systematic guidance and the trial-and-error nature of current approaches. This process is further impeded by two key challenges: (1) the difficulty in evaluating encoded quantum states prior to training, and (2) the lack of intuitive methods for analyzing an encoder's ability to effectively distinguish data features. To address these issues, we introduce a novel visualization tool, XQAI-Eyes, which enables QNN developers to compare classical data features with their corresponding encoded quantum states and to examine the mixed quantum states across different classes. By bridging classical and quantum perspectives, XQAI-Eyes facilitates a deeper understanding of how encoders influence QNN performance. Evaluations across diverse datasets and encoder designs demonstrate XQAI-Eyes's potential to support the exploration of the relationship between encoder design and QNN effectiveness, offering a holistic and transparent approach to optimizing quantum encoders. Moreover, domain experts used XQAI-Eyes to derive two key practices for quantum encoder selection, grounded in the principles of pattern preservation and feature mapping.
Authors: Emanuele Artioli, Farzad Tashtarian, Christian Timmerer
Abstract: The primary challenge of video streaming is to balance high video quality with smooth playback. Traditional codecs are well tuned for this trade-off, yet their inability to use context means they must encode the entire video data and transmit it to the client. This paper introduces ELVIS (End-to-end Learning-based VIdeo Streaming Enhancement Pipeline), an end-to-end architecture that combines server-side encoding optimizations with client-side generative in-painting to remove and reconstruct redundant video data. Its modular design allows ELVIS to integrate different codecs, inpainting models, and quality metrics, making it adaptable to future innovations. Our results show that current technologies achieve improvements of up to 11 VMAF points over baseline benchmarks, though challenges remain for real-time applications due to computational demands. ELVIS represents a foundational step toward incorporating generative AI into video streaming pipelines, enabling higher quality experiences without increased bandwidth requirements.
Authors: Timo Klein, Thomas Lang, Andrii Shkabrii, Alexander Sturm, Kevin Sidak, Lukas Miklautz, Claudia Plant, Yllka Velaj, Sebastian Tschiatschek
Abstract: The performance of reinforcement learning (RL) agents depends critically on the quality of the underlying feature representations. Hyperbolic feature spaces are well-suited for this purpose, as they naturally capture hierarchical and relational structure often present in complex RL environments. However, leveraging these spaces commonly faces optimization challenges due to the nonstationarity of RL. In this work, we identify key factors that determine the success and failure of training hyperbolic deep RL agents. By analyzing the gradients of core operations in the Poincar\'e Ball and Hyperboloid models of hyperbolic geometry, we show that large-norm embeddings destabilize gradient-based training, leading to trust-region violations in proximal policy optimization (PPO). Based on these insights, we introduce Hyper++, a new hyperbolic PPO agent that consists of three components: (i) stable critic training through a categorical value loss instead of regression; (ii) feature regularization guaranteeing bounded norms while avoiding the curse of dimensionality from clipping; and (iii) using a more optimization-friendly formulation of hyperbolic network layers. In experiments on ProcGen, we show that Hyper++ guarantees stable learning, outperforms prior hyperbolic agents, and reduces wall-clock time by approximately 30%. On Atari-5 with Double DQN, Hyper++ strongly outperforms Euclidean and hyperbolic baselines. We release our code at https://github.com/Probabilistic-and-Interactive-ML/hyper-rl .
URLs: https://github.com/Probabilistic-and-Interactive-ML/hyper-rl
Authors: Mengxue Zhang, Qingrui Cai, Yinyin Chen, Hang Jin, Jianjun Zhou, Qiu Guo, Peijun Zhao, Zhiping Mao, Xingxing Zhang, Yuyu Xia, Xianwang Jiang, Qin Xu, Chunyan Xiong, Yirong Zhou, Chengyan Wang, Xiaobo Qu
Abstract: Physics-Informed Neural Networks (PINN) are emerging as a promising approach for quantitative parameter estimation of Magnetic Resonance Imaging (MRI). While existing deep learning methods can provide an accurate quantitative estimation of the T2 parameter, they still require large amounts of training data and lack theoretical support and a recognized gold standard. Thus, given the absence of PINN-based approaches for T2 estimation, we propose embedding the fundamental physics of MRI, the Bloch equation, in the loss of PINN, which is solely based on target scan data and does not require a pre-defined training database. Furthermore, by deriving rigorous upper bounds for both the T2 estimation error and the generalization error of the Bloch equation solution, we establish a theoretical foundation for evaluating the PINN's quantitative accuracy. Even without access to the ground truth or a gold standard, this theory enables us to estimate the error with respect to the real quantitative parameter T2. The accuracy of T2 mapping and the validity of the theoretical analysis are demonstrated on a numerical cardiac model and a water phantom, where our method exhibits excellent quantitative precision in the myocardial T2 range. Clinical applicability is confirmed in 94 acute myocardial infarction (AMI) patients, achieving low-error quantitative T2 estimation under the theoretical error bound, highlighting the robustness and potential of PINN.
Authors: Marthe Ballon, Andres Algaba, Brecht Verbeken, Vincent Ginis
Abstract: Recent advances in the finetuning of large language models (LLMs) have significantly improved their performance on established benchmarks, emphasizing the need for increasingly difficult, synthetic data. A key step in this data generation pipeline is a method for estimating problem difficulty. Current approaches, such as human calibration or performance-based scoring, fail to generalize to out-of-distribution problems, i.e. problems currently unsolvable by humans and LLMs, because they are not scalable, time-consuming, and ground truth dependent. Therefore, we propose a new method for estimating problem difficulty, LLM compare, that addresses these limitations. An LLM performs pairwise difficulty comparisons, and then Bradley-Terry scores are computed based on the outcomes. To validate our method, we first propose a conceptual framework that positions existing approaches on three orthogonal planes--construction, scale and dependence--identifying which quadrants a measure needs to occupy to score out-of-distribution problems. LLM compare naturally occupies all desirable quadrants as the first measure that is continuous and dynamic, model-agnostic and independent of ground truth information. As a second validation, we show that LLM compare demonstrates strong alignment with human annotations: Pearson $r \geq 0.80$ for $n=1876$. Thirdly, we show that LLM compare is robust to hallucinations, with less than $6\%$ degradation in Pearson correlation for $10\%$ noise injection. Our work represents a significant step towards replacing time-consuming human annotations and synthetic data generation, and will be an important driver for curriculum design, model evaluation, and AI-assisted research ideation.
Authors: Ruozhao Yang, Mingfei Cheng, Gelei Deng, Tianwei Zhang, Junjie Wang, Xiaofei Xie
Abstract: Penetration testing is essential for assessing and strengthening system security against real-world threats, yet traditional workflows remain highly manual, expertise-intensive, and difficult to scale. Although recent advances in Large Language Models (LLMs) offer promising opportunities for automation, existing applications rely on simplistic prompting without task decomposition or domain adaptation, resulting in unreliable black-box behavior and limited insight into model capabilities across penetration testing stages. To address this gap, we introduce PentestEval, the first comprehensive benchmark for evaluating LLMs across six decomposed penetration testing stages: Information Collection, Weakness Gathering and Filtering, Attack Decision-Making, Exploit Generation and Revision. PentestEval integrates expert-annotated ground truth with a fully automated evaluation pipeline across 346 tasks covering all stages in 12 realistic vulnerable scenarios. Our stage-level evaluation of 9 widely used LLMs reveals generally weak performance and distinct limitations across the stages of penetration-testing workflow. End-to-end pipelines reach only 31% success rate, and existing LLM-powered systems such as PentestGPT, PentestAgent, and VulnBot exhibit similar limitations, with autonomous agents failing almost entirely. These findings highlight that autonomous penetration testing demands stronger structured reasoning, where modularization enhances each individual stage and improves overall performance. PentestEval provides the foundational benchmark needed for future research on fine-grained, stage-level evaluation, paving the way toward more reliable LLM-based automation.
Authors: Salvatore Romano, Marco Grassia, Giuseppe Mangioni
Abstract: Graph generation is a crucial task in many fields, including network science and bioinformatics, as it enables the creation of synthetic graphs that mimic the properties of real-world networks for various applications. Graph Generative Models (GGMs) have emerged as a promising solution to this problem, leveraging deep learning techniques to learn the underlying distribution of real-world graphs and generate new samples that closely resemble them. Examples include approaches based on Variational Auto-Encoders, Recurrent Neural Networks, and more recently, diffusion-based models. However, the main limitation often lies in the evaluation process, which typically relies on Maximum Mean Discrepancy (MMD) as a metric to assess the distribution of graph properties in the generated ensemble. This paper introduces a novel methodology for evaluating GGMs that overcomes the limitations of MMD, which we call RGM (Representation-aware Graph-generation Model evaluation). As a practical demonstration of our methodology, we present a comprehensive evaluation of two state-of-the-art Graph Generative Models: Graph Recurrent Attention Networks (GRAN) and Efficient and Degree-guided graph GEnerative model (EDGE). We investigate their performance in generating realistic graphs and compare them using a Geometric Deep Learning model trained on a custom dataset of synthetic and real-world graphs, specifically designed for graph classification tasks. Our findings reveal that while both models can generate graphs with certain topological properties, they exhibit significant limitations in preserving the structural characteristics that distinguish different graph domains. We also highlight the inadequacy of Maximum Mean Discrepancy as an evaluation metric for GGMs and suggest alternative approaches for future research.
Authors: Yiqing Zhou, Yu Lei, Shuzheng Si, Qingyan Sun, Wei Wang, Yifei Wu, Hao Wen, Gang Chen, Fanchao Qi, Maosong Sun
Abstract: Managing extensive context remains a critical bottleneck for Large Language Models (LLMs), particularly in applications like long-document question answering and autonomous agents where lengthy inputs incur high computational costs and introduce noise. Existing compression techniques often disrupt local coherence through discrete token removal or rely on implicit latent encoding that suffers from positional bias and incompatibility with closed-source APIs. To address these limitations, we introduce the EDU-based Context Compressor, a novel explicit compression framework designed to preserve both global structure and fine-grained details. Our approach reformulates context compression as a structure-then-select process. First, our LingoEDU transforms linear text into a structural relation tree of Elementary Discourse Units (EDUs) which are anchored strictly to source indices to eliminate hallucination. Second, a lightweight ranking module selects query-relevant sub-trees for linearization. To rigorously evaluate structural understanding, we release StructBench, a manually annotated dataset of 248 diverse documents. Empirical results demonstrate that our method achieves state-of-the-art structural prediction accuracy and significantly outperforms frontier LLMs while reducing costs. Furthermore, our structure-aware compression substantially enhances performance across downstream tasks ranging from long-context tasks to complex Deep Search scenarios.
Authors: Nick Leenders, Thomas Quadt, Boris Cule, Roy Lindelauf, Herman Monsuur, Joost van Oijen, Mark Voskuijl
Abstract: Current Preferential Bayesian Optimization methods rely on Gaussian Processes (GPs) as surrogate models. These models are hard to interpret, struggle with handling categorical data, and are computationally complex, limiting their real-world usability. In this paper, we introduce an inherently interpretable decision tree-based surrogate model capable of handling both categorical and continuous data, and scalable to large datasets. Extensive numerical experiments on eight increasingly spiky optimization functions show that our model outperforms GP-based alternatives on spiky functions and has only marginally lower performance for non-spiky functions. Moreover, we apply our model to the real-world Sushi dataset and show its ability to learn an individual's sushi preferences. Finally, we show some initial work on using historical preference data to speed up the optimization process for new unseen users.
Authors: Panayiotis Smeros, Vincent Emonet, Ruijie Wang, Ana-Claudia Sima, Tarcisio Mendes de Farias
Abstract: The advent of large language models is contributing to the emergence of novel approaches that promise to better tackle the challenge of generating structured queries, such as SPARQL queries, from natural language. However, these new approaches mostly focus on response accuracy over a single source while ignoring other evaluation criteria, such as federated query capability over distributed data stores, as well as runtime and cost to generate SPARQL queries. Consequently, they are often not production-ready or easy to deploy over (potentially federated) knowledge graphs with good accuracy. To mitigate these issues, in this paper, we extend our previous work and describe and systematically evaluate SPARQL-LLM, an open-source and triplestore-agnostic approach, powered by lightweight metadata, that generates SPARQL queries from natural language text. First, we describe its architecture, which consists of dedicated components for metadata indexing, prompt building, and query generation and execution. Then, we evaluate it based on a state-of-the-art challenge with multilingual questions, and a collection of questions from three of the most prevalent knowledge graphs within the field of bioinformatics. Our results demonstrate a substantial increase of 24% in the F1 Score on the state-of-the-art challenge, adaptability to high-resource languages such as English and Spanish, as well as ability to form complex and federated bioinformatics queries. Furthermore, we show that SPARQL-LLM is up to 36x faster than other systems participating in the challenge, while costing a maximum of $0.01 per question, making it suitable for real-time, low-cost text-to-SPARQL applications. One such application deployed over real-world decentralized knowledge graphs can be found at https://www.expasy.org/chat.
Authors: Marvin Kopka, Azeem Majeed, Gabriella Spinelli, Austen El-Osta, Markus Feufel
Abstract: Artificial Intelligence tools such as large language models are increasingly used by the public to obtain health information and guidance. In health-related contexts, following or rejecting AI-generated advice can have direct clinical implications. Existing instruments like the Trust in Automated Systems Survey assess trustworthiness of generic technology, and no validated instrument measures users' trust in AI-generated health advice specifically. This study developed and validated the Trust in AI-Generated Health Advice (TAIGHA) scale and its four-item short form (TAIGHA-S) as theory-based instruments measuring trust and distrust, each with cognitive and affective components. The items were developed using a generative AI approach, followed by content validation with 10 domain experts, face validation with 30 lay participants, and psychometric validation with 385 UK participants who received AI-generated advice in a symptom-assessment scenario. After automated item reduction, 28 items were retained and reduced to 10 based on expert ratings. TAIGHA showed excellent content validity (S-CVI/Ave=0.99) and CFA confirmed a two-factor model with excellent fit (CFI=0.98, TLI=0.98, RMSEA=0.07, SRMR=0.03). Internal consistency was high ({\alpha}=0.95). Convergent validity was supported by correlations with the Trust in Automated Systems Survey (r=0.67/-0.66) and users' reliance on the AI's advice (r=0.37 for trust), while divergent validity was supported by low correlations with reading flow and mental load (all |r|<0.25). TAIGHA-S correlated highly with the full scale (r=0.96) and showed good reliability ({\alpha}=0.88). TAIGHA and TAIGHA-S are validated instruments for assessing user trust and distrust in AI-generated health advice. Reporting trust and distrust separately permits a more complete evaluation of AI interventions, and the short scale is well-suited for time-constrained settings.
Authors: Agrippina Mwangi (Utrecht University, The Netherlands), Le\'on Navarro-Hilfiker ({\O}rsted, USA), Lukasz Brewka ({\O}rsted, Denmark), Mikkel Gryning ({\O}rsted, Denmark), Elena Fumagalli (Utrecht University, The Netherlands), Madeleine Gibescu (Utrecht University, The Netherlands)
Abstract: Stochastic disruptions such as flash events arising from benign traffic bursts and switch thermal fluctuations are major contributors to intermittent service degradation in software-defined industrial networks. These events violate IEC~61850-derived quality-of-service requirements and user-defined service-level agreements, hindering the reliable and timely delivery of control, monitoring, and best-effort traffic in IEC~61400-25-compliant wind power plants. Failure to maintain these requirements often results in delayed or lost control signals, reduced operational efficiency, and increased risk of wind turbine generator downtime. To address these challenges, this study proposes a threshold-triggered Deep Q-Network self-healing agent that autonomically detects, analyzes, and mitigates network disruptions while adapting routing behavior and resource allocation in real time. The proposed agent was trained, validated, and tested on an emulated tri-clustered switch network deployed in a cloud-based proof-of-concept testbed. Simulation results show that the proposed agent improves disruption recovery performance by 53.84% compared to a baseline shortest-path and load-balanced routing approach and outperforms state-of-the-art methods, including the Adaptive Network-based Fuzzy Inference System by 13.1% and the Deep Q-Network and traffic prediction-based routing optimization method by 21.5%, in a super-spine leaf data-plane architecture. Additionally, the agent maintains switch thermal stability by proactively initiating external rack cooling when required. These findings highlight the potential of deep reinforcement learning in building resilience in software-defined industrial networks deployed in mission-critical, time-sensitive application scenarios.
Authors: Akila Premarathna, Kanishka Hewageegana, Garcia Andarcia Mariangel
Abstract: In regions of the Middle East and North Africa (MENA), there is a high demand for wastewater treatment plants (WWTPs), crucial for sustainable water management. Precise identification of WWTPs from satellite images enables environmental monitoring. Traditional methods like YOLOv8 segmentation require extensive manual labeling. But studies indicate that vision-language models (VLMs) are an efficient alternative to achieving equivalent or superior results through inherent reasoning and annotation. This study presents a structured methodology for VLM comparison, divided into zero-shot and few-shot streams specifically to identify WWTPs. The YOLOv8 was trained on a governmental dataset of 83,566 high-resolution satellite images from Egypt, Saudi Arabia, and UAE: ~85% WWTPs (positives), 15% non-WWTPs (negatives). Evaluated VLMs include LLaMA 3.2 Vision, Qwen 2.5 VL, DeepSeek-VL2, Gemma 3, Gemini, and Pixtral 12B (Mistral), used to identify WWTP components such as circular/rectangular tanks, aeration basins and distinguish confounders via expert prompts producing JSON outputs with confidence and descriptions. The dataset comprises 1,207 validated WWTP locations (198 UAE, 354 KSA, 655 Egypt) and equal non-WWTP sites from field/AI data, as 600mx600m Geo-TIFF images (Zoom 18, EPSG:4326). Zero-shot evaluations on WWTP images showed several VLMs out-performing YOLOv8's true positive rate, with Gemma-3 highest. Results confirm that VLMs, particularly with zero-shot, can replace YOLOv8 for efficient, annotation-free WWTP classification, enabling scalable remote sensing.
Authors: Shuai Dong, Jie Zhang, Guoying Zhao, Shiguang Shan, Xilin Chen
Abstract: Text-guided image editing via diffusion models, while powerful, raises significant concerns about misuse, motivating efforts to immunize images against unauthorized edits using imperceptible perturbations. Prevailing metrics for evaluating immunization success typically rely on measuring the visual dissimilarity between the output generated from a protected image and a reference output generated from the unprotected original. This approach fundamentally overlooks the core requirement of image immunization, which is to disrupt semantic alignment with attacker intent, regardless of deviation from any specific output. We argue that immunization success should instead be defined by the edited output either semantically mismatching the prompt or suffering substantial perceptual degradations, both of which thwart malicious intent. To operationalize this principle, we propose Synergistic Intermediate Feature Manipulation (SIFM), a method that strategically perturbs intermediate diffusion features through dual synergistic objectives: (1) maximizing feature divergence from the original edit trajectory to disrupt semantic alignment with the expected edit, and (2) minimizing feature norms to induce perceptual degradations. Furthermore, we introduce the Immunization Success Rate (ISR), a novel metric designed to rigorously quantify true immunization efficacy for the first time. ISR quantifies the proportion of edits where immunization induces either semantic failure relative to the prompt or significant perceptual degradations, assessed via Multimodal Large Language Models (MLLMs). Extensive experiments show our SIFM achieves the state-of-the-art performance for safeguarding visual content against malicious diffusion-based manipulation.
Authors: Yanning Dai, Chenyu Tang, Ruizhi Zhang, Wenyu Yang, Yilan Zhang, Yuhui Wang, Junliang Chen, Xuhang Chen, Ruimou Xie, Yangyue Cao, Qiaoying Li, Jin Cao, Tao Li, Hubin Zhao, Yu Pan, Arokia Nathan, Xin Gao, Peter Smielewski, Shuo Gao
Abstract: Dynamic prediction of locomotor capacity after stroke is crucial for tailoring rehabilitation, yet current assessments provide only static impairment scores and do not indicate whether patients can safely perform specific tasks such as slope walking or stair climbing. Here, we develop a data-physics hybrid generative framework that reconstructs an individual stroke survivor's neuromuscular control from a single 20 m level-ground walking trial and predicts task-conditioned locomotion across rehabilitation scenarios. The system combines wearable-sensor kinematics, a proportional-derivative physics controller, a population Healthy Motion Atlas, and goal-conditioned deep reinforcement learning with behaviour cloning and generative adversarial imitation learning to generate physically plausible, patient-specific gait simulations for slopes and stairs. In 11 stroke survivors, the personalized controllers preserved idiosyncratic gait patterns while improving joint-angle and endpoint fidelity by 4.73% and 12.10%, respectively, and reducing training time to 25.56% relative to a physics-only baseline. In a multicentre pilot involving 21 inpatients, clinicians who used our locomotion predictions to guide task selection and difficulty obtained larger gains in Fugl-Meyer lower-extremity scores over 28 days of standard rehabilitation than control clinicians (mean change 6.0 versus 3.7 points). These findings indicate that our generative, task-predictive framework can augment clinical decision-making in post-stroke gait rehabilitation and provide a template for dynamically personalized motor recovery strategies.
Authors: Sahibpreet Singh, Manjit Singh
Abstract: AI revolutionizes transportation through autonomous vehicles (AVs) but introduces complex criminal liability issues regarding infractions. This study employs a comparative legal analysis of primary statutes, real-world liability claims, and academic literature across the US, Germany, UK, China, and India; jurisdictions selected for their technological advancement and contrasting regulatory approaches. The research examines the attribution of human error, AI moral agency, and the identification of primary offenders in AV incidents. Findings reveal fragmented regulatory landscapes: India and the US rely on loose networks of state laws, whereas the UK enacted the pioneering Automated and Electric Vehicles Act 2018. Germany enforces strict safety standards, distinguishing liability based on the vehicle's operating mode, while China similarly aims for a stringent liability regime. The study concludes that globally harmonized legal standards are essential to foster technological innovation while ensuring minimum risk and clear liability attribution.
Authors: Yannis Belkhiter, Seshu Tirupathi, Giulio Zizzo, John D. Kelleher
Abstract: The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that LRMs are still inefficient, over-generating verification and reflection steps. To address this challenge, we introduce the Step-Tagging framework, a lightweight sentence-classifier enabling real-time annotation of the type of reasoning steps that an LRM is generating. To monitor reasoning behaviors, we introduced ReasonType: a novel taxonomy of reasoning steps. Building on this framework, we demonstrated that online monitoring of the count of specific steps can produce effective interpretable early stopping criteria of LRM inferences. We evaluate the Step-tagging framework on three open-source reasoning models across standard benchmark datasets: MATH500, GSM8K, AIME and non-mathematical tasks (GPQA and MMLU-Pro). We achieve 20 to 50\% token reduction while maintaining comparable accuracy to standard generation, with largest gains observed on more computation-heavy tasks. This work offers a novel way to increase control over the generation of LRMs, and a new tool to study behaviors of LRMs.
Authors: Jie Zhang, Shuai Dong, Shiguang Shan, Xilin Chen
Abstract: Recent progress in text-to-image diffusion models has transformed image editing via text prompts, yet this also introduces significant ethical challenges from potential misuse in creating deceptive or harmful content. While current defenses seek to mitigate this risk by embedding imperceptible perturbations, their effectiveness is limited against malicious tampering. To address this issue, we propose a Dual Attention-Guided Noise Perturbation (DANP) immunization method that adds imperceptible perturbations to disrupt the model's semantic understanding and generation process. DANP functions over multiple timesteps to manipulate both cross-attention maps and the noise prediction process, using a dynamic threshold to generate masks that identify text-relevant and irrelevant regions. It then reduces attention in relevant areas while increasing it in irrelevant ones, thereby misguides the edit towards incorrect regions and preserves the intended targets. Additionally, our method maximizes the discrepancy between the injected noise and the model's predicted noise to further interfere with the generation. By targeting both attention and noise prediction mechanisms, DANP exhibits impressive immunity against malicious edits, and extensive experiments confirm that our method achieves state-of-the-art performance.
Authors: Jie Zhang, Shuai Dong, Shiguang Shan, Xilin Chen
Abstract: Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer from limited transferability in cross-model evaluations. To address this, we propose Transferable Defense Against Malicious Image Edits (TDAE), a novel bimodal framework that enhances image immunity against malicious edits through coordinated image-text optimization. Specifically, at the visual defense level, we introduce FlatGrad Defense Mechanism (FDM), which incorporates gradient regularization into the adversarial objective. By explicitly steering the perturbations toward flat minima, FDM amplifies immune robustness against unseen editing models. For textual enhancement protection, we propose an adversarial optimization paradigm named Dynamic Prompt Defense (DPD), which periodically refines text embeddings to align the editing outcomes of immunized images with those of the original images, then updates the images under optimized embeddings. Through iterative adversarial updates to diverse embeddings, DPD enforces the generation of immunized images that seek a broader set of immunity-enhancing features, thereby achieving cross-model transferability. Extensive experimental results demonstrate that our TDAE achieves state-of-the-art performance in mitigating malicious edits under both intra- and cross-model evaluations.
Authors: Kanglong Fan, Yunqiao Yang, Chen Ma
Abstract: Deep neural networks have demonstrated remarkable performance across various domains, yet their decision-making processes remain opaque. Although many explanation methods are dedicated to bringing the obscurity of DNNs to light, they exhibit significant limitations: post-hoc explanation methods often struggle to faithfully reflect model behaviors, while self-explaining neural networks sacrifice performance and compatibility due to their specialized architectural designs. To address these challenges, we propose a novel self-explaining framework that integrates Shapley value estimation as an auxiliary task during training, which achieves two key advancements: 1) a fair allocation of the model prediction scores to image patches, ensuring explanations inherently align with the model's decision logic, and 2) enhanced interpretability with minor structural modifications, preserving model performance and compatibility. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art interpretability.
Authors: Nicholas Tagliapietra, Katharina Ensinger, Christoph Zimmer, Osman Mian
Abstract: Real world systems evolve in continuous-time according to their underlying causal relationships, yet their dynamics are often unknown. Existing approaches to learning such dynamics typically either discretize time -- leading to poor performance on irregularly sampled data -- or ignore the underlying causality. We propose CaDyT, a novel method for causal discovery on dynamical systems addressing both these challenges. In contrast to state-of-the-art causal discovery methods that model the problem using discrete-time Dynamic Bayesian networks, our formulation is grounded in Difference-based causal models, which allow milder assumptions for modeling the continuous nature of the system. CaDyT leverages exact Gaussian Process inference for modeling the continuous-time dynamics which is more aligned with the underlying dynamical process. We propose a practical instantiation that identifies the causal structure via a greedy search guided by the Algorithmic Markov Condition and Minimum Description Length principle. Our experiments show that CaDyT outperforms state-of-the-art methods on both regularly and irregularly-sampled data, discovering causal networks closer to the true underlying dynamics.
Authors: Huayang Li, Tianyu Zhao, Richard Sproat
Abstract: In-context learning is fundamental to modern Large Language Models (LLMs); however, prevailing architectures impose a rigid and fixed contextual structure by assigning linear or constant positional indices. Drawing on Cognitive Load Theory (CLT), we argue that this uninformative structure increases extraneous cognitive load, consuming finite working memory capacity that should be allocated to deep reasoning and attention allocation. To address this, we propose RePo, a novel mechanism that reduces extraneous load via context re-positioning. Unlike standard approaches, RePo utilizes a differentiable module, $f_\phi$, to assign token positions that capture contextual dependencies, rather than replying on pre-defined integer range. By continually pre-training on the OLMo-2 1B backbone, we demonstrate that RePo significantly enhances performance on tasks involving noisy contexts, structured data, and longer context length, while maintaining competitive performance on general short-context tasks. Detailed analysis reveals that RePo successfully allocate higher attention to distant but relevant information, assign positions in dense and non-linear space, and capture the intrinsic structure of the input context. Our code is available at https://github.com/SakanaAI/repo.
Authors: Nakamasa Inoue, Kanoko Goto, Masanari Oi, Martyna Gruszka, Mahiro Ukai, Takumi Hirose, Yusuke Sekikawa
Abstract: Large vision-language models (LVLMs) have shown impressive performance across a broad range of multimodal tasks. However, robust image caption evaluation using LVLMs remains challenging, particularly under domain-shift scenarios. To address this issue, we introduce the Distribution-Aware Score Decoder (DISCODE), a novel finetuning-free method that generates robust evaluation scores better aligned with human judgments across diverse domains. The core idea behind DISCODE lies in its test-time adaptive evaluation approach, which introduces the Adaptive Test-Time (ATT) loss, leveraging a Gaussian prior distribution to improve robustness in evaluation score estimation. This loss is efficiently minimized at test time using an analytical solution that we derive. Furthermore, we introduce the Multi-domain Caption Evaluation (MCEval) benchmark, a new image captioning evaluation benchmark covering six distinct domains, designed to assess the robustness of evaluation metrics. In our experiments, we demonstrate that DISCODE achieves state-of-the-art performance as a reference-free evaluation metric across MCEval and four representative existing benchmarks.
Authors: Gabriele Prato, Shagun Sodhani, Alessandro Sordoni, Sarath Chandar
Abstract: The standard practice for training large language models involves packing multiple documents together to optimize computational efficiency. However, the impact of this process on the models' capabilities remains largely unexplored. To address this gap, we investigate how different document-packing strategies influence the latent multi-hop reasoning abilities of LLMs. Our findings indicate that packing can improve model performance compared to training on individual documents, at the expense of more compute. To further understand the underlying mechanisms, we conduct an ablation study, identifying key factors that explain the advantages of packing. Ultimately, our research deepens the understanding of LLM training dynamics and provides practical insights for optimizing model development.
Authors: Xingfu Zhou, Pengfei Wang
Abstract: Large Language Model (LLM) agents relying on external retrieval are increasingly deployed in high-stakes environments. While existing adversarial attacks primarily focus on content falsification or instruction injection, we identify a novel, process-oriented attack surface: the agent's reasoning style. We propose Reasoning-Style Poisoning (RSP), a paradigm that manipulates how agents process information rather than what they process. We introduce Generative Style Injection (GSI), an attack method that rewrites retrieved documents into pathological tones--specifically "analysis paralysis" or "cognitive haste"--without altering underlying facts or using explicit triggers. To quantify these shifts, we develop the Reasoning Style Vector (RSV), a metric tracking Verification depth, Self-confidence, and Attention focus. Experiments on HotpotQA and FEVER using ReAct, Reflection, and Tree of Thoughts (ToT) architectures reveal that GSI significantly degrades performance. It increases reasoning steps by up to 4.4 times or induces premature errors, successfully bypassing state-of-the-art content filters. Finally, we propose RSP-M, a lightweight runtime monitor that calculates RSV metrics in real-time and triggers alerts when values exceed safety thresholds. Our work demonstrates that reasoning style is a distinct, exploitable vulnerability, necessitating process-level defenses beyond static content analysis.
Authors: Andreas Sj\"olander, Valeria Belloni, Robel Fekadu, Andrea Nascetti
Abstract: Tunnels are essential elements of transportation infrastructure, but are increasingly affected by ageing and deterioration mechanisms such as cracking. Regular inspections are required to ensure their safety, yet traditional manual procedures are time-consuming, subjective, and costly. Recent advances in mobile mapping systems and Deep Learning (DL) enable automated visual inspections. However, their effectiveness is limited by the scarcity of tunnel datasets. This paper introduces a new publicly available dataset containing annotated images of three different tunnel linings, capturing typical defects: cracks, leaching, and water infiltration. The dataset is designed to support supervised, semi-supervised, and unsupervised DL methods for defect detection and segmentation. Its diversity in texture and construction techniques also enables investigation of model generalization and transferability across tunnel types. By addressing the critical lack of domain-specific data, this dataset contributes to advancing automated tunnel inspection and promoting safer, more efficient infrastructure maintenance strategies.
Authors: Shizhuo Mao, Song Chen, Yi Kang
Abstract: Large language models (LLMs) excel at natural language tasks but face deployment challenges due to their growing size outpacing GPU memory advancements. Model quantization mitigates this issue by lowering weight and activation precision, but existing solutions face fundamental trade-offs: dynamic quantization incurs high computational overhead and poses deployment challenges on edge devices, while static quantization sacrifices accuracy. Existing approaches of quantization-aware training (QAT) further suffer from weight training costs. We propose SASQ: a lightweight QAT framework specifically tailored for activation quantization factors. SASQ exclusively optimizes only the quantization factors (without changing pre-trained weights), enabling static inference with high accuracy while maintaining deployment efficiency. SASQ adaptively truncates some outliers, thereby reducing the difficulty of quantization while preserving the distributional characteristics of the activations. SASQ not only surpasses existing SOTA quantization schemes but also outperforms the corresponding FP16 models. On LLaMA2-7B, it achieves 5.2% lower perplexity than QuaRot and 4.7% lower perplexity than the FP16 model on WikiText2.
Authors: Andreas Lolos, Theofilos Christodoulou, Aris L. Moustakas, Stergios Christodoulidis, Maria Vakalopoulou
Abstract: In computational pathology, weak supervision has become the standard for deep learning due to the gigapixel scale of WSIs and the scarcity of pixel-level annotations, with Multiple Instance Learning (MIL) established as the principal framework for slide-level model training. In this paper, we introduce a novel setting for MIL methods, inspired by proceedings in Neural Partial Differential Equation (PDE) Solvers. Instead of relying on complex attention-based aggregation, we propose an efficient, aggregator-agnostic framework that removes the complexity of correlation learning from the MIL aggregator. CAPRMIL produces rich context-aware patch embeddings that promote effective correlation learning on downstream tasks. By projecting patch features -- extracted using a frozen patch encoder -- into a small set of global context/morphology-aware tokens and utilizing multi-head self-attention, CAPRMIL injects global context with linear computational complexity with respect to the bag size. Paired with a simple Mean MIL aggregator, CAPRMIL matches state-of-the-art slide-level performance across multiple public pathology benchmarks, while reducing the total number of trainable parameters by 48%-92.8% versus SOTA MILs, lowering FLOPs during inference by 52%-99%, and ranking among the best models on GPU memory efficiency and training time. Our results indicate that learning rich, context-aware instance representations before aggregation is an effective and scalable alternative to complex pooling for whole-slide analysis. Our code is available at https://github.com/mandlos/CAPRMIL
Authors: David Samuel, Lucas Georges Gabriel Charpentier
Abstract: This paper combines autoregressive and masked-diffusion training objectives without any architectural modifications, resulting in flexible language models that outperform single-objective models. Autoregressive modeling has been a popular approach, partly because of its training efficiency; however, that comes at the cost of sensitivity to overfitting. On the other hand, masked-diffusion models are less efficient to train while being more resilient to overfitting. In this work, we demonstrate that dual-objective training achieves the best of both worlds. To derive the optimal ratio between both objectives, we train and evaluate 50 language models under varying levels of data repetition. We show that it is optimal to combine both objectives under all evaluated settings and that the optimal ratio is similar whether targeting autoregressive or masked-diffusion downstream performance.
Authors: Nguyen Tien Dong, Minh-Anh Nguyen, Thanh Dat Hoang, Nguyen Tuan Ngoc, Dao Xuan Quang Minh, Phan Phi Hai, Nguyen Thi Ngoc Anh, Dang Van Tu, Binh Vu
Abstract: The rapid advancement of large language models (LLMs) has enabled new possibilities for applying artificial intelligence within the legal domain. Nonetheless, the complexity, hierarchical organization, and frequent revisions of Vietnamese legislation pose considerable challenges for evaluating how well these models interpret and utilize legal knowledge. To address this gap, Vietnamese Legal Benchmark (VLegal-Bench) is introduced, the first comprehensive benchmark designed to systematically assess LLMs on Vietnamese legal tasks. Informed by Bloom's cognitive taxonomy, VLegal-Bench encompasses multiple levels of legal understanding through tasks designed to reflect practical usage scenarios. The benchmark comprises 10,450 samples generated through a rigorous annotation pipeline, where legal experts label and cross-validate each instance using our annotation system to ensure every sample is grounded in authoritative legal documents and mirrors real-world legal assistant workflows, including general legal questions and answers, retrieval-augmented generation, multi-step reasoning, and scenario-based problem solving tailored to Vietnamese law. By providing a standardized, transparent, and cognitively informed evaluation framework, VLegal-Bench establishes a solid foundation for assessing LLM performance in Vietnamese legal contexts and supports the development of more reliable, interpretable, and ethically aligned AI-assisted legal systems.
Authors: Xianwei Cao, Dou Quan, Shuang Wang, Ning Huyan, Wei Wang, Yunan Li, Licheng Jiao
Abstract: Image retrieval-based cross-view geo-localization (IRCVGL) aims to match images captured from significantly different viewpoints, such as satellite and street-level images. Existing methods predominantly rely on learning robust global representations or implicit feature alignment, which often fail to model explicit spatial correspondences crucial for accurate localization. In this work, we propose a novel correspondence-aware feature refinement framework, termed CLNet, that explicitly bridges the semantic and geometric gaps between different views. CLNet decomposes the view alignment process into three learnable and complementary modules: a Neural Correspondence Map (NCM) that spatially aligns cross-view features via latent correspondence fields; a Nonlinear Embedding Converter (NEC) that remaps features across perspectives using an MLP-based transformation; and a Global Feature Recalibration (GFR) module that reweights informative feature channels guided by learned spatial cues. The proposed CLNet can jointly capture both high-level semantics and fine-grained alignments. Extensive experiments on four public benchmarks, CVUSA, CVACT, VIGOR, and University-1652, demonstrate that our proposed CLNet achieves state-of-the-art performance while offering better interpretability and generalizability.
Authors: Tejaswani Dash, Dinesh Karri, Anudeep Vurity, Gautam Datla, Tazeem Ahmad, Saima Rafi, Rohith Tangudu
Abstract: This paper introduces PolyPersona, a generative framework for synthesizing persona-conditioned survey responses across multiple domains. The framework instruction-tunes compact chat models using parameter-efficient LoRA adapters with 4-bit quantization under a resource-adaptive training setup. A dialogue-based data pipeline explicitly preserves persona cues, ensuring consistent behavioral alignment across generated responses. Using this pipeline, we construct a dataset of 3,568 synthetic survey responses spanning ten domains and 433 distinct personas, enabling controlled instruction tuning and systematic multi-domain evaluation. We evaluate the generated responses using a multi-metric evaluation suite that combines standard text generation metrics, including BLEU, ROUGE, and BERTScore, with survey-specific metrics designed to assess structural coherence, stylistic consistency, and sentiment alignment.Experimental results show that compact models such as TinyLlama 1.1B and Phi-2 achieve performance comparable to larger 7B to 8B baselines, with a highest BLEU score of 0.090 and ROUGE-1 of 0.429. These findings demonstrate that persona-conditioned fine-tuning enables small language models to generate reliable and coherent synthetic survey data. The proposed framework provides an efficient and reproducible approach for survey data generation, supporting scalable evaluation while facilitating bias analysis through transparent and open protocols.
Authors: Tejaswani Dash, Gautam Datla, Anudeep Vurity, Tazeem Ahmad, Mohd Adnan, Saima Rafi, Saisha Patro, Saina Patro
Abstract: Cardiovascular disease (CVD) remains the leading cause of mortality worldwide, underscoring the need for reliable and efficient predictive tools that support early intervention. Traditional diagnostic approaches rely on handcrafted features and clinician expertise, while machine learning methods improve reproducibility but often struggle to generalize across noisy and heterogeneous clinical data. In this work, we propose Residual GRU with Multi-Head Self-Attention, a compact deep learning architecture designed for tabular clinical records. The model integrates residual bidirectional gated recurrent units for sequential modeling of feature columns, a channel reweighting block, and multi-head self-attention pooling with a learnable classification token to capture global context. We evaluate the model on the UCI Heart Disease dataset using 5-fold stratified cross-validation and compare it against classical methods such as Logistic Regression, Random Forest, and Support Vector Machines, as well as modern deep learning baselines including DeepMLP, convolutional networks, recurrent networks, and Transformers. The proposed model achieves an accuracy of 0.861, macro-F1 of 0.860, ROC-AUC of 0.908, and PR-AUC of 0.904, outperforming all baselines. Ablation studies confirm the individual contributions of residual recurrence, channel gating, and attention pooling. t-SNE visualizations further indicate that the learned embeddings exhibit clearer separation between disease and non-disease classes compared to raw features. These results demonstrate that lightweight hybrid recurrent and attention-based architectures provide a strong balance between accuracy and efficiency for clinical risk prediction, supporting deployment in resource-constrained healthcare settings.
Authors: Ekaterina Artemova, Laurie Burchell, Daryna Dementieva, Shu Okabe, Mariya Shmatova, Pedro Ortiz Suarez
Abstract: This tutorial (https://tum-nlp.github.io/low-resource-tutorial) is designed for NLP practitioners, researchers, and developers working with multilingual and low-resource languages who seek to create more equitable and socially impactful language technologies. Participants will walk away with a practical toolkit for building end-to-end NLP pipelines for underrepresented languages -- from data collection and web crawling to parallel sentence mining, machine translation, and downstream applications such as text classification and multimodal reasoning. The tutorial presents strategies for tackling the challenges of data scarcity and cultural variance, offering hands-on methods and modeling frameworks. We will focus on fair, reproducible, and community-informed development approaches, grounded in real-world scenarios. We will showcase a diverse set of use cases covering over 10 languages from different language families and geopolitical contexts, including both digitally resource-rich and severely underrepresented languages.
Authors: Adarsha Shrestha, Basanta Pokharel, Binit Shrestha, Smriti Adhikari, Dinesh Gothe
Abstract: Nepali, a low-resource language spoken by over 32 million people, continues to face challenges in natural language processing (NLP) due to its complex grammar, agglutinative morphology, and limited availability of high-quality corpora. Most efforts to date have centered on basic encoder architectures; they remain insufficient for Nepali-specific text generation. This study presents a GPT-2-based Nepali language model trained using several training strategies inspired by GPT-3, including optimized learning rate schedules, batch scaling, and architectural refinements. A custom 16k Byte-Pair Encoding (BPE) tokenizer was trained exclusively on Nepali text to ensure more consistent segmentation and improved input representation. The model was pretrained on a combined dataset comprising a 10.75GB cleaned NepBERTa corpus and additional web-scraped Nepali news articles. FlashAttention was integrated to reduce memory usage and stabilize training. After two epochs, the model achieved a training loss of 3.168177, a validation loss of 3.081982, and a final perplexity of 21.80, demonstrating its capability to generate coherent Nepali news-style text.
Authors: Zhaolun Li, Jichang Li, Yinqi Cai, Junye Chen, Xiaonan Luo, Guanbin Li, Rushi Lan
Abstract: In this paper, we propose FakeRadar, a novel deepfake video detection framework designed to address the challenges of cross-domain generalization in real-world scenarios. Existing detection methods typically rely on manipulation-specific cues, performing well on known forgery types but exhibiting severe limitations against emerging manipulation techniques. This poor generalization stems from their inability to adapt effectively to unseen forgery patterns. To overcome this, we leverage large-scale pretrained models (e.g. CLIP) to proactively probe the feature space, explicitly highlighting distributional gaps between real videos, known forgeries, and unseen manipulations. Specifically, FakeRadar introduces Forgery Outlier Probing, which employs dynamic subcluster modeling and cluster-conditional outlier generation to synthesize outlier samples near boundaries of estimated subclusters, simulating novel forgery artifacts beyond known manipulation types. Additionally, we design Outlier-Guided Tri-Training, which optimizes the detector to distinguish real, fake, and outlier samples using proposed outlier-driven contrastive learning and outlier-conditioned cross-entropy losses. Experiments show that FakeRadar outperforms existing methods across various benchmark datasets for deepfake video detection, particularly in cross-domain evaluations, by handling the variety of emerging manipulation techniques.
Authors: Alessandro Trapasso, Luca Iocchi, Fabio Patrizi
Abstract: Many practical decision-making problems involve tasks whose success depends on the entire system history, rather than on achieving a state with desired properties. Markovian Reinforcement Learning (RL) approaches are not suitable for such tasks, while RL with non-Markovian reward decision processes (NMRDPs) enables agents to tackle temporal-dependency tasks. This approach has long been known to lack formal guarantees on both (near-)optimality and sample efficiency. We contribute to solving both issues with QR-MAX, a novel model-based algorithm for discrete NMRDPs that factorizes Markovian transition learning from non-Markovian reward handling via reward machines. To the best of our knowledge, this is the first model-based RL algorithm for discrete-action NMRDPs that exploits this factorization to obtain PAC convergence to $\varepsilon$-optimal policies with polynomial sample complexity. We then extend QR-MAX to continuous state spaces with Bucket-QR-MAX, a SimHash-based discretiser that preserves the same factorized structure and achieves fast and stable learning without manual gridding or function approximation. We experimentally compare our method with modern state-of-the-art model-based RL approaches on environments of increasing complexity, showing a significant improvement in sample efficiency and increased robustness in finding optimal policies.
Authors: Atsuyuki Miyai, Shota Onohara, Jeonghun Baek, Kiyoharu Aizawa
Abstract: This paper introduces JMMMU-Pro, an image-based Japanese Multi-discipline Multimodal Understanding Benchmark, and Vibe Benchmark Construction, a scalable construction method. Following the evolution from MMMU to MMMU-Pro, JMMMU-Pro extends JMMMU by composing the question image and question text into a single image, thereby creating a benchmark that requires integrated visual-textual understanding through visual perception. To build JMMMU-Pro, we propose Vibe Benchmark Construction, a methodology in which an image generative model (e.g., Nano Banana Pro) produces candidate visual questions, and humans verify the outputs and, when necessary, regenerate with adjusted prompts to ensure quality. By leveraging Nano Banana Pro's highly realistic image generation capabilities and its ability to embed clean Japanese text, we construct a high-quality benchmark at low cost, covering a wide range of background and layout designs. Experimental results show that all open-source LMMs struggle substantially with JMMMU-Pro, underscoring JMMMU-Pro as an important benchmark for guiding future efforts in the open-source community. We believe that JMMMU-Pro provides a more rigorous evaluation tool for assessing the Japanese capabilities of LMMs and that our Vibe Benchmark Construction also offers an efficient guideline for future development of image-based VQA benchmarks.
Authors: Yash Vishe, Eric Xue, Xunyi Jiang, Zachary Novack, Junda Wu, Julian McAuley, Xin Xu
Abstract: Music editing plays a vital role in modern music production, with applications in film, broadcasting, and game development. Recent advances in music generation models have enabled diverse editing tasks such as timbre transfer, instrument substitution, and genre transformation. However, many existing works overlook the evaluation of their ability to preserve musical facets that should remain unchanged during editing a property we define as Music Context Preservation (MCP). While some studies do consider MCP, they adopt inconsistent evaluation protocols and metrics, leading to unreliable and unfair comparisons. To address this gap, we introduce the first MCP evaluation benchmark, MuseCPBench, which covers four categories of musical facets and enables comprehensive comparisons across five representative music editing baselines. Through systematic analysis along musical facets, methods, and models, we identify consistent preservation gaps in current music editing methods and provide insightful explanations. We hope our findings offer practical guidance for developing more effective and reliable music editing strategies with strong MCP capability
Authors: Rao Muhammad Umer, Daniel Sens, Jonathan Noll, Christian Matek, Lukas Wolfseher, Rainer Spang, Ralf Huss, Johannes Raffler, Sarah Reinke, Wolfram Klapper, Katja Steiger, Kristina Schwamborn, Carsten Marr
Abstract: Timely and accurate lymphoma diagnosis is essential for guiding cancer treatment. Standard diagnostic practice combines hematoxylin and eosin (HE)-stained whole slide images with immunohistochemistry, flow cytometry, and molecular genetic tests to determine lymphoma subtypes, a process requiring costly equipment, skilled personnel, and causing treatment delays. Deep learning methods could assist pathologists by extracting diagnostic information from routinely available HE-stained slides, yet comprehensive benchmarks for lymphoma subtyping on multicenter data are lacking. In this work, we present the first multicenter lymphoma benchmarking dataset covering four common lymphoma subtypes and healthy control tissue. We systematically evaluate five publicly available pathology foundation models (H-optimus-1, H0-mini, Virchow2, UNI2, Titan) combined with attention-based (AB-MIL) and transformer-based (TransMIL) multiple instance learning aggregators across three magnifications (10x, 20x, 40x). On in-distribution test sets, models achieve multiclass balanced accuracies exceeding 80% across all magnifications, with all foundation models performing similarly and both aggregation methods showing comparable results. The magnification study reveals that 40x resolution is sufficient, with no performance gains from higher resolutions or cross-magnification aggregation. However, on out-of-distribution test sets, performance drops substantially to around 60%, highlighting significant generalization challenges. To advance the field, larger multicenter studies covering additional rare lymphoma subtypes are needed. We provide an automated benchmarking pipeline to facilitate such future research.
Authors: Alban Puech, Matteo Mazzonelli, Celia Cintas, Tamara R. Govindasamy, Mangaliso Mngomezulu, Jonas Weiss, Matteo Ba\`u, Anna Varbella, Fran\c{c}ois Mirall\`es, Kibaek Kim, Le Xie, Hendrik F. Hamann, Etienne Vos, Thomas Brunschwiler
Abstract: We introduce gridfm-datakit-v1, a Python library for generating realistic and diverse Power Flow (PF) and Optimal Power Flow (OPF) datasets for training Machine Learning (ML) solvers. Existing datasets and libraries face three main challenges: (1) lack of realistic stochastic load and topology perturbations, limiting scenario diversity; (2) PF datasets are restricted to OPF-feasible points, hindering generalization of ML solvers to cases that violate operating limits (e.g., branch overloads or voltage violations); and (3) OPF datasets use fixed generator cost functions, limiting generalization across varying costs. gridfm-datakit addresses these challenges by: (1) combining global load scaling from real-world profiles with localized noise and supporting arbitrary N-k topology perturbations to create diverse yet realistic datasets; (2) generating PF samples beyond operating limits; and (3) producing OPF data with varying generator costs. It also scales efficiently to large grids (up to 10,000 buses). Comparisons with OPFData, OPF-Learn, PGLearn, and PF$\Delta$ are provided. Available on GitHub at https://github.com/gridfm/gridfm-datakit under Apache 2.0 and via `pip install gridfm-datakit`.
Authors: Sicheng Xu, Guojun Chen, Jiaolong Yang, Yizhong Zhang, Yu Deng, Steve Lin, Baining Guo
Abstract: We propose VASA-3D, an audio-driven, single-shot 3D head avatar generator. This research tackles two major challenges: capturing the subtle expression details present in real human faces, and reconstructing an intricate 3D head avatar from a single portrait image. To accurately model expression details, VASA-3D leverages the motion latent of VASA-1, a method that yields exceptional realism and vividness in 2D talking heads. A critical element of our work is translating this motion latent to 3D, which is accomplished by devising a 3D head model that is conditioned on the motion latent. Customization of this model to a single image is achieved through an optimization framework that employs numerous video frames of the reference head synthesized from the input image. The optimization takes various training losses robust to artifacts and limited pose coverage in the generated training data. Our experiment shows that VASA-3D produces realistic 3D talking heads that cannot be achieved by prior art, and it supports the online generation of 512x512 free-viewpoint videos at up to 75 FPS, facilitating more immersive engagements with lifelike 3D avatars.
Authors: Chuan He
Abstract: Stochastic optimization is fundamental to modern machine learning. Recent research has extended the study of stochastic first-order methods (SFOMs) from light-tailed to heavy-tailed noise, which frequently arises in practice, with clipping emerging as a key technique for controlling heavy-tailed gradients. Extensive theoretical advances have further shown that the oracle complexity of SFOMs depends on the tail index $\alpha$ of the noise. Nonetheless, existing complexity results often cover only the case $\alpha \in (1,2]$, that is, the regime where the noise has a finite mean, while the complexity bounds tend to infinity as $\alpha$ approaches $1$. This paper tackles the general case of noise with tail index $\alpha\in(0,2]$, covering regimes ranging from noise with bounded variance to noise with an infinite mean, where the latter case has been scarcely studied. Through a novel analysis of the bias-variance trade-off in gradient clipping, we show that when a symmetry measure of the noise tail is controlled, clipped SFOMs achieve improved complexity guarantees in the presence of heavy-tailed noise for any tail index $\alpha \in (0,2]$. Our analysis of the bias-variance trade-off not only yields new unified complexity guarantees for clipped SFOMs across this full range of tail indices, but is also straightforward to apply and can be combined with classical analyses under light-tailed noise to establish oracle complexity guarantees under heavy-tailed noise. Finally, numerical experiments validate our theoretical findings.
Authors: Yen-Ju Lu, Kunxiao Gao, Mingrui Liang, Helin Wang, Thomas Thebaud, Laureano Moro-Velazquez, Najim Dehak, Jesus Villalba
Abstract: Recent audio language models can follow long conversations. However, research on emotion-aware or spoken dialogue summarization is constrained by the lack of data that links speech, summaries, and paralinguistic cues. We introduce Spoken DialogSum, the first corpus aligning raw conversational audio with factual summaries, emotion-rich summaries, and utterance-level labels for speaker age, gender, and emotion. The dataset is built in two stages: first, an LLM rewrites DialogSum scripts with Switchboard-style fillers and back-channels, then tags each utterance with emotion, pitch, and speaking rate. Second, an expressive TTS engine synthesizes speech from the tagged scripts, aligned with paralinguistic labels. Spoken DialogSum comprises 13,460 emotion-diverse dialogues, each paired with both a factual and an emotion-focused summary. The dataset is available online at https://fatfat-emosum.github.io/EmoDialog-Sum-Audio-Samples/. Baselines show that an Audio-LLM raises emotional-summary ROUGE-L by 28% relative to a cascaded ASR-LLM system, confirming the value of end-to-end speech modeling.
URLs: https://fatfat-emosum.github.io/EmoDialog-Sum-Audio-Samples/.
Authors: Jianfeng Xiang, Xiaoxue Chen, Sicheng Xu, Ruicheng Wang, Zelong Lv, Yu Deng, Hongyuan Zhu, Yue Dong, Hao Zhao, Nicholas Jing Yuan, Jiaolong Yang
Abstract: Recent advancements in 3D generative modeling have significantly improved the generation realism, yet the field is still hampered by existing representations, which struggle to capture assets with complex topologies and detailed appearance. This paper present an approach for learning a structured latent representation from native 3D data to address this challenge. At its core is a new sparse voxel structure called O-Voxel, an omni-voxel representation that encodes both geometry and appearance. O-Voxel can robustly model arbitrary topology, including open, non-manifold, and fully-enclosed surfaces, while capturing comprehensive surface attributes beyond texture color, such as physically-based rendering parameters. Based on O-Voxel, we design a Sparse Compression VAE which provides a high spatial compression rate and a compact latent space. We train large-scale flow-matching models comprising 4B parameters for 3D generation using diverse public 3D asset datasets. Despite their scale, inference remains highly efficient. Meanwhile, the geometry and material quality of our generated assets far exceed those of existing models. We believe our approach offers a significant advancement in 3D generative modeling.
Authors: Yue Zhao, Hanwen Jiang, Zhenlin Xu, Chutong Yang, Ehsan Adeli, Philipp Kr\"ahenb\"uhl
Abstract: Non-parametric quantization has received much attention due to its efficiency on parameters and scalability to a large codebook. In this paper, we present a unified formulation of different non-parametric quantization methods through the lens of lattice coding. The geometry of lattice codes explains the necessity of auxiliary loss terms when training auto-encoders with certain existing lookup-free quantization variants such as BSQ. As a step forward, we explore a few possible candidates, including random lattices, generalized Fibonacci lattices, and densest sphere packing lattices. Among all, we find the Leech lattice-based quantization method, which is dubbed as Spherical Leech Quantization ($\Lambda_{24}$-SQ), leads to both a simplified training recipe and an improved reconstruction-compression tradeoff thanks to its high symmetry and even distribution on the hypersphere. In image tokenization and compression tasks, this quantization approach achieves better reconstruction quality across all metrics than BSQ, the best prior art, while consuming slightly fewer bits. The improvement also extends to state-of-the-art auto-regressive image generation frameworks.
Authors: Jun Zhang, Teng Wang, Yuying Ge, Yixiao Ge, Xinhao Li, Ying Shan, Limin Wang
Abstract: This paper does not introduce a novel method but instead establishes a straightforward, incremental, yet essential baseline for video temporal grounding (VTG), a core capability in video understanding. While multimodal large language models (MLLMs) excel at various video understanding tasks, the recipes for optimizing them for VTG remain under-explored. In this paper, we present TimeLens, a systematic investigation into building MLLMs with strong VTG ability, along two primary dimensions: data quality and algorithmic design. We first expose critical quality issues in existing VTG benchmarks and introduce TimeLens-Bench, comprising meticulously re-annotated versions of three popular benchmarks with strict quality criteria. Our analysis reveals dramatic model re-rankings compared to legacy benchmarks, confirming the unreliability of prior evaluation standards. We also address noisy training data through an automated re-annotation pipeline, yielding TimeLens-100K, a large-scale, high-quality training dataset. Building on our data foundation, we conduct in-depth explorations of algorithmic design principles, yielding a series of meaningful insights and effective yet efficient practices. These include interleaved textual encoding for time representation, a thinking-free reinforcement learning with verifiable rewards (RLVR) approach as the training paradigm, and carefully designed recipes for RLVR training. These efforts culminate in TimeLens models, a family of MLLMs with state-of-the-art VTG performance among open-source models and even surpass proprietary models such as GPT-5 and Gemini-2.5-Flash. All codes, data, and models will be released to facilitate future research.
Authors: Huiliang Zhang, Di Wu, Arnaud Zinflou, Benoit Boulet
Abstract: The building sector is one of the largest contributors to global energy consumption. Improving its energy efficiency is essential for reducing operational costs and greenhouse gas emissions. Energy management systems (EMS) play a key role in monitoring and controlling building appliances efficiently and reliably. With the increasing integration of renewable energy, intelligent EMS solutions have received growing attention. Reinforcement learning (RL) has recently been explored for this purpose and shows strong potential. However, most RL-based EMS methods require a large number of training steps to learn effective control policies, especially when adapting to unseen buildings, which limits their practical deployment. This paper introduces MetaEMS, a meta-reinforcement learning framework for EMS. MetaEMS improves learning efficiency by transferring knowledge from previously solved tasks to new ones through group-level and building-level adaptation, enabling fast adaptation and effective control across diverse building environments. Experimental results demonstrate that MetaEMS adapts more rapidly to unseen buildings and consistently outperforms baseline methods across various scenarios.
Authors: Timothy Ossowski, Danyal Maqbool, Jixuan Chen, Zefan Cai, Tyler Bradshaw, Junjie Hu
Abstract: The rapid advances of multimodal agents built on large foundation models have largely overlooked their potential for language-based communication between agents in collaborative tasks. This oversight presents a critical gap in understanding their effectiveness in real-world deployments, particularly when communicating with humans. Existing agentic benchmarks fail to address key aspects of inter-agent communication and collaboration, particularly in scenarios where agents have unequal access to information and must work together to achieve tasks beyond the scope of individual capabilities. To fill this gap, we introduce COMMA: a novel puzzle benchmark designed to evaluate the collaborative performance of multimodal multi-agent systems through language communication. Our benchmark features a variety of multimodal puzzles, providing a comprehensive evaluation across four key categories of agentic capability in a communicative collaboration setting. Our findings reveal surprising weaknesses in state-of-the-art models, including strong proprietary models like GPT-4o and reasoning models like o4-mini. Many chain of thought reasoning models such as R1-Onevision and LLaVA-CoT struggle to outperform even a random baseline in agent-agent collaboration, indicating a potential growth area in their communication abilities.
Authors: Mattia Birti, Andrea Maurino, Francesco Osborne
Abstract: The integration of Environmental, Social, and Governance (ESG) factors into corporate decision-making is a fundamental aspect of sustainable finance. However, ensuring that business practices align with evolving regulatory frameworks remains a persistent challenge. AI-driven solutions for automatically assessing the alignment of sustainability reports and non-financial disclosures with specific ESG activities could greatly support this process. Yet, this task remains complex due to the limitations of general-purpose Large Language Models (LLMs) in domain-specific contexts and the scarcity of structured, high-quality datasets. In this paper, we investigate the ability of current-generation LLMs to identify text related to environmental activities. Furthermore, we demonstrate that their performance can be significantly enhanced through fine-tuning on a combination of original and synthetically generated data. To this end, we introduce ESG-Activities, a benchmark dataset containing 1,325 labelled text segments classified according to the EU ESG taxonomy. Our experimental results show that fine-tuning on ESG-Activities significantly enhances classification accuracy, with open models such as Llama 7B and Gemma 7B outperforming large proprietary solutions in specific configurations. These findings have important implications for financial analysts, policymakers, and AI researchers seeking to enhance ESG transparency and compliance through advanced natural language processing techniques.
Authors: Md Millat Hosen
Abstract: The current study describes a cost-effective method for adapting large language models (LLMs) for academic advising with study-abroad contexts in mind and for application in low-resource methods for acculturation. With the Mistral-7B-Instruct model applied with a Low-Rank Adaptation (LoRA) method and a 4-bit quantization method, the model underwent training in two distinct stages related to this study's purpose to enhance domain specificity while maintaining computational efficiency. In Phase 1, the model was conditioned with a synthetic dataset via the Gemini Pro API, and in Phase 2, it was trained with manually curated datasets from the StudyAbroadGPT project to achieve enhanced, contextualized responses. Technical innovations entailed memory-efficient quantization, parameter-efficient adaptation, and continuous training analytics via Weights & Biases. After training, this study demonstrated a reduction in training loss by 52.7%, 92% accuracy in domain-specific recommendations, achieved 95% markdown-based formatting support, and a median run-rate of 100 samples per second on off-the-shelf GPU equipment. These findings support the effective application of instruction-tuned LLMs within educational advisers, especially in low-resource institutional scenarios. Limitations included decreased generalizability and the application of a synthetically generated dataset, but this framework is scalable for adding new multilingual-augmented and real-time academic advising processes. Future directions may include plans for the integration of retrieval-augmented generation, applying dynamic quantization routines, and connecting to real-time academic databases to increase adaptability and accuracy.
Authors: Zifeng Wang, Jiacheng Lin, Qiao Jin, Junyi Gao, Jathurshan Pradeepkumar, Pengcheng Jiang, Zhiyong Lu, Jimeng Sun
Abstract: Developing artificial intelligence (AI) for clinical research requires a comprehensive data foundation that supports model training and rigorous evaluation. Here, we introduce TrialPanorama, a large-scale structured resource that aggregates 1.6M clinical trial records from fifteen global registries and links them with biomedical ontologies and associated literature. To demonstrate its utility, we build a pipeline that constructs 152K training and testing samples for eight key clinical research tasks. Three tasks support systematic review workflows, including study search, study screening, and evidence summarization. Five tasks focus on trial design and optimization, including arm design, eligibility criteria design, endpoint selection, sample size estimation, and trial completion assessment and rationalization. Benchmarking cutting-edge large language models (LLMs) reveals that generic LLMs have limited capability in clinical reasoning. In contrast, an 8B LLM we developed on TrialPanorama using supervised finetuning and reinforcement learning wins over the 70B generic counterparts in all eight tasks, with a relative improvement of 73.7%, 67.6%, 38.4%, 37.8%, 26.5%, 20.7%, 20.0%, 18.1%, and 5.2%, respectively. We envision that TrialPanorama provides a solid foundation for future scaling of AI for clinical research.
Authors: Aryo Pradipta Gema, Alexander H\"agele, Runjin Chen, Andy Arditi, Jacob Goldman-Wetzler, Kit Fraser-Taliente, Henry Sleight, Linda Petrini, Julian Michael, Beatrice Alex, Pasquale Minervini, Yanda Chen, Joe Benton, Ethan Perez
Abstract: We construct evaluation tasks where extending the reasoning length of Large Reasoning Models (LRMs) deteriorates performance, exhibiting an inverse scaling relationship between test-time compute and accuracy. Our evaluation tasks span four categories: simple counting tasks with distractors, regression tasks with spurious features, deduction tasks with constraint tracking, and advanced AI risks. We identify five distinct failure modes when models reason for longer: 1) Claude models become increasingly distracted by irrelevant information; 2) OpenAI o-series models resist distractors but overfit to problem framings; 3) models shift from reasonable priors to spurious correlations; 4) all models show difficulties in maintaining focus on complex deductive tasks; and 5) extended reasoning may amplify concerning behaviors, with Claude Sonnet 4 showing increased expressions of self-preservation. These findings suggest that while test-time compute scaling remains promising for improving model capabilities, it may inadvertently reinforce problematic reasoning patterns. Our results demonstrate the importance of evaluating models across diverse reasoning lengths to identify and address these failure modes in LRMs.
Authors: Fengxiao Fan, Jingzhe Ni, Xiaolong Yin, Sirui Wang, Xingyu Lu, Qiang Zou, Ruofeng Tong, Min Tang, Peng Du
Abstract: Computer Aided Design (CAD) plays a pivotal role in industrial manufacturing but typically requires a high level of expertise from designers. To lower the entry barrier and improve design efficiency, we present an agent for CAD conceptual design powered by large language models (LLMs). The agent accepts both textual descriptions and sketches as input, engaging in interactive dialogue with users to refine and clarify design requirements through comprehensive requirement analysis. Built upon a novel Explicit Context Imperative Paradigm (ECIP), the agent generates high-quality CAD modeling code. During the generation process, the agent incorporates iterative visual feedback to improve model quality. Generated design cases are stored in a structured knowledge base, enabling continuous improvement of the agent's code generation capabilities. Experimental results demonstrate that our method achieves state-of-the-art performance in CAD code generation.
Authors: Jakub Grudzien Kuba, Mengting Gu, Qi Ma, Yuandong Tian, Vijai Mohan, Jason Chen
Abstract: Large language models (LLMs) have advanced rapidly in recent years, driven by scale, abundant high-quality training data, and reinforcement learning. Yet this progress faces a fundamental bottleneck: the need for ever more data from which models can continue to learn. In this work, we propose a reinforcement learning approach that removes this dependency by enabling models to improve without additional data. Our method leverages a game-theoretic framework of self-play, where a model's capabilities are cast as performance in a competitive game and stronger policies emerge by having the model play against itself-a process we call Language Self-Play (LSP). Experiments with Llama-3.2-3B-Instruct on instruction-following, mathematics, and coding benchmarks show that pretrained models can be effectively improved with self-play alone.
Authors: Jiaqi Wang, Binquan Ji, Haibo Luo, Yiyang Qi, Ruiting Li, Huiyan Wang, Yuantao Han, Cangyi Yang, jiaxu Zhang, Feiliang Ren
Abstract: Complex Reasoning in Large Language Models can be dynamically optimized using Test-Time Scaling (TTS) to mitigate Overthinking. Methods such as Coconut, SoftCoT and its variant are effective in continuous latent space inference, the core bottleneck still lies in the efficient generation and utilization of high-quality Latent Thought. Drawing from the theory of SoftCoT++ that a larger variance in the generated Latent Thought distribution more closely approximates the golden truth distribution, we propose a Latent Thought-Augmented Training Framework--LTA-Thinker, which improves distributional variance and enhances reasoning performance from two perspectives. First, LTA-Thinker constructs a Latent Thought generation architecture based on a learnable prior. This architecture aims to increase the variance distribution of generated Latent Thought Vectors in order to simplify the overall structure and raise the performance ceiling. Second, LTA-Thinker introduces a distribution-based directional optimization paradigm that jointly constrains both distribution locality and distribution scale. This mechanism improves information efficiency and computational cost through a multi-objective co-training strategy, which combines standard Supervised Fine-Tuning (SFT) loss with two novel losses: Semantic Alignment Loss, which utilizes KL divergence to ensure that the Latent Thought is highly relevant to the semantics of the question; Reasoning Focus Loss, which utilizes a contrastive learning mechanism to guide the model to focus on the most critical reasoning steps. Experiments show that LTA-thinker achieves state-of-the-art (SOTA) performance among various baselines and demonstrates a higher performance ceiling and better scaling effects.
Authors: Hang Xu, Zang Yu, Yehui Tang, Pengbo Hu, Yuhao Tang, Hao Dong
Abstract: This paper introduces MCTS-EP, an online learning framework that combines large language models (LLM) with Monte Carlo Tree Search (MCTS) for training embodied agents. MCTS-EP integrates three key components: MCTS-guided exploration for preference data collection, efficient multi-modal reasoning mechanism, and iterative training pipeline based on preference optimization. We theoretically prove that MCTS-EP achieves better performance bounds than conventional on-policy algorithms when the loss function is strongly convex, and demonstrate that it can be formulated as a search-enhanced variant of GAIL. MCTS-EP achieves state-of-the-art performace across serval benchmarks. In ALFWorld, it achieves 92% and 87% success rates for textual and visual tasks. In WebShop, it reaches an average reward of 0.81. MTCS-EP also reduces average interaction steps from from 18.7/19.5 to 10.2/9.9 steps in visual ALFWorld.Code available at: https://github.com/xuhang-2/Embodied-Agent-Planning
Authors: Heming Zhang, Di Huang, Wenyu Li, Michael Province, Yixin Chen, Philip Payne, Fuhai Li
Abstract: In precision medicine, quantitative multi-omic features, topological context, and textual biological knowledge play vital roles in identifying disease-critical signaling pathways and targets. Existing pipelines capture only part of these-numerical omics ignore topological context, text-centric LLMs lack quantitative grounded reasoning, and graph-only models underuse node semantics and the generalization of LLMs-limiting mechanistic interpretability. Although Process Reward Models (PRMs) aim to guide reasoning in LLMs, they remain limited by unreliable intermediate evaluation, and vulnerability to reward hacking with computational cost. These gaps motivate integrating quantitative multi-omic signals, topological structure with node annotations, and literature-scale text via LLMs, using subgraph reasoning as the principle bridge linking numeric evidence, topological knowledge and language context. Therefore, we propose GALAX (Graph Augmented LAnguage model with eXplainability), an innovative framework that integrates pretrained Graph Neural Networks (GNNs) into Large Language Models (LLMs) via reinforcement learning guided by a Graph Process Reward Model (GPRM), which generates disease-relevant subgraphs in a step-wise manner initiated by an LLM and iteratively evaluated by a pretrained GNN and schema-based rule check, enabling process-level supervision without explicit labels. As an application, we also introduced Target-QA, a benchmark combining CRISPR-identified targets, multi-omic profiles, and biomedical graph knowledge across diverse cancer cell lines, which enables GNN pretraining for supervising step-wise graph construction and supports long-context reasoning over text-numeric graphs (TNGs), providing a scalable and biologically grounded framework for explainable, reinforcement-guided subgraph reasoning toward reliable and interpretable target discovery in precision medicine.
Authors: Aleksandar Terzi\'c, Nicolas Menet, Michael Hersche, Thomas Hofmann, Abbas Rahimi
Abstract: Modern state-space models (SSMs) often utilize transition matrices which enable efficient computation but pose restrictions on the model's expressivity, as measured in terms of the ability to emulate finite-state automata (FSA). While unstructured transition matrices are optimal in terms of expressivity, they come at a prohibitively high compute and memory cost even for moderate state sizes. We propose a structured sparse parametrization of transition matrices in SSMs that enables FSA state tracking with optimal state size and depth, while keeping the computational cost of the recurrence comparable to that of diagonal SSMs. Our method, PD-SSM, parametrizes the transition matrix as the product of a column one-hot matrix ($P$) and a complex-valued diagonal matrix ($D$). Consequently, the computational cost of parallel scans scales linearly with the state size. Theoretically, the model is BIBO-stable and can emulate any $N$-state FSA with one layer of dimension $N$ and a linear readout of size $N \times N$, significantly improving on all current structured SSM guarantees. Experimentally, the model significantly outperforms a wide collection of modern SSM variants on various FSA state tracking tasks. On multiclass time-series classification, the performance is comparable to that of neural controlled differential equations, a paradigm explicitly built for time-series analysis. Finally, we integrate PD-SSM into a hybrid Transformer-SSM architecture and demonstrate that the model can effectively track the states of a complex FSA in which transitions are encoded as a set of variable-length English sentences. The code is available at https://github.com/IBM/expressive-sparse-state-space-model
URLs: https://github.com/IBM/expressive-sparse-state-space-model
Authors: Evan Heus, Rick Bookstaber, Dhruv Sharma
Abstract: Large Language Models (LLMs) struggle with the complex, multi-modal, and network-native data underlying financial risk. Standard Retrieval-Augmented Generation (RAG) oversimplifies relationships, while specialist models are costly and static. We address this gap with an LLM-centric agent framework for supply chain risk analysis. Our core contribution is to exploit the inherent duality between networks and knowledge graphs (KG). We treat the supply chain network as a KG, allowing us to use structural network science principles for retrieval. A graph traverser, guided by network centrality scores, efficiently extracts the most economically salient risk paths. An agentic architecture orchestrates this graph retrieval alongside data from numerical factor tables and news streams. Crucially, it employs novel ``context shells'' -- descriptive templates that embed raw figures in natural language -- to make quantitative data fully intelligible to the LLM. This lightweight approach enables the model to generate concise, explainable, and context-rich risk narratives in real-time without costly fine-tuning or a dedicated graph database.
Authors: Huiliang Zhang, Di Wu, Arnaud Zinflou, Benoit Boulet
Abstract: Building energy management is essential for achieving carbon reduction goals, improving occupant comfort, and reducing energy costs. Coordinated building energy management faces critical challenges in exploiting spatial-temporal dependencies while ensuring operational safety across multi-building systems. Current multi-building energy systems face three key challenges: insufficient spatial-temporal information exploitation, lack of rigorous safety guarantees, and system complexity. This paper proposes Spatial-Temporal Enhanced Safe Multi-Agent Coordination (STEMS), a novel safety-constrained multi-agent reinforcement learning framework for coordinated building energy management. STEMS integrates two core components: (1) a spatial-temporal graph representation learning framework using a GCN-Transformer fusion architecture to capture inter-building relationships and temporal patterns, and (2) a safety-constrained multi-agent RL algorithm incorporating Control Barrier Functions to provide mathematical safety guarantees. Extensive experiments on real-world building datasets demonstrate STEMS's superior performance over existing methods, showing that STEMS achieves 21% cost reduction, 18% emission reduction, and dramatically reduces safety violations from 35.1% to 5.6% while maintaining optimal comfort with only 0.13 discomfort proportion. The framework also demonstrates strong robustness during extreme weather conditions and maintains effectiveness across different building types.
Authors: Ruofan Zhang, Bin Xia, Zhen Cheng, Cairen Jian, Minglun Yang, Ngai Wong, Yuan Cheng
Abstract: Adaptive reasoning is essential for aligning the computational effort of large language models (LLMs) with the intrinsic difficulty of problems. Current chain-of-thought methods boost reasoning ability but indiscriminately generate long explanations, leading to evident inefficiency. However, existing reinforcement learning approaches to adaptive thinking remain unstable and heavily reward-dependent. Here we propose \textbf{DART}, a supervised \textbf{D}ifficulty-\textbf{A}daptive \textbf{R}easoning \textbf{T}runcation framework that adjusts thinking length according to problem difficulty. By distilling concise reasoning patterns from stronger models, interpolating them into a continuum of reasoning styles, and curating optimal training data that balances correctness and compactness, DART learns when to ``stop thinking''. Across multiple mathematical benchmarks, experimental results demonstrate its remarkable efficiency while preserving or improving accuracy, achieving a significant 81.2\% reasoning truncation (DeepSeek-R1-Distill-Qwen-7B on GSM8K dataset) with 5.33$\times$ computational acceleration. DART provides a stable and general paradigm for efficient reasoning, advancing the development of adaptive intelligence in LLMs.
Authors: Zhikang Xie, Weilin Wan, Peizhu Gong, Weizhong Zhang, Cheng Jin
Abstract: Black-box tuning is an emerging paradigm for adapting large language models (LLMs) to better achieve desired behaviors, particularly when direct access to model parameters is unavailable. Current strategies, however, often present a dilemma of suboptimal extremes: either separately train a small proxy model and then use it to shift the predictions of the foundation model, offering notable efficiency but often yielding limited improvement; or making API calls in each tuning iteration to the foundation model, which entails prohibitive computational costs. Therefore, we propose a novel advanced black-box tuning method for LLMs with limited API calls. Our core strategy involves training a Gaussian Process (GP) surrogate model with "LogitMap Pairs" derived from querying the foundation model on a minimal but highly informative training subset. This surrogate can approximate the outputs of the foundation model to guide the training of the proxy model, thereby effectively reducing the need for direct queries to the foundation model. Extensive experiments verify that our approach elevates pre-trained language model accuracy from 55.92% to 86.85%, reducing the frequency of API queries to merely 1.38%. This significantly outperforms offline approaches that operate entirely without API access. Notably, our method also achieves comparable or superior accuracy to query-intensive approaches, while significantly reducing API costs. This offers a robust and high-efficiency paradigm for language model adaptation.
Authors: Tianyi Zhang, Xiangyuan Xue, Lingyan Ruan, Shiya Fu, Feng Xia, Simon D'Alfonso, Vassilis Kostakos, Ting Dang, Hong Jia
Abstract: Mental health conditions affect hundreds of millions globally, yet early detection remains limited. While large language models (LLMs) have shown promise in mental health applications, their size and computational demands hinder practical deployment. Small language models (SLMs) offer a lightweight alternative, but their use for social media--based mental health prediction remains largely underexplored. In this study, we introduce Menta, the first optimized SLM fine-tuned specifically for multi-task mental health prediction from social media data. Menta is jointly trained across six classification tasks using a LoRA-based framework, a cross-dataset strategy, and a balanced accuracy--oriented loss. Evaluated against nine state-of-the-art SLM baselines, Menta achieves an average improvement of 15.2\% across tasks covering depression, stress, and suicidality compared with the best-performing non--fine-tuned SLMs. It also achieves higher accuracy on depression and stress classification tasks compared to 13B-parameter LLMs, while being approximately 3.25x smaller. Moreover, we demonstrate real-time, on-device deployment of Menta on an iPhone 15 Pro Max, requiring only approximately 3GB RAM. Supported by a comprehensive benchmark against existing SLMs and LLMs, Menta highlights the potential for scalable, privacy-preserving mental health monitoring. Code is available at: https://hong-labs.github.io/menta-project/
Authors: Hongye Cao, Zhixin Bai, Ziyue Peng, Boyan Wang, Tianpei Yang, Jing Huo, Yuyao Zhang, Yang Gao
Abstract: Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy collapse, which reduces policy exploration and limits reasoning capabilities. To address this challenge, we propose an efficient reinforcement learning framework that leverages entropy signals at both the semantic and token levels to improve reasoning. From the data perspective, we introduce semantic entropy-guided curriculum learning, organizing training data from low to high semantic entropy to guide progressive optimization from easier to more challenging tasks. For the algorithmic design, we adopt non-uniform token treatment by imposing KL regularization on low-entropy tokens that critically impact policy exploration and applying stronger constraints on high-covariance portions within these tokens. By jointly optimizing data organization and algorithmic design, our method effectively mitigates entropy collapse and enhances LLM reasoning. Experimental results across 6 benchmarks with 3 different parameter-scale base models demonstrate that our method outperforms other entropy-based approaches in improving reasoning.
Authors: Shuyue Hu, Haoyang Yan, Yiqun Zhang, Yang Chen, Dongzhan Zhou, Lei Bai
Abstract: Foundation models (FMs) are increasingly assuming the role of the ''brain'' of AI agents. While recent efforts have begun to equip FMs with native single-agent abilities -- such as GUI interaction or integrated tool use -- we argue that the next frontier is endowing FMs with native multi-agent intelligence. We identify four core capabilities of FMs in multi-agent contexts: understanding, planning, efficient communication, and adaptation. Contrary to assumptions about the spontaneous emergence of such abilities, we provide extensive empirical evidence, across 41 large language models and 7 challenging benchmarks, showing that scaling single-agent performance alone does not automatically yield robust multi-agent intelligence. To address this gap, we outline key research directions -- spanning dataset construction, evaluation, training paradigms, and safety considerations -- for building FMs with native multi-agent intelligence.
Authors: Moein Heidari, Mohammad Amin Roohi, Ilker Hacihaliloglu
Abstract: Echocardiography is central to contemporary cardiovascular care, but full-study interpretation remains a cognitively demanding, multi-view task that is still performed manually. While recent foundation models for echocardiography can achieve strong performance on individual perceptual subtasks such as view classification, segmentation, or disease prediction, they typically operate in isolation and do not provide a unified, clinically coherent assessment. In this work, we introduce Echo-CoPilot, a multi-view, multi-task agent that uses a large language model to orchestrate a suite of specialized echocardiography tools. Within a ReAct-style loop, the agent decomposes clinician queries, invokes tools for view recognition, cardiac structure segmentation, measurement and disease prediction, and report synthesis, and integrates their outputs into guideline-aware answers and narrative summaries. We evaluate Echo-CoPilot on the public MIMIC-EchoQA benchmark, where it achieves an accuracy of 50.8\%, outperforming both general-purpose and biomedical video vision-language models. Qualitative analyses further show that the agent leverages quantitative measurements and physiologic context to resolve challenging cases near clinical decision thresholds, such as borderline left ventricular hypertrophy or pericardial effusion severity. The code will be released upon acceptance of the paper.
Authors: Anika Sharma, Malavika Mampally, Chidaksh Ravuru, Kandyce Brennan, Neil Gaikwad
Abstract: As large language models increasingly mediate stigmatized health decisions, their capacity to genuinely understand complex psychological and physiological phenomena remains poorly evaluated. Can AI understand what we cannot say? We investigate whether LLMs coherently represent abortion stigma across the cognitive, interpersonal, and structural levels where it operates. We systematically tested 627 demographically diverse personas across five leading LLMs using the validated Individual Level Abortion Stigma Scale (ILAS). Our multilevel analysis examined whether models coherently represent stigma at the cognitive level (self-judgment), interpersonal level (anticipated judgment and isolation), and structural level (community condemnation and disclosure patterns), as well as overall stigma. Models fail tests of genuine understanding across all levels. They overestimate interpersonal stigma while underestimating cognitive stigma, assume uniform community condemnation, introduce demographic biases absent from human validation data, miss the empirically validated stigma-secrecy relationship, and contradict themselves within theoretical constructs. These patterns reveal that current alignment approaches ensure appropriate language but not coherent multilevel understanding. This work provides empirical evidence that current LLMs lack coherent multilevel understanding of psychological and physiological constructs. AI safety in high-stakes contexts demands new approaches to design (multilevel coherence), evaluation (continuous auditing), governance and regulation (mandatory audits, accountability, deployment restrictions), and AI literacy in domains where understanding what people cannot say determines whether support helps or harms.
Authors: Junwei Kuang, Jiaheng Xie, Zhijun Yan
Abstract: The early identification and intervention of latent depression are of significant societal importance for mental health governance. While current automated detection methods based on social media have shown progress, their decision-making processes often lack a clinically interpretable framework, particularly in capturing the duration and dynamic evolution of depressive symptoms. To address this, this study introduces a semantic parsing network integrated with multi-scale temporal prototype learning. The model detects depressive states by capturing temporal patterns and semantic prototypes in users' emotional expression, providing a duration-aware interpretation of underlying symptoms. Validated on a large-scale social media dataset, the model outperforms existing state-of-the-art methods. Analytical results indicate that the model can identify emotional expression patterns not systematically documented in traditional survey-based approaches, such as sustained narratives expressing admiration for an "alternative life." Further user evaluation demonstrates the model's superior interpretability compared to baseline methods. This research contributes a structurally transparent, clinically aligned framework for depression detection in social media to the information systems literature. In practice, the model can generate dynamic emotional profiles for social platform users, assisting in the targeted allocation of mental health support resources.
Authors: Xiaoyun Xu, Shujian Yu, Zhuoran Liu, Stjepan Picek
Abstract: Vision Transformers (ViTs) have emerged as a fundamental architecture and serve as the backbone of modern vision-language models. Despite their impressive performance, ViTs exhibit notable vulnerability to evasion attacks, necessitating the development of specialized Adversarial Training (AT) strategies tailored to their unique architecture. While a direct solution might involve applying existing AT methods to ViTs, our analysis reveals significant incompatibilities, particularly with state-of-the-art (SOTA) approaches such as Generalist (CVPR 2023) and DBAT (USENIX Security 2024). This paper presents a systematic investigation of adversarial robustness in ViTs and provides a novel theoretical Mutual Information (MI) analysis in its autoencoder-based self-supervised pre-training. Specifically, we show that MI between the adversarial example and its latent representation in ViT-based autoencoders should be constrained via derived MI bounds. Building on this insight, we propose a self-supervised AT method, MIMIR, that employs an MI penalty to facilitate adversarial pre-training by masked image modeling with autoencoders. Extensive experiments on CIFAR-10, Tiny-ImageNet, and ImageNet-1K show that MIMIR can consistently provide improved natural and robust accuracy, where MIMIR outperforms SOTA AT results on ImageNet-1K. Notably, MIMIR demonstrates superior robustness against unforeseen attacks and common corruption data and can also withstand adaptive attacks where the adversary possesses full knowledge of the defense mechanism. Our code and trained models are publicly available at: https://github.com/xiaoyunxxy/MIMIR.
Authors: Xinbang Dai, Huiying Li, Nan Hu, Yongrui Chen, Rihui Jin, Huikang Hu, Guilin Qi
Abstract: Spatio-temporal knowledge graphs (STKGs) enhance traditional KGs by integrating temporal and spatial annotations, enabling precise reasoning over questions with spatio-temporal dependencies. Despite their potential, research on spatio-temporal knowledge graph question answering (STKGQA) remains limited. This is primarily due to the lack of datasets that simultaneously contain spatio-temporal information, as well as methods capable of handling implicit spatio-temporal reasoning. To bridge this gap, we introduce the spatio-temporal question answering dataset (STQAD), the first comprehensive benchmark comprising 10,000 natural language questions that require both temporal and spatial reasoning. STQAD is constructed with real-world facts containing spatio-temporal information, ensuring that the dataset reflects practical scenarios. Furthermore, our experiments reveal that existing KGQA methods underperform on STQAD, primarily due to their inability to model spatio-temporal interactions. To address this, we propose the spatio-temporal complex question answering (STCQA) method, which jointly embeds temporal and spatial features into KG representations and dynamically filters answers through constraint-aware reasoning. STCQA achieves state-of-the-art performance, significantly outperforming existing baselines. Our work not only provides a valuable resource for future research but also advances the field by offering a robust baseline for answering complex spatio-temporal questions.
Authors: Denis Antipov, Aneta Neumann, Frank Neumann, Andrew M. Sutton
Abstract: Diversity optimization is the class of optimization problems in which we aim to find a diverse set of good solutions. One of the frequently-used approaches to solve such problems is to use evolutionary algorithms that evolve a desired diverse population. This approach is called evolutionary diversity optimization (EDO). In this paper, we analyze EDO on a three-objective function LOTZ$_k$, which is a modification of the two-objective benchmark function (LeadingOnes, TrailingZeros). We prove that the GSEMO computes a set of all Pareto-optimal solutions in $O(kn^3)$ expected iterations. We also analyze the runtime of the GSEMO$_D$ algorithm (a modification of the GSEMO for diversity optimization) until it finds a population with the best possible diversity for two different diversity measures: the total imbalance and the sorted imbalances vector. For the first measure we show that the GSEMO$_D$ optimizes it in $O(kn^2\log(n))$ expected iterations (which is asymptotically faster than the upper bound on the runtime until it finds a Pareto-optimal population), and for the second measure we show an upper bound of $O(k^2n^3\log(n))$ expected iterations. We complement our theoretical analysis with an empirical study, which shows a very similar behavior for both diversity measures. The results of experiments suggest that our bounds for the total imbalance measure are tight, while the bounds for the imbalances vector are too pessimistic.
Authors: Shuqi Zhu, Ziyi Ye, Qingyao Ai, Yiqun Liu
Abstract: Exploring brain activity in relation to visual perception provides insights into the biological representation of the world. While functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG) have enabled effective image classification and reconstruction, their high cost and bulk limit practical use. Electroencephalography (EEG), by contrast, offers low cost and excellent temporal resolution, but its potential has been limited by the scarcity of large, high-quality datasets and by block-design experiments that introduce temporal confounds. To fill this gap, we present CrossPT-EEG, a benchmark for cross-participant and cross-time generalization of visual decoding from EEG. We collected EEG data from 16 participants while they viewed 4,000 images sampled from ImageNet, with image stimuli annotated at multiple levels of granularity. Our design includes two stages separated in time to allow cross-time generalization and avoid block-design artifacts. We also introduce benchmarks tailored to non-block design classification, as well as pre-training experiments to assess cross-time and cross-participant generalization. These findings highlight the dataset's potential to enhance EEG-based visual brain-computer interfaces, deepen our understanding of visual perception in biological systems, and suggest promising applications for improving machine vision models.
Authors: Ryuichi Sumida, Koji Inoue, Tatsuya Kawahara
Abstract: While Retrieval-Augmented Generation (RAG) has shown promise in enhancing long-term conversations, the increasing memory load as conversations progress degrades retrieval accuracy. Drawing on psychological insights, we propose LUFY, a simple yet effective method that focuses on emotionally arousing memories and retains less than 10% of the conversation. In the user experiment, participants interacted with three types of RAG chatbots, each for 2 hours over 4 sessions, marking the most extensive assessment of a chatbot's long-term capabilities to date -- more than four times longer than any existing benchmark. The results demonstrate that prioritizing arousing memories while forgetting the majority of the conversation significantly enhances user experience. This study pushes the frontier of long-term conversations and highlights the importance of forgetting unimportant parts of conversations. Code and Dataset: https://github.com/ryuichi-sumida/LUFY
Authors: Lecheng Zheng, Zhengzhang Chen, Haifeng Chen
Abstract: Root Cause Analysis (RCA) is essential for pinpointing the root causes of failures in microservice systems. Traditional data-driven RCA methods are typically limited to offline applications due to high computational demands, and existing online RCA methods handle only single-modal data, overlooking complex interactions in multi-modal systems. In this paper, we introduce OCEAN, a novel online multi-modal causal structure learning method for root cause localization. OCEAN employs a dilated convolutional neural network to capture long-term temporal dependencies and graph neural networks to learn causal relationships among system entities and key performance indicators. We further design a multi-factor attention mechanism to analyze and reassess the relationships among different metrics and log indicators/attributes for enhanced online causal graph learning. Additionally, a contrastive mutual information maximization-based graph fusion module is developed to effectively model the relationships across various modalities. Extensive experiments on three real-world datasets demonstrate the effectiveness and efficiency of our proposed method.
Authors: Luigi Bellomarini, Costanza Catalano, Andrea Coletta, Michela Iezzi, Pierangela Samarati
Abstract: We propose a novel framework to enable Knowledge Graphs (KGs) sharing while ensuring that information that should remain private is not directly released nor indirectly exposed via derived knowledge, maintaining at the same time the embedded knowledge of the KGs to support business downstream tasks. Our approach produces a privacy-preserving KG as an augmentation of the input one via controlled addition of nodes and edges as well as re-labeling of nodes and perturbation of weights. We introduce a novel privacy measure for KGs, which considers derived knowledge, a new utility metric that captures the business semantics we want to preserve, and propose two novel anonymisation algorithms. Our extensive experimental evaluation, with both synthetic graphs and real-world datasets, confirms the effectiveness of our approach.
Authors: Yida Xiong, Kun Li, Jiameng Chen, Hongzhi Zhang, Di Lin, Yan Che, Wenbin Hu
Abstract: Molecular optimization (MO) is a crucial stage in drug discovery in which task-oriented generated molecules are optimized to meet practical industrial requirements. Existing mainstream MO approaches primarily utilize external property predictors to guide iterative property optimization. However, learning all molecular samples in the vast chemical space is unrealistic for predictors. As a result, errors and noise are inevitably introduced during property prediction due to the nature of approximation. This leads to discrepancy accumulation, generalization reduction and suboptimal molecular candidates. In this paper, we propose a text-guided multi-property molecular optimization method utilizing transformer-based diffusion language model (TransDLM). TransDLM leverages standardized chemical nomenclature as semantic representations of molecules and implicitly embeds property requirements into textual descriptions, thereby mitigating error propagation during diffusion process. By fusing physically and chemically detailed textual semantics with specialized molecular representations, TransDLM effectively integrates diverse information sources to guide precise optimization, which enhances the model's ability to balance structural retention and property enhancement. Additionally, the success of a case study further demonstrates TransDLM's ability to solve practical problems. Experimentally, our approach surpasses state-of-the-art methods in maintaining molecular structural similarity and enhancing chemical properties on the benchmark dataset.
Authors: Jiacong Zhou, Xianyun Wang, Min Zhang, Jun Yu
Abstract: Aligning large language models with human preferences is essential for improving interaction quality and safety by ensuring outputs better reflect human values. A promising strategy involves Reinforcement Learning from Human Feedback (RLHF), starting with collecting and ranking responses generated by a supervised fine-tuning model to refine alignment. Existing methods such as Direct Preference Optimization (DPO) focus on pairwise comparisons, categorizing responses into preferred and less preferred pairs and optimizing pairwise margins. However, this pairwise approach cannot capture the holistic ranking relationships among multiple responses or effectively leverage the rich preference information available in list-wise comparisons. To address this challenge, this paper introduces \underline{D}irect \underline{R}anking \underline{P}reference \underline{O}ptimization (DRPO), a novel method that views human preference alignment as a Learning-to-Rank (LTR) task. Unlike pairwise methods, DRPO optimizes the preference ranking of entire response lists by computing holistic utility scores through NDCG, a standard LTR metric. To enable end-to-end optimization with the non-differentiable NDCG, we propose diffNDCG loss, a differentiable approximation facilitated by a sorting network. Furthermore, we introduce a novel margin-based Adaptive Rank Policy Score to enhance the discriminative quality of generated responses. Extensive experiments have shown that DRPO outperforms existing methods, enhancing the quality of the generated responses.
Authors: Mohamad Mohamad, Francesco Ponzio, Santa Di Cataldo, Damien Ambrosetti, Xavier Descombes
Abstract: Renal Cell Carcinoma is typically asymptomatic at the early stages for many patients. This leads to a late diagnosis of the tumor, where the curability likelihood is lower, and makes the mortality rate of Renal Cell Carcinoma high, with respect to its incidence rate. To increase the survival chance, a fast and correct categorization of the tumor subtype is paramount. Nowadays, computerized methods, based on artificial intelligence, represent an interesting opportunity to improve the productivity and the objectivity of the microscopy-based Renal Cell Carcinoma diagnosis. Nonetheless, much of their exploitation is hampered by the paucity of annotated dataset, essential for a proficient training of supervised machine learning technologies. This study sets out to investigate a novel self supervised training strategy for machine learning diagnostic tools, based on the multi-resolution nature of the histological samples. We aim at reducing the need of annotated dataset, without significantly reducing the accuracy of the tool. We demonstrate the classification capability of our tool on a whole slide imaging dataset for Renal Cancer subtyping, and we compare our solution with several state-of-the-art classification counterparts.
Authors: Zhengyao Ding, Ziyu Li, Yujian Hu, Youyao Xu, Chengchen Zhao, Yiheng Mao, Haitao Li, Zhikang Li, Qian Li, Jing Wang, Yue Chen, Mengjia Chen, Longbo Wang, Xuesen Chu, Weichao Pan, Ziyi Liu, Fei Wu, Hongkun Zhang, Ting Chen, Zhengxing Huang
Abstract: Cardiovascular diseases (CVDs) are the leading cause of global mortality, necessitating accessible and accurate diagnostic tools. While cardiac magnetic resonance imaging (CMR) provides gold-standard insights into cardiac structure and function, its clinical utility is limited by high cost and complexity. In contrast, electrocardiography (ECG) is inexpensive and widely available but lacks the granularity of CMR. We propose CardioNets, a deep learning framework that translates 12-lead ECG signals into CMR-level functional parameters and synthetic images, enabling scalable cardiac assessment. CardioNets integrates cross-modal contrastive learning and generative pretraining, aligning ECG with CMR-derived cardiac phenotypes and synthesizing high-resolution CMR images via a masked autoregressive model. Trained on 159,819 samples from five cohorts, including the UK Biobank (n=42,483) and MIMIC-IV-ECG (n=164,550), and externally validated on independent clinical datasets (n=3,767), CardioNets achieved strong performance across disease screening and phenotype estimation tasks. In the UK Biobank, it improved cardiac phenotype regression R2 by 24.8% and cardiomyopathy AUC by up to 39.3% over baseline models. In MIMIC, it increased AUC for pulmonary hypertension detection by 5.6%. Generated CMR images showed 36.6% higher SSIM and 8.7% higher PSNR than prior approaches. In a reader study, ECG-only CardioNets achieved 13.9% higher accuracy than human physicians using both ECG and real CMR. These results suggest that CardioNets offers a promising, low-cost alternative to CMR for large-scale CVD screening, particularly in resource-limited settings. Future efforts will focus on clinical deployment and regulatory validation of ECG-based synthetic imaging.
Authors: Yanli Wang, Yanlin Wang, Suiquan Wang, Daya Guo, Jiachi Chen, John Grundy, Xilin Liu, Yuchi Ma, Mingzhi Mao, Hongyu Zhang, Zibin Zheng
Abstract: Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the performance of such code translators. However, previous benchmarks mostly provide fine-grained samples, focusing at either code snippet, function, or file-level code translation. Such benchmarks do not accurately reflect real-world demands, where entire repositories often need to be translated, involving longer code length and more complex functionalities. To address this gap, we propose a new benchmark, named RepoTransBench, which is a real-world multilingual repository-level code translation benchmark featuring 1,897 real-world repository samples across 13 language pairs with automatically executable test suites. Besides, we introduce RepoTransAgent, a general agent framework to perform repository-level code translation. We evaluate both our benchmark's challenges and agent's effectiveness using several methods and backbone LLMs, revealing that repository-level translation remains challenging, where the best-performing method achieves only a 32.8% success rate. Furthermore, our analysis reveals that translation difficulty varies significantly by language pair direction, with dynamic-to-static language translation being much more challenging than the reverse direction (achieving below 10% vs. static-to-dynamic at 45-63%). Finally, we conduct a detailed error analysis and highlight current LLMs' deficiencies in repository-level code translation, which could provide a reference for further improvements. We provide the code and data at https://github.com/DeepSoftwareAnalytics/RepoTransBench.
URLs: https://github.com/DeepSoftwareAnalytics/RepoTransBench.
Authors: Yuxuan Yang, Dalin Zhang, Yuxuan Liang, Hua Lu, Gang Chen, Huan Li
Abstract: Time Series Forecasting (TSF) is a crucial task in various domains, yet existing TSF models rely heavily on high-quality data and insufficiently exploit all available data. This paper explores a novel self-supervised approach to re-label time series datasets by inherently constructing candidate datasets. During the optimization of a simple reconstruction network, intermediates are used as pseudo labels in a self-supervised paradigm, improving generalization for any predictor. We introduce the Self-Correction with Adaptive Mask (SCAM), which discards overfitted components and selectively replaces them with pseudo labels generated from reconstructions. Additionally, we incorporate Spectral Norm Regularization (SNR) to further suppress overfitting from a loss landscape perspective. Our experiments on eleven real-world datasets demonstrate that SCAM consistently improves the performance of various backbone models. This work offers a new perspective on constructing datasets and enhancing the generalization of TSF models through self-supervised learning. The code is available at https://github.com/SuDIS-ZJU/SCAM.
Authors: Thomas De Min, Subhankar Roy, St\'ephane Lathuili\`ere, Elisa Ricci, Massimiliano Mancini
Abstract: Machine unlearning is an emerging paradigm to remove the influence of specific training data (i.e., the forget set) from a model while preserving its knowledge of the rest of the data (i.e., the retain set). Previous approaches assume the forget data to be uniformly distributed from all training datapoints. However, if the data to unlearn is dominant in one group (e.g., ethnicity, gender), we empirically show that performance for this group degrades, leading to fairness issues. To perform unlearning while preserving fairness, this work addresses the overlooked problem of non-uniformly distributed forget sets, which we refer to as group-robust machine unlearning. We formalize the problem and present a simple and effective exact unlearning strategy that mitigates the performance loss in dominant groups via sample distribution reweighting. Moreover, we present MIU (Mutual Information-aware Machine Unlearning), the first approach for group robustness in approximate machine unlearning. MIU minimizes the mutual information between model features and group information, achieving unlearning while reducing performance degradation in the dominant group of the forget set. Additionally, MIU exploits sample distribution reweighting and mutual information calibration with the original model to preserve group robustness. We conduct experiments on three datasets and show that MIU outperforms standard methods, achieving unlearning without compromising model robustness. Source code available at https://github.com/tdemin16/group-robust_machine_unlearning
URLs: https://github.com/tdemin16/group-robust_machine_unlearning
Authors: Felix M\"achtle, Nils Loose, Tim Schulz, Florian Sieck, Jan-Niclas Serr, Ralf M\"oller, Thomas Eisenbarth
Abstract: As the number of web applications and API endpoints exposed to the Internet continues to grow, so does the number of exploitable vulnerabilities. Manually identifying such vulnerabilities is tedious. Meanwhile, static security scanners tend to produce many false positives. While machine learning-based approaches are promising, they typically perform well only in scenarios where training and test data are closely related. A key challenge for ML-based vulnerability detection is providing suitable and concise code context, as excessively long contexts negatively affect the code comprehension capabilities of machine learning models, particularly smaller ones. This work introduces Trace Gadgets, a novel code representation that minimizes code context by removing non-related code. Trace Gadgets precisely capture the statements that cover the path to the vulnerability. As input for ML models, Trace Gadgets provide a minimal but complete context, thereby improving the detection performance. Moreover, we collect a large-scale dataset generated from real-world applications with manually curated labels to further improve the performance of ML-based vulnerability detectors. Our results show that state-of-the-art machine learning models perform best when using Trace Gadgets compared to previous code representations, surpassing the detection capabilities of industry-standard static scanners such as GitHub's CodeQL by at least 4% on a fully unseen dataset. By applying our framework to real-world applications, we identify and report previously unknown vulnerabilities in widely deployed software.
Authors: Jerry Yao-Chieh Hu, Hude Liu, Hong-Yu Chen, Weimin Wu, Han Liu
Abstract: We prove that with linear transformations, both (i) two-layer self-attention and (ii) one-layer self-attention followed by a softmax function are universal approximators for continuous sequence-to-sequence functions on compact domains. Our main technique is a new interpolation-based method for analyzing attention's internal mechanism. This leads to our key insight: self-attention is able to approximate a generalized version of ReLU to arbitrary precision, and hence subsumes many known universal approximators. Building on these, we show that two-layer multi-head attention alone suffices as a sequence-to-sequence universal approximator. In contrast, prior works rely on feed-forward networks to establish universal approximation in Transformers. Furthermore, we extend our techniques to show that, (softmax-)attention-only layers are capable of approximating various statistical models in-context. We believe these techniques hold independent interest.
Authors: Mohamed-Khalil Bouzidi, Christian Schlauch, Nicole Scheuerer, Yue Yao, Nadja Klein, Daniel G\"ohring, J\"org Reichardt
Abstract: Fueled by motion prediction competitions and benchmarks, recent years have seen the emergence of increasingly large learning based prediction models, many with millions of parameters, focused on improving open-loop prediction accuracy by mere centimeters. However, these benchmarks fail to assess whether such improvements translate to better performance when integrated into an autonomous driving stack. In this work, we systematically evaluate the interplay between state-of-the-art motion predictors and motion planners. Our results show that higher open-loop accuracy does not always correlate with better closed-loop driving behavior and that other factors, such as temporal consistency of predictions and planner compatibility, also play a critical role. Furthermore, we investigate downsized variants of these models, and, surprisingly, find that in some cases models with up to 86% fewer parameters yield comparable or even superior closed-loop driving performance. Our code is available at https://github.com/aumovio/pred2plan.
Authors: Guangda Liu, Chengwei Li, Zhenyu Ning, Jing Lin, Yiwu Yao, Danning Ke, Minyi Guo, Jieru Zhao
Abstract: Large language models (LLMs) have been widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size grows proportionally with context length. While KV cache compression methods are proposed to address this issue, KV dropping methods incur considerable accuracy loss, and KV retrieval methods suffer from significant efficiency bottlenecks. We propose FreeKV, an algorithm-system co-optimization framework to enhance KV retrieval efficiency while preserving accuracy. On the algorithm side, FreeKV introduces speculative retrieval to shift the KV selection and recall processes out of the critical path, combined with fine-grained correction to ensure accuracy. On the system side, FreeKV employs hybrid KV layouts across CPU and GPU memory to eliminate fragmented data transfers, and leverages double-buffered streamed recall to further improve efficiency. Experiments demonstrate that FreeKV achieves near-lossless accuracy across various scenarios and models, delivering up to 13$\times$ speedup compared to SOTA KV retrieval methods.
Authors: Reyhaneh Keshavarzpour, Eghbal Mansoori
Abstract: Identification of antimicrobial peptides is an important and necessary issue in today's era. Antimicrobial peptides are essential as an alternative to antibiotics for biomedical applications and many other practical applications. These oligopeptides are useful in drug design and cause innate immunity against microorganisms. Artificial intelligence algorithms have played a significant role in the ease of identifying these peptides.This research is improved by improving proposed method in the field of antimicrobial peptides prediction. Suggested method is improved by combining the best coding method from different perspectives, In the following a deep neural network to balance the imbalanced combined datasets. The results of this research show that the proposed method have a significant improvement in the accuracy and efficiency of the prediction of antimicrobial peptides and are able to provide the best results compared to the existing methods. These development in the field of prediction and classification of antimicrobial peptides, basically in the fields of medicine and pharmaceutical industries, have high effectiveness and application.
Authors: Zhihao Zhang, Qiaole Dong, Qi Zhang, Jun Zhao, Enyu Zhou, Zhiheng Xi, Senjie Jin, Xiaoran Fan, Yuhao Zhou, Mingqi Wu, Yanwei Fu, Tao Ji, Tao Gui, Xuanjing Huang, Kai Chen
Abstract: Post-training algorithms such as Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT) are widely used to adapt multimodal large language models to downstream tasks. While effective at task adaptation, their impact on prior knowledge remains unclear. In this paper, we introduce jigsaw puzzles as a novel task absent from existing pretraining corpora and systematically study the behavior of SFT and RFT on open-source multimodal model, Qwen2.5-VL series. Our experiments reveal a sharp trade-off: SFT enables rapid task acquisition but leads to catastrophic forgetting, whereas RFT learns more slowly but maintains prior knowledge. We study this phenomenon through learning dynamics by examining both the magnitude and direction of how training data influence prior knowledge. Our analysis shows that RFT mainly reinforces correct samples naturally aligned with the base model's probability landscape, leading to weaker interference with prior knowledge. Moreover, training on RFT-simulated rollouts, which exert a small magnitude of influence and are well aligned in direction to prior knowledge, allows SFT to preserve prior knowledge better while rapidly learning new tasks. These findings suggest that distribution of training data, rather than algorithmic differences, plays a central role in forgetting, and highlight RFT's potential for stable continual learning in multimodal large language models.
Authors: Saierdaer Yusuyin, Te Ma, Hao Huang, Zhijian Ou
Abstract: Recently, pre-trained models with phonetic supervision have demonstrated their advantages for crosslingual speech recognition in data efficiency and information sharing across languages. However, a limitation is that a pronunciation lexicon is needed for such phoneme-based crosslingual speech recognition. In this study, we aim to eliminate the need for pronunciation lexicons and propose a latent variable model based method, with phonemes being treated as discrete latent variables. The new method consists of a speech-to-phoneme (S2P) model and a phoneme-to-grapheme (P2G) model, and a grapheme-to-phoneme (G2P) model is introduced as an auxiliary inference model. To jointly train the three models, we utilize the joint stochastic approximation (JSA) algorithm, which is a stochastic extension of the EM (expectation-maximization) algorithm and has demonstrated superior performance particularly in estimating discrete latent variable models. Furthermore, we propose marginal likelihood scoring (MLS) decoding to align inference with the training objective and P2G augmentation to improve the robustness of P2G mapping. Based on the Whistle multilingual pre-trained S2P model, crosslingual experiments are conducted in Polish (130 h) and Indonesian (20 h). With only 10 minutes of phoneme supervision, the new method, JSA-SPG, achieves 5% error rate reductions compared to the best crosslingual fine-tuning approach using subword or full phoneme supervision. Furthermore, it is found that in language domain adaptation (i.e., utilizing cross-domain text-only data), JSA-SPG outperforms the standard practice of language model fusion via the auxiliary support of the G2P model by 9% error rate reductions. To facilitate reproducibility and encourage further exploration in this field, we open-source the JSA-SPG training code and complete pipeline.
Authors: Sehyun Ryu, Hyun Jong Yang
Abstract: Reducing feedback overhead in beyond 5G networks is a critical challenge, as the growing number of antennas in modern massive MIMO systems substantially increases the channel state information (CSI) feedback demand in frequency division duplex (FDD) systems. To address this, extensive research has focused on CSI compression and prediction, with neural network-based approaches gaining momentum and being considered for integration into the 3GPP 5G-Advanced standards. While deep learning has been effectively applied to CSI-limited beamforming and handover optimization, reference signal allocation under such constraints remains surprisingly underexplored. To fill this gap, we introduce the concept of channel prediction-based reference signal allocation (CPRS), which jointly optimizes channel prediction and DM-RS allocation to improve data throughput without requiring CSI feedback. We further propose a standards-compliant ViViT/CNN-based architecture that implements CPRS by treating evolving CSI matrices as sequential image-like data, enabling efficient and adaptive transmission in dynamic environments. Simulation results using ray-tracing channel data generated in NVIDIA Sionna validate the proposed method, showing up to 36.60% throughput improvement over benchmark strategies.
Authors: Alex Liu, Lief Esbenshade, Shawon Sarkar, Victor Tian, Zachary Zhang, Kevin He, Min Sun
Abstract: This study investigates how K-12 educators use generative AI tools in real-world instructional contexts and how large language models (LLMs) can support scalable qualitative analysis of these interactions. Drawing on over 13,000 unscripted educator-AI conversations from an open-access platform, we examine educators' use of AI for lesson planning, differentiation, assessment, and pedagogical reflection. Methodologically, we introduce a replicable, LLM-assisted qualitative analysis pipeline that supports inductive theme discovery, codebook development, and large-scale annotation while preserving researcher control over conceptual synthesis. Empirically, the findings surface concrete patterns in how educators prompt, adapt, and evaluate AI-generated suggestions as part of their instructional reasoning. This work demonstrates the feasibility of combining LLM support with qualitative rigor to analyze complex educator behaviors at scale and inform the design of AI-powered educational tools.
Authors: Lucas Robinet, Ahmad Berjaoui, Elizabeth Cohen-Jonathan Moyal
Abstract: Self-supervised learning (SSL) has driven major advances in computational pathology by enabling the learning of rich representations from histopathology data. Yet, tissue analysis alone may fall short in capturing broader molecular complexity, as key complementary information resides in high-dimensional omics profiles such as transcriptomics, methylomics, and genomics. To address this gap, we introduce MORPHEUS, the first multimodal pre-training strategy that integrates histopathology images and multi-omics data within a shared transformer-based architecture. At its core, MORPHEUS relies on a novel masked omics modeling objective that encourages the model to learn meaningful cross-modal relationships. This yields a general-purpose pre-trained encoder that can be applied to histopathology alone or in combination with any subset of omics modalities. Beyond inference, MORPHEUS also supports flexible any-to-any omics reconstruction, enabling one or more omics profiles to be reconstructed from any modality subset that includes histopathology. Pre-trained on a large pan-cancer cohort, MORPHEUS shows substantial improvements over supervised and SSL baselines across diverse tasks and modality combinations. Together, these capabilities position it as a promising direction for the development of multimodal foundation models in oncology. Code is publicly available at https://github.com/Lucas-rbnt/MORPHEUS
Authors: Fan Gao, Cheng Huang, Nyima Tashi, Yutong Liu, Xiangxiang Wang, Thupten Tsering, Ban Ma-bao, Renzeg Duojie, Gadeng Luosang, Rinchen Dongrub, Dorje Tashi, Xiao Feng, Hao Wang, Yongbin Yu
Abstract: To address the severe data scarcity in Tibetan, a low-resource language spoken by over six million people, we introduce TIBSTC-CoT, the large-scale, multi-domain Tibetan dataset automatically constructed via chain-of-thought prompting with large language models (LLMs). TIBSTC-CoT establishes a scalable and reproducible framework for dataset creation in low-resource settings, covering diverse domains and reasoning patterns essential for language understanding and generation. Building on this dataset, we develop the Sunshine-thinking LLM family, a series of Tibetan-centric LLMs equipped with chain-of-thought capabilities. Trained entirely on TIBSTC-CoT, Sunshine-thinking has demonstrated strong reasoning and generation performance, comparable to state-of-the-art (SOTA) multilingual LLMs. Our work marks a significant step toward inclusive AI by enabling high-quality Tibetan language processing through both resource creation and model innovation. All data are available: https://github.com/Vicentvankor/sun-shine.
Authors: Ruida Cheng, Tejas Sudharshan Mathai, Pritam Mukherjee, Benjamin Hou, Qingqing Zhu, Zhiyong Lu, Matthew McAuliffe, Ronald M. Summers
Abstract: Segmentation of lesions on CT enables automatic measurement for clinical assessment of chronic diseases (e.g., lymphoma). Integrating large language models (LLMs) into the lesion segmentation workflow has the potential to combine imaging features with descriptions of lesion characteristics from the radiology reports. In this study, we investigate the feasibility of integrating text into the Swin-UMamba architecture for the task of lesion segmentation. The publicly available ULS23 DeepLesion dataset was used along with short-form descriptions of the findings from the reports. On the test dataset, our method achieved a high Dice score of 82.64, and a low Hausdorff distance of 6.34 pixels was obtained for lesion segmentation. The proposed Text-Swin-U/Mamba model outperformed prior approaches: 37.79% improvement over the LLM-driven LanGuideMedSeg model (p < 0.001), and surpassed the purely image-based XLSTM-UNet and nnUNet models by 2.58% and 1.01%, respectively. The dataset and code can be accessed at https://github.com/ruida/LLM-Swin-UMamba
Authors: Jongyeop Hyun, Bumsoo Kim
Abstract: Recent advancements in Large Language Models (LLMs) have significantly improved reasoning capabilities, with in-context learning (ICL) emerging as a key technique for adaptation without retraining. While previous works have focused on leveraging correct examples, recent research highlights the importance of learning from errors to enhance performance. However, existing methods lack a structured framework for analyzing and mitigating errors, particularly in Multimodal Large Language Models (MLLMs), where integrating visual and textual inputs adds complexity. To address this issue, we propose REFINE: Retrieval-Enhanced Feedback via In-context Neural Error-book, a teacher-student framework that systematically structures errors and provides targeted feedback. REFINE introduces three systematic queries to construct structured feedback -- Feed-Target, Feed-Check, and Feed-Path -- to enhance multimodal reasoning by prioritizing relevant visual information, diagnosing critical failure points, and formulating corrective actions. Unlike prior approaches that rely on redundant retrievals, REFINE optimizes structured feedback retrieval, improving inference efficiency, token usage, and scalability. Our results demonstrate substantial speedup, reduced computational costs, and successful generalization, highlighting REFINE's potential for enhancing multimodal reasoning.
Authors: Jungsuk Oh, Jay-Yoon Lee
Abstract: Probabilistic decoding in Large Language Models (LLMs) often yields inconsistent outputs, particularly on complex or long-form questions. Self-Consistency (SC) mitigates this for short-form QA by majority voting over exact strings, whereas Universal Self-Consistency (USC) and Weighted Unigram Consistency Score (WUCS) extend to long-form responses but lose accuracy on short-form benchmarks. We introduce \textbf{Latent Self-Consistency (LSC)}, which selects the most semantically consistent response using learnable token embeddings. LSC's lightweight forward processing of summary tokens only introduces negligible runtime overhead (at most $0.9\%$) on top of standard decoding of the base LLM, and requires no changes to the model architecture. Across 6 short-form and 5 long-form reasoning benchmarks (e.g., MATH, MMLU, TruthfulQA), LSC surpasses SC, USC, and WUCS on both short-form and long-form on average performance, while adding negligible computational overhead on vanilla inference. These results position LSC as a reliable consistency-selection method that works effectively across various answer formats. Additionally, LSC provides well-calibrated confidence estimates, maintaining low expected calibration error across both answer formats.
Authors: Elham Sadeghi, Xianqi Deng, I-Hsin Lin, Stacy M. Copp, Petko Bogdanov
Abstract: Biological sequence design (DNA, RNA, or peptides) with desired functional properties has applications in discovering novel nanomaterials, biosensors, antimicrobial drugs, and beyond. One common challenge is the ability to optimize complex high-dimensional properties such as target emission spectra of DNA-mediated fluorescent nanoparticles, photo and chemical stability, and antimicrobial activity of peptides across target microbes. Existing models rely on simple binary labels (e.g., binding/non-binding) rather than high-dimensional complex properties. To address this gap, we propose a geometry-preserving variational autoencoder framework, called PrIVAE, which learns latent sequence embeddings that respect the geometry of their property space. Specifically, we model the property space as a high-dimensional manifold that can be locally approximated by a nearest neighbor graph, given an appropriately defined distance measure. We employ the property graph to guide the sequence latent representations using (1) graph neural network encoder layers and (2) an isometric regularizer. PrIVAE learns a property-organized latent space that enables rational design of new sequences with desired properties by employing the trained decoder. We evaluate the utility of our framework for two generative tasks: (1) design of DNA sequences that template fluorescent metal nanoclusters and (2) design of antimicrobial peptides. The trained models retain high reconstruction accuracy while organizing the latent space according to properties. Beyond in silico experiments, we also employ sampled sequences for wet lab design of DNA nanoclusters, resulting in up to 16.1-fold enrichment of rare-property nanoclusters compared to their abundance in training data, demonstrating the practical utility of our framework.
Authors: Nikhil N S (Indian Institute of Science, Bengaluru, India), Bilal Muhammed (TCS Research and Innovation, Tata Consultancy Services Ltd), Soban Babu Beemaraj (TCS Research and Innovation, Tata Consultancy Services Ltd), Amol Dilip Joshi (TCS Research and Innovation, Tata Consultancy Services Ltd)
Abstract: Selecting a solution algorithm for the Facility Layout Problem (FLP), an NP-hard optimization problem with multiobjective trade-off, is a complex task that requires deep expert knowledge. The performance of a given algorithm depends on the specific characteristics of the problem, such as the number of facilities, objectives, and constraints. This creates a need for a data-driven recommendation method to guide algorithm selection in automated design systems. This paper introduces a new recommendation method to make this expertise accessible, based on a Knowledge Graph-Based Retrieval-Augmented Generation (KG-RAG) framework. In this framework, a domain-specific knowledge graph (KG) is constructed from the literature. The method then employs a multifaceted retrieval mechanism to gather relevant evidence from this KG using three distinct approaches: precise graph-based search, flexible vector-based search, and cluster-based high-level search. The retrieved evidence is utilized by a Large Language Model (LLM) to generate algorithm recommendations based on data-driven reasoning. This KG-RAG framework is tested on a use case consisting of six problems comprising of complex multi-objective and multi-constraint FLP case. The results are compared with the Gemini 1.5 Flash chatbot. The results show that KG-RAG achieves an average reasoning score of 4.7 out of 5 compared to 3.3 for the baseline chatbot.
Authors: Yiwei Lyu, Samir Harake, Asadur Chowdury, Soumyanil Banerjee, Rachel Gologorsky, Shixuan Liu, Anna-Katharina Meissner, Akshay Rao, Chenhui Zhao, Akhil Kondepudi, Cheng Jiang, Xinhai Hou, Rushikesh S. Joshi, Volker Neuschmelting, Ashok Srinivasan, Dawn Kleindorfer, Brian Athey, Vikas Gulani, Aditya Pandey, Honglak Lee, Todd Hollon
Abstract: Neuroimaging is a ubiquitous tool for evaluating patients with neurological diseases. The global demand for magnetic resonance imaging (MRI) studies has risen steadily, placing significant strain on health systems, prolonging turnaround times, and intensifying physician burnout. These challenges disproportionately impact patients in low-resource and rural settings. Here, we utilized a large academic health system as a data engine to develop Prima, the first vision language model (VLM) serving as an AI foundation for neuroimaging that supports real-world, clinical MRI studies as input. Trained on over 220,000 MRI studies, Prima uses a hierarchical vision architecture that provides general and transferable MRI features. Prima was tested in a 1-year health system-wide study that included 30K MRI studies. Across 52 radiologic diagnoses from the major neurologic disorders, including neoplastic, inflammatory, infectious, and developmental lesions, Prima achieved a mean diagnostic area under the ROC curve of 92.0, outperforming other state-of-the-art general and medical AI models. Prima offers explainable differential diagnoses, worklist priority for radiologists, and clinical referral recommendations across diverse patient demographics and MRI systems. Prima demonstrates algorithmic fairness across sensitive groups and can help mitigate health system biases, such as prolonged turnaround times for low-resource populations. These findings highlight the transformative potential of health system-scale VLMs and Prima's role in advancing AI-driven healthcare.
Authors: Hyunwoo Lee, Hayoung Choi, Hyunju Kim
Abstract: Activation functions critically influence trainability and expressivity, and recent work has therefore explored a broad range of nonlinearities. However, widely used Gaussian i.i.d. initializations are designed to preserve activation variance under wide or infinite width assumptions. In deep and relatively narrow networks with sigmoidal nonlinearities, these schemes often drive preactivations into saturation, and collapse gradients. To address this, we introduce an odd-sigmoid activations and propose an activation aware initialization tailored to any function in this class. Our method remains robust over a wide band of variance scales, preserving both forward signal variance and backpropagated gradient norms even in very deep and narrow networks. Empirically, across standard image benchmarks we find that the proposed initialization is substantially less sensitive to depth, width, and activation scale than Gaussian initializations. In physics informed neural networks (PINNs), scaled odd-sigmoid activations combined with our initialization achieve lower losses than Gaussian based setups, suggesting that diagonal-plus-noise weights provide a practical alternative when Gaussian initialization breaks down.
Authors: Jiayuan Sheng, Hanyang Zhao, Haoxian Chen, David D. Yao, Wenpin Tang
Abstract: Reinforcement Learning from Human Feedback (RLHF) is increasingly used to fine-tune diffusion models, but a key challenge arises from the mismatch between stochastic samplers used during training and deterministic samplers used during inference. In practice, models are fine-tuned using stochastic SDE samplers to encourage exploration, while inference typically relies on deterministic ODE samplers for efficiency and stability. This discrepancy induces a reward gap, raising concerns about whether high-quality outputs can be expected during inference. In this paper, we theoretically characterize this reward gap and provide non-vacuous bounds for general diffusion models, along with sharper convergence rates for Variance Exploding (VE) and Variance Preserving (VP) Gaussian models. Methodologically, we adopt the generalized denoising diffusion implicit models (gDDIM) framework to support arbitrarily high levels of stochasticity, preserving data marginals throughout. Empirically, our findings through large-scale experiments on text-to-image models using denoising diffusion policy optimization (DDPO) and mixed group relative policy optimization (MixGRPO) validate that reward gaps consistently narrow over training, and ODE sampling quality improves when models are updated using higher-stochasticity SDE training.
Authors: Austin Jia, Avaneesh Ramesh, Zain Shamsi, Daniel Zhang, Alex Liu
Abstract: Retrieval-Augmented Generation (RAG) has emerged as the dominant architectural pattern to operationalize Large Language Model (LLM) usage in Cyber Threat Intelligence (CTI) systems. However, this design is susceptible to poisoning attacks, and previously proposed defenses can fail for CTI contexts as cyber threat information is often completely new for emerging attacks, and sophisticated threat actors can mimic legitimate formats, terminology, and stylistic conventions. To address this issue, we propose that the robustness of modern RAG defenses can be accelerated by applying source credibility algorithms on corpora, using PageRank as an example. In our experiments, we demonstrate quantitatively that our algorithm applies a lower authority score to malicious documents while promoting trusted content, using the standardized MS MARCO dataset. We also demonstrate proof-of-concept performance of our algorithm on CTI documents and feeds.
Authors: Vladyslav Moroshan, Julien Siems, Arber Zela, Timur Carstensen, Frank Hutter
Abstract: Foundation models for zero-shot time series forecasting face challenges in efficient long-horizon prediction and reproducibility, with existing synthetic-only approaches underperforming on challenging benchmarks. This paper presents TempoPFN, a univariate time series foundation model based on linear Recurrent Neural Networks (RNNs) pre-trained exclusively on synthetic data. The model uses a GatedDeltaProduct architecture with state-weaving for fully parallelizable training across sequence lengths, eliminating the need for windowing or summarization techniques while maintaining robust temporal state-tracking. Our comprehensive synthetic data pipeline unifies diverse generators, including stochastic differential equations, Gaussian processes, and audio synthesis, with novel augmentations. In zero-shot evaluations on the Gift-Eval, fev-bench and Chronos-ZS benchmarks, TempoPFN achieves top-tier competitive performance, outperforming all existing synthetic-only approaches and surpassing the majority of models trained on real-world data, while being more efficient than existing baselines by leveraging fully parallelizable training and inference. We open-source our complete data generation pipeline and training code, providing a reproducible foundation for future research.
Authors: Romain Cosentino, Sarath Shekkizhar, Adam Earle
Abstract: We develop and analyze a theoretical framework for agent-to-agent interactions in a simplified in-context linear regression setting. In our model, each agent is instantiated as a single-layer transformer with linear self-attention (LSA) trained to implement gradient-descent-like updates on a quadratic regression objective from in-context examples. We then study the coupled dynamics when two such LSA agents alternately update from each other's outputs under potentially misaligned fixed objectives. Within this framework, we characterize the generation dynamics and show that misalignment leads to a biased equilibrium where neither agent reaches its target, with residual errors predictable from the objective gap and the prompt-induced geometry. We further contrast this fixed objective regime with an adaptive multi-agent setting, wherein a helper agent updates a turn-based objective to implement a Newton-like step for the main agent, eliminating the plateau and accelerating its convergence. Experiments with trained LSA agents, as well as black-box GPT-5-mini runs on in-context linear regression tasks, are consistent with our theoretical predictions within this simplified setting. We view our framework as a mechanistic framework that links prompt geometry and objective misalignment to stability, bias, and robustness, and as a stepping stone toward analyzing more realistic multi-agent LLM systems.
Authors: Johannes Kiechle, Stefan M. Fischer, Daniel M. Lang, Cosmin I. Bercea, Matthew J. Nyflot, Lina Felsner, Julia A. Schnabel, Jan C. Peeken
Abstract: The sharp rise in medical tomography examinations has created a demand for automated systems that can reliably extract informative features for downstream tasks such as tumor characterization. Although 3D volumes contain richer information than individual slices, effective 3D classification remains difficult: volumetric data encode complex spatial dependencies, and the scarcity of large-scale 3D datasets has constrained progress toward 3D foundation models. As a result, many recent approaches rely on 2D vision foundation models trained on natural images, repurposing them as feature extractors for medical scans with surprisingly strong performance. Despite their practical success, current methods that apply 2D foundation models to 3D scans via slice-based decomposition remain fundamentally limited. Standard slicing along axial, sagittal, and coronal planes often fails to capture the true spatial extent of a structure when its orientation does not align with these canonical views. More critically, most approaches aggregate slice features independently, ignoring the underlying 3D geometry and losing spatial coherence across slices. To overcome these limitations, we propose TomoGraphView, a novel framework that integrates omnidirectional volume slicing with spherical graph-based feature aggregation. Instead of restricting the model to axial, sagittal, or coronal planes, our method samples both canonical and non-canonical cross-sections generated from uniformly distributed points on a sphere enclosing the volume. We publicly share our accessible code base at http://github.com/compai-lab/2025-MedIA-kiechle and provide a user-friendly library for omnidirectional volume slicing at https://pypi.org/project/OmniSlicer.
URLs: http://github.com/compai-lab/2025-MedIA-kiechle, https://pypi.org/project/OmniSlicer.
Authors: Lifan Zheng, Jiawei Chen, Qinghong Yin, Jingyuan Zhang, Xinyi Zeng, Yu Tian
Abstract: Ensuring the reliability of agent architectures and effectively identifying problematic agents when failures occur are crucial challenges in multi-agent systems (MAS). Advances in large language models (LLMs) have established LLM-based agents as a major branch of MAS, enabling major breakthroughs in complex problem solving and world modeling. However, the reliability implications of this shift remain largely unexplored. i.e., whether substituting traditional agents with LLM-based agents can effectively enhance the reliability of MAS. In this work, we investigate and quantify the reliability of LLM-based agents from the perspective of Byzantine fault tolerance. We observe that LLM-based agents demonstrate stronger skepticism when processing erroneous message flows, a characteristic that enables them to outperform traditional agents across different topological structures. Motivated by the results of the pilot experiment, we design CP-WBFT, a confidence probe-based weighted Byzantine Fault Tolerant consensus mechanism to enhance the stability of MAS with different topologies. It capitalizes on the intrinsic reflective and discriminative capabilities of LLMs by employing a probe-based, weighted information flow transmission method to improve the reliability of LLM-based agents. Extensive experiments demonstrate that CP-WBFT achieves superior performance across diverse network topologies under extreme Byzantine conditions (85.7\% fault rate). Notably, our approach surpasses traditional methods by attaining remarkable accuracy on various topologies and maintaining strong reliability in both mathematical reasoning and safety assessment tasks.
Authors: Chunlei Shi, Han Xu, Yinghao Li, Yi-Lin Wei, Yongchao Feng, Yecheng Zhang, Dan Niu
Abstract: Satellite-based radar retrieval methods are widely employed to fill coverage gaps in ground-based radar systems, especially in remote areas affected by terrain blockage and limited detection range. Existing methods predominantly rely on overly simplistic spatial-domain architectures constructed from a single data source, limiting their ability to accurately capture complex precipitation patterns and sharply defined meteorological boundaries. To address these limitations, we propose WaveC2R, a novel wavelet-driven coarse-to-refined framework for radar retrieval. WaveC2R integrates complementary multi-source data and leverages frequency-domain decomposition to separately model low-frequency components for capturing precipitation patterns and high-frequency components for delineating sharply defined meteorological boundaries. Specifically, WaveC2R consists of two stages (i)Intensity-Boundary Decoupled Learning, which leverages wavelet decomposition and frequency-specific loss functions to separately optimize low-frequency intensity and high-frequency boundaries; and (ii)Detail-Enhanced Diffusion Refinement, which employs frequency-aware conditional priors and multi-source data to progressively enhance fine-scale precipitation structures while preserving coarse-scale meteorological consistency. Experimental results on the publicly available SEVIR dataset demonstrate that WaveC2R achieves state-of-the-art performance in satellite-based radar retrieval, particularly excelling at preserving high-intensity precipitation features and sharply defined meteorological boundaries.
Authors: Mathew Vanherreweghe, Michael H. Freedman, Keith M. Adams
Abstract: Recent work by Freedman and Mulligan demonstrated that shallow multilayer perceptrons spontaneously develop Kolmogorov-Arnold geometric (KAG) structure during training on synthetic three-dimensional tasks. However, it remained unclear whether this phenomenon persists in realistic high-dimensional settings and what spatial properties this geometry exhibits. We extend KAG analysis to MNIST digit classification (784 dimensions) using 2-layer MLPs with systematic spatial analysis at multiple scales. We find that KAG emerges during training and appears consistently across spatial scales, from local 7-pixel neighborhoods to the full 28x28 image. This scale-agnostic property holds across different training procedures: both standard training and training with spatial augmentation produce the same qualitative pattern. These findings reveal that neural networks spontaneously develop organized, scale-invariant geometric structure during learning on realistic high-dimensional data.
Authors: Hang Yu, Di Zhang, Qiwei Du, Yanping Zhao, Hai Zhang, Guang Chen, Eduardo E. Veas, Junqiao Zhao
Abstract: Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented trajectories present challenges for reward propagation, resulting in inaccurate value estimation and degraded policy performance. While trajectory stitching via generative models offers a promising solution, existing augmentation methods frequently produce trajectories that are either confined to the support of the behavior policy or violate the underlying dynamics, thereby limiting their effectiveness for policy improvement. We propose ASTRO, a data augmentation framework that generates distributionally novel and dynamics-consistent trajectories for offline RL. ASTRO first learns a temporal-distance representation to identify distinct and reachable stitch targets. We then employ a dynamics-guided stitch planner that adaptively generates connecting action sequences via Rollout Deviation Feedback, defined as the gap between target state sequence and the actual arrived state sequence by executing predicted actions, to improve trajectory stitching's feasibility and reachability. This approach facilitates effective augmentation through stitching and ultimately enhances policy learning. ASTRO outperforms prior offline RL augmentation methods across various algorithms, achieving notable performance gain on the challenging OGBench suite and demonstrating consistent improvements on standard offline RL benchmarks such as D4RL.
Authors: Jason Lunder
Abstract: In creating sentence embeddings for Natural Language Inference (NLI) tasks, using transformer-based models like BERT leads to high accuracy, but require hundreds of millions of parameters. These models take in sentences as a sequence of tokens, and learn to encode the meaning of the sequence into embeddings such that those embeddings can be used reliably for NLI tasks. Essentially, every word is considered against every other word in the sequence, and the transformer model is able to determine the relationships between them, entirely from scratch. However, a model that accepts explicit linguistic structures like dependency parse trees may be able to leverage prior encoded information about these relationships, without having to learn them from scratch, thus improving learning efficiency. To investigate this, we adapt Graph Matching Networks (GMN) to operate on dependency parse trees, creating Tree Matching Networks (TMN). We compare TMN to a BERT based model on the SNLI entailment task and on the SemEval similarity task. TMN is able to achieve significantly better results with a significantly reduced memory footprint and much less training time than the BERT based model on the SNLI task, while both models struggled to preform well on the SemEval. Explicit structural representations significantly outperform sequence-based models at comparable scales, but current aggregation methods limit scalability. We propose multi-headed attention aggregation to address this limitation.
Authors: Ishaan Gangwani, Aayam Bansal
Abstract: Zero-shot foundation models (FMs) promise training-free prediction on tabular data, yet their hardware footprint remains poorly characterized. We present a fully reproducible benchmark that reports test accuracy together with wall-clock latency, peak CPU RAM, and peak GPU VRAM on four public datasets: Adult-Income, Higgs-100k, Wine-Quality, and California-Housing. Two open FMs (TabPFN-1.0 and TabICL-base) are compared against tuned XGBoost, LightGBM, and Random Forest baselines on a single NVIDIA T4 GPU. The tree ensembles equal or surpass FM accuracy on three datasets while completing full-test batches in <= 0.40 s and <= 150 MB RAM, using zero VRAM. TabICL achieves a 0.8 percentage-point gain on Higgs but requires roughly 40,000 times more latency (960 s) and 9 GB VRAM. TabPFN matches tree-model accuracy on Wine and Housing but peaks at 4 GB VRAM and cannot process the full 100k-row Higgs table. These results quantify the substantial hardware-versus-accuracy trade-offs in current tabular FMs and provide an open baseline for future efficiency-oriented research.
Authors: Timo Stoll, Chendi Qian, Ben Finkelshtein, Ali Parviz, Darius Weber, Fabrizio Frasca, Hadar Shavit, Antoine Siraudin, Arman Mielke, Marie Anastacio, Erik M\"uller, Maya Bechler-Speicher, Michael Bronstein, Mikhail Galkin, Holger Hoos, Mathias Niepert, Bryan Perozzi, Jan T\"onshoff, Christopher Morris
Abstract: Machine learning on graphs has recently achieved impressive progress in various domains, including molecular property prediction and chip design. However, benchmarking practices remain fragmented, often relying on narrow, task-specific datasets and inconsistent evaluation protocols, which hampers reproducibility and broader progress. To address this, we introduce GraphBench, a comprehensive benchmarking suite that spans diverse domains and prediction tasks, including node-level, edge-level, graph-level, and generative settings. GraphBench provides standardized evaluation protocols -- with consistent dataset splits and performance metrics that account for out-of-distribution generalization -- as well as a unified hyperparameter tuning framework. Additionally, we benchmark GraphBench using message-passing neural networks and graph transformer models, providing principled baselines and establishing a reference performance. See www.graphbench.io for further details.
Authors: Hua Wang, Jinghao Lu, Fan Zhang
Abstract: Deep learning has shown strong performance in time series forecasting tasks. However, issues such as missing values and anomalies in sequential data hinder its further development in prediction tasks. Previous research has primarily focused on extracting feature information from sequence data or addressing these suboptimal data as positive samples for knowledge transfer. A more effective approach would be to leverage these non-ideal negative samples to enhance event prediction. In response, this study highlights the advantages of non-ideal negative samples and proposes the IdealTSF framework, which integrates both ideal positive and negative samples for time series forecasting. IdealTSF consists of three progressive steps: pretraining, training, and optimization. It first pretrains the model by extracting knowledge from negative sample data, then transforms the sequence data into ideal positive samples during training. Additionally, a negative optimization mechanism with adversarial disturbances is applied. Extensive experiments demonstrate that negative sample data unlocks significant potential within the basic attention architecture for time series forecasting. Therefore, IdealTSF is particularly well-suited for applications with noisy samples or low-quality data.
Authors: Yuan Gao, Chen Chen, Tianrong Chen, Jiatao Gu
Abstract: Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growing interest in leveraging high-quality pre-trained visual representations, either by aligning them inside VAEs or directly within the generative model. However, adapting such representations remains challenging due to fundamental mismatches between understanding-oriented features and generation-friendly latent spaces. Representation encoders benefit from high-dimensional latents that capture diverse hypotheses for masked regions, whereas generative models favor low-dimensional latents that must faithfully preserve injected noise. This discrepancy has led prior work to rely on complex objectives and architectures. In this work, we propose FAE (Feature Auto-Encoder), a simple yet effective framework that adapts pre-trained visual representations into low-dimensional latents suitable for generation using as little as a single attention layer, while retaining sufficient information for both reconstruction and understanding. The key is to couple two separate deep decoders: one trained to reconstruct the original feature space, and a second that takes the reconstructed features as input for image generation. FAE is generic; it can be instantiated with a variety of self-supervised encoders (e.g., DINO, SigLIP) and plugged into two distinct generative families: diffusion models and normalizing flows. Across class-conditional and text-to-image benchmarks, FAE achieves strong performance. For example, on ImageNet 256x256, our diffusion model with CFG attains a near state-of-the-art FID of 1.29 (800 epochs) and 1.70 (80 epochs). Without CFG, FAE reaches the state-of-the-art FID of 1.48 (800 epochs) and 2.08 (80 epochs), demonstrating both high quality and fast learning.
Authors: Kevin Vallier
Abstract: Von Neumann founded both game theory and the theory of self-reproducing automata, but the two programs never merged. This paper provides the synthesis. The Theory of Strategic Evolution analyzes strategic replicators: entities that optimize under resource constraints and spawn copies of themselves. We introduce Games with Endogenous Players (GEPs), where lineages (not instances) are the fundamental strategic units, and define Evolutionarily Stable Distributions of Intelligence (ESDIs) as the resulting equilibrium concept. The central mathematical object is a hierarchy of strategic layers linked by cross-level gain matrices. Under a small-gain condition (spectral radius less than one), the system admits a global Lyapunov function at every finite depth. We prove closure under meta-selection: adding governance levels, innovation, or constitutional evolution preserves the dynamical structure. The Alignment Impossibility Theorem shows that unrestricted self-modification destroys this structure; stable alignment requires bounded modification classes. Applications include AI deployment dynamics, market concentration, and institutional design. The framework shows why personality engineering fails under selection pressure and identifies constitutional constraints necessary for stable multi-agent systems.
Authors: Mahmoud Srewa, Tianyu Zhao, Salma Elmalaki
Abstract: This paper addresses the challenge of aligning large language models (LLMs) with diverse human preferences within federated learning (FL) environments, where standard methods often fail to adequately represent diverse viewpoints. We introduce a comprehensive evaluation framework that systematically assesses the trade-off between alignment quality and fairness when using different aggregation strategies for human preferences. In our federated setting, each group locally evaluates rollouts and produces reward signals, and the server aggregates these group-level rewards without accessing any raw data. Specifically, we evaluate standard reward aggregation techniques (min, max, and average) and introduce a novel adaptive scheme that dynamically adjusts preference weights based on a group's historical alignment performance. Our experiments on question-answering (Q/A) tasks using a PPO-based RLHF pipeline demonstrate that our adaptive approach consistently achieves superior fairness while maintaining competitive alignment scores. This work offers a robust methodology for evaluating LLM behavior across diverse populations and provides a practical solution for developing truly pluralistic and fairly aligned models.
Authors: Chengqi Dong, Chuhuai Yue, Hang He, Rongge Mao, Fenghe Tang, S Kevin Zhou, Zekun Xu, Xiaohan Wang, Jiajun Chai, Wei Lin, Guojun Yin
Abstract: Recent VLM-based agents aim to replicate OpenAI O3's ``thinking with images" via tool use, but most open-source methods limit input to a single image, falling short on real-world multi-image QA tasks. To address this, we propose IMAgent, an open-source vision agent trained via end-to-end reinforcement learning dedicated for complex multi-image tasks. By leveraging a multi-agent system, we generate challenging and visually-rich multi-image QA pairs to fully activate the tool-use potential of the base VLM. Through manual verification, we obtain MIFG-QA, comprising 10k samples for training and evaluation. With deeper reasoning steps, VLMs may increasingly ignore visual inputs. We therefore develop two specialized tools for visual reflection and confirmation, allowing the model to proactively reallocate its attention to image content during inference. Benefiting from our well-designed action-trajectory two-level mask strategy, IMAgent achieves stable tool use behavior via pure RL training without requiring costly supervised fine-tuning data. Extensive experiments demonstrate that IMAgent maintains strong performance on existing single-image benchmarks while achieving substantial improvements on our proposed multi-image dataset, with our analysis providing actionable insights for the research community. Codes and data will be released soon.
Authors: Zhaodong Wang, Zhenting Qi, Sherman Wong, Nathan Hu, Samuel Lin, Jun Ge, Erwin Gao, Wenlin Chen, Yilun Du, Minlan Yu, Ying Zhang
Abstract: Real-world software engineering tasks require coding agents that can operate over massive repositories, sustain long-horizon sessions, and reliably coordinate complex toolchains at test time. Existing research-grade agents offer transparency but struggle when scaled to real-world workloads, while proprietary systems achieve strong practical performance but provide limited extensibility, interpretability, and controllability. We introduce the Confucius Code Agent (CCA), a scalable software engineering agent that can operate at enterprise-level codebases. CCA is built on top of the Confucius SDK, an agent development platform structured around three complementary perspectives: Agent Experience (AX), User Experience (UX), and Developer Experience (DX). The SDK integrates a unified orchestrator with hierarchical working memory for long-context operation, a persistent note-taking mechanism for cross-session continual learning, and a modular extension system for reliable tool use. In addition, we introduce a meta-agent that automates the synthesis, evaluation, and refinement of agent configurations through a build-test-improve loop, enabling rapid adaptation to new tasks, environments, and tool stacks. Instantiated with these mechanisms, CCA demonstrates strong performance on real-world software engineering tasks. On SWE-Bench-Pro, CCA achieves a Resolve@1 of 54.3%, surpassing both research-grade and proprietary coding agents under comparable model conditions. Together, the Confucius SDK and CCA form a general, extensible, and production-grade foundation for building robust coding agents, bridging the gap between research prototypes and practical large-scale deployment.
Authors: Yijiong Yu, Jiale Liu, Qingyun Wu, Huazheng Wang, Ji Pei
Abstract: The self-attention mechanism in Transformer-based Large Language Models (LLMs) scales quadratically with input length, making long-context inference expensive. Sliding window attention (SWA) reduces this cost to linear complexity, but naively enabling complete SWA at inference-time for models pretrained with full attention (FA) causes severe long-context performance degradation due to training-inference mismatch. This makes us wonder: Can FA-pretrained LLMs be well adapted to SWA without pretraining? We investigate this by proposing Sliding Window Attention Adaptation (SWAA), a set of practical recipes that combine five methods for better adaptation: (1) applying SWA only during prefilling; (2) preserving "sink" tokens; (3) interleaving FA/SWA layers; (4) chain-of-thought (CoT); and (5) fine-tuning. Our experiments show that SWA adaptation is feasible while non-trivial: no single method suffices, yet specific synergistic combinations effectively recover the original long-context performance. We further analyze the performance-efficiency trade-offs of different SWAA configurations and provide recommended recipes for diverse scenarios, which can greatly and fundamentally accelerate LLM long-context inference speed by up to 100%. Our code is available at https://github.com/yuyijiong/sliding-window-attention-adaptation
URLs: https://github.com/yuyijiong/sliding-window-attention-adaptation
Authors: Arif D\"onmez
Abstract: We propose Symmetry-Loss, a brain-inspired algorithmic principle that enforces invariance and equivariance through a differentiable constraint derived from environmental symmetries. The framework models learning as the iterative refinement of an effective symmetry group, paralleling developmental processes in which cortical representations align with the world's structure. By minimizing structural surprise, i.e. deviations from symmetry consistency, Symmetry-Loss operationalizes a Free-Energy--like objective for representation learning. This formulation bridges predictive-coding and group-theoretic perspectives, showing how efficient, stable, and compositional representations can emerge from symmetry-based self-organization. The result is a general computational mechanism linking developmental learning in the brain with principled representation learning in artificial systems.
Authors: Fengyi Xu, Jun Ma, Waishan Qiu, Cui Guo, Jack C. P. Cheng
Abstract: Crowdsourced street-view imagery from social media provides real-time visual evidence of urban flooding and other crisis events, yet it often lacks reliable geographic metadata for emergency response. Existing image geo-localization approaches, also known as Visual Place Recognition (VPR) models, exhibit substantial performance degradation when applied to such imagery due to visual distortions and domain shifts in cross-source scenarios. This paper presents VPR-AttLLM, a model-agnostic framework that integrates the semantic reasoning and geo-knowledge of Large Language Models (LLMs) into established VPR pipelines through attention-guided descriptor enhancement. By leveraging LLMs to identify location-informative regions within the city context and suppress visual noise, VPR-AttLLM improves retrieval performance without requiring model retraining or additional data. Comprehensive evaluations are conducted on extended benchmarks including SF-XL enriched with real social-media flood images, synthetic flooding scenarios over established query sets and Mapillary photos, and a new HK-URBAN dataset capturing morphologically distinct cityscapes. Integrating VPR-AttLLM with three state-of-the-art VPR models-CosPlace, EigenPlaces, and SALAD-consistently improves recall performance, yielding relative gains typically between 1-3% and reaching up to 8% on the most challenging real flood imagery. Beyond measurable gains in retrieval accuracy, this study establishes a generalizable paradigm for LLM-guided multimodal fusion in visual retrieval systems. By embedding principles from urban perception theory into attention mechanisms, VPR-AttLLM bridges human-like spatial reasoning with modern VPR architectures. Its plug-and-play design, strong cross-source robustness, and interpretability highlight its potential for scalable urban monitoring and rapid geo-localization of crowdsourced crisis imagery.
Authors: Milad Malekzadeh, Magdalena Biernacka, Elias Willberg, Jussi Torkko, Edyta {\L}aszkiewicz, Tuuli Toivonen
Abstract: Understanding greenspace attractiveness is essential for designing livable and inclusive urban environments, yet existing assessment approaches often overlook informal or transient spaces and remain too resource intensive to capture subjective perceptions at scale. This study examines the ability of multimodal large language models (MLLMs), ChatGPT GPT-4o, Claude 3.5 Haiku, and Gemini 2.0 Flash, to assess greenspace attractiveness similarly to humans using Google Street View imagery. We compared model outputs with responses from a geo-questionnaire of residents in Lodz, Poland, across both formal (for example, parks and managed greenspaces) and informal (for example, meadows and wastelands) greenspaces. Survey respondents and models indicated whether each greenspace was attractive or unattractive and provided up to three free text explanations. Analyses examined how often their attractiveness judgments aligned and compared their explanations after classifying them into shared reasoning categories. Results show high AI human agreement for attractive formal greenspaces and unattractive informal spaces, but low alignment for attractive informal and unattractive formal greenspaces. Models consistently emphasized aesthetic and design oriented features, underrepresenting safety, functional infrastructure, and locally embedded qualities valued by survey respondents. While these findings highlight the potential for scalable pre-assessment, they also underscore the need for human oversight and complementary participatory approaches. We conclude that MLLMs can support, but not replace, context sensitive greenspace evaluation in planning practice.
Authors: Mulham Fawakherji, Bruce Race, Driss Benhaddou
Abstract: Globally, on-road transportation accounts for 15% of greenhouse gas (GHG) emissions and an estimated 385,000 premature deaths from PM2.5. Cities play a critical role in meeting IPCC targets, generating 75% of global energy-related GHG emissions. In Houston, Texas, on-road transportation represents 48% of baseline emissions in the Climate Action Plan (CAP). To reach net-zero by 2050, the CAP targets a 70% emissions reduction from a 2014 baseline, offset by 30% renewable energy. This goal is challenging because Houston is low-density and auto-dependent, with 89% of on-road emissions from cars and small trucks and limited public transit usage. Socio-economic disparities further constrain Zero Emissions Vehicle (ZEV) adoption. Strategies focus on expanding ZEV access and reducing Vehicle Miles Traveled (VMT) by 20% through transit improvements and city design. This paper presents methods for establishing an on-road emissions baseline and evaluating policies that leverage socio-economic indicators and Intelligent Transportation Systems (ITS) to accelerate ZEV adoption and reduce VMT. Smart parking, transit incentives, secure data systems, and ZEV fleet management support improvements in modal split and system reliability. Policy options are analyzed and potential actions identified. To support evaluation, a simulation environment was developed in Unity 3D, enabling dynamic modeling of urban mobility and visualization of policy scenarios. Auto-dependent cities aiming for 2050 emission targets can benefit from the indicators, metrics, and technologies discussed.
Authors: Junhyung Park, Yuqing Zhou
Abstract: The notion of causal effect is fundamental across many scientific disciplines. Traditionally, quantitative researchers have studied causal effects at the level of variables; for example, how a certain drug dose (W) causally affects a patient's blood pressure (Y). However, in many modern data domains, the raw variables-such as pixels in an image or tokens in a language model-do not have the semantic structure needed to formulate meaningful causal questions. In this paper, we offer a more fine-grained perspective by studying causal effects at the level of events, drawing inspiration from probability theory, where core notions such as independence are first given for events and sigma-algebras, before random variables enter the picture. Within the measure-theoretic framework of causal spaces, a recently introduced axiomatisation of causality, we first introduce several binary definitions that determine whether a causal effect is present, as well as proving some properties of them linking causal effect to (in)dependence under an intervention measure. Further, we provide quantifying measures that capture the strength and nature of causal effects on events, and show that we can recover the common measures of treatment effect as special cases.
Authors: Antonio Guillen-Perez
Abstract: The development of robust Autonomous Vehicles (AVs) is bottlenecked by the scarcity of "Long-Tail" training data. While fleets collect petabytes of video logs, identifying rare safety-critical events (e.g., erratic jaywalking, construction diversions) remains a manual, cost-prohibitive process. Existing solutions rely on coarse metadata search, which lacks precision, or cloud-based VLMs, which are privacy-invasive and expensive. We introduce Semantic-Drive, a local-first, neuro-symbolic framework for semantic data mining. Our approach decouples perception into two stages: (1) Symbolic Grounding via a real-time open-vocabulary detector (YOLOE) to anchor attention, and (2) Cognitive Analysis via a Reasoning VLM that performs forensic scene analysis. To mitigate hallucination, we implement a "System 2" inference-time alignment strategy, utilizing a multi-model "Judge-Scout" consensus mechanism. Benchmarked on the nuScenes dataset against the Waymo Open Dataset (WOD-E2E) taxonomy, Semantic-Drive achieves a Recall of 0.966 (vs. 0.475 for CLIP) and reduces Risk Assessment Error by 40% ccompared to the best single scout models. The system runs entirely on consumer hardware (NVIDIA RTX 3090), offering a privacy-preserving alternative to the cloud.
Authors: Erik Larsen
Abstract: Current safety evaluations of large language models rely on single-shot testing, implicitly assuming that model responses are deterministic and representative of the model's safety alignment. We challenge this assumption by investigating the stability of safety refusal decisions across random seeds and temperature settings. Testing four instruction-tuned models from three families (Llama 3.1 8B, Qwen 2.5 7B, Qwen 3 8B, Gemma 3 12B) on 876 harmful prompts across 20 different sampling configurations (4 temperatures x 5 random seeds), we find that 18-28% of prompts exhibit decision flips--the model refuses in some configurations but complies in others--depending on the model. Our Safety Stability Index (SSI) reveals that higher temperatures significantly reduce decision stability (Friedman chi-squared = 396.81, p < 0.001), with mean within-temperature SSI dropping from 0.977 at temperature 0.0 to 0.942 at temperature 1.0. We validate our findings across all model families using Claude 3.5 Haiku as a unified external judge, achieving 89.0% inter-judge agreement with our primary Llama 70B judge (Cohen's kappa = 0.62). Within each model, prompts with higher compliance rates exhibit lower stability (Spearman rho = -0.47 to -0.70, all p < 0.001), indicating that models "waver" more on borderline requests. These findings demonstrate that single-shot safety evaluations are insufficient for reliable safety assessment and that evaluation protocols must account for stochastic variation in model behavior. We show that single-shot evaluation agrees with multi-sample ground truth only 92.4% of the time when pooling across temperatures (94.2-97.7% at fixed temperature depending on setting), and recommend using at least 3 samples per prompt for reliable safety assessment.
Authors: Lily Erickson
Abstract: With the advent of machine learning and quantum computing, the 21st century has gone from a place of relative algorithmic security, to one of speculative unease and possibly, cyber catastrophe. Modern algorithms like Elliptic Curve Cryptography (ECC) are the bastion of current cryptographic security protocols that form the backbone of consumer protection ranging from Hypertext Transfer Protocol Secure (HTTPS) in the modern internet browser, to cryptographic financial instruments like Bitcoin. And there's been very little work put into testing the strength of these ciphers. Practically the only study that I could find was on side-channel recognition, a joint paper from the University of Milan, Italy and King's College, London\cite{battistello2025ecc}. These algorithms are already considered bulletproof by many consumers, but exploits already exist for them, and with computing power and distributed, federated compute on the rise, it's only a matter of time before these current bastions fade away into obscurity, and it's on all of us to stand up when we notice something is amiss, lest we see such passages claim victims in that process. In this paper, we seek to explore the use of modern language model architecture in cracking the association between a known public key, and its associated private key, by intuitively learning to reverse engineer the public keypair generation process, effectively solving the curve. Additonally, we attempt to ascertain modern machine learning's ability to memorize public-private secp256r1 keypairs, and to then test their ability to reverse engineer the public keypair generation process. It is my belief that proof-for would be equally valuable as proof-against in either of these categories. Finally, we'll conclude with some number crunching on where we see this particular field heading in the future.
Authors: Sreemaee Akshathala, Bassam Adnan, Mahisha Ramesh, Karthik Vaidhyanathan, Basil Muhammed, Kannan Parthasarathy
Abstract: Recent advances in agentic AI have shifted the focus from standalone Large Language Models (LLMs) to integrated systems that combine LLMs with tools, memory, and other agents to perform complex tasks. These multi-agent architectures enable coordinated reasoning, planning, and execution across diverse domains, allowing agents to collaboratively automate complex workflows. Despite these advances, evaluation and assessment of LLM agents and the multi-agent systems they constitute remain a fundamental challenge. Although various approaches have been proposed in the software engineering literature for evaluating conventional software components, existing methods for AI-based systems often overlook the non-deterministic nature of models. This non-determinism introduces behavioral uncertainty during execution, yet existing evaluations rely on binary task completion metrics that fail to capture it. Evaluating agentic systems therefore requires examining additional dimensions, including the agent ability to invoke tools, ingest and retrieve memory, collaborate with other agents, and interact effectively with its environment. These challenges emerged during our ongoing industry collaboration with MontyCloud Inc., when we deployed an agentic system in production. These limitations surfaced during deployment, highlighting practical gaps in the current evaluation methods and the need for a systematic assessment of agent behavior beyond task outcomes. Informed by these observations and established definitions of agentic systems, we propose an end-to-end Agent Assessment Framework with four evaluation pillars encompassing LLMs, Memory, Tools, and Environment. We validate the framework on a representative Autonomous CloudOps use case, where experiments reveal behavioral deviations overlooked by conventional metrics, demonstrating its effectiveness in capturing runtime uncertainties.
Authors: Xianchao Guan, Zhiyuan Fan, Yifeng Wang, Fuqiang Chen, Yanjiang Zhou, Zengyang Che, Hongxue Meng, Xin Li, Yaowei Wang, Hongpeng Wang, Min Zhang, Heng Tao Shen, Zheng Zhang, Yongbing Zhang
Abstract: The development of clinical-grade artificial intelligence in pathology is limited by the scarcity of diverse, high-quality annotated datasets. Generative models offer a potential solution but suffer from semantic instability and morphological hallucinations that compromise diagnostic reliability. To address this challenge, we introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS), the first generative foundation model for pathology-specific text-to-image synthesis. By leveraging a dual-stage training strategy on approximately 2.8 million image-caption pairs, CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy. This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations. Furthermore, CRAFTS-augmented datasets enhance the performance across various clinical tasks, including classification, cross-modal retrieval, self-supervised learning, and visual question answering. In addition, coupling CRAFTS with ControlNet enables precise control over tissue architecture from inputs such as nuclear segmentation masks and fluorescence images. By overcoming the critical barriers of data scarcity and privacy concerns, CRAFTS provides a limitless source of diverse, annotated histology data, effectively unlocking the creation of robust diagnostic tools for rare and complex cancer phenotypes.
Authors: Chendong Sun, mingmin Chen, Lei Xu
Abstract: Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in parallel. However, its core component -- the rejection sampling mechanism -- relies on a fixed, context-independent random threshold. This leads to a significant "random rejection" problem in high-uncertainty generation scenarios, where plausible candidate tokens are frequently rejected due to random chance, undermining inference efficiency. This paper introduces Efficient Adaptive Rejection Sampling (EARS), a novel method that dynamically adjusts the acceptance threshold by incorporating the target model's own predictive uncertainty, measured as 1 - max(P_target). By introducing a tolerance term proportional to this uncertainty, EARS intelligently relaxes the acceptance criterion when the model is uncertain, effectively reducing random rejections while maintaining strict standards when the model is confident. Experiments on creative writing and open-domain QA tasks demonstrate that EARS significantly enhances the efficiency of speculative decoding, achieving up to an 18.12% increase in throughput with a negligible 0.84% accuracy drop on the GSM8K benchmark. The method requires no modifications to model architectures and can be seamlessly integrated into existing speculative decoding frameworks.
Authors: Hao Fu, Wei Liu, Shuai Zhou
Abstract: This paper investigates the application of reinforcement learning (RL) to multi-robot social formation navigation, a critical capability for enabling seamless human-robot coexistence. While RL offers a promising paradigm, the inherent unpredictability and often uncooperative dynamics of pedestrian behavior pose substantial challenges, particularly concerning the efficiency of coordinated exploration among robots. To address this, we propose a novel coordinated-exploration multi-robot RL algorithm introducing an intrinsic motivation exploration. Its core component is a self-learning intrinsic reward mechanism designed to collectively alleviate policy conservatism. Moreover, this algorithm incorporates a dual-sampling mode within the centralized training and decentralized execution framework to enhance the representation of both the navigation policy and the intrinsic reward, leveraging a two-time-scale update rule to decouple parameter updates. Empirical results on social formation navigation benchmarks demonstrate the proposed algorithm's superior performance over existing state-of-the-art methods across crucial metrics. Our code and video demos are available at: https://github.com/czxhunzi/CEMRRL.
Authors: Kei Saito
Abstract: Current artificial intelligence systems, despite remarkable capabilities in text generation and pattern recognition, exhibit a fundamental architectural limitation: they resolve ambiguity prematurely. This premature semantic collapse -- the tendency to collapse multiple valid interpretations into a single output -- stems from classical identity assumptions embedded in standard neural architectures. We propose Non-Resolution Reasoning (NRR), a computational framework that treats ambiguity retention as a valid reasoning mode rather than a defect to be eliminated. NRR introduces three core principles: (1) Non-Identity (A $\ne$ A) -- the same symbol refers to different entities across contexts; (2) Approximate Identity (A $\approx$ A) -- entities share partial structural overlap without being identical; and (3) Non-Resolution -- conflicting interpretations can coexist without forced convergence. We formalize these principles through three architectural components: Multi-Vector Embeddings for context-dependent representation, Non-Collapsing Attention for parallel interpretation retention, and Contextual Identity Tracking (CIT) for maintaining A $\ne$ A across inference. We demonstrate NRR's advantages through case studies in paradox handling, creative generation, and context-dependent reasoning. Crucially, we provide a minimal empirical validation on a synthetic context-shift task where an NRR-lite model achieves 90.9% out-of-distribution accuracy compared to 9.1% for standard architectures, demonstrating that ambiguity preservation enables structural generalization. NRR challenges the assumption that meaning must collapse to be useful, offering a foundation for AI systems capable of sophisticated ambiguity handling and creative reasoning. The question is not whether AI should resolve ambiguity, but when, how, and under whose control.