# Research Papers — 2026-01 · bundle page 145 of 189 > Full-text markdown of papers #7201–7250 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/145 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/144.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/146.md) ### EvidFuse: Writing-Time Evidence Learning for Consistent Text-Chart Data Reporting Authors: Huanxiang Lin, Qianyue Wang, Jinwu Hu, Bailin Chen, Qing Du, Mingkui Tan Published: 2026-01-09 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2601.05487v1 Data-driven reports communicate decision-relevant insights by tightly interleaving narrative text with charts grounded in underlying tables. However, current LLM-based systems typically generate narratives and visualizations in staged pipelines, following either a text-first-graph-second or a graph-first-text-second paradigm. These designs often lead to chart-text inconsistency and insight freezing, where the intermediate evidence space becomes fixed and the model can no longer retrieve or construct new visual evidence as the narrative evolves, resulting in shallow and predefined analysis. To address the limitations, we propose \textbf{EvidFuse}, a training-free multi-agent framework that enables writing-time text-chart interleaved generation for data-driven reports. EvidFuse decouples visualization analysis from long-form drafting via two collaborating components: a \textbf{Data-Augmented Analysis Agent}, equipped with Exploratory Data Analysis (EDA)-derived knowledge and access to raw tables, and a \textbf{Real-Time Evidence Construction Writer} that plans an outline and drafts the report while intermittently issuing fine-grained analysis requests. This design allows visual evidence to be constructed and incorporated exactly when the narrative requires it, directly constraining subsequent claims and enabling on-demand expansion of the evidence space. Experiments demonstrate that EvidFuse attains the top rank in both LLM-as-a-judge and human evaluations on chart quality, chart-text alignment, and report-level usefulness. --- ### MMUEChange: A Generalized LLM Agent Framework for Intelligent Multi-Modal Urban Environment Change Analysis Authors: Zixuan Xiao, Jun Ma, Siwei Zhang Published: 2026-01-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.05483v2 Understanding urban environment change is essential for sustainable development. However, current approaches, particularly remote sensing change detection, often rely on rigid, single-modal analysis. To overcome these limitations, we propose MMUEChange, a multi-modal agent framework that flexibly integrates heterogeneous urban data via a modular toolkit and a core module, Modality Controller for cross- and intra-modal alignment, enabling robust analysis of complex urban change scenarios. Case studies include: a shift toward small, community-focused parks in New York, reflecting local green space efforts; the spread of concentrated water pollution across districts in Hong Kong, pointing to coordinated water management; and a notable decline in open dumpsites in Shenzhen, with contrasting links between nighttime economic activity and waste types, indicating differing urban pressures behind domestic and construction waste. Compared to the best-performing baseline, the MMUEChange agent achieves a 46.7% improvement in task success rate and effectively mitigates hallucination, demonstrating its capacity to support complex urban change analysis tasks with real-world policy implications. --- ### Multi-Image Super Resolution Framework for Detection and Analysis of Plant Roots Authors: Shubham Agarwal, Ofek Nourian, Michael Sidorov, Sharon Chemweno, Ofer Hadar, Naftali Lazarovitch, Jhonathan E. Ephrath Published: 2026-01-09 Categories: cs.CV, cs.ET arXiv: https://arxiv.org/abs/2601.05482v1 Understanding plant root systems is critical for advancing research in soil-plant interactions, nutrient uptake, and overall plant health. However, accurate imaging of roots in subterranean environments remains a persistent challenge due to adverse conditions such as occlusion, varying soil moisture, and inherently low contrast, which limit the effectiveness of conventional vision-based approaches. In this work, we propose a novel underground imaging system that captures multiple overlapping views of plant roots and integrates a deep learning-based Multi-Image Super Resolution (MISR) framework designed to enhance root visibility and detail. To train and evaluate our approach, we construct a synthetic dataset that simulates realistic underground imaging scenarios, incorporating key environmental factors that affect image quality. Our proposed MISR algorithm leverages spatial redundancy across views to reconstruct high-resolution images with improved structural fidelity and visual clarity. Quantitative evaluations show that our approach outperforms state-of-the-art super resolution baselines, achieving a 2.3 percent reduction in BRISQUE, indicating improved image quality with the same CLIP-IQA score, thereby enabling enhanced phenotypic analysis of root systems. This, in turn, facilitates accurate estimation of critical root traits, including root hair count and root hair density. The proposed framework presents a promising direction for robust automatic underground plant root imaging and trait quantification for agricultural and ecological research. --- ### The Facade of Truth: Uncovering and Mitigating LLM Susceptibility to Deceptive Evidence Authors: Herun Wan, Jiaying Wu, Minnan Luo, Fanxiao Li, Zhi Zeng, Min-Yen Kan Published: 2026-01-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.05478v1 To reliably assist human decision-making, LLMs must maintain factual internal beliefs against misleading injections. While current models resist explicit misinformation, we uncover a fundamental vulnerability to sophisticated, hard-to-falsify evidence. To systematically probe this weakness, we introduce MisBelief, a framework that generates misleading evidence via collaborative, multi-round interactions among multi-role LLMs. This process mimics subtle, defeasible reasoning and progressive refinement to create logically persuasive yet factually deceptive claims. Using MisBelief, we generate 4,800 instances across three difficulty levels to evaluate 7 representative LLMs. Results indicate that while models are robust to direct misinformation, they are highly sensitive to this refined evidence: belief scores in falsehoods increase by an average of 93.0\%, fundamentally compromising downstream recommendations. To address this, we propose Deceptive Intent Shielding (DIS), a governance mechanism that provides an early warning signal by inferring the deceptive intent behind evidence. Empirical results demonstrate that DIS consistently mitigates belief shifts and promotes more cautious evidence evaluation. --- ### MaxCode: A Max-Reward Reinforcement Learning Framework for Automated Code Optimization Authors: Jiefu Ou, Sapana Chaudhary, Kaj Bostrom, Nathaniel Weir, Shuai Zhang, Huzefa Rangwala, George Karypis Published: 2026-01-09 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.05475v1 Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized code (such as performant CUDA kernels and competition-level CPU code) requires expertise in systems, algorithms and specific languages and (ii) requires interpretation of performance metrics like timing and device utilization beyond binary correctness. In this work, we explore inference-time search algorithms that guide the LLM to discover better solutions through iterative refinement based on execution feedback. Our approach, called MaxCode unifies existing search methods under a max-reward reinforcement learning framework, making the observation and action-value functions modular for modification. To enhance the observation space, we integrate a natural language critique model that converts raw execution feedback into diagnostic insights about errors and performance bottlenecks, and the best-discounted reward seen so far. Together, these provide richer input to the code proposal function. To improve exploration during search, we train a generative reward-to-go model using action values from rollouts to rerank potential solutions. Testing on the KernelBench (CUDA) and PIE (C++) optimization benchmarks shows that MaxCode improves optimized code performance compared to baselines, achieving 20.3% and 10.1% relative improvements in absolute speedup value and relative speedup ranking, respectively. --- ### Efficient Differentiable Causal Discovery via Reliable Super-Structure Learning Authors: Pingchuan Ma, Qixin Zhang, Shuai Wang, Dacheng Tao Published: 2026-01-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.05474v1 Recently, differentiable causal discovery has emerged as a promising approach to improve the accuracy and efficiency of existing methods. However, when applied to high-dimensional data or data with latent confounders, these methods, often based on off-the-shelf continuous optimization algorithms, struggle with the vast search space, the complexity of the objective function, and the nontrivial nature of graph-theoretical constraints. As a result, there has been a surge of interest in leveraging super-structures to guide the optimization process. Nonetheless, learning an appropriate super-structure at the right level of granularity, and doing so efficiently across various settings, presents significant challenges. In this paper, we propose ALVGL, a novel and general enhancement to the differentiable causal discovery pipeline. ALVGL employs a sparse and low-rank decomposition to learn the precision matrix of the data. We design an ADMM procedure to optimize this decomposition, identifying components in the precision matrix that are most relevant to the underlying causal structure. These components are then combined to construct a super-structure that is provably a superset of the true causal graph. This super-structure is used to initialize a standard differentiable causal discovery method with a more focused search space, thereby improving both optimization efficiency and accuracy. We demonstrate the versatility of ALVGL by instantiating it across a range of structural causal models, including both Gaussian and non-Gaussian settings, with and without unmeasured confounders. Extensive experiments on synthetic and real-world datasets show that ALVGL not only achieves state-of-the-art accuracy but also significantly improves optimization efficiency, making it a reliable and effective solution for differentiable causal discovery. --- ### Towards Valid Student Simulation with Large Language Models Authors: Zhihao Yuan, Yunze Xiao, Ming Li, Weihao Xuan, Richard Tong, Mona Diab, Tom Mitchell Published: 2026-01-09 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2601.05473v1 This paper presents a conceptual and methodological framework for large language model (LLM) based student simulation in educational settings. The authors identify a core failure mode, termed the "competence paradox" in which broadly capable LLMs are asked to emulate partially knowledgeable learners, leading to unrealistic error patterns and learning dynamics. To address this, the paper reframes student simulation as a constrained generation problem governed by an explicit Epistemic State Specification (ESS), which defines what a simulated learner can access, how errors are structured, and how learner state evolves over time. The work further introduces a Goal-by-Environment framework to situate simulated student systems according to behavioral objectives and deployment contexts. Rather than proposing a new system or benchmark, the paper synthesizes prior literature, formalizes key design dimensions, and articulates open challenges related to validity, evaluation, and ethical risks. Overall, the paper argues for epistemic fidelity over surface realism as a prerequisite for using LLM-based simulated students as reliable scientific and pedagogical instruments. --- ### ROAP: A Reading-Order and Attention-Prior Pipeline for Optimizing Layout Transformers in Key Information Extraction Authors: Tingwei Xie, Jinxin He, Yonghong Song Published: 2026-01-09 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2601.05470v1 The efficacy of Multimodal Transformers in visually-rich document understanding (VrDU) is critically constrained by two inherent limitations: the lack of explicit modeling for logical reading order and the interference of visual tokens that dilutes attention on textual semantics. To address these challenges, this paper presents ROAP, a lightweight and architecture-agnostic pipeline designed to optimize attention distributions in Layout Transformers without altering their pre-trained backbones. The proposed pipeline first employs an Adaptive-XY-Gap (AXG-Tree) to robustly extract hierarchical reading sequences from complex layouts. These sequences are then integrated into the attention mechanism via a Reading-Order-Aware Relative Position Bias (RO-RPB). Furthermore, a Textual-Token Sub-block Attention Prior (TT-Prior) is introduced to adaptively suppress visual noise and enhance fine-grained text-text interactions. Extensive experiments on the FUNSD and CORD benchmarks demonstrate that ROAP consistently improves the performance of representative backbones, including LayoutLMv3 and GeoLayoutLM. These findings confirm that explicitly modeling reading logic and regulating modality interference are critical for robust document understanding, offering a scalable solution for complex layout analysis. The implementation code will be released at https://github.com/KevinYuLei/ROAP. --- ### STELP: Secure Transpilation and Execution of LLM-Generated Programs Authors: Swapnil Shinde, Sahil Wadhwa, Andy Luo, Akshay Gupta, Mohammad Shahed Sorower Published: 2026-01-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.05467v3 Rapid evolution of Large Language Models (LLMs) has achieved major advances in reasoning, planning, and function-calling capabilities. Multi-agentic collaborative frameworks using such LLMs place them at the center of solving software development-related tasks such as code generation. However, direct use of LLM generated code in production software development systems is problematic. The code could be unstable or erroneous and contain vulnerabilities such as data poisoning, malicious attacks, and hallucinations that could lead to widespread system malfunctions. This prohibits the adoption of LLM generated code in production AI systems where human code reviews and traditional secure testing tools are impractical or untrustworthy. In this paper, we discuss safety and reliability problems with the execution of LLM generated code and propose a Secure Transpiler and Executor of LLM-Generated Program (STELP), capable of executing LLM-generated code in a controlled and safe manner. STELP secures autonomous production AI systems involving code generation, filling the critical void left by the impracticality or limitations of traditional secure testing methodologies and human oversight. This includes applications such as headless code generation-execution and LLMs that produce executable code snippets as an action plan to be executed in real time. We contribute a human-validated dataset of insecure code snippets and benchmark our approach on publicly available datasets for correctness, safety, and latency. Our results demonstrate that our approach outperforms an existing method by a significant margin, particularly in its ability to safely execute risky code snippets. Warning: This paper contains malicious code snippets that should be run with caution. --- ### Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning Authors: Zhaoqi Wang, Zijian Zhang, Daqing He, Pengtao Kou, Xin Li, Jiamou Liu, Jincheng An, Yong Liu Published: 2026-01-09 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.05466v1 Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, however, they remain critically vulnerable to jailbreak attacks that elicit harmful responses violating human values and safety guidelines. Despite extensive research on defense mechanisms, existing safeguards prove insufficient against sophisticated adversarial strategies. In this work, we propose iMIST (\underline{i}nteractive \underline{M}ulti-step \underline{P}rogre\underline{s}sive \underline{T}ool-disguised Jailbreak Attack), a novel adaptive jailbreak method that synergistically exploits vulnerabilities in current defense mechanisms. iMIST disguises malicious queries as normal tool invocations to bypass content filters, while simultaneously introducing an interactive progressive optimization algorithm that dynamically escalates response harmfulness through multi-turn dialogues guided by real-time harmfulness assessment. Our experiments on widely-used models demonstrate that iMIST achieves higher attack effectiveness, while maintaining low rejection rates. These results reveal critical vulnerabilities in current LLM safety mechanisms and underscore the urgent need for more robust defense strategies. --- ### PRISMA: Reinforcement Learning Guided Two-Stage Policy Optimization in Multi-Agent Architecture for Open-Domain Multi-Hop Question Answering Authors: Yu Liu, Wenxiao Zhang, Cong Cao, Wenxuan Lu, Fangfang Yuan, Diandian Guo, Kun Peng, Qiang Sun, Kaiyan Zhang, Yanbing Liu, Jin B. Hong, Bowen Zhou et al. Published: 2026-01-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.05465v1 Answering real-world open-domain multi-hop questions over massive corpora is a critical challenge in Retrieval-Augmented Generation (RAG) systems. Recent research employs reinforcement learning (RL) to end-to-end optimize the retrieval-augmented reasoning process, directly enhancing its capacity to resolve complex queries. However, reliable deployment is hindered by two obstacles. 1) Retrieval Collapse: iterative retrieval over large corpora fails to locate intermediate evidence containing bridge answers without reasoning-guided planning, causing downstream reasoning to collapse. 2) Learning Instability: end-to-end trajectory training suffers from weak credit assignment across reasoning chains and poor error localization across modules, causing overfitting to benchmark-specific heuristics that limit transferability and stability. To address these problems, we propose PRISMA, a decoupled RL-guided framework featuring a Plan-Retrieve-Inspect-Solve-Memoize architecture. PRISMA's strength lies in reasoning-guided collaboration: the Inspector provides reasoning-based feedback to refine the Planner's decomposition and fine-grained retrieval, while enforcing evidence-grounded reasoning in the Solver. We optimize individual agent capabilities via Two-Stage Group Relative Policy Optimization (GRPO). Stage I calibrates the Planner and Solver as specialized experts in planning and reasoning, while Stage II utilizes Observation-Aware Residual Policy Optimization (OARPO) to enhance the Inspector's ability to verify context and trigger targeted recovery. Experiments show that PRISMA achieves state-of-the-art performance on ten benchmarks and can be deployed efficiently in real-world scenarios. --- ### Do LLMs Need Inherent Reasoning Before Reinforcement Learning? A Study in Korean Self-Correction Authors: Hongjin Kim, Jaewook Lee, Kiyoung Lee, Jong-hun Shin, Soojong Lim, Oh-Woog Kwon Published: 2026-01-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.05459v1 Large Language Models (LLMs) demonstrate strong reasoning and self-correction abilities in high-resource languages like English, but their performance remains limited in low-resource languages such as Korean. In this study, we investigate whether reinforcement learning (RL) can enhance Korean reasoning abilities to a degree comparable to English. Our findings reveal that RL alone yields limited improvements when applied to models lacking inherent Korean reasoning capabilities. To address this, we explore several fine-tuning strategies and show that aligning the model's internal reasoning processes with Korean inputs-particularly by tuning Korean-specific neurons in early layers-is key to unlocking RL's effectiveness. We introduce a self-correction code-switching dataset to facilitate this alignment and observe significant performance gains in both mathematical reasoning and self-correction tasks. Ultimately, we conclude that the crucial factor in multilingual reasoning enhancement is not injecting new linguistic knowledge, but effectively eliciting and aligning existing reasoning capabilities. Our study provides a new perspective on how internal translation and neuron-level tuning contribute to multilingual reasoning alignment in LLMs. --- ### ART: Adaptive Reasoning Trees for Explainable Claim Verification Authors: Sahil Wadhwa, Himanshu Kumar, Guanqun Yang, Abbaas Alif Mohamed Nishar, Pranab Mohanty, Swapnil Shinde, Yue Wu Published: 2026-01-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.05455v1 Large Language Models (LLMs) are powerful candidates for complex decision-making, leveraging vast encoded knowledge and remarkable zero-shot abilities. However, their adoption in high-stakes environments is hindered by their opacity; their outputs lack faithful explanations and cannot be effectively contested to correct errors, undermining trustworthiness. In this paper, we propose ART (Adaptive Reasoning Trees), a hierarchical method for claim verification. The process begins with a root claim, which branches into supporting and attacking child arguments. An argument's strength is determined bottom-up via a pairwise tournament of its children, adjudicated by a judge LLM, allowing a final, transparent and contestable verdict to be systematically derived which is missing in methods like Chain-of-Thought (CoT). We empirically validate ART on multiple datasets, analyzing different argument generators and comparison strategies. Our findings show that ART's structured reasoning outperforms strong baselines, establishing a new benchmark for explainable claim verification which is more reliable and ensures clarity in the overall decision making step. --- ### RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learning Authors: Marko Sterbentz, Kevin Cushing, Cameron Barrie, Kristian J. Hammond Published: 2026-01-09 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.05451v2 Recent advances in text-to-SQL have been driven by larger models, better datasets, and new training methods like RLVR. However, progress remains limited by scarce high-quality training data, a problem RLVR is especially sensitive to since noisy data can produce spurious rewards. Manual data creation is expensive, and existing synthetic methods trade off reliability for scalability: template-based approaches guarantee correct SQL but need schema-specific templates and lack diversity, while LLM-based generation scales easily but lacks quality guarantees. We introduce RingSQL, a hybrid framework for generating question-SQL pairs that combines schema-independent query templates with LLM-based paraphrasing of natural language questions. By grounding question generation in complete template questions, RingSQL preserves question-query correctness across all levels of query complexity, a property purely LLM-based methods fail to maintain. RingSQL also produces the only synthetic dataset that improves RLVR training performance across all tested model architectures and benchmarks, achieving 69.8% average accuracy and surpassing both the next-best synthetic dataset by 2.1% and human-annotated data from Spider and BIRD. Code and data are available at https://github.com/nu-c3lab/RingSQL. --- ### TAPM-Net: Trajectory-Aware Perturbation Modeling for Infrared Small Target Detection Authors: Hongyang Xie, Hongyang He, Victor Sanchez Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05446v1 Infrared small target detection (ISTD) remains a long-standing challenge due to weak signal contrast, limited spatial extent, and cluttered backgrounds. Despite performance improvements from convolutional neural networks (CNNs) and Vision Transformers (ViTs), current models lack a mechanism to trace how small targets trigger directional, layer-wise perturbations in the feature space, which is an essential cue for distinguishing signal from structured noise in infrared scenes. To address this limitation, we propose the Trajectory-Aware Mamba Propagation Network (TAPM-Net), which explicitly models the spatial diffusion behavior of target-induced feature disturbances. TAPM-Net is built upon two novel components: a Perturbation-guided Path Module (PGM) and a Trajectory-Aware State Block (TASB). The PGM constructs perturbation energy fields from multi-level features and extracts gradient-following feature trajectories that reflect the directionality of local responses. The resulting feature trajectories are fed into the TASB, a Mamba-based state-space unit that models dynamic propagation along each trajectory while incorporating velocity-constrained diffusion and semantically aligned feature fusion from word-level and sentence-level embeddings. Unlike existing attention-based methods, TAPM-Net enables anisotropic, context-sensitive state transitions along spatial trajectories while maintaining global coherence at low computational cost. Experiments on NUAA-SIRST and IRSTD-1K demonstrate that TAPM-Net achieves state-of-the-art performance in ISTD. --- ### Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models Authors: Songze Li, Ruishi He, Xiaojun Jia, Jun Wang, Zhihui Fu Published: 2026-01-09 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2601.05445v1 Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined by several critical limitations: they struggle to maintain a coherent progression over long interactions, often losing track of what has been accomplished and what remains to be done; they rely on rigid or pre-defined patterns, and fail to adapt to the LLM's dynamic and unpredictable conversational state. To address these shortcomings, we introduce Mastermind, a multi-turn jailbreak framework that adopts a dynamic and self-improving approach. Mastermind operates in a closed loop of planning, execution, and reflection, enabling it to autonomously build and refine its knowledge of model vulnerabilities through interaction. It employs a hierarchical planning architecture that decouples high-level attack objectives from low-level tactical execution, ensuring long-term focus and coherence. This planning is guided by a knowledge repository that autonomously discovers and refines effective attack patterns by reflecting on interactive experiences. Mastermind leverages this accumulated knowledge to dynamically recombine and adapt attack vectors, dramatically improving both effectiveness and resilience. We conduct comprehensive experiments against state-of-the-art models, including GPT-5 and Claude 3.7 Sonnet. The results demonstrate that Mastermind significantly outperforms existing baselines, achieving substantially higher attack success rates and harmfulness ratings. Moreover, our framework exhibits notable resilience against multiple advanced defense mechanisms. --- ### What Functions Does XGBoost Learn? Authors: Dohyeong Ki, Adityanand Guntuboyina Published: 2026-01-09 Categories: math.ST, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.05444v1 This paper establishes a rigorous theoretical foundation for the function class implicitly learned by XGBoost, bridging the gap between its empirical success and our theoretical understanding. We introduce an infinite-dimensional function class $\mathcal{F}^{d, s}_{\infty-\text{ST}}$ that extends finite ensembles of bounded-depth regression trees, together with a complexity measure $V^{d, s}_{\infty-\text{XGB}}(\cdot)$ that generalizes the $L^1$ regularization penalty used in XGBoost. We show that every optimizer of the XGBoost objective is also an optimizer of an equivalent penalized regression problem over $\mathcal{F}^{d, s}_{\infty-\text{ST}}$ with penalty $V^{d, s}_{\infty-\text{XGB}}(\cdot)$, providing an interpretation of XGBoost as implicitly targeting a broader function class. We also develop a smoothness-based interpretation of $\mathcal{F}^{d, s}_{\infty-\text{ST}}$ and $V^{d, s}_{\infty-\text{XGB}}(\cdot)$ in terms of Hardy--Krause variation. We prove that the least squares estimator over $\{f \in \mathcal{F}^{d, s}_{\infty-\text{ST}}: V^{d, s}_{\infty-\text{XGB}}(f) \le V\}$ achieves a nearly minimax-optimal rate of convergence $n^{-2/3} (\log n)^{4(\min(s, d) - 1)/3}$, thereby avoiding the curse of dimensionality. Our results provide the first rigorous characterization of the function space underlying XGBoost, clarify its connection to classical notions of variation, and identify an important open problem: whether the XGBoost algorithm itself achieves minimax optimality over this class. --- ### A brief note on learning problem with global perspectives Authors: Getachew K. Befekadu Published: 2026-01-09 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2601.05441v1 This brief note considers the problem of learning with dynamic-optimizing principal-agent setting, in which the agents are allowed to have global perspectives about the learning process, i.e., the ability to view things according to their relative importances or in their true relations based-on some aggregated information shared by the principal. Whereas, the principal, which is exerting an influence on the learning process of the agents in the aggregation, is primarily tasked to solve a high-level optimization problem posed as an empirical-likelihood estimator under conditional moment restrictions model that also accounts information about the agents' predictive performances on out-of-samples as well as a set of private datasets available only to the principal. In particular, we present a coherent mathematical argument which is necessary for characterizing the learning process behind this abstract principal-agent learning framework, although we acknowledge that there are a few conceptual and theoretical issues still need to be addressed. --- ### Tracing Moral Foundations in Large Language Models Authors: Chenxiao Yu, Bowen Yi, Farzan Karimi-Malekabadi, Suhaib Abdurahman, Jinyi Ye, Shrikanth Narayanan, Yue Zhao, Morteza Dehghani Published: 2026-01-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.05437v3 Large language models often produce human-like moral judgments, but it is unclear whether this reflects an internal conceptual structure or superficial ``moral mimicry.'' Using Moral Foundations Theory (MFT) as an analytic framework, we study how moral foundations are encoded, organized, and expressed across 14 base and instruction-tuned LLMs spanning four model families (Llama, Qwen2.5, Qwen3-MoE, Mistral) and scales from 7B to 70B. We employ a multi-level approach combining (i) layer-wise analysis of MFT concept representations and their alignment with human moral perceptions, (ii) pretrained sparse autoencoders (SAEs) over the residual stream to identify sparse features that support moral concepts, and (iii) causal steering interventions using dense MFT vectors and sparse SAE features. We find that models represent and distinguish moral foundations in a manner that aligns with human judgments, and that this moral geometry naturally emerges from pretraining and is selectively rewired by post-training. At a finer scale, SAE features show clear semantic links to specific foundations, suggesting partially disentangled mechanisms within shared representations. Finally, steering along either dense vectors or sparse features produces predictable shifts in foundation-relevant behavior, demonstrating a causal connection between internal representations and moral outputs. Together, our results provide mechanistic evidence that moral concepts in LLMs are distributed, layered, and partly disentangled, suggesting that pluralistic moral structure can emerge as a latent pattern from the statistical regularities of language alone. --- ### Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems Authors: Uday Allu, Sonu Kedia, Tanmay Odapally, Biddwan Ahmed Published: 2026-01-08 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.04936v1 Retrieval-Augmented Generation (RAG) systems critically depend on effective document chunking strategies to balance retrieval quality, latency, and operational cost. Traditional chunking approaches, such as fixed-size, rule-based, or fully agentic chunking, often suffer from high token consumption, redundant text generation, limited scalability, and poor debuggability, especially for large-scale web content ingestion. In this paper, we propose Web Retrieval-Aware Chunking (W-RAC), a novel, cost-efficient chunking framework designed specifically for web-based documents. W-RAC decouples text extraction from semantic chunk planning by representing parsed web content as structured, ID-addressable units and leveraging large language models (LLMs) only for retrieval-aware grouping decisions rather than text generation. This significantly reduces token usage, eliminates hallucination risks, and improves system observability.Experimental analysis and architectural comparison demonstrate that W-RAC achieves comparable or better retrieval performance than traditional chunking approaches while reducing chunking-related LLM costs by an order of magnitude. --- ### ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods Authors: Rushikesh Deotale, Adithya Srinivasan, Yuan Tian, Tianyi Zhang, Pavlos Vlachos, Hector Gomez Published: 2026-01-08 Categories: cs.CE, cs.AI, cs.LG, cs.MS, math.NA arXiv: https://arxiv.org/abs/2603.21011v2 Finite element (FE) analysis guides the design and verification of nearly all manufactured objects. It is at the core of computational engineering, enabling simulation of complex physical systems, from fluids and solids to multiphysics systems. However, implementing FE codes and analyzing simulation results demands expertise across numerical analysis, continuum mechanics, and programming. Conventional Large Language Models (LLMs) can generate FE code, but they hallucinate, lack awareness of variational structures, and cannot close the loop from problem statement to a verified solution. Here, we propose ALL-FEM, an autonomous simulation system that integrates agentic AI with domain-specific, fine-tuned LLMs for FEniCS code generation across solid, fluid, and multiphysics applications. We construct a corpus of 1000+ verified FEniCS scripts by combining 500+ curated expert codes with a retrieval-augmented, multi-LLM pipeline that generates and filters codes for diverse PDEs, geometries, and boundary conditions. We used the corpus to fine-tune LLMs with 3B to 120B parameters. Our agentic framework orchestrates specialized agents, powered by fine-tuned LLMs, to formulate problems as PDEs, generate and debug code and visualize the results. We evaluated the system on 39 benchmarks that include problems of linear/nonlinear elasticity, plasticity, Newtonian/non-Newtonian flow, thermofluids, fluid-structure interaction, phase separation, and transport on moving domains. Embedded in a multi-agent workflow with runtime feedback, the best fine-tuned model (GPT OSS 120B) achieves code-level success of 71.79%, outperforming a non-agentic deployment of GPT 5 Thinking. By showing that relatively small, fine-tuned LLMs, orchestrated through agentic frameworks, can automate FE workflows, ALL-FEM offers a blueprint for autonomous simulation systems in computational science and engineering. --- ### Commitment Checklist: Auditing Author Commitments in Peer Review Authors: Chung-Chi Chen, Iryna Gurevych Published: 2026-01-08 Categories: cs.CY, cs.CL, cs.DL arXiv: https://arxiv.org/abs/2603.00003v1 Peer review author responses often include commitments to add experiments, release code, or clarify content in the final paper. Yet, there is currently no systematic mechanism to ensure authors fulfill these promises. In this position paper, we present a large-scale audit of author commitments using large language models (LLMs) to compare rebuttals against camera-ready versions. Analyzing the commitments from ICLR-2025 and EMNLP-2024, we find that while a majority of promised changes are implemented, a significant share (about 25%) are not, with "missing experiments" and other high-impact items among the most frequently unfulfilled. We demonstrate that LLM-based tools can feasibly detect the promises. Finally, we propose the idea of Author Commitment Checklist, which would alert authors and organizers to unaddressed promises, increasing accountability and strengthening the integrity of the peer review process. We discuss the benefits of this practice and advocate for its adoption in future conferences. --- ### PiC-BNN: A 128-kbit 65 nm Processing-in-CAM-Based End-to-End Binary Neural Network Accelerator Authors: Yuval Harary, Almog Sharoni, Esteban Garzón, Marco Lanuzza, Adam Teman, Leonid Yavits Published: 2026-01-08 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2601.19920v1 Binary Neural Networks (BNNs), where weights and activations are constrained to binary values (+1, -1), are a highly efficient alternative to traditional neural networks. Unfortunately, typical BNNs, while binarizing linear layers (matrix-vector multiplication), still implement other network layers (batch normalization, softmax, output layer, and sometimes the input layer of a convolutional neural network) in full precision. This limits the area and energy benefits and requires architectural support for full precision operations. We propose PiC-BNN, a true end-to-end binary in-approximate search (Hamming distance tolerant) Content Addressable Memory based BNN accelerator. PiC-BNN is designed and manufactured in a commercial 65nm process. PiC-BNN uses Hamming distance tolerance to apply the law of large numbers to enable accurate classification without implementing full precision operations. PiC-BNN achieves baseline software accuracy (95.2%) on the MNIST dataset and 93.5% on the Hand Gesture (HG) dataset, a throughput of 560K inferences/s, and presents a power efficiency of 703M inferences/s/W when implementing a binary MLP model for MNIST/HG dataset classification. --- ### ASKD-Whisper: Adaptive Self-knowledge Distillation for Efficient and Low-Latency Automatic Speech Recognition Authors: Junseok Lee, Nahun Kim, Sangyong Lee, Chang-Jae Chun Published: 2026-01-08 Categories: cs.CL, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2601.19919v2 Knowledge distillation (KD) is one of the most effective paradigms for compressing large-scale foundation models into deployable architectures. In the context of Automatic Speech Recognition (ASR), previous studies have predominantly focused on forcing the student model to strictly mimic the predictive distribution of a massive teacher model. However, this static dependency often presents an inherent trade-off: while the student rapidly acquires basic linguistic representations, it simultaneously inherits the teacher's domain-specific blind spots and over-confident hallucinations, leading to a severe decline in out-of-distribution generalization capacity. To effectively mitigate this issue, we propose Adaptive Self-Knowledge Distillation (ASKD), a dynamic curriculum framework. ASKD systematically decays the dependency on the teacher's distribution as training progresses-thereby unlocking the student's independent reasoning capacity-and subsequently employs a self-knowledge distillation phase to act as a structural regularizer. By applying ASKD, we distill the massive Whisper architecture into a compact variant, ASKD-Whisper. In our comprehensive evaluations across diverse acoustic domains, ASKD-Whisper not only achieves a 5x speedup in inference latency but also outperforms its teacher model by yielding a 1.07% lower word error rate (WER). These results demonstrate that ASKD effectively prevents teacher-induced overfitting and establishes a new state-of-the-art for generalizable model compression. --- ### Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models Authors: Longteng Zhang, Sen Wu, Shuai Hou, Zhengyu Qing, Zhuo Zheng, Danning Ke, Qihong Lin, Qiang Wang, Shaohuai Shi, Xiaowen Chu Published: 2026-01-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.16991v3 Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation (LoRA) reduces trainable parameters by factorizing weight updates, yet the underlying dense weights still impose high storage and computation costs. Magnitude-based pruning can yield sparse models but typically degrades LoRA's performance when applied naively. In this paper, we introduce SALR (Sparsity-Aware Low-Rank Representation), a novel fine-tuning paradigm that unifies low-rank adaptation with sparse pruning under a rigorous mean-squared-error framework. We prove that statically pruning only the frozen base weights minimizes the pruning error bound, and we recover the discarded residual information via a truncated-SVD low-rank adapter, which provably reduces per-entry MSE by a factor of $(1 - r/\min(d,k))$. To maximize hardware efficiency, we fuse multiple low-rank adapters into a single concatenated GEMM, and we adopt a bitmap-based encoding with a two-stage pipelined decoding + GEMM design to achieve true model compression and speedup. Empirically, SALR attains 50\% sparsity on various LLMs while matching the performance of LoRA on GSM8K and MMLU, reduces model size by $2\times$, and delivers up to a $1.7\times$ inference speedup. --- ### Neutral Substrates: A Design Constraint for Shared Records Under Persistent Interpretive Disagreement Authors: Denise M. Case Published: 2026-01-08 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.14271v2 Shared accountability records are often used by parties who may never agree about causation, responsibility, or normative interpretation. For such records, neutrality cannot be achieved by omitting contested information, because accountability requires preserving the claims parties made, with their sources and provenance. Nor can neutrality be achieved by asserting one contested interpretation as the shared base. This paper defines a neutral substrate as a shared representational layer that provides stable reference while making no object-level substrate-layer commitments to causal or normative propositions. The central design constraint is that, when causal and normative propositions are contestable across admissible frameworks and the substrate's referential commitments are common ground, the substrate's neutrality is guaranteed at design time if and only if its foundational layer is restricted to those referential commitments and attribution propositions whose attributional basis is fixed by them. Causal and normative content may still be represented, but not as object-level foundational-layer commitments: it may appear there only as the content of attributed assertions with provenance, made by some identified framework, source, agent, institution, record, or document. The representational machinery used here is standard: reification, attribution, and provenance. The contribution is the constraint: a checkable condition on the foundational layer of a shared record, stated together with the assumptions it depends on and the boundary condition under which the constraint does not apply. A neutral substrate says enough to preserve accountability, but it does not turn one party's interpretation into an object-level substrate-layer commitment. The constraint does not apply at that layer when the referential regime or attributional basis is contested among the frameworks in play. --- ### A Multimodal Data Processing Pipeline for MIMIC-IV Dataset Authors: Farzana Islam Adiba, Varsha Danduri, Fahmida Liza Piya, Ali Abbasi, Mehak Gupta, Rahmatollah Beheshti Published: 2026-01-08 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.11606v1 The MIMIC-IV dataset is a large, publicly available electronic health record (EHR) resource widely used for clinical machine learning research. It comprises multiple modalities, including structured data, clinical notes, waveforms, and imaging data. Working with these disjointed modalities requires an extensive manual effort to preprocess and align them for downstream analysis. While several pipelines for MIMIC-IV data extraction are available, they target a small subset of modalities or do not fully support arbitrary downstream applications. In this work, we greatly expand our prior popular unimodal pipeline and present a comprehensive and customizable multimodal pipeline that can significantly reduce multimodal processing time and enhance the reproducibility of MIMIC-based studies. Our pipeline systematically integrates the listed modalities, enabling automated cohort selection, temporal alignment across modalities, and standardized multimodal output formats suitable for arbitrary static and time-series downstream applications. We release the code, a simple UI, and a Python package for selective integration (with embedding) at https://github.com/healthylaife/MIMIC-IV-Data-Pipeline. --- ### Hindsight Preference Replay Improves Preference-Conditioned Multi-Objective Reinforcement Learning Authors: Jonaid Shianifar, Michael Schukat, Karl Mason Published: 2026-01-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.11604v1 Multi-objective reinforcement learning (MORL) enables agents to optimize vector-valued rewards while respecting user preferences. CAPQL, a preference-conditioned actor-critic method, achieves this by conditioning on weight vectors w and restricts data usage to the specific preferences under which it was collected, leaving off-policy data from other preferences unused. We introduce Hindsight Preference Replay (HPR), a simple and general replay augmentation strategy that retroactively relabels stored transitions with alternative preferences. This densifies supervision across the preference simplex without altering the CAPQL architecture or loss functions. Evaluated on six MO-Gymnasium locomotion tasks at a fixed 300000-step budget using expected utility (EUM), hypervolume (HV), and sparsity, HPR-CAPQL improves HV in five of six environments and EUM in four of six. On mo-humanoid-v5, for instance, EUM rises from $323\!\pm\!125$ to $1613\!\pm\!464$ and HV from 0.52M to 9.63M, with strong statistical support. mo-halfcheetah-v5 remains a challenging exception where CAPQL attains higher HV at comparable EUM. We report final summaries and Pareto-front visualizations across all tasks. --- ### Differentiating through binarized topology changes: Second-order subpixel-smoothed projection Authors: Giuseppe Romano, Rodrigo Arrieta, Steven G. Johnson Published: 2026-01-08 Categories: eess.SP, cond-mat.mtrl-sci, cs.CV, math.OC arXiv: https://arxiv.org/abs/2601.10737v1 A key challenge in topology optimization (TopOpt) is that manufacturable structures, being inherently binary, are non-differentiable, creating a fundamental tension with gradient-based optimization. The subpixel-smoothed projection (SSP) method addresses this issue by smoothing sharp interfaces at the subpixel level through a first-order expansion of the filtered field. However, SSP does not guarantee differentiability under topology changes, such as the merging of two interfaces, and therefore violates the convergence guarantees of many popular gradient-based optimization algorithms. We overcome this limitation by regularizing SSP with the Hessian of the filtered field, resulting in a twice-differentiable projected density during such transitions, while still guaranteeing an almost-everywhere binary structure. We demonstrate the effectiveness of our second-order SSP (SSP2) methodology on both thermal and photonic problems, showing that SSP2 has faster convergence than SSP for connectivity-dominant cases -- where frequent topology changes occur -- while exhibiting comparable performance otherwise. Beyond improving convergence guarantees for CCSA optimizers, SSP2 enables the use of a broader class of optimization algorithms with stronger theoretical guarantees, such as interior-point methods. Since SSP2 adds minimal complexity relative to SSP or traditional projection schemes, it can be used as a drop-in replacement in existing TopOpt codes. --- ### Formal Safety Guarantees for Autonomous Vehicles using Barrier Certificates Authors: Oumaima Barhoumi, Mohamed H Zaki, Sofiène Tahar Published: 2026-01-08 Categories: cs.RO, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2601.09740v1 Modern AI technologies enable autonomous vehicles to perceive complex scenes, predict human behavior, and make real-time driving decisions. However, these data-driven components often operate as black boxes, lacking interpretability and rigorous safety guarantees. Autonomous vehicles operate in dynamic, mixed-traffic environments where interactions with human-driven vehicles introduce uncertainty and safety challenges. This work develops a formally verified safety framework for Connected and Autonomous Vehicles (CAVs) that integrates Barrier Certificates (BCs) with interpretable traffic conflict metrics, specifically Time-to-Collision (TTC) as a spatio-temporal safety metric. Safety conditions are verified using Satisfiability Modulo Theories (SMT) solvers, and an adaptive control mechanism ensures vehicles comply with these constraints in real time. Evaluation on real-world highway datasets shows a significant reduction in unsafe interactions, with up to 40\% fewer events where TTC falls below a 3 seconds threshold, and complete elimination of conflicts in some lanes. This approach provides both interpretable and provable safety guarantees, demonstrating a practical and scalable strategy for safe autonomous driving. --- ### MLLM-VADStory: Domain Knowledge-Driven Multimodal LLMs for Video Ad Storyline Insights Authors: Jasmine Yang, Poppy Zhang, Shawndra Hill Published: 2026-01-08 Categories: cs.MM, cs.CV arXiv: https://arxiv.org/abs/2601.07850v1 We propose MLLM-VADStory, a novel domain knowledge-guided multimodal large language models (MLLM) framework to systematically quantify and generate insights for video ad storyline understanding at scale. The framework is centered on the core idea that ad narratives are structured by functional intent, with each scene unit performing a distinct communicative function, delivering product and brand-oriented information within seconds. MLLM-VADStory segments ads into functional units, classifies each unit's functionality using a novel advertising-specific functional role taxonomy, and then aggregates functional sequences across ads to recover data-driven storyline structures. Applying the framework to 50k social media video ads across four industry subverticals, we find that story-based creatives improve video retention, and we recommend top-performing story arcs to guide advertisers in creative design. Our framework demonstrates the value of using domain knowledge to guide MLLMs in generating scalable insights for video ad storylines, making it a versatile tool for understanding video creatives in general. --- ### SPINAL -- Scaling-law and Preference Integration in Neural Alignment Layers Authors: Arion Das, Partha Pratim Saha, Amit Dhanda, Vinija Jain, Aman Chadha, Amitava Das Published: 2026-01-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.06238v1 Direct Preference Optimization (DPO) is a principled, scalable alternative to RLHF for aligning large language models from pairwise preferences, but its internal geometric footprint remains undercharacterized, limiting audits, checkpoint comparisons, and failure prediction. We introduce SPINAL (Scaling-law and Preference Integration in Neural Alignment Layers), a diagnostic that measures how alignment reshapes representations across depth by tracing localized structural change layer by layer. Across model families, DPO produces a layerwise calibration effect concentrated in the final decoder blocks (often layers 21-30), where preference gradients most directly affect the next-token distribution. SPINAL encodes each checkpoint as a depth trace over (layer index, contraction score, transport score). The contraction score summarizes how quickly the tail of a layer's spectrum decays (how fast small modes vanish); higher values indicate stronger contraction into fewer effective directions. The transport score summarizes how much the token distribution shifts between adjacent layers using a bounded overlap measure; lower values indicate shorter, smoother steps through representation space. Aligned checkpoints show a late-layer ramp-up in contraction and a smooth reduction in transport, consistent with tightened and stabilized policy mass, while unaligned models trace higher-curvature, more entropic, and geometrically incoherent depth paths. Overall, alignment is geometrically localized: the final layers encode the dominant preference-induced corrections. SPINAL turns this localization into a practical audit signal, quantifying where alignment concentrates, how strongly it manifests, and when it begins to destabilize during training. --- ### CEEMDAN-Based Multiscale CNN for Wind Turbine Gearbox Fault Detection Authors: Nejad Alagha, Anis Salwa Mohd Khairuddin, Obada Al-Khatib, Abigail Copiaco Published: 2026-01-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.06217v1 Wind turbines play a critical role in the shift toward sustainable energy generation. Their operation relies on multiple interconnected components, and a failure in any of these can compromise the entire system's functionality. Detecting faults accurately is challenging due to the intricate, non-linear, and non-stationary nature of vibration signals, influenced by dynamic loading, environmental variations, and mechanical interactions. As such, effective signal processing techniques are essential for extracting meaningful features to enhance diagnostic accuracy. This study presents a hybrid approach for fault detection in wind turbine gearboxes, combining Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and a Multiscale Convolutional Neural Network (MSCNN). CEEMDAN is employed to decompose vibration signals into intrinsic mode functions, isolating critical features at different time-frequency scales. These are then input into the MSCNN, which performs deep hierarchical feature extraction and classification. The proposed method achieves an F1 Score of 98.95\%, evaluated on real-world datasets, and demonstrates superior performance in both detection accuracy and computational speed compared to existing approaches. This framework offers a balanced solution for reliable and efficient fault diagnosis in wind turbine systems. --- ### LLM Agents in Law: Taxonomy, Applications, and Challenges Authors: Shuang Liu, Ruijia Zhang, Ruoyun Ma, Yujia Deng, Lanyi Zhu, Jiayu Li, Zelong Li, Zhibin Shen, Mengnan Du Published: 2026-01-08 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.06216v1 Large language models (LLMs) have precipitated a dramatic improvement in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability. Recently, LLM agents have attracted significant attention as a solution to these challenges, utilizing advanced capabilities such as planning, memory, and tool usage to meet the rigorous standards of legal practice. In this paper, we present a comprehensive survey of LLM agents for legal tasks, analyzing how these architectures bridge the gap between technical capabilities and domain-specific needs. Our major contributions include: (1) systematically analyzing the technical transition from standard legal LLMs to legal agents; (2) presenting a structured taxonomy of current agent applications across distinct legal practice areas; (3) discussing evaluation methodologies specifically for agentic performance in law; and (4) identifying open challenges and outlining future directions for developing robust and autonomous legal assistants. --- ### Dynamics-inspired Structure Hallucination for Protein-protein Interaction Modeling Authors: Fang Wu, Stan Z. Li Published: 2026-01-08 Categories: cs.LG, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2601.06214v1 Protein-protein interaction (PPI) represents a central challenge within the biology field, and accurately predicting the consequences of mutations in this context is crucial for drug design and protein engineering. Deep learning (DL) has shown promise in forecasting the effects of such mutations, but is hindered by two primary constraints. First, the structures of mutant proteins are often elusive to acquire. Secondly, PPI takes place dynamically, which is rarely integrated into the DL architecture design. To address these obstacles, we present a novel framework named Refine-PPI with two key enhancements. First, we introduce a structure refinement module trained by a mask mutation modeling (MMM) task on available wild-type structures, which is then transferred to produce the inaccessible mutant structures. Second, we employ a new kind of geometric network, called the probability density cloud network (PDC-Net), to capture 3D dynamic variations and encode the atomic uncertainty associated with PPI. Comprehensive experiments on SKEMPI.v2 substantiate the superiority of Refine-PPI over all existing tools for predicting free energy change. These findings underscore the effectiveness of our hallucination strategy and the PDC module in addressing the absence of mutant protein structure and modeling geometric uncertainty. --- ### Cyber Threat Detection and Vulnerability Assessment System using Generative AI and Large Language Model Authors: Keerthi Kumar. M, Swarun Kumar Joginpelly, Sunil Khemka, Lakshmi. S R, Navin Chhibber Published: 2026-01-08 Categories: cs.CR, cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2601.06213v1 Background: Cyber-attacks have evolved rapidly in recent years, many individuals and business owners have been affected by cyber-attacks in various ways. Cyber-attacks include various threats such as ransomware, malware, phishing, and Denial of Service (DoS)-related attacks. Challenges: Traditional models such as Generative Artificial Intelligence (AI) and Security Bidirectional Encoder Representations from Transformers (BERT) were implemented to detect cyber threats. However, the existing Security BERT model has a limited contextual understanding of text data, which has less impact on detecting cyber-attacks. Proposed Methodology: To overcome the above-mentioned challenges, Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach (RoBERTa) model is proposed which consists of diverse words of vocabulary understanding. Initially, data are extracted from a Packet Capture (PCAP) file and encrypted using Fully Harmonic Encryption (FHE). Subsequently, a Byte-level and Byte Pair Encoding (BBPE) tokenizer was used to generate tokens and help maintain the vocabulary for the encrypted values. Then, these values are applied to the RoBERTa model of the transformer with extensive training. Finally, Softmax is used for the detection and classification of attacks. The proposed RoBERTa model achieved better results than the existing BERT model in terms of accuracy (0.99), recall (0.91), and precision (0.89) respectively. --- ### Akasha 2: Hamiltonian State Space Duality and Visual-Language Joint Embedding Predictive Architectur Authors: Yani Meziani Published: 2026-01-08 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.06212v2 We present Akasha 2, a state-of-the-art multimodal architecture that integrates Hamiltonian State Space Duality (H-SSD) with Visual-Language Joint Embedding Predictive Architecture (VL-JEPA). The system leverages the Mamba-3 Selective State Space Model (SSM) augmented by a Sparse Mixture of Hamiltonian Experts (SMoE-HE) that enforces latent physical conservation laws through symplectic integration. For visual synthesis, we introduce Hamiltonian Flow Matching (HFM) and persistent 3D Gaussian Splatting (3DGS), enabling ultra-low latency (<50ms) on mobile hardware. This work establishes a new paradigm in latent world models, achieving unprecedented spatiotemporal coherence through a holographic memory architecture. Our approach demonstrates that incorporating physics-inspired inductive biases into neural architectures yields significant improvements: state-of-the-art video prediction (FVD: 287), 4x faster visual synthesis than diffusion models, and 3-18x inference speedup over transformer baselines while maintaining energy conservation over extended horizons. --- ### When Imbalance Comes Twice: Active Learning under Simulated Class Imbalance and Label Shift in Binary Semantic Segmentation Authors: Julien Combes, Alexandre Derville, Jean-François Coeurjolly Published: 2026-01-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.06209v1 The aim of Active Learning is to select the most informative samples from an unlabelled set of data. This is useful in cases where the amount of data is large and labelling is expensive, such as in machine vision or medical imaging. Two particularities of machine vision are first, that most of the images produced are free of defects, and second, that the amount of images produced is so big that we cannot store all acquired images. This results, on the one hand, in a strong class imbalance in defect distribution and, on the other hand, in a potential label shift caused by limited storage. To understand how these two forms of imbalance affect active learning algorithms, we propose a simulation study based on two open-source datasets. We artificially create datasets for which we control the levels of class imbalance and label shift. Three standard active learning selection strategies are compared: random sampling, entropy-based selection, and core-set selection. We demonstrate that active learning strategies, and in particular the entropy-based and core-set selections, remain interesting and efficient even for highly imbalanced datasets. We also illustrate and measure the loss of efficiency that occurs in the situation a strong label shift. --- ### Towards Public Administration Research Based on Interpretable Machine Learning Authors: Zhanyu Liu, Yang Yu Published: 2026-01-08 Categories: cs.CY, cs.LG arXiv: https://arxiv.org/abs/2601.06205v1 Causal relationships play a pivotal role in research within the field of public administration. Ensuring reliable causal inference requires validating the predictability of these relationships, which is a crucial precondition. However, prediction has not garnered adequate attention within the realm of quantitative research in public administration and the broader social sciences. The advent of interpretable machine learning presents a significant opportunity to integrate prediction into quantitative research conducted in public administration. This article delves into the fundamental principles of interpretable machine learning while also examining its current applications in social science research. Building upon this foundation, the article further expounds upon the implementation process of interpretable machine learning, encompassing key aspects such as dataset construction, model training, model evaluation, and model interpretation. Lastly, the article explores the disciplinary value of interpretable machine learning within the field of public administration, highlighting its potential to enhance the generalization of inference, facilitate the selection of optimal explanations for phenomena, stimulate the construction of theoretical hypotheses, and provide a platform for the translation of knowledge. As a complement to traditional causal inference methods, interpretable machine learning ushers in a new era of credibility in quantitative research within the realm of public administration. --- ### Cascading multi-agent anomaly detection in surveillance systems via vision-language models and embedding-based classification Authors: Tayyab Rehman, Giovanni De Gasperis, Aly Shmahell Published: 2026-01-08 Categories: cs.CV, cs.MA arXiv: https://arxiv.org/abs/2601.06204v3 Intelligent anomaly detection in dynamic visual environments requires reconciling real-time performance with semantic interpretability. Conventional approaches address only fragments of this challenge. Reconstruction-based models capture low-level deviations without contextual reasoning, object detectors provide speed but limited semantics, and large vision-language systems deliver interpretability at prohibitive computational cost. This work introduces a cascading multi-agent framework that unifies these complementary paradigms into a coherent and interpretable architecture. Early modules perform reconstruction-gated filtering and object-level assessment, while higher-level reasoning agents are selectively invoked to interpret semantically ambiguous events. The system employs adaptive escalation thresholds and a publish-subscribe communication backbone, enabling asynchronous coordination and scalable deployment across heterogeneous hardware. Extensive evaluation on large-scale monitoring data demonstrates that the proposed cascade achieves a threefold reduction in latency compared to direct vision-language inference, while maintaining high perceptual fidelity (PSNR = 38.3 dB, SSIM = 0.965) and consistent semantic labeling. The framework advances beyond conventional detection pipelines by combining early-exit efficiency, adaptive multi-agent reasoning, and explainable anomaly attribution, establishing a reproducible and energy-efficient foundation for scalable intelligent visual monitoring. --- ### QwenStyle: Content-Preserving Style Transfer with Qwen-Image-Edit Authors: Shiwen Zhang, Haibin Huang, Chi Zhang, Xuelong Li Published: 2026-01-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.06202v1 Content-Preserving Style transfer, given content and style references, remains challenging for Diffusion Transformers (DiTs) due to its internal entangled content and style features. In this technical report, we propose the first content-preserving style transfer model trained on Qwen-Image-Edit, which activates Qwen-Image-Edit's strong content preservation and style customization capability. We collected and filtered high quality data of limited specific styles and synthesized triplets with thousands categories of style images in-the-wild. We introduce the Curriculum Continual Learning framework to train QwenStyle with such mixture of clean and noisy triplets, which enables QwenStyle to generalize to unseen styles without degradation of the precise content preservation capability. Our QwenStyle V1 achieves state-of-the-art performance in three core metrics: style similarity, content consistency, and aesthetic quality. --- ### RiskBridge: Turning CVEs into Business-Aligned Patch Priorities Authors: Yelena Mujibur Sheikh, Awez Akhtar Khatik, Luoxi Tang, Yuqiao Meng, Zhaohan Xi Published: 2026-01-08 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.06201v2 Enterprises are confronted with an unprecedented escalation in cybersecurity vulnerabilities, with thousands of new CVEs disclosed each month. Conventional prioritization frameworks such as CVSS offer static severity metrics that fail to account for exploit probability, compliance urgency, and operational impact, resulting in inefficient and delayed remediation. This paper introduces RiskBridge, an explainable and compliance-aware vulnerability management framework that integrates multi-source intelligence from CVSS v4, EPSS, and CISA KEV to produce dynamic, business -- aligned patch priorities. RiskBridge employs a probabilistic Zero-Day Exposure Simulation (ZDES) model to forecast near-term exploit likelihood, a Policy-as-Code Engine to translate regulatory mandates (e.g., PCI DSS, NIST SP 800-53) into automated SLA logic, and an ROI-driven Optimizer to maximize cumulative risk reduction per remediation effort. Experimental evaluations using live CVE datasets demonstrate an 88% reduction in residual risk, an 18-day improvement in SLA compliance, and a 35% increase in remediation efficiency compared to state-of-the-art commercial baselines. These findings validate RiskBridge as a practical and auditable decision-intelligence system that unifies probabilistic modeling, compliance reasoning, and optimization analytics. The framework represents a step toward automated, explainable, and business-centric vulnerability management in modern enterprise environments --- ### Leveraging Membership Inference Attacks for Privacy Measurement in Federated Learning for Remote Sensing Images Authors: Anh-Kiet Duong, Petra Gomez-Krämer, Hoàng-Ân Lê, Minh-Tan Pham Published: 2026-01-08 Categories: cs.CR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.06200v1 Federated Learning (FL) enables collaborative model training while keeping training data localized, allowing us to preserve privacy in various domains including remote sensing. However, recent studies show that FL models may still leak sensitive information through their outputs, motivating the need for rigorous privacy evaluation. In this paper, we leverage membership inference attacks (MIA) as a quantitative privacy measurement framework for FL applied to remote sensing image classification. We evaluate multiple black-box MIA techniques, including entropy-based attacks, modified entropy attacks, and the likelihood ratio attack, across different FL algorithms and communication strategies. Experiments conducted on two public scene classification datasets demonstrate that MIA effectively reveals privacy leakage not captured by accuracy alone. Our results show that communication-efficient FL strategies reduce MIA success rates while maintaining competitive performance. These findings confirm MIA as a practical metric and highlight the importance of integrating privacy measurement into FL system design for remote sensing applications. --- ### FastSLM: Hierarchical Temporal Abstraction for Efficient Long-Form Speech Adaptation Authors: Junseok Lee, Chang-Jae Chun Published: 2026-01-08 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2601.06199v5 Scaling Multimodal Large Language Models (MLLMs) to long-form speech is bottlenecked by the explosive growth of input tokens. Existing speech-language models project high-frame-rate acoustic features directly into the LLM input space, making long-context processing computationally prohibitive. Unlike images or videos, speech lacks spatial redundancy, making extreme token compression particularly challenging. To address this limitation, we propose FastSLM, a token-efficient architecture featuring the Hierarchical Temporal Abstractor (HTA), which progressively distills acoustic features across multiple temporal scales. HTA achieves an extreme compression rate of 1.67 tokens per second (97% reduction) while preserving essential linguistic information for downstream speech-language understanding. Experimental results demonstrate that FastSLM achieves competitive performance across diverse speech-language tasks while requiring substantially fewer speech tokens and FLOPs than existing speech-language models. The source code and model checkpoints are available at https://github.com/Lee-junseok1025/FastSLM. --- ### How Does India Cook Biryani? Authors: Shubham Goel, Farzana S, C V Rishi, Aditya Arun, C V Jawahar Published: 2026-01-08 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.06198v1 Biryani, one of India's most celebrated dishes, exhibits remarkable regional diversity in its preparation, ingredients, and presentation. With the growing availability of online cooking videos, there is unprecedented potential to study such culinary variations using computational tools systematically. However, existing video understanding methods fail to capture the fine-grained, multimodal, and culturally grounded differences in procedural cooking videos. This work presents the first large-scale, curated dataset of biryani preparation videos, comprising 120 high-quality YouTube recordings across 12 distinct regional styles. We propose a multi-stage framework leveraging recent advances in vision-language models (VLMs) to segment videos into fine-grained procedural units and align them with audio transcripts and canonical recipe text. Building on these aligned representations, we introduce a video comparison pipeline that automatically identifies and explains procedural differences between regional variants. We construct a comprehensive question-answer (QA) benchmark spanning multiple reasoning levels to evaluate procedural understanding in VLMs. Our approach employs multiple VLMs in complementary roles, incorporates human-in-the-loop verification for high-precision tasks, and benchmarks several state-of-the-art models under zero-shot and fine-tuned settings. The resulting dataset, comparison methodology, and QA benchmark provide a new testbed for evaluating VLMs on structured, multimodal reasoning tasks and open new directions for computational analysis of cultural heritage through cooking videos. We release all data, code, and the project website at https://farzanashaju.github.io/how-does-india-cook-biryani/. --- ### AI Safeguards, Generative AI and the Pandora Box: AI Safety Measures to Protect Businesses and Personal Reputation Authors: Prasanna Kumar Published: 2026-01-08 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2601.06197v1 Generative AI has unleashed the power of content generation and it has also unwittingly opened the pandora box of realistic deepfake causing a number of social hazards and harm to businesses and personal reputation. The investigation & ramification of Generative AI technology across industries, the resolution & hybridization detection techniques using neural networks allows flagging of the content. Good detection techniques & flagging allow AI safety - this is the main focus of this paper. The research provides a significant method for efficiently detecting dark side problems by imposing a Temporal Consistency Learning (TCL) technique. Through pretrained Temporal Convolutional Networks (TCNs) model training and performance comparison, this paper showcases that TCN models outperforms the other approaches and achieves significant accuracy for five dark side problems. Findings highlight how important it is to take proactive measures in identification to reduce any potential risks associated with generative artificial intelligence. --- ### Geometry-Aware Hallucination Detection in Large Language Models Authors: Bodla Krishna Vamshi, Rohan Bhatnagar, Haizhao Yang Published: 2026-01-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.06196v3 Large language models (LLMs) frequently generate factually incorrect or unsupported content, commonly referred to as hallucinations. Prior work has explored decoding strategies, retrieval augmentation, and supervised fine-tuning for hallucination detection, while recent studies show that in-context learning (ICL) can substantially influence factual reliability. However, existing ICL demonstration selection methods often rely on surface-level similarity heuristics and exhibit limited robustness across tasks and models. We propose GA-ICL, a geometry-aware demonstration sampling framework for selecting in-context demonstrations that leverages latent representations extracted from frozen LLMs. By jointly modeling local manifold structure and class-aware prototype geometry, GA-ICL selects demonstrations based on their proximity to learned prototypes rather than lexical or embedding similarity alone. Across factual verification (FEVER) and hallucination detection (HaluEval) benchmarks, GA-ICL outperforms standard ICL selection baselines in the majority of evaluated settings, with particularly strong gains on dialogue and summarization tasks. The method remains robust under temperature perturbations and model variation, indicating improved stability compared to heuristic retrieval strategies. While lexical retrieval can remain competitive in certain question-answering regimes at smaller model scales, our results demonstrate that geometry-aware prototype selection provides a reliable and training-light approach for hallucination detection without modifying LLM parameters. Extended evaluations on Phi-14B and Qwen3-32B confirm that GA-ICL scales effectively to larger models, outperforming all compared baselines including on QA tasks where smaller models show boundary-condition limitations, offering a principled direction for improved ICL demonstration selection. --- ### EntroLnn: Entropy-Guided Liquid Neural Networks for Operando Refinement of Battery Capacity Fade Trajectories Authors: Wei Li, Wei Zhang, Qingyu Yan Published: 2026-01-08 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.06195v1 Battery capacity degradation prediction has long been a central topic in battery health analytics, and most studies focus on state of health (SoH) estimation and end of life (EoL) prediction. This study extends the scope to online refinement of the entire capacity fade trajectory (CFT) through EntroLnn, a framework based on entropy-guided transformable liquid neural networks (LNNs). EntroLnn treats CFT refinement as an integrated process rather than two independent tasks for pointwise SoH and EoL. We introduce entropy-based features derived from online temperature fields, applied for the first time in battery analytics, and combine them with customized LNNs that model temporal battery dynamics effectively. The framework enhances both static and dynamic adaptability of LNNs and achieves robust and generalizable CFT refinement across different batteries and operating conditions. The approach provides a high fidelity battery health model with lightweight computation, achieving mean absolute errors of only 0.004577 for CFT and 18 cycles for EoL prediction. This work establishes a foundation for entropy-informed learning in battery analytics and enables self-adaptive, lightweight, and interpretable battery health prediction in practical battery management systems. --- ### Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias Authors: Adib Sakhawat, Tahsin Islam, Takia Farhin, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan Published: 2026-01-08 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.06194v2 As large language models (LLMs) are increasingly deployed, understanding how they express political positioning is important for evaluating alignment and downstream effects. We audit 26 contemporary LLMs using three political psychometric inventories (Political Compass, SapplyValues, 8Values) and a news bias labeling task. To test robustness, inventories are administered across multiple semantic prompt variants and analyzed with a two-way ANOVA separating model and prompt effects. Most models cluster in a similar ideological region, with 96.3% located in the Libertarian-Left quadrant of the Political Compass, and model identity explaining most variance across prompt variants ($η^2 > 0.90$). Cross-instrument comparisons suggest that the Political Compass social axis aligns more strongly with cultural progressivism than authority-related measures ($r=-0.64$). We observe differences between open-weight and closed-source models and asymmetric performance in detecting extreme political bias in downstream classification. Regression analysis finds that psychometric ideological positioning does not significantly predict classification errors, providing no evidence of a statistically significant relationship between conversational ideological identity and task-level behavior. These findings suggest that single-axis evaluations are insufficient and that multidimensional auditing frameworks are important to characterize alignment behavior in deployed LLMs. Our code and data are publicly available at https://github.com/sakhadib/PolAlignLLM. --- ### MLB: A Scenario-Driven Benchmark for Evaluating Large Language Models in Clinical Applications Authors: Qing He, Dongsheng Bi, Jianrong Lu, Minghui Yang, Zixiao Chen, Jiacheng Lu, Jing Chen, Nannan Du, Xiao Cu, Sijing Wu, Peng Xiang, Yinyin Hu et al. Published: 2026-01-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.06193v1 The proliferation of Large Language Models (LLMs) presents transformative potential for healthcare, yet practical deployment is hindered by the absence of frameworks that assess real-world clinical utility. Existing benchmarks test static knowledge, failing to capture the dynamic, application-oriented capabilities required in clinical practice. To bridge this gap, we introduce a Medical LLM Benchmark MLB, a comprehensive benchmark evaluating LLMs on both foundational knowledge and scenario-based reasoning. MLB is structured around five core dimensions: Medical Knowledge (MedKQA), Safety and Ethics (MedSE), Medical Record Understanding (MedRU), Smart Services (SmartServ), and Smart Healthcare (SmartCare). The benchmark integrates 22 datasets (17 newly curated) from diverse Chinese clinical sources, covering 64 clinical specialties. Its design features a rigorous curation pipeline involving 300 licensed physicians. Besides, we provide a scalable evaluation methodology, centered on a specialized judge model trained via Supervised Fine-Tuning (SFT) on expert annotations. Our comprehensive evaluation of 10 leading models reveals a critical translational gap: while the top-ranked model, Kimi-K2-Instruct (77.3% accuracy overall), excels in structured tasks like information extraction (87.8% accuracy in MedRU), performance plummets in patient-facing scenarios (61.3% in SmartServ). Moreover, the exceptional safety score (90.6% in MedSE) of the much smaller Baichuan-M2-32B highlights that targeted training is equally critical. Our specialized judge model, trained via SFT on a 19k expert-annotated medical dataset, achieves 92.1% accuracy, an F1-score of 94.37%, and a Cohen's Kappa of 81.3% for human-AI consistency, validating a reproducible and expert-aligned evaluation protocol. MLB thus provides a rigorous framework to guide the development of clinically viable LLMs. ---