# Research Papers — 2026-01 · bundle page 161 of 189

> Full-text markdown of papers #8001–8050 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/161
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/160.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/162.md)

### Deontic Knowledge Graphs for Privacy Compliance in Multimodal Disaster Data Sharing

Authors: Kelvin Uzoma Echenim, Karuna Pande Joshi
Published: 2026-01-07
Categories: cs.CR, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2601.03587v1

Disaster response requires sharing heterogeneous artifacts, from tabular assistance records to UAS imagery, under overlapping privacy mandates. Operational systems often reduce compliance to binary access control, which is brittle in time-critical workflows. We present a novel deontic knowledge graph-based framework that integrates a Disaster Management Knowledge Graph (DKG) with a Policy Knowledge Graph (PKG) derived from IoT-Reg and FEMA/DHS privacy drivers. Our release decision function supports three outcomes: Allow, Block, and Allow-with-Transform. The latter binds obligations to transforms and verifies post-transform compliance via provenance-linked derived artifacts; blocked requests are logged as semantic privacy incidents. Evaluation on a 5.1M-triple DKG with 316K images shows exact-match decision correctness, sub-second per-decision latency, and interactive query performance across both single-graph and federated workloads.

---

### Detecting AI-Generated Images via Distributional Deviations from Real Images

Authors: Yakun Niu, Yingjian Chen, Lei Zhang
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03586v1

The rapid advancement of generative models has significantly enhanced the quality of AI-generated images, raising concerns about misinformation and the erosion of public trust. Detecting AI-generated images has thus become a critical challenge, particularly in terms of generalizing to unseen generative models. Existing methods using frozen pre-trained CLIP models show promise in generalization but treat the image encoder as a basic feature extractor, failing to fully exploit its potential. In this paper, we perform an in-depth analysis of the frozen CLIP image encoder (CLIP-ViT), revealing that it effectively clusters real images in a high-level, abstract feature space. However, it does not truly possess the ability to distinguish between real and AI-generated images. Based on this analysis, we propose a Masking-based Pre-trained model Fine-Tuning (MPFT) strategy, which introduces a Texture-Aware Masking (TAM) mechanism to mask textured areas containing generative model-specific patterns during fine-tuning. This approach compels CLIP-ViT to attend to the "distributional deviations"from authentic images for AI-generated image detection, thereby achieving enhanced generalization performance. Extensive experiments on the GenImage and UniversalFakeDetect datasets demonstrate that our method, fine-tuned with only a minimal number of images, significantly outperforms existing approaches, achieving up to 98.2% and 94.6% average accuracy on the two datasets, respectively.

---

### Local Gradient Regulation Stabilizes Federated Learning under Client Heterogeneity

Authors: Ping Luo, Jiahuan Wang, Ziqing Wen, Tao Sun, Dongsheng Li
Published: 2026-01-07
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2601.03584v1

Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, yet its stability is fundamentally challenged by statistical heterogeneity in realistic deployments. Here, we show that client heterogeneity destabilizes FL primarily by distorting local gradient dynamics during client-side optimization, causing systematic drift that accumulates across communication rounds and impedes global convergence. This observation highlights local gradients as a key regulatory lever for stabilizing heterogeneous FL systems. Building on this insight, we develop a general client-side perspective that regulates local gradient contributions without incurring additional communication overhead. Inspired by swarm intelligence, we instantiate this perspective through Exploratory--Convergent Gradient Re-aggregation (ECGR), which balances well-aligned and misaligned gradient components to preserve informative updates while suppressing destabilizing effects. Theoretical analysis and extensive experiments, including evaluations on the LC25000 medical imaging dataset, demonstrate that regulating local gradient dynamics consistently stabilizes federated learning across state-of-the-art methods under heterogeneous data distributions.

---

### SpatiaLoc: Leveraging Multi-Level Spatial Enhanced Descriptors for Cross-Modal Localization

Authors: Tianyi Shang, Pengjie Xu, Zhaojun Deng, Zhenyu Li, Zhicong Chen, Lijun Wu
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03579v1

Cross-modal localization using text and point clouds enables robots to localize themselves via natural language descriptions, with applications in autonomous navigation and interaction between humans and robots. In this task, objects often recur across text and point clouds, making spatial relationships the most discriminative cues for localization. Given this characteristic, we present SpatiaLoc, a framework utilizing a coarse-to-fine strategy that emphasizes spatial relationships at both the instance and global levels. In the coarse stage, we introduce a Bezier Enhanced Object Spatial Encoder (BEOSE) that models spatial relationships at the instance level using quadratic Bezier curves. Additionally, a Frequency Aware Encoder (FAE) generates spatial representations in the frequency domain at the global level. In the fine stage, an Uncertainty Aware Gaussian Fine Localizer (UGFL) regresses 2D positions by modeling predictions as Gaussian distributions with a loss function aware of uncertainty. Extensive experiments on KITTI360Pose demonstrate that SpatiaLoc significantly outperforms existing state-of-the-art (SOTA) methods.

---

### PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics

Authors: Yaling Shen, Stephanie Fong, Yiwen Jiang, Zimu Wang, Feilong Tang, Qingyang Xu, Xiangyu Zhao, Zhongxing Xu, Jiahe Liu, Jinpeng Hu, Dominic Dwyer, Zongyuan Ge
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03578v1

The increasing integration of large language models (LLMs) into mental health applications necessitates robust frameworks for evaluating professional safety alignment. Current evaluative approaches primarily rely on refusal-based safety signals, which offer limited insight into the nuanced behaviors required in clinical practice. In mental health, clinically inadequate refusals can be perceived as unempathetic and discourage help-seeking. To address this gap, we move beyond refusal-centric metrics and introduce \texttt{PsychEthicsBench}, the first principle-grounded benchmark based on Australian psychology and psychiatry guidelines, designed to evaluate LLMs' ethical knowledge and behavioral responses through multiple-choice and open-ended tasks with fine-grained ethicality annotations. Empirical results across 14 models reveal that refusal rates are poor indicators of ethical behavior, revealing a significant divergence between safety triggers and clinical appropriateness. Notably, we find that domain-specific fine-tuning can degrade ethical robustness, as several specialized models underperform their base backbones in ethical alignment. PsychEthicsBench provides a foundation for systematic, jurisdiction-aware evaluation of LLMs in mental health, encouraging more responsible development in this domain.

---

### Variational Inference, Entropy, and Orthogonality: A Unified Theory of Mixture-of-Experts

Authors: Ye Su, Yong Liu
Published: 2026-01-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.03577v1

Mixture-of-Experts models enable large language models to scale efficiently, as they only activate a subset of experts for each input. Their core mechanisms, Top-k routing and auxiliary load balancing, remain heuristic, however, lacking a cohesive theoretical underpinning to support them. To this end, we build the first unified theoretical framework that rigorously derives these practices as optimal sparse posterior approximation and prior regularization from a Bayesian perspective, while simultaneously framing them as mechanisms to minimize routing ambiguity and maximize channel capacity from an information-theoretic perspective. We also pinpoint the inherent combinatorial hardness of routing, defining it as the NP-hard sparse subset selection problem. We rigorously prove the existence of a "Coherence Barrier"; when expert representations exhibit high mutual coherence, greedy routing strategies theoretically fail to recover the optimal expert subset. Importantly, we formally verify that imposing geometric orthogonality in the expert feature space is sufficient to narrow the divide between the NP-hard global optimum and polynomial-time greedy approximation. Our comparative analyses confirm orthogonality regularization as the optimal engineering relaxation for large-scale models. Our work offers essential theoretical support and technical assurance for a deeper understanding and novel designs of MoE.

---

### How Do Large Language Models Learn Concepts During Continual Pre-Training?

Authors: Barry Menglong Yao, Sha Li, Yunzhi Yao, Minqian Liu, Zaishuo Xia, Qifan Wang, Lifu Huang
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03570v2

Human beings primarily understand the world through concepts (e.g., dog), abstract mental representations that structure perception, reasoning, and learning. However, how large language models (LLMs) acquire, retain, and forget such concepts during continual pretraining remains poorly understood. In this work, we study how individual concepts are acquired and forgotten, as well as how multiple concepts interact through interference and synergy. We link these behavioral dynamics to LLMs' internal concept circuits, computational subgraphs associated with specific concepts, and incorporate graph metrics to characterize circuit topology. Our analysis reveals: (1) LLMs concept circuits provide a non-trivial, consistent signal of concept learning and forgetting; (2) concept circuits exhibit a stage-wise temporal pattern during continual pretraining, with an early increase followed by gradual decrease and stabilization; (3) concepts with larger learning gains tend to exhibit greater forgetting under subsequent training; (4) semantically similar concepts induce stronger interference than weakly related ones; (5) conceptual knowledge differs in their transferability, with some significantly facilitating the learning of others. Together, our findings provide a circuit-level view of concept learning dynamics and motivate concept-aware training strategies, such as Circuit-aware Experience Replay, which uses circuit topology to prioritize concepts vulnerable to forgetting.

---

### Local Intrinsic Dimensionality of Ground Motion Data for Early Detection of Catastrophic Slope Failure

Authors: Yuansan Liu, James Bailey, Antoinette Tordesillas
Published: 2026-01-07
Categories: cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2601.03569v3

Local Intrinsic Dimensionality (LID) has shown strong potential for anomaly detection in high-dimensional data, including landslide failure detection in granular media, where early and accurate identification of failure zones is crucial for effective geohazard mitigation. However, this task is still challenging due to the spatial correlations and temporal dynamics that are inherently present in surface displacement data. To address this gap, we propose a novel unsupervised framework called spatiotemporal LID (st-LID) that generalizes the LID for robust failure detection in landslide monitoring networks. Our approach introduces three key innovations: (1) Kinematic enhancement, incorporating velocity into the LID computation to capture instantaneous deformation rates and short-term temporal dynamics; (2) Bayesian spatial fusion, which aggregates LID values across spatial neighborhoods via Bayesian estimation, to embed spatial correlations and account for localized noise; and (3) Temporal modeling (t-LID), a new variant that characterizes long-term dynamics of displacement data, providing a robust temporal representation of displacement behavior. By unifying these components, st-LID identifies complex, multi-stage failure zones often overlooked by existing methods. Extensive experiments show that st-LID consistently outperforms state-of-the-art unsupervised baselines in detection precision and lead-time, providing a robust foundation for landslide early warning systems and targeted risk intervention to enhance community resilience and preparedness strategies.

---

### Provably Convergent Decentralized Optimization over Directed Graphs under Generalized Smoothness

Authors: Yanan Bo, Yongqiang Wang
Published: 2026-01-07
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2601.03566v1

Decentralized optimization has become a fundamental tool for large-scale learning systems; however, most existing methods rely on the classical Lipschitz smoothness assumption, which is often violated in problems with rapidly varying gradients. Motivated by this limitation, we study decentralized optimization under the generalized $(L_0, L_1)$-smoothness framework, in which the Hessian norm is allowed to grow linearly with the gradient norm, thereby accommodating rapidly varying gradients beyond classical Lipschitz smoothness. We integrate gradient-tracking techniques with gradient clipping and carefully design the clipping threshold to ensure accurate convergence over directed communication graphs under generalized smoothness. In contrast to existing distributed optimization results under generalized smoothness that require a bounded gradient dissimilarity assumption, our results remain valid even when the gradient dissimilarity is unbounded, making the proposed framework more applicable to realistic heterogeneous data environments. We validate our approach via numerical experiments on standard benchmark datasets, including LIBSVM and CIFAR-10, using regularized logistic regression and convolutional neural networks, demonstrating superior stability and faster convergence over existing methods.

---

### A Proposed Paradigm for Imputing Missing Multi-Sensor Data in the Healthcare Domain

Authors: Vaibhav Gupta, Florian Grensing, Beyza Cinar, Maria Maleshkova
Published: 2026-01-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.03565v1

Chronic diseases such as diabetes pose significant management challenges, particularly due to the risk of complications like hypoglycemia, which require timely detection and intervention. Continuous health monitoring through wearable sensors offers a promising solution for early prediction of glycemic events. However, effective use of multisensor data is hindered by issues such as signal noise and frequent missing values. This study examines the limitations of existing datasets and emphasizes the temporal characteristics of key features relevant to hypoglycemia prediction. A comprehensive analysis of imputation techniques is conducted, focusing on those employed in state-of-the-art studies. Furthermore, imputation methods derived from machine learning and deep learning applications in other healthcare contexts are evaluated for their potential to address longer gaps in time-series data. Based on this analysis, a systematic paradigm is proposed, wherein imputation strategies are tailored to the nature of specific features and the duration of missing intervals. The review concludes by emphasizing the importance of investigating the temporal dynamics of individual features and the implementation of multiple, feature-specific imputation techniques to effectively address heterogeneous temporal patterns inherent in the data.

---

### Neural Operators for Biomedical Spherical Heterogeneity

Authors: Hao Tang, Hao Chen, Hao Li, Chao Li
Published: 2026-01-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.03561v3

Spherical deep learning has been widely applied to a broad range of real-world problems. Existing approaches often face challenges in balancing strong spherical geometric inductive biases with the need to model real-world heterogeneity. To solve this while retaining spherical geometry, we first introduce a designable Green's function framework (DGF) to provide new spherical operator solution strategy: Design systematic Green's functions under rotational group. Based on DGF, to model biomedical heterogeneity, we propose Green's-Function Spherical Neural Operator (GSNO) fusing 3 operator solutions: (1) Equivariant Solution derived from Equivariant Green's Function for symmetry-consistent modeling; (2) Invariant Solution derived from Invariant Green's Function to eliminate nuisance heterogeneity, e.g., consistent background field; (3) Anisotropic Solution derived from Anisotropic Green's Function to model anisotropic systems, especially fibers with preferred direction. Therefore, the resulting model, GSNO can adapt to real-world heterogeneous systems with nuisance variability and anisotropy while retaining spectral efficiency. Evaluations on spherical MNIST, Shallow Water Equation, diffusion MRI fiber prediction, cortical parcellation and molecule structure modeling demonstrate the superiority of GSNO.

---

### DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs

Authors: Shidong Cao, Hongzhan Lin, Yuxuan Gu, Ziyang Luo, Jing Ma
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03559v2

Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but remains vulnerable to exposure bias and error accumulation, as early mistakes propagate irreversibly through autoregressive decoding. In this work, we propose DiffCoT, a diffusion-styled CoT framework that reformulates CoT reasoning as an iterative denoising process. DiffCoT integrates diffusion principles at the reasoning-step level via a sliding-window mechanism, enabling unified generation and retrospective correction of intermediate steps while preserving token-level autoregression. To maintain causal consistency, we further introduce a causal diffusion noise schedule that respects the temporal structure of reasoning chains. Extensive experiments on three multi-step CoT reasoning benchmarks across diverse model backbones demonstrate that DiffCoT consistently outperforms existing CoT preference optimization methods, yielding improved robustness and error-correction capability in CoT reasoning.

---

### SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models

Authors: Yuxuan Jiang, Francis Ferraro
Published: 2026-01-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.03555v3

Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning. While process-level reward models offer a promising direction, existing LLM-based judges often produce noisy and inconsistent signals because they lack fine-grained, task-specific rubrics to distinguish high-level planning from low-level execution. In this work, we introduce SCRIBE (Skill-Conditioned Reward with Intermediate Behavioral Evaluation), a reinforcement learning framework that intervenes at a novel mid-level abstraction. SCRIBE grounds reward modeling in a curated library of skill prototypes, transforming open-ended LLM evaluation into a constrained verification problem. By routing each subgoal to a corresponding prototype, the reward model is equipped with precise, structured rubrics that substantially reduce reward variance. Experimental results show that SCRIBE achieves state-of-the-art performance across a range of reasoning and tool-use benchmarks. In particular, it improves the AIME25 accuracy of a Qwen3-4B model from 43.3% to 63.3%, and significantly increases success rates in complex multi-turn tool interactions. Further analysis of training dynamics reveals a co-evolution across abstraction levels, where mastery of mid-level skills consistently precedes the emergence of effective high-level planning behaviors. Finally, we demonstrate that SCRIBE is additive to low-level tool optimizations, providing a scalable and complementary pathway toward more autonomous and reliable tool-using agents.

---

### Evaluating LLMs for Police Decision-Making: A Framework Based on Police Action Scenarios

Authors: Sangyub Lee, Heedou Kim, Hyeoncheol Kim
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03553v1

The use of Large Language Models (LLMs) in police operations is growing, yet an evaluation framework tailored to police operations remains absent. While LLM's responses may not always be legally incorrect, their unverified use still can lead to severe issues such as unlawful arrests and improper evidence collection. To address this, we propose PAS (Police Action Scenarios), a systematic framework covering the entire evaluation process. Applying this framework, we constructed a novel QA dataset from over 8,000 official documents and established key metrics validated through statistical analysis with police expert judgements. Experimental results show that commercial LLMs struggle with our new police-related tasks, particularly in providing fact-based recommendations. This study highlights the necessity of an expandable evaluation framework to ensure reliable AI-driven police operations. We release our data and prompt template.

---

### ReEfBench: Quantifying the Reasoning Efficiency of LLMs

Authors: Zhizhang Fu, Yuancheng Gu, Chenkai Hu, Hanmeng Liu, Yue Zhang
Published: 2026-01-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.03550v1

Test-time scaling has enabled Large Language Models (LLMs) to tackle complex reasoning, yet the limitations of current Chain-of-Thought (CoT) evaluation obscures whether performance gains stem from genuine reasoning or mere verbosity. To address this, (1) we propose a novel neuro-symbolic framework for the non-intrusive, comprehensive process-centric evaluation of reasoning. (2) Through this lens, we identify four distinct behavioral prototypes and diagnose the failure modes. (3) We examine the impact of inference mode, training strategy, and model scale. Our analysis reveals that extended token generation is not a prerequisite for deep reasoning. Furthermore, we reveal critical constraints: mixing long and short CoT data in training risks in premature saturation and collapse, while distillation into smaller models captures behavioral length but fails to replicate logical efficacy due to intrinsic capacity limits.

---

### FEA-SLT: A Gloss-Free End-to-End Framework for Facial-Expression-Aware Sign Language Translation

Authors: Guobin Tu, Di Weng
Published: 2026-01-07
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2601.03549v3

Sign Language Translation (SLT) is a challenging cross-modal task requiring joint modeling of manual articulations and non-manual signals. Existing gloss-free SLT methods effectively capture gestural dynamics but often underutilize facial expressions, which play crucial grammatical and disambiguating roles. This limitation can cause semantic degradation when distinct concepts share similar manual configurations. To address this issue, we propose FEA-SLT (**F**acial-**E**xpression-**A**ware **S**ign **L**anguage **T**ranslation), a gloss-free end-to-end framework that uses facial dynamics to provide complementary cues to manual signals. FEA-SLT employs a domain-transferred facial encoder to extract expression-sensitive representations and integrates them with manual features through a linguistically motivated *Facial-Expression-Aware Fusion* (FEAF) module. FEAF captures reciprocal dependencies between manual and facial channels via bidirectional modulation, enhancing syntactic fidelity. Experiments on PHOENIX14T and CSL-Daily show that FEA-SLT achieves state-of-the-art BLEU performance among gloss-free methods, while targeted analyses support improved translation of facial-sensitive utterances. Code is available at https://github.com/TuGuobin/FEA-SLT.

---

### Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict

Authors: Guanyu Chen, Chenxiao Yu, Xiyang Hu
Published: 2026-01-07
Categories: cs.CL, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2601.03546v2

Large language models (LLMs) are increasingly used to simulate decision-making tasks involving personal data sharing, where privacy concerns and prosocial motivations can push choices in opposite directions. Existing evaluations often measure privacy-related attitudes or sharing intentions in isolation, which makes it difficult to determine whether a model's expressed values jointly predict its downstream data-sharing actions as in real human behaviors. We introduce a context-based assessment protocol that sequentially administers standardized questionnaires for privacy attitudes, prosocialness, and acceptance of data sharing within a bounded, history-carrying session. To evaluate value-action alignments under competing attitudes, we use multi-group structural equation modeling (MGSEM) to identify relations from privacy concerns and prosocialness to data sharing. We propose Value-Action Alignment Rate (VAAR), a human-referenced directional agreement metric that aggregates path-level evidence for expected signs. Across multiple LLMs, we observe stable but model-specific Privacy-PSA-AoDS profiles, and substantial heterogeneity in value-action alignment.

---

### EvolMem: A Cognitive-Driven Benchmark for Multi-Session Dialogue Memory

Authors: Ye Shen, Dun Pei, Yiqiu Guo, Junying Wang, Yijin Guo, Zicheng Zhang, Qi Jia, Jun Zhou, Guangtao Zhai
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03543v1

Despite recent advances in understanding and leveraging long-range conversational memory, existing benchmarks still lack systematic evaluation of large language models(LLMs) across diverse memory dimensions, particularly in multi-session settings. In this work, we propose EvolMem, a new benchmark for assessing multi-session memory capabilities of LLMs and agent systems. EvolMem is grounded in cognitive psychology and encompasses both declarative and non-declarative memory, further decomposed into multiple fine-grained abilities. To construct the benchmark, we introduce a hybrid data synthesis framework that consists of topic-initiated generation and narrative-inspired transformations. This framework enables scalable generation of multi-session conversations with controllable complexity, accompanied by sample-specific evaluation guidelines. Extensive evaluation reveals that no LLM consistently outperforms others across all memory dimensions. Moreover, agent memory mechanisms do not necessarily enhance LLMs' capabilities and often exhibit notable efficiency limitations. Data and code will be released at https://github.com/shenye7436/EvolMem.

---

### Layer-Order Inversion: Rethinking Latent Multi-Hop Reasoning in Large Language Models

Authors: Xukai Liu, Ye Liu, Jipeng Zhang, Yanghai Zhang, Kai Zhang, Qi Liu
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03542v2

Large language models (LLMs) perform well on multi-hop reasoning, yet how they internally compose multiple facts remains unclear. Recent work proposes \emph{hop-aligned circuit hypothesis}, suggesting that bridge entities are computed sequentially across layers before later-hop answers. Through systematic analyses on real-world multi-hop queries, we show that this hop-aligned assumption does not generalize: later-hop answer entities can become decodable earlier than bridge entities, a phenomenon we call \emph{layer-order inversion}, which strengthens with total hops. To explain this behavior, we propose a \emph{probabilistic recall-and-extract} framework that models multi-hop reasoning as broad probabilistic recall in shallow MLP layers followed by selective extraction in deeper attention layers. This framework is empirically validated through systematic probing analyses, reinterpreting prior layer-wise decoding evidence, explaining chain-of-thought gains, and providing a mechanistic diagnosis of multi-hop failures despite correct single-hop knowledge. Code is available at https://github.com/laquabe/Layer-Order-Inversion.

---

### DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing

Authors: Hongzhi Zhang, Yuanze Hu, Tinghai Zhang, Jia Fu, Tao Wang, Junwei Jing, Zhaoxin Fan, Qi Wang, Ruiming Tang, Han Li, Guorui Zhou, Kun Gai
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03540v1

The evolution of Large Language Models (LLMs) towards autonomous agents has catalyzed progress in Deep Research. While retrieval capabilities are well-benchmarked, the post-retrieval synthesis stage--where agents must digest massive amounts of context and consolidate fragmented evidence into coherent, long-form reports--remains under-evaluated due to the subjectivity of open-ended writing. To bridge this gap, we introduce DeepSynth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities. We leverage high-quality survey papers as gold standards, reverse-engineering research requests and constructing "Oracle Contexts" from their bibliographies to isolate synthesis from retrieval noise. We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization), transforming subjective judgment into verifiable metrics. Experiments across 96 tasks reveal that synthesizing information from hundreds of references remains a significant challenge. Our results demonstrate that agentic plan-and-write workflows significantly outperform single-turn generation, effectively reducing hallucinations and improving adherence to complex structural constraints.

---

### STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules

Authors: Di Wu, Yanyan Zhao, Xin Lu, Mingzhe Li, Bing Qin
Published: 2026-01-07
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.03537v1

Defending against jailbreak attacks is crucial for the safe deployment of Large Language Models (LLMs). Recent research has attempted to improve safety by training models to reason over safety rules before responding. However, a key issue lies in determining what form of safety reasoning effectively defends against jailbreak attacks, which is difficult to explicitly design or directly obtain. To address this, we propose \textbf{STAR-S} (\textbf{S}elf-\textbf{TA}ught \textbf{R}easoning based on \textbf{S}afety rules), a framework that integrates the learning of safety rule reasoning into a self-taught loop. The core of STAR-S involves eliciting reasoning and reflection guided by safety rules, then leveraging fine-tuning to enhance safety reasoning. Repeating this process creates a synergistic cycle. Improvements in the model's reasoning and interpretation of safety rules allow it to produce better reasoning data under safety rule prompts, which is then utilized for further training. Experiments show that STAR-S effectively defends against jailbreak attacks, outperforming baselines. Code is available at: https://github.com/pikepokenew/STAR_S.git.

---

### Persona-aware and Explainable Bikeability Assessment: A Vision-Language Model Approach

Authors: Yilong Dai, Ziyi Wang, Chenguang Wang, Kexin Zhou, Yiheng Qian, Susu Xu, Xiang Yan
Published: 2026-01-07
Categories: cs.CL, cs.CV, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2601.03534v1

Bikeability assessment is essential for advancing sustainable urban transportation and creating cyclist-friendly cities, and it requires incorporating users' perceptions of safety and comfort. Yet existing perception-based bikeability assessment approaches face key limitations in capturing the complexity of road environments and adequately accounting for heterogeneity in subjective user perceptions. This paper proposes a persona-aware Vision-Language Model framework for bikeability assessment with three novel contributions: (i) theory-grounded persona conditioning based on established cyclist typology that generates persona-specific explanations via chain-of-thought reasoning; (ii) multi-granularity supervised fine-tuning that combines scarce expert-annotated reasoning with abundant user ratings for joint prediction and explainable assessment; and (iii) AI-enabled data augmentation that creates controlled paired data to isolate infrastructure variable impacts. To test and validate this framework, we developed a panoramic image-based crowdsourcing system and collected 12,400 persona-conditioned assessments from 427 cyclists. Experiment results show that the proposed framework offers competitive bikeability rating prediction while uniquely enabling explainable factor attribution.

---

### Online Learning with Limited Information in the Sliding Window Model

Authors: Vladimir Braverman, Sumegha Garg, Chen Wang, David P. Woodruff, Samson Zhou
Published: 2026-01-07
Categories: stat.ML, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2601.03533v1

Motivated by recent work on the experts problem in the streaming model, we consider the experts problem in the sliding window model. The sliding window model is a well-studied model that captures applications such as traffic monitoring, epidemic tracking, and automated trading, where recent information is more valuable than older data. Formally, we have $n$ experts, $T$ days, the ability to query the predictions of $q$ experts on each day, a limited amount of memory, and should achieve the (near-)optimal regret $\sqrt{nW}\text{polylog}(nT)$ regret over any window of the last $W$ days. While it is impossible to achieve such regret with $1$ query, we show that with $2$ queries we can achieve such regret and with only $\text{polylog}(nT)$ bits of memory. Not only are our algorithms optimal for sliding windows, but we also show for every interval $\mathcal{I}$ of days that we achieve $\sqrt{n|\mathcal{I}|}\text{polylog}(nT)$ regret with $2$ queries and only $\text{polylog}(nT)$ bits of memory, providing an exponential improvement on the memory of previous interval regret algorithms. Building upon these techniques, we address the bandit problem in data streams, where $q=1$, achieving $n T^{2/3}\text{polylog}(T)$ regret with $\text{polylog}(nT)$ memory, which is the first sublinear regret in the streaming model in the bandit setting with polylogarithmic memory; this can be further improved to the optimal $\mathcal{O}(\sqrt{nT})$ regret if the best expert's losses are in a random order.

---

### PALM-Bench: A Comprehensive Benchmark for Personalized Audio-Language Models

Authors: Yuwen Wang, Xinyuan Qian, Tian-Hao Zhang, Jiaran Gao, Yuchen Pan, Xin Wang, Zhou Pan, Chen Wei, Yiming Wang
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03531v1

Large Audio-Language Models (LALMs) have demonstrated strong performance in audio understanding and generation. Yet, our extensive benchmarking reveals that their behavior is largely generic (e.g., summarizing spoken content) and fails to adequately support personalized question answering (e.g., summarizing what my best friend says). In contrast, human conditions their interpretation and decision-making on each individual's personal context. To bridge this gap, we formalize the task of Personalized LALMs (PALM) for recognizing personal concepts and reasoning within personal context. Moreover, we create the first benchmark (PALM-Bench) to foster the methodological advances in PALM and enable structured evaluation on several tasks across multi-speaker scenarios. Our extensive experiments on representative open-source LALMs, show that existing training-free prompting and supervised fine-tuning strategies, while yield improvements, remains limited in modeling personalized knowledge and transferring them across tasks robustly. Data and code will be released.

---

### CloudMatch: Weak-to-Strong Consistency Learning for Semi-Supervised Cloud Detection

Authors: Jiayi Zhao, Changlu Chen, Jingsheng Li, Tianxiang Xue, Kun Zhan
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03528v1

Due to the high cost of annotating accurate pixel-level labels, semi-supervised learning has emerged as a promising approach for cloud detection. In this paper, we propose CloudMatch, a semi-supervised framework that effectively leverages unlabeled remote sensing imagery through view-consistency learning combined with scene-mixing augmentations. An observation behind CloudMatch is that cloud patterns exhibit structural diversity and contextual variability across different scenes and within the same scene category. Our key insight is that enforcing prediction consistency across diversely augmented views, incorporating both inter-scene and intra-scene mixing, enables the model to capture the structural diversity and contextual richness of cloud patterns. Specifically, CloudMatch generates one weakly augmented view along with two complementary strongly augmented views for each unlabeled image: one integrates inter-scene patches to simulate contextual variety, while the other employs intra-scene mixing to preserve semantic coherence. This approach guides pseudolabel generation and enhances generalization. Extensive experiments show that CloudMatch achieves good performance, demonstrating its capability to utilize unlabeled data efficiently and advance semi-supervised cloud detection.

---

### Physics-Constrained Cross-Resolution Enhancement Network for Optics-Guided Thermal UAV Image Super-Resolution

Authors: Zhicheng Zhao, Fengjiao Peng, Jinquan Yan, Wei Lu, Chenglong Li, Jin Tang
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03526v1

Optics-guided thermal UAV image super-resolution has attracted significant research interest due to its potential in all-weather monitoring applications. However, existing methods typically compress optical features to match thermal feature dimensions for cross-modal alignment and fusion, which not only causes the loss of high-frequency information that is beneficial for thermal super-resolution, but also introduces physically inconsistent artifacts such as texture distortions and edge blurring by overlooking differences in the imaging physics between modalities. To address these challenges, we propose PCNet to achieve cross-resolution mutual enhancement between optical and thermal modalities, while physically constraining the optical guidance process via thermal conduction to enable robust thermal UAV image super-resolution. In particular, we design a Cross-Resolution Mutual Enhancement Module (CRME) to jointly optimize thermal image super-resolution and optical-to-thermal modality conversion, facilitating effective bidirectional feature interaction across resolutions while preserving high-frequency optical priors. Moreover, we propose a Physics-Driven Thermal Conduction Module (PDTM) that incorporates two-dimensional heat conduction into optical guidance, modeling spatially-varying heat conduction properties to prevent inconsistent artifacts. In addition, we introduce a temperature consistency loss that enforces regional distribution consistency and boundary gradient smoothness to ensure generated thermal images align with real-world thermal radiation principles. Extensive experiments on VGTSR2.0 and DroneVehicle datasets demonstrate that PCNet significantly outperforms state-of-the-art methods on both reconstruction quality and downstream tasks including semantic segmentation and object detection.

---

### Beyond Binary: Turning Partial Success into Dense Verifiable Rewards for Reinforcement Learning in Code Generation

Authors: Longwen Wang, Yirui Liu, Xuan'er Wu, Xiaohui Hu, Yuankai Fan, Kaidong Yu, Qizhen Weng, Wei Xi, Xuelong Li
Published: 2026-01-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.03525v3

Effective reward design is a central challenge in Reinforcement Learning (RL) for code generation. Mainstream test-suite-level outcome rewards enforce functional correctness but induce sparsity, while external Reward Models (RMs) provide dense supervision at the cost of misalignment and additional overhead. Since code evaluation naturally yields multiple test-case-level outcomes, partial success, i.e., passing a subset of test cases, offers an intrinsic, verifiable source of dense supervision. In this paper, we propose VeRPO (Verifiable Dense Reward Policy Optimization), an RL framework that systematically turns verifiable partial success into reliable dense rewards. We analyze partial-success rewards using a weighted sum formulation, theoretically identifying a critical cardinality bias that causes policy updates to disproportionately favor gains from easy-test successes over progress on frontier tests. Based on this, VeRPO introduces a dynamic, density-calibrated local reward that explicitly corrects this bias and provides robust dense supervision from partial success. To enhance alignment with end-to-end functional correctness, VeRPO further integrates the local dense reward with global execution outcomes. Extensive experiments across diverse benchmarks and settings demonstrate that VeRPO outperforms outcome-driven and RM-based baselines, achieving up to +8.83 pass@1 gain with negligible time cost (< 0.02%) and zero GPU memory overhead.

---

### Variance Computation for Weighted Model Counting with Knowledge Compilation Approach

Authors: Kengo Nakamura, Masaaki Nishino, Norihito Yasuda
Published: 2026-01-07
Categories: cs.AI, cs.DS
arXiv: https://arxiv.org/abs/2601.03523v2

One of the most important queries in knowledge compilation is weighted model counting (WMC), which has been applied to probabilistic inference on various models, such as Bayesian networks. In practical situations on inference tasks, the model's parameters have uncertainty because they are often learned from data, and thus we want to compute the degree of uncertainty in the inference outcome. One possible approach is to regard the inference outcome as a random variable by introducing distributions for the parameters and evaluate the variance of the outcome. Unfortunately, the tractability of computing such a variance is hardly known. Motivated by this, we consider the problem of computing the variance of WMC and investigate this problem's tractability. First, we derive a polynomial time algorithm to evaluate the WMC variance when the input is given as a structured d-DNNF. Second, we prove the hardness of this problem for structured DNNFs, d-DNNFs, and FBDDs, which is intriguing because the latter two allow polynomial time WMC algorithms. Finally, we show an application that measures the uncertainty in the inference of Bayesian networks. We empirically show that our algorithm can evaluate the variance of the marginal probability on real-world Bayesian networks and analyze the impact of the variances of parameters on the variance of the marginal.

---

### A Reinforcement Learning-Based Model for Mapping and Goal-Directed Navigation Using Multiscale Place Fields

Authors: Bekarys Dukenbaev, Andrew Gerstenslager, Alexander Johnson, Ali A. Minai
Published: 2026-01-07
Categories: cs.NE, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2601.03520v1

Autonomous navigation in complex and partially observable environments remains a central challenge in robotics. Several bio-inspired models of mapping and navigation based on place cells in the mammalian hippocampus have been proposed. This paper introduces a new robust model that employs parallel layers of place fields at multiple spatial scales, a replay-based reward mechanism, and dynamic scale fusion. Simulations show that the model improves path efficiency and accelerates learning compared to single-scale baselines, highlighting the value of multiscale spatial representations for adaptive robot navigation.

---

### Semantic Belief-State World Model for 3D Human Motion Prediction

Authors: Sarim Chaudhry
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03517v1

Human motion prediction has traditionally been framed as a sequence regression problem where models extrapolate future joint coordinates from observed pose histories. While effective over short horizons this approach does not separate observation reconstruction with dynamics modeling and offers no explicit representation of the latent causes governing motion. As a result, existing methods exhibit compounding drift, mean-pose collapse, and poorly calibrated uncertainty when rolled forward beyond the training regime. Here we propose a Semantic Belief-State World Model (SBWM) that reframes human motion prediction as latent dynamical simulation on the human body manifold. Rather than predicting poses directly, SBWM maintains a recurrent probabilistic belief state whose evolution is learned independently of pose reconstruction and explicitly aligned with the SMPL-X anatomical parameterization. This alignment imposes a structural information bottleneck that prevents the latent state from encoding static geometry or sensor noise, forcing it to capture motion dynamics, intent, and control-relevant structure. Inspired by belief-state world models developed for model-based reinforcement learning, SBWM adapts stochastic latent transitions and rollout-centric training to the domain of human motion. In contrast to RSSM-based, transformer, and diffusion approaches optimized for reconstruction fidelity, SBWM prioritizes stable forward simulation. We demonstrate coherent long-horizon rollouts, and competitive accuracy at substantially lower computational cost. These results suggest that treating the human body as part of the world models state space rather than its output fundamentally changes how motion is simulated, and predicted.

---

### Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents

Authors: Yuanchen Bei, Tianxin Wei, Xuying Ning, Yanjun Zhao, Zhining Liu, Xiao Lin, Yada Zhu, Hendrik Hamann, Jingrui He, Hanghang Tong
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03515v1

Long-term memory is a critical capability for multimodal large language model (MLLM) agents, particularly in conversational settings where information accumulates and evolves over time. However, existing benchmarks either evaluate multi-session memory in text-only conversations or assess multimodal understanding within localized contexts, failing to evaluate how multimodal memory is preserved, organized, and evolved across long-term conversational trajectories. Thus, we introduce Mem-Gallery, a new benchmark for evaluating multimodal long-term conversational memory in MLLM agents. Mem-Gallery features high-quality multi-session conversations grounded in both visual and textual information, with long interaction horizons and rich multimodal dependencies. Building on this dataset, we propose a systematic evaluation framework that assesses key memory capabilities along three functional dimensions: memory extraction and test-time adaptation, memory reasoning, and memory knowledge management. Extensive benchmarking across thirteen memory systems reveals several key findings, highlighting the necessity of explicit multimodal information retention and memory organization, the persistent limitations in memory reasoning and knowledge management, as well as the efficiency bottleneck of current models.

---

### Deploy-Master: Automating the Deployment of 50,000+ Agent-Ready Scientific Tools in One Day

Authors: Yi Wang, Zhenting Huang, Zhaohan Ding, Ruoxue Liao, Yuan Huang, Xinzijian Liu, Jiajun Xie, Siheng Chen, Linfeng Zhang
Published: 2026-01-07
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.03513v1

Open-source scientific software is abundant, yet most tools remain difficult to compile, configure, and reuse, sustaining a small-workshop mode of scientific computing. This deployment bottleneck limits reproducibility, large-scale evaluation, and the practical integration of scientific tools into modern AI-for-Science (AI4S) and agentic workflows. We present Deploy-Master, a one-stop agentic workflow for large-scale tool discovery, build specification inference, execution-based validation, and publication. Guided by a taxonomy spanning 90+ scientific and engineering domains, our discovery stage starts from a recall-oriented pool of over 500,000 public repositories and progressively filters it to 52,550 executable tool candidates under license- and quality-aware criteria. Deploy-Master transforms heterogeneous open-source repositories into runnable, containerized capabilities grounded in execution rather than documentation claims. In a single day, we performed 52,550 build attempts and constructed reproducible runtime environments for 50,112 scientific tools. Each successful tool is validated by a minimal executable command and registered in SciencePedia for search and reuse, enabling direct human use and optional agent-based invocation. Beyond delivering runnable tools, we report a deployment trace at the scale of 50,000 tools, characterizing throughput, cost profiles, failure surfaces, and specification uncertainty that become visible only at scale. These results explain why scientific software remains difficult to operationalize and motivate shared, observable execution substrates as a foundation for scalable AI4S and agentic science.

---

### Bootstrapping Code Translation with Weighted Multilanguage Exploration

Authors: Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu
Published: 2026-01-07
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.03512v2

Code translation across multiple programming languages is essential yet challenging due to two vital obstacles: scarcity of parallel data paired with executable test oracles, and optimization imbalance when handling diverse language pairs. We propose BootTrans, a bootstrapping method that resolves both obstacles. Its key idea is to leverage the functional invariance and cross-lingual portability of test suites, adapting abundant pivot-language unit tests to serve as universal verification oracles for multilingual reinforcement learning (RL) training. Our method introduces a dual-pool architecture with seed and exploration pools to progressively expand training data via execution-guided experience collection. Furthermore, we design a language-aware weighting mechanism that dynamically prioritizes harder translation directions based on relative performance across sibling languages, mitigating optimization imbalance. Extensive experiments on the HumanEval-X and TransCoder-Test benchmarks demonstrate substantial improvements over baseline LLMs across all translation directions, with ablation studies validating the effectiveness of both bootstrapping and weighting components.

---

### IntroLM: Introspective Language Models via Prefilling-Time Self-Evaluation

Authors: Hossein Hosseini Kasnavieh, Gholamreza Haffari, Chris Leckie, Adel N. Toosi
Published: 2026-01-07
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.03511v2

A major challenge for the operation of large language models (LLMs) is how to predict whether a specific LLM will produce sufficiently high-quality output for a given query. Existing approaches rely on external classifiers, most commonly BERT based models, which suffer from limited context windows, constrained representational capacity, and additional computational overhead. We propose IntroLM, a method that enables causal language models to predict their own output quality during the prefilling phase without affecting generation using introspective tokens. By introducing token conditional LoRA that activates only for the introspective token, the model learns to predict the output quality for a given query while preserving the original backbone behavior and avoiding external evaluators. On question answering benchmarks, IntroLM applied to Qwen3 8B achieves a ROC AUC of 90 precent for success prediction, outperforming a DeBERTa classifier by 14 precent. When integrated into multi model routing systems, IntroLM achieves superior cost performance tradeoffs, reducing latency by up to 33 precent and large model usage by up to 50 precent at matched reliability.

---

### G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation

Authors: Hojun Song, Chae-yeong Song, Jeong-hun Hong, Chaewon Moon, Soo Ye Kim, Yiyi Liao, Jaehyup Lee, Sang-hyo Park
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03510v3

Point cloud segmentation is critical for 3D scene understanding. However, sparse and irregular point distributions provide limited appearance evidence, making geometry-only features insufficient to distinguish objects with similar shapes but distinct appearances e.g., color, texture, and material. We propose Gaussian-to-Point (G2P), which transfers Gaussian attributes from 3D Gaussian Splatting to point clouds for more discriminative and appearance-consistent segmentation. Our G2P addresses the misalignment between optimized Gaussians and original point geometry by establishing point-wise correspondences. By distilling opacity-derived visibility cues, we mitigate the geometric ambiguity that limits existing models. Additionally, Gaussian scale attributes enable precise boundary localization in complex 3D scenes. Extensive experiments demonstrate that our approach achieves competitive performance on standard benchmarks and shows notable improvements on geometrically challenging classes, without pretrained 2D features or language supervision in our segmentation pipeline.

---

### Evolving Programmatic Skill Networks

Authors: Haochen Shi, Xingdi Yuan, Bang Liu
Published: 2026-01-07
Categories: cs.AI, cs.NE
arXiv: https://arxiv.org/abs/2601.03509v2

We study continual skill acquisition in open-ended embodied environments where an agent must construct, refine, and reuse an expanding library of executable skills. We introduce the Programmatic Skill Network (PSN), a framework in which skills are executable symbolic programs forming a compositional network that evolves through experience. PSN defines three core mechanisms instantiated via large language models: (1)~\opreflect for structured fault localization over skill compositions, (2)~progressive optimization with maturity-aware update gating that stabilizes reliable skills while maintaining plasticity for uncertain ones, and (3)~canonical structural refactoring under rollback validation that maintains network compactness. We further show that PSN's learning dynamics exhibit structural parallels to neural network training. Experiments on MineDojo and Crafter demonstrate robust skill reuse, rapid adaptation, and strong generalization across open-ended task distributions.

---

### REFA: Real-time Egocentric Facial Animations for Virtual Reality

Authors: Qiang Zhang, Tong Xiao, Haroun Habeeb, Larissa Laich, Sofien Bouaziz, Patrick Snape, Wenjing Zhang, Matthew Cioffi, Peizhao Zhang, Pavel Pidlypenskyi, Winnie Lin, Luming Ma et al.
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03507v1

We present a novel system for real-time tracking of facial expressions using egocentric views captured from a set of infrared cameras embedded in a virtual reality (VR) headset. Our technology facilitates any user to accurately drive the facial expressions of virtual characters in a non-intrusive manner and without the need of a lengthy calibration step. At the core of our system is a distillation based approach to train a machine learning model on heterogeneous data and labels coming form multiple sources, \eg synthetic and real images. As part of our dataset, we collected 18k diverse subjects using a lightweight capture setup consisting of a mobile phone and a custom VR headset with extra cameras. To process this data, we developed a robust differentiable rendering pipeline enabling us to automatically extract facial expression labels. Our system opens up new avenues for communication and expression in virtual environments, with applications in video conferencing, gaming, entertainment, and remote collaboration.

---

### QA-Merging: Query-Adaptive Reasoning via Layer Selective Model Merging

Authors: Zhaofeng Zhong, Wei Yuan, Tong Chen, Liang Qu, Xiangyu Zhao, Quoc Viet Hung Nguyen, Hongzhi Yin
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03506v2

Recent large reasoning models (LRMs) have achieved strong performance on complex reasoning tasks by generating a long chain-of-thought (Long-CoT). However, such lengthy reasoning is often unnecessary for simple queries, leading to additional computation and latency. Existing approaches to adaptive reasoning typically rely on retraining the model or designing sophisticated prompting, which are either prohibitively expensive or highly sensitive to the prompt formulation. Model merging provides a more balanced alternative for adaptive reasoning by avoiding expensive training and integrating Long-CoT and Short-CoT behaviors. However, existing merging methods are often static and input-agnostic, or rely on costly all-layer calibration, which limits their effectiveness for query-adaptive reasoning. To tackle these challenges, we propose Query-adaptive Layer Selective Merging (QA-Merging), an activation-based merging framework that integrates a Long-CoT model and a Short-CoT model to obtain a query-adaptive reasoner without training from scratch or requiring large-scale additional data. QA-Merging first constructs a small pattern-labeled calibration set that assigns each query an appropriate reasoning pattern. Motivated by our empirical analysis that Long-CoT and Short-CoT behaviors diverge unevenly across transformer layers, QA-Merging identifies layers with high reasoning pattern divergence and calibrates only these layers through feature alignment and contrastive shaping, while applying closed-form hidden-state correction to the remaining layers. Experiments on seven widely used reasoning benchmarks across two model scales demonstrate that QA-Merging reduces inference cost and maintains strong performance.

---

### Beyond Perplexity: A Lightweight Benchmark for Knowledge Retention in Supervised Fine-Tuning

Authors: Soheil Zibakhsh Shabgahi, Pedram Aghazadeh, Farinaz Koushanfar
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03505v1

Supervised Fine-Tuning (SFT) is a standard approach for injecting domain knowledge into Large Language Models (LLMs). However, relying on validation perplexity to monitor training is often insufficient, as it confounds stylistic mimicry with genuine factual internalization. To address this, we introduce the Knowledge Retention (KR) Test , a lightweight, corpus-grounded evaluation framework designed to distinguish factual learning from linguistics. KR-Test utilizes automatically generated contrastive examples to measure likelihood preferences for correct versus incorrect continuations, requiring no instruction tuning or generative decoding. We validate the framework's integrity through a "blind vs. oracle" baseline analysis. Furthermore, we demonstrate the diagnostic capabilities of KR-Test by analyzing the training dynamics of Low-Rank Adaptation (LoRA). By exposing the fine-grained dissociation between linguistic convergence and knowledge retention, KR-Test enhances the interpretability of fine-tuning dynamics.

---

### SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models

Authors: Yuxuan Xia, Siheng Wang, Peng Li
Published: 2026-01-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.03500v1

Large Vision-Language Models (LVLMs) demonstrate significant progress in multimodal understanding and reasoning, yet object hallucination remains a critical challenge. While existing research focuses on mitigating language priors or high-level statistical biases, they often overlook the internal complexities of the visual encoding process. We identify that visual statistical bias, arising from the inherent Bag-of-Patches behavior of Vision Encoders under weak structural supervision, acts as a contributing factor of object hallucinations. Under this bias, models prioritize local texture features within individual patches over holistic geometric structures. This tendency may induce spurious visual confidence and result in hallucinations. To address this, we introduce a training-free algorithm called Structure-Disrupted Contrastive Decoding (SDCD), which performs contrastive calibration of the output distribution by introducing a shuffled structure-disrupted view. By penalizing tokens that maintain high confidence under this structure-less view, SDCD effectively suppresses the texture-driven bias. Experimental results demonstrate that SDCD significantly mitigates hallucinations across multiple benchmarks and enhances the overall multimodal capabilities of LVLMs.

---

### GeoDiff-SAR: A Geometric Prior Guided Diffusion Model for SAR Image Generation

Authors: Fan Zhang, Xuanting Wu, Fei Ma, Qiang Yin, Yuxin Hu
Published: 2026-01-07
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.03499v2

Synthetic aperture radar (SAR) image generation can mitigate data scarcity, but controllablegeneration under sparse observation angles remains difficult. Recent SAR generative studies im-prove texture realism, yet explicit geometry-aware control is still limited. This paper studiesthe focused and verifiable setting of intermediate-azimuth completion: 3D-model-derived geo-metric priors guide a diffusion model to synthesize the views missing from sparse-angle trainingdata. GeoDiff-SAR constructs a lightweight multi-bounce ray-tracing prior, encodes the result-ing point cloud, and fuses it with text conditioning while adapting Stable Diffusion 3.5 Mediumthrough low-rank adaptation. On a real four-category aircraft dataset, GeoDiff-SAR reaches anSSIM of 0.812 and azimuth consistency of 0.940, compared with 0.738 and 0.782 for the text-conditioned SD3.5 Medium baseline. The same sparse-angle protocol on five MSTAR vehicleclasses yields an SSIM of 0.878 and azimuth consistency of 0.917. These results support theconclusion that a lightweight 3D geometric prior improves viewpoint adherence for controllableSAR generation; it is intended as generation guidance rather than high-fidelity electromagneticreconstruction.

---

### A Quantifiable Information-Processing Hierarchy Provides a Necessary Condition for Detecting Agency

Authors: Brett J. Kagan, Valentina Baccetti, Brian D. Earp, J. Lomax Boyd, Julian Savulescu, Adeel Razi
Published: 2026-01-07
Categories: q-bio.NC, cs.IT, physics.data-an, stat.ML
arXiv: https://arxiv.org/abs/2601.03498v1

As intelligent systems are developed across diverse substrates - from machine learning models and neuromorphic hardware to in vitro neural cultures - understanding what gives a system agency has become increasingly important. Existing definitions, however, tend to rely on top-down descriptions that are difficult to quantify. We propose a bottom-up framework grounded in a system's information-processing order: the extent to which its transformation of input evolves over time. We identify three orders of information processing. Class I systems are reactive and memoryless, mapping inputs directly to outputs. Class II systems incorporate internal states that provide memory but follow fixed transformation rules. Class III systems are adaptive; their transformation rules themselves change as a function of prior activity. While not sufficient on their own, these dynamics represent necessary informational conditions for genuine agency. This hierarchy offers a measurable, substrate-independent way to identify the informational precursors of agency. We illustrate the framework with neurophysiological and computational examples, including thermostats and receptor-like memristors, and discuss its implications for the ethical and functional evaluation of systems that may exhibit agency.

---

### STELLA: Self-Reflective Terminology-Aware Framework for Building an Aerospace Information Retrieval Benchmark

Authors: Bongmin Kim
Published: 2026-01-07
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2601.03496v1

Tasks in the aerospace industry heavily rely on searching and reusing large volumes of technical documents, yet there is no public information retrieval (IR) benchmark that reflects the terminology- and query-intent characteristics of this domain. To address this gap, this paper proposes the STELLA (Self-Reflective TErminoLogy-Aware Framework for BuiLding an Aerospace Information Retrieval Benchmark) framework. Using this framework, we introduce the STELLA benchmark, an aerospace-specific IR evaluation set constructed from NASA Technical Reports Server (NTRS) documents via a systematic pipeline that comprises document layout detection, passage chunking, terminology dictionary construction, synthetic query generation, and cross-lingual extension. The framework generates two types of queries: the Terminology Concordant Query (TCQ), which includes the terminology verbatim to evaluate lexical matching, and the Terminology Agnostic Query (TAQ), which utilizes the terminology's description to assess semantic matching. This enables a disentangled evaluation of the lexical and semantic matching capabilities of embedding models. In addition, we combine Chain-of-Density (CoD) and the Self-Reflection method with query generation to improve quality and implement a hybrid cross-lingual extension that reflects real user querying practices. Evaluation of seven embedding models on the STELLA benchmark shows that large decoder-based embedding models exhibit the strongest semantic understanding, while lexical matching methods such as BM25 remain highly competitive in domains where exact lexical matching technical term is crucial. The STELLA benchmark provides a reproducible foundation for reliable performance evaluation and improvement of embedding models in aerospace-domain IR tasks. The STELLA benchmark can be found in https://huggingface.co/datasets/telepix/STELLA.

---

### Cyberattack Detection in Virtualized Microgrids Using LightGBM and Knowledge-Distilled Classifiers

Authors: Osasumwen Cedric Ogiesoba-Eguakun, Suman Rath
Published: 2026-01-07
Categories: eess.SY, cs.AI
arXiv: https://arxiv.org/abs/2601.03495v2

Modern microgrids depend on distributed sensing and communication interfaces, making them increasingly vulnerable to cyber physical disturbances that threaten operational continuity and equipment safety. In this work, a complete virtual microgrid was designed and implemented in MATLAB/Simulink, integrating heterogeneous renewable sources and secondary controller layers. A structured cyberattack framework was developed using MGLib to inject adversarial signals directly into the secondary control pathways. Multiple attack classes were emulated, including ramp, sinusoidal, additive, coordinated stealth, and denial of service behaviors. The virtual environment was used to generate labeled datasets under both normal and attack conditions. The datasets trained Light Gradient Boosting Machine (LightGBM) models to perform two functions: detecting the presence of an intrusion (binary) and distinguishing among attack types (multiclass). The multiclass model attained 99.72% accuracy and a 99.62% F1 score, while the binary model attained 94.8% accuracy and a 94.3% F1 score. A knowledge-distillation step reduced the size of the multiclass model, allowing faster predictions with only a small drop in performance. Real-time tests showed a processing delay of about 54 to 67 ms per 1000 samples, demonstrating suitability for CPU-based edge deployment in microgrid controllers. The results confirm that lightweight machine learning based intrusion detection methods can provide fast, accurate, and efficient cyberattack detection without relying on complex deep learning models. Key contributions include: (1) development of a complete MATLAB-based virtual microgrid, (2) structured attack injection at the control layer, (3) creation of multiclass labeled datasets, and (4) design of low-cost AI models suitable for practical microgrid cybersecurity.

---

### Submodular Evaluation Subset Selection in Automatic Prompt Optimization

Authors: Jinming Nian, Zhiyuan Peng, Hongwei Shang, Dae Hoon Park, Yi Fang
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03493v1

Automatic prompt optimization reduces manual prompt engineering, but relies on task performance measured on a small, often randomly sampled evaluation subset as its main source of feedback signal. Despite this, how to select that evaluation subset is usually treated as an implementation detail. We study evaluation subset selection for prompt optimization from a principled perspective and propose SESS, a submodular evaluation subset selection method. We frame selection as maximizing an objective set function and show that, under mild conditions, it is monotone and submodular, enabling greedy selection with theoretical guarantees. Across GSM8K, MATH, and GPQA-Diamond, submodularly selected evaluation subsets can yield better optimized prompts than random or heuristic baselines.

---

### CroBIM-U: Uncertainty-Driven Referring Remote Sensing Image Segmentation

Authors: Yuzhe Sun, Zhe Dong, Haochen Jiang, Tianzhu Liu, Yanfeng Gu
Published: 2026-01-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.03490v1

Referring remote sensing image segmentation aims to localize specific targets described by natural language within complex overhead imagery. However, due to extreme scale variations, dense similar distractors, and intricate boundary structures, the reliability of cross-modal alignment exhibits significant \textbf{spatial non-uniformity}. Existing methods typically employ uniform fusion and refinement strategies across the entire image, which often introduces unnecessary linguistic perturbations in visually clear regions while failing to provide sufficient disambiguation in confused areas. To address this, we propose an \textbf{uncertainty-guided framework} that explicitly leverages a pixel-wise \textbf{referring uncertainty map} as a spatial prior to orchestrate adaptive inference. Specifically, we introduce a plug-and-play \textbf{Referring Uncertainty Scorer (RUS)}, which is trained via an online error-consistency supervision strategy to interpretably predict the spatial distribution of referential ambiguity. Building on this prior, we design two plug-and-play modules: 1) \textbf{Uncertainty-Gated Fusion (UGF)}, which dynamically modulates language injection strength to enhance constraints in high-uncertainty regions while suppressing noise in low-uncertainty ones; and 2) \textbf{Uncertainty-Driven Local Refinement (UDLR)}, which utilizes uncertainty-derived soft masks to focus refinement on error-prone boundaries and fine details. Extensive experiments demonstrate that our method functions as a unified, plug-and-play solution that significantly improves robustness and geometric fidelity in complex remote sensing scenes without altering the backbone architecture.

---

### From Bits to Chips: An LLM-based Hardware-Aware Quantization Agent for Streamlined Deployment of LLMs

Authors: Kaiyuan Deng, Hangyu Zheng, Minghai Qing, Kunxiong Zhu, Gen Li, Yang Xiao, Lan Emily Zhang, Linke Guo, Bo Hui, Yanzhi Wang, Geng Yuan, Gagan Agrawal et al.
Published: 2026-01-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.03484v2

Deploying models, especially large language models (LLMs), is becoming increasingly attractive to a broader user base, including those without specialized expertise. However, due to the resource constraints of certain hardware, maintaining high accuracy with larger model while meeting the hardware requirements remains a significant challenge. Model quantization technique helps mitigate memory and compute bottlenecks, yet the added complexities of tuning and deploying quantized models further exacerbates these challenges, making the process unfriendly to most of the users. We introduce the Hardware-Aware Quantization Agent (HAQA), an automated framework that leverages LLMs to streamline the entire quantization and deployment process by enabling efficient hyperparameter tuning and hardware configuration, thereby simultaneously improving deployment quality and ease of use for a broad range of users. Our results demonstrate up to a 2.3x speedup in inference, along with increased throughput and improved accuracy compared to unoptimized models on Llama. Additionally, HAQA is designed to implement adaptive quantization strategies across diverse hardware platforms, as it automatically finds optimal settings even when they appear counterintuitive, thereby reducing extensive manual effort and demonstrating superior adaptability. Code will be released.

---

### CALM: Culturally Self-Aware Language Models

Authors: Lingzhi Shen, Xiaohao Cai, Yunfei Long, Imran Razzak, Guanming Chen, Shoaib Jameel
Published: 2026-01-07
Categories: cs.CL, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2601.03483v1

Cultural awareness in language models is the capacity to understand and adapt to diverse cultural contexts. However, most existing approaches treat culture as static background knowledge, overlooking its dynamic and evolving nature. This limitation reduces their reliability in downstream tasks that demand genuine cultural sensitivity. In this work, we introduce CALM, a novel framework designed to endow language models with cultural self-awareness. CALM disentangles task semantics from explicit cultural concepts and latent cultural signals, shaping them into structured cultural clusters through contrastive learning. These clusters are then aligned via cross-attention to establish fine-grained interactions among related cultural features and are adaptively integrated through a Mixture-of-Experts mechanism along culture-specific dimensions. The resulting unified representation is fused with the model's original knowledge to construct a culturally grounded internal identity state, which is further enhanced through self-prompted reflective learning, enabling continual adaptation and self-correction. Extensive experiments conducted on multiple cross-cultural benchmark datasets demonstrate that CALM consistently outperforms state-of-the-art methods.

---

### Personalization of Large Foundation Models for Health Interventions

Authors: Stefan Konigorski, Johannes E. Vedder, Babajide Alamu Owoyele, İbrahim Özkan
Published: 2026-01-07
Categories: cs.AI, cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2601.03482v1

Large foundation models (LFMs) transform healthcare AI in prevention, diagnostics, and treatment. However, whether LFMs can provide truly personalized treatment recommendations remains an open question. Recent research has revealed multiple challenges for personalization, including the fundamental generalizability paradox: models achieving high accuracy in one clinical study perform at chance level in others, demonstrating that personalization and external validity exist in tension. This exemplifies broader contradictions in AI-driven healthcare: the privacy-performance paradox, scale-specificity paradox, and the automation-empathy paradox. As another challenge, the degree of causal understanding required for personalized recommendations, as opposed to mere predictive capacities of LFMs, remains an open question. N-of-1 trials -- crossover self-experiments and the gold standard for individual causal inference in personalized medicine -- resolve these tensions by providing within-person causal evidence while preserving privacy through local experimentation. Despite their impressive capabilities, this paper argues that LFMs cannot replace N-of-1 trials. We argue that LFMs and N-of-1 trials are complementary: LFMs excel at rapid hypothesis generation from population patterns using multimodal data, while N-of-1 trials excel at causal validation for a given individual. We propose a hybrid framework that combines the strengths of both to enable personalization and navigate the identified paradoxes: LFMs generate ranked intervention candidates with uncertainty estimates, which trigger subsequent N-of-1 trials. Clarifying the boundary between prediction and causation and explicitly addressing the paradoxical tensions are essential for responsible AI integration in personalized medicine.

---

### Self-Explaining Hate Speech Detection with Moral Rationales

Authors: Francielle Vargas, Jackson Trager, Diego Alves, Surendrabikram Thapa, Matteo Guida, Berk Atil, Daryna Dementieva, Andrew Smart, Ameeta Agrawal
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03481v2

Existing hate speech detection models are often opaque and rely on surface-level lexical cues, which makes them vulnerable to spurious correlations and limits robustness, interpretability and cultural contextualization. We propose Supervised Moral Rationale Attention (SMRA), the first self-explaining hate speech detection framework to incorporate moral rationales as direct supervision for attention alignment. Based on Moral Foundations Theory, SMRA aligns token-level attention with expert-annotated moral rationales, guiding models to attend to morally salient spans. Unlike prior rationale-supervised or post-hoc approaches, SMRA integrates moral rationale supervision directly into the training objective, producing inherently interpretable and contextualized explanations. To support our framework, we also introduce HateBRMoralXplain, a Brazilian Portuguese benchmark dataset annotated with hate labels, moral categories, token-level moral rationales, and socio-political metadata. Across binary hate speech detection and multi-label moral sentiment classification, SMRA consistently improves performance while enhancing both faithful and plausible explanations. Although explanations become more concise, sufficiency decreases, indicating more compact and informative rationales. Fairness remains stable, suggesting that improvements in explanation quality do not introduce significant bias trade-offs.

---