# Research Papers — 2026-01 · bundle page 83 of 189

> Full-text markdown of papers #4101–4150 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/83
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/82.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/84.md)

### TrackletGPT: A Language-like GPT Framework for White Matter Tract Segmentation

Authors: Anoushkrit Goel, Simroop Singh, Ankita Joshi, Ranjeet Ranjan Jha, Chirag Ahuja, Aditya Nigam, Arnav Bhavsar
Published: 2026-01-20
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.13935v1

White Matter Tract Segmentation is imperative for studying brain structural connectivity, neurological disorders and neurosurgery. This task remains complex, as tracts differ among themselves, across subjects and conditions, yet have similar 3D structure across hemispheres and subjects. To address these challenges, we propose TrackletGPT, a language-like GPT framework which reintroduces sequential information in tokens using tracklets. TrackletGPT generalises seamlessly across datasets, is fully automatic, and encodes granular sub-streamline segments, Tracklets, scaling and refining GPT models in Tractography Segmentation. Based on our experiments, TrackletGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores on TractoInferno and HCP datasets, even on inter-dataset experiments.

---

### Generating consensus and dissent on massive discussion platforms with a semantic-vector model

Authors: A. Ferrer, D. Muñoz-Jordán, A. Rivero, A. Tarancón, C. Tarancón, D. Yllanes
Published: 2026-01-20
Categories: physics.soc-ph, cond-mat.stat-mech, cs.CL
arXiv: https://arxiv.org/abs/2601.13932v2

Reaching consensus on massive discussion networks is critical for reducing noise and achieving optimal collective outcomes. However, the natural tendency of humans to preserve their initial ideas constrains the emergence of global solutions. To address this, Collective Intelligence (CI) platforms facilitate the discovery of globally superior solutions. We introduce a dynamical system based on the standard $O(N)$ model to drive the aggregation of semantically similar ideas. The system consists of users represented as nodes in a $d=2$ lattice with nearest-neighbor interactions, where their ideas are represented by semantic vectors computed with a pretrained embedding model. We analyze the system's equilibrium states as a function of the coupling parameter $β$. Our results show that $β> 0$ drives the system toward a ferromagnetic-like phase (global consensus), while $β< 0$ induces an antiferromagnetic-like state (maximum dissent), where users maximize semantic distance from their neighbors. This framework offers a controllable method for managing the tradeoff between cohesion and diversity in CI platforms.

---

### Towards Effective Negation Modeling in Joint Audio-Text Models for Music

Authors: Yannis Vasilakis, Rachel Bittner, Johan Pauwels
Published: 2026-01-20
Categories: cs.SD, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2601.13931v1

Joint audio-text models are widely used for music retrieval, yet they struggle with semantic phenomena such as negation. Negation is fundamental for distinguishing the absence (or presence) of musical elements (e.g., "with vocals" vs. "without vocals"), but current systems fail to represent this reliably. In this work, we investigate and mitigate this limitation by training CLAP models from scratch on the Million Song Dataset with LP-MusicCaps-MSD captions. We introduce negation through text augmentation and a dissimilarity-based contrastive loss, designed to explicitly separate original and negated captions in the joint embedding space. To evaluate progress, we propose two protocols that frame negation modeling as retrieval and binary classification tasks. Experiments demonstrate that both methods, individually and combined, improve negation handling while largely preserving retrieval performance.

---

### SCG With Your Phone: Diagnosis of Rhythmic Spectrum Disorders in Field Conditions

Authors: Peter Golenderov, Yaroslav Matushenko, Anastasia Tushina, Michal Barodkin
Published: 2026-01-20
Categories: q-bio.QM, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2601.13926v1

Aortic valve opening (AO) events are crucial for detecting frequency and rhythm disorders, especially in real-world settings where seismocardiography (SCG) signals collected via consumer smartphones are subject to noise, motion artifacts, and variability caused by device heterogeneity. In this work, we present a robust deep-learning framework for SCG segmentation and rhythm analysis using accelerometer recordings obtained with consumer smartphones. We develop an enhanced U-Net v3 architecture that integrates multi-scale convolutions, residual connections, and attention gates, enabling reliable segmentation of noisy SCG signals. A dedicated post-processing pipeline converts probability masks into precise AO timestamps, whereas a novel adaptive 3D-to-1D projection method ensures robustness to arbitrary smartphone orientation. Experimental results demonstrate that the proposed method achieves consistently high accuracy and robustness across various device types and unsupervised data-collection conditions. Our approach enables practical, low-cost, and automated cardiac-rhythm monitoring using everyday mobile devices, paving the way for scalable, field-deployable cardiovascular assessment and future multimodal diagnostic systems.

---

### Automatic Prompt Optimization for Dataset-Level Feature Discovery

Authors: Adrian Cosma, Oleg Szehr, David Kletz, Alessandro Antonucci, Olivier Pelletier
Published: 2026-01-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.13922v1

Feature extraction from unstructured text is a critical step in many downstream classification pipelines, yet current approaches largely rely on hand-crafted prompts or fixed feature schemas. We formulate feature discovery as a dataset-level prompt optimization problem: given a labelled text corpus, the goal is to induce a global set of interpretable and discriminative feature definitions whose realizations optimize a downstream supervised learning objective. To this end, we propose a multi-agent prompt optimization framework in which language-model agents jointly propose feature definitions, extract feature values, and evaluate feature quality using dataset-level performance and interpretability feedback. Instruction prompts are iteratively refined based on this structured feedback, enabling optimization over prompts that induce shared feature sets rather than per-example predictions. This formulation departs from prior prompt optimization methods that rely on per-sample supervision and provides a principled mechanism for automatic feature discovery from unstructured text.

---

### Asymmetric regularization mechanism for GAN training with Variational Inequalities

Authors: Spyridon C. Giagtzoglou, Mark H. M. Winands, Barbara Franci
Published: 2026-01-20
Categories: cs.GT, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.13920v1

We formulate the training of generative adversarial networks (GANs) as a Nash equilibrium seeking problem. To stabilize the training process and find a Nash equilibrium, we propose an asymmetric regularization mechanism based on the classic Tikhonov step and on a novel zero-centered gradient penalty. Under smoothness and a local identifiability condition induced by a Gauss-Newton Gramian, we obtain explicit Lipschitz and (strong)-monotonicity constants for the regularized operator. These constants ensure last-iterate linear convergence of a single-call Extrapolation-from-the-Past (EFTP) method. Empirical simulations on an academic example show that, even when strong monotonicity cannot be achieved, the asymmetric regularization is enough to converge to an equilibrium and stabilize the trajectory.

---

### HyperWalker: Dynamic Hypergraph-Based Deep Diagnosis for Multi-Hop Clinical Modeling across EHR and X-Ray in Medical VLMs

Authors: Yuezhe Yang, Hao Wang, Yige Peng, Jinman Kim, Lei Bi
Published: 2026-01-20
Categories: cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2601.13919v1

Automated clinical diagnosis remains a core challenge in medical AI, which usually requires models to integrate multi-modal data and reason across complex, case-specific contexts. Although recent methods have advanced medical report generation (MRG) and visual question answering (VQA) with medical vision-language models (VLMs), these methods, however, predominantly operate under a sample-isolated inference paradigm, as such processing cases independently without access to longitudinal electronic health records (EHRs) or structurally related patient examples. This paradigm limits reasoning to image-derived information alone, which ignores external complementary medical evidence for potentially more accurate diagnosis. To overcome this limitation, we propose \textbf{HyperWalker}, a \textit{Deep Diagnosis} framework that reformulates clinical reasoning via dynamic hypergraphs and test-time training. First, we construct a dynamic hypergraph, termed \textbf{iBrochure}, to model the structural heterogeneity of EHR data and implicit high-order associations among multimodal clinical information. Within this hypergraph, a reinforcement learning agent, \textbf{Walker}, navigates to and identifies optimal diagnostic paths. To ensure comprehensive coverage of diverse clinical characteristics in test samples, we incorporate a \textit{linger mechanism}, a multi-hop orthogonal retrieval strategy that iteratively selects clinically complementary neighborhood cases reflecting distinct clinical attributes. Experiments on MRG with MIMIC and medical VQA on EHRXQA demonstrate that HyperWalker achieves state-of-the-art performance. Code is available at: https://github.com/Bean-Young/HyperWalker

---

### AgentEHR: Advancing Autonomous Clinical Decision-Making via Retrospective Summarization

Authors: Yusheng Liao, Chuan Xuan, Yutong Cai, Lina Yang, Zhe Chen, Yanfeng Wang, Yu Wang
Published: 2026-01-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.13918v1

Large Language Models have demonstrated profound utility in the medical domain. However, their application to autonomous Electronic Health Records~(EHRs) navigation remains constrained by a reliance on curated inputs and simplified retrieval tasks. To bridge the gap between idealized experimental settings and realistic clinical environments, we present AgentEHR. This benchmark challenges agents to execute complex decision-making tasks, such as diagnosis and treatment planning, requiring long-range interactive reasoning directly within raw and high-noise databases. In tackling these tasks, we identify that existing summarization methods inevitably suffer from critical information loss and fractured reasoning continuity. To address this, we propose RetroSum, a novel framework that unifies a retrospective summarization mechanism with an evolving experience strategy. By dynamically re-evaluating interaction history, the retrospective mechanism prevents long-context information loss and ensures unbroken logical coherence. Additionally, the evolving strategy bridges the domain gap by retrieving accumulated experience from a memory bank. Extensive empirical evaluations demonstrate that RetroSum achieves performance gains of up to 29.16% over competitive baselines, while significantly decreasing total interaction errors by up to 92.3%.

---

### On the Role of Rotation Equivariance in Monocular 2D-to-3D Human Pose Lifting

Authors: Pavlo Melnyk, Cuong Le, Urs Waldmann, Per-Erik Forssén, Bastian Wandt
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.13913v3

We consider monocular 3D human pose estimation (HPE), where the goal is to predict 3D human skeletal joints from a single 2D image, typically via 2D keypoint detection followed by 2D-to-3D lifting. Despite their success, we find that current lifting models exhibit strong performance degradation under rotations. We systematically study rotation equivariance across lifting architectures with increasing degrees of equivariant inductive bias, and investigate whether equivariance should be enforced by architectural design or learned from data, given the inherent ambiguity of monocular 2D-to-3D lifting. Utilising common HPE benchmarks, we demonstrate that rotation equivariance can be effectively learned via rotation-based data augmentation applied jointly to input and output poses. Compared with non-augmented models, this reduces error on rotated poses by over 30% across the benchmarks, with reductions of up to 72%. Moreover, augmentation-based models achieve up to 15% lower error than methods that are fully equivariant by design, while providing up to 37$\times$ faster inference. We further show that these findings generalise to real-world human pose sequences involving full-body rotations and to a state-of-the-art HPE model.

---

### PREFAB: PREFerence-based Affective Modeling for Low-Budget Self-Annotation

Authors: Jaeyoung Moon, Youjin Choi, Yucheon Park, David Melhart, Georgios N. Yannakakis, Kyung-Joong Kim
Published: 2026-01-20
Categories: cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.13904v2

Self-annotation is the gold standard for collecting affective state labels in affective computing. Existing methods typically rely on full annotation, requiring users to continuously label affective states across entire sessions. While this process yields fine-grained data, it is time-consuming, cognitively demanding, and prone to fatigue and errors. To address these issues, we present PREFAB, a low-budget retrospective self-annotation method that targets affective inflection regions rather than full annotation. Grounded in the peak-end rule and ordinal representations of emotion, PREFAB employs a preference-learning model to detect relative affective changes, directing annotators to label only selected segments while interpolating the remainder of the stimulus. We further introduce a preview mechanism that provides brief contextual cues to assist annotation. We evaluate PREFAB through a technical performance study and a 25-participant user study. Results show that PREFAB outperforms baselines in modeling affective inflections while mitigating workload (and conditionally mitigating temporal burden). Importantly PREFAB improves annotator confidence without degrading annotation quality.

---

### Towards Visually Explaining Statistical Tests with Applications in Biomedical Imaging

Authors: Masoumeh Javanbakhat, Piotr Komorowski, Dilyara Bareeva, Wei-Chang Lai, Wojciech Samek, Christoph Lippert
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.13899v2

Deep neural two-sample tests have recently shown strong power for detecting distributional differences between groups, yet their black-box nature limits interpretability and practical adoption in biomedical analysis. Moreover, most existing post-hoc explainability methods rely on class labels, making them unsuitable for label-free statistical testing settings. We propose an explainable deep statistical testing framework that augments deep two-sample tests with sample-level and feature-level explanations, revealing which individual samples and which input features drive statistically significant group differences. Our method highlights which image regions and which individual samples contribute most to the detected group difference, providing spatial and instance-wise insight into the test's decision. Applied to biomedical imaging data, the proposed framework identifies influential samples and highlights anatomically meaningful regions associated with disease-related variation. This work bridges statistical inference and explainable AI, enabling interpretable, label-free population analysis in medical imaging.

---

### TractRLFusion: A GPT-Based Multi-Critic Policy Fusion Framework for Fiber Tractography

Authors: Ankita Joshi, Ashutosh Sharma, Anoushkrit Goel, Ranjeet Ranjan Jha, Chirag Ahuja, Arnav Bhavsar, Aditya Nigam
Published: 2026-01-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.13897v1

Tractography plays a pivotal role in the non-invasive reconstruction of white matter fiber pathways, providing vital information on brain connectivity and supporting precise neurosurgical planning. Although traditional methods relied mainly on classical deterministic and probabilistic approaches, recent progress has benefited from supervised deep learning (DL) and deep reinforcement learning (DRL) to improve tract reconstruction. A persistent challenge in tractography is accurately reconstructing white matter tracts while minimizing spurious connections. To address this, we propose TractRLFusion, a novel GPT-based policy fusion framework that integrates multiple RL policies through a data-driven fusion strategy. Our method employs a two-stage training data selection process for effective policy fusion, followed by a multi-critic fine-tuning phase to enhance robustness and generalization. Experiments on HCP, ISMRM, and TractoInferno datasets demonstrate that TractRLFusion outperforms individual RL policies as well as state-of-the-art classical and DRL methods in accuracy and anatomical reliability.

---

### OmniOVCD: Streamlining Open-Vocabulary Change Detection with SAM 3

Authors: Xu Zhang, Danyang Li, Yingjie Xia, Xiaohang Dong, Hualong Yu, Jianye Wang, Qicheng Li
Published: 2026-01-20
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.13895v2

Change Detection (CD) is a fundamental task in remote sensing. It monitors the evolution of land cover over time. Based on this, Open-Vocabulary Change Detection (OVCD) introduces a new requirement. It aims to reduce the reliance on predefined categories. Existing training-free OVCD methods mostly use CLIP to identify categories. These methods also need extra models like DINO to extract features. However, combining different models often causes problems in matching features and makes the system unstable. Recently, the Segment Anything Model 3 (SAM 3) is introduced. It integrates segmentation and identification capabilities within one promptable model, which offers new possibilities for the OVCD task. In this paper, we propose OmniOVCD, a standalone framework designed for OVCD. By leveraging the decoupled output heads of SAM 3, we propose a Synergistic Fusion to Instance Decoupling (SFID) strategy. SFID first fuses the semantic, instance, and presence outputs of SAM 3 to construct land-cover masks, and then decomposes them into individual instance masks for change comparison. This design preserves high accuracy in category recognition and maintains instance-level consistency across images. As a result, the model can generate accurate change masks. Experiments on four public benchmarks (LEVIR-CD, WHU-CD, S2Looking, and SECOND) demonstrate SOTA performance, achieving IoU scores of 67.2, 66.5, 24.5, and 27.1 (class-average), respectively, surpassing all previous methods. The code is available at https://github.com/Erxucomeon/OmniOVCD.

---

### Multi-Objective Hierarchical Optimization with Large Language Models

Authors: Andrej Schwanke, Lyubomir Ivanov, David Salinas, Frank Hutter, Arber Zela
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.13892v1

Despite their widespread adoption in various domains, especially due to their powerful reasoning capabilities, Large Language Models (LLMs) are not the off-the-shelf choice to drive multi-objective optimization yet. Conventional strategies rank high in benchmarks due to their intrinsic capabilities to handle numerical inputs and careful modelling choices that balance exploration and Pareto-front exploitation, as well as handle multiple (conflicting) objectives. In this paper, we close this gap by leveraging LLMs as surrogate models and candidate samplers inside a structured hierarchical search strategy. By adaptively partitioning the input space into disjoint hyperrectangular regions and ranking them with a composite score function, we restrict the generative process of the LLM to specific, high-potential sub-spaces, hence making the problem easier to solve as the LLM doesn't have to reason about the global structure of the problem, but only locally instead. We show that under standard regularity assumptions, our algorithm generates candidate solutions that converge to the true Pareto set in Hausdorff distance. Empirically, it consistently outperforms the global LLM-based multi-objective optimizer and is on par with standard evolutionary and Bayesian optimization algorithm on synthetic and real-world benchmarks.

---

### Human Simulation Computation: A Human-Inspired Framework for Adaptive AI Systems

Authors: Hong Su
Published: 2026-01-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.13887v2

Large language models (LLMs) have demonstrated strong capabilities in knowledge representation and reasoning based on textual data. However, their reliance on language material alone limits their ability to adapt, verify reasoning outcomes, and operate effectively in open and dynamic real-world environments. In this paper, we propose Human Simulation Computation (HSC), a human-inspired computational framework that models intelligence as a continuous, closed-loop process involving thinking, action, learning, reflection, and activity scheduling, collectively referred to as the internal reasoning process. HSC emphasizes active participation both within the internal reasoning process and in interactions with the environment, where actions are used not only to achieve goals but also to automatically refine and improve internal reasoning mechanisms without external intervention. Furthermore, HSC incorporates commonly used human thinking strategies across all stages of the internal reasoning process, such as main-feature-oriented reasoning, scope expansion through action, and on-time learning driven by environmental feedback. Through theoretical analysis, we argue that human simulation strategies cannot be fully learned from language material alone, and that human-like reasoning processes and action-grounded reasoning methods are essential for robust adaptation and effective interaction with real-world environments.

---

### Revisiting Multi-Task Visual Representation Learning

Authors: Shangzhe Di, Zhonghua Zhai, Weidi Xie
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.13886v1

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures yet struggle with high-level semantic context. We argue that these paradigms are fundamentally complementary and can be integrated into a principled multi-task framework, further enhanced by dense spatial supervision. We introduce MTV, a multi-task visual pretraining framework that jointly optimizes a shared backbone across vision-language contrastive, self-supervised, and dense spatial objectives. To mitigate the need for manual annotations, we leverage high-capacity "expert" models -- such as Depth Anything V2 and OWLv2 -- to synthesize dense, structured pseudo-labels at scale. Beyond the framework, we provide a systematic investigation into the mechanics of multi-task visual learning, analyzing: (i) the marginal gain of each objective, (ii) task synergies versus interference, and (iii) scaling behavior across varying data and model scales. Our results demonstrate that MTV achieves "best-of-both-worlds" performance, significantly enhancing fine-grained spatial reasoning without compromising global semantic understanding. Our findings suggest that multi-task learning, fueled by high-quality pseudo-supervision, is a scalable path toward more general visual encoders.

---

### Confident Rankings with Fewer Items: Adaptive LLM Evaluation with Continuous Scores

Authors: Esma Balkır, Alice Pernthaller, Marco Basaldella, José Hernández-Orallo, Nigel Collier
Published: 2026-01-20
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.13885v2

Computerized Adaptive Testing (CAT) has proven effective for efficient LLM evaluation on multiple-choice benchmarks, but modern LLM evaluation increasingly relies on generation tasks where outputs are scored continuously rather than marked correct/incorrect. We present a principled extension of IRT-based adaptive testing to continuous bounded scores (ROUGE, BLEU, LLM-as-a-Judge) by replacing the Bernoulli response distribution with a heteroskedastic normal distribution. Building on this, we introduce an uncertainty aware ranker with adaptive stopping criteria that achieves reliable model ranking while testing as few items and as cheaply as possible. We validate our method on five benchmarks spanning n-gram-based, embedding-based, and LLM-as-judge metrics. Our method improves ranking correlation by 0.13 $τ$ over random sampling and has 99% accuracy on confident predictions while using 2% of the items after a one-time calibration step.

---

### OpenLearnLM Benchmark: A Unified Framework for Evaluating Knowledge, Skill, and Attitude in Educational Large Language Models

Authors: Unggi Lee, Sookbun Lee, Heungsoo Choi, Jinseo Lee, Haeun Park, Younghoon Jeon, Sungmin Cho, Minju Kang, Junbo Koh, Jiyeong Bae, Minwoo Nam, Juyeon Eun et al.
Published: 2026-01-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.13882v1

Large Language Models are increasingly deployed as educational tools, yet existing benchmarks focus on narrow skills and lack grounding in learning sciences. We introduce OpenLearnLM Benchmark, a theory-grounded framework evaluating LLMs across three dimensions derived from educational assessment theory: Knowledge (curriculum-aligned content and pedagogical understanding), Skills (scenario-based competencies organized through a four-level center-role-scenario-subscenario hierarchy), and Attitude (alignment consistency and deception resistance). Our benchmark comprises 124K+ items spanning multiple subjects, educational roles, and difficulty levels based on Bloom's taxonomy. The Knowledge domain prioritizes authentic assessment items from established benchmarks, while the Attitude domain adapts Anthropic's Alignment Faking methodology to detect behavioral inconsistency under varying monitoring conditions. Evaluation of seven frontier models reveals distinct capability profiles: Claude-Opus-4.5 excels in practical skills despite lower content knowledge, while Grok-4.1-fast leads in knowledge but shows alignment concerns. Notably, no single model dominates all dimensions, validating the necessity of multi-axis evaluation. OpenLearnLM provides an open, comprehensive framework for advancing LLM readiness in authentic educational contexts.

---

### LifeAgentBench: Benchmarking LLMs for Long-Horizon, Cross-Dimensional Lifestyle Health Reasoning

Authors: Ye Tian, Zihao Wang, Onat Gungor, Xiaoran Fan, Tajana Rosing
Published: 2026-01-20
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.13880v2

Personalized lifestyle health analysis requires long-horizon, multi-dimensional reasoning over heterogeneous lifestyle signals, and recent advances in mobile sensing and large language models (LLMs) make such support increasingly feasible. However, the capabilities of current LLMs in this setting remain insufficiently understood due to the lack of systematic benchmarks. In this paper, we introduce LifeAgentBench, a large-scale QA benchmark for long-horizon, cross-dimensional, and multi-user lifestyle health reasoning, containing 22,573 questions spanning from basic retrieval to complex reasoning. We release an extensible benchmark construction pipeline and a standardized evaluation protocol, deriving verifiable answers through executable queries and programs to support reliable assessment. We then systematically evaluate 13 representative LLMs on LifeAgentBench and identify key bottlenecks in long-horizon aggregation and cross-dimensional reasoning. Motivated by these findings, we propose LifeAgent, a tool-augmented reasoning baseline that decomposes complex queries, performs multi-step evidence retrieval, and invokes tools for deterministic aggregation. LifeAgent substantially enhances LLMs' capabilities on challenging reasoning tasks, achieving clear improvements over widely used baselines and showing potential for health reasoning in everyday scenarios. The benchmark is publicly available.

---

### Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring

Authors: Dongxu Zhang, Yiding Sun, Cheng Tan, Wenbiao Yan, Ning Yang, Jihua Zhu, Haijun Zhang
Published: 2026-01-20
Categories: cs.MM, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2601.13879v4

While Chain-of-Thought (CoT) reasoning significantly enhances the performance of Multimodal Large Language Models (MLLMs), its autoregressive nature incurs prohibitive latency constraints. Current efforts to mitigate this via token compression often fail by blindly applying text-centric metrics to multimodal contexts. We identify a critical failure mode termed Visual Amnesia, where linguistically redundant tokens are erroneously pruned, leading to hallucinations. To address this, we introduce V-Skip that reformulates token pruning as a Visual-Anchored Information Bottleneck (VA-IB) optimization problem. V-Skip employs a dual-path gating mechanism that weighs token importance through both linguistic surprisal and cross-modal attention flow, effectively rescuing visually salient anchors. Extensive experiments on Qwen2-VL and Llama-3.2 families demonstrate that V-Skip achieves a $2.9\times$ speedup with negligible accuracy loss. Specifically, it preserves fine-grained visual details, outperforming other baselines over 30\% on the DocVQA.

---

### Pedagogical Alignment for Vision-Language-Action Models: A Comprehensive Framework for Data, Architecture, and Evaluation in Education

Authors: Unggi Lee, Jahyun Jeong, Sunyoung Shin, Haeun Park, Jeongsu Moon, Youngchang Song, Jaechang Shim, JaeHwan Lee, Yunju Noh, Seungwon Choi, Ahhyun Kim, TaeHyeon Kim et al.
Published: 2026-01-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.13876v1

Science demonstrations are important for effective STEM education, yet teachers face challenges in conducting them safely and consistently across multiple occasions, where robotics can be helpful. However, current Vision-Language-Action (VLA) models require substantial computational resources and sacrifice language generation capabilities to maximize efficiency, making them unsuitable for resource-constrained educational settings that require interpretable, explanation-generating systems. We present \textit{Pedagogical VLA Framework}, a framework that applies pedagogical alignment to lightweight VLA models through four components: text healing to restore language generation capabilities, large language model (LLM) distillation to transfer pedagogical knowledge, safety training for educational environments, and pedagogical evaluation adjusted to science education contexts. We evaluate Pedagogical VLA Framework across five science demonstrations spanning physics, chemistry, biology, and earth science, using an evaluation framework developed in collaboration with science education experts. Our evaluation assesses both task performance (success rate, protocol compliance, efficiency, safety) and pedagogical quality through teacher surveys and LLM-as-Judge assessment. We additionally provide qualitative analysis of generated texts. Experimental results demonstrate that Pedagogical VLA Framework achieves comparable task performance to baseline models while producing contextually appropriate educational explanations.

---

### Finite-Sample Unbiased Variance of MMD under Unbalanced Sampling: Exact Estimation and Quasi-Linear Computation

Authors: Shijie Zhong, Yikun Yang, Da Gong, Jiangfeng Fu
Published: 2026-01-20
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.13874v3

Accurately and efficiently estimating the variance of the Maximum Mean Discrepancy (MMD) remains challenging, particularly for unbalanced sample sizes. In this paper, we derive a finite-sample unbiased estimator of the MMD variance. To overcome the traditional $\mathcal{O}(N^2)$ computational bottleneck, we develop a recursive prefix-suffix accumulation scheme for the Laplace kernel, reducing the computational complexity to $\mathcal{O}(N \log N)$ while requiring $\mathcal{O}(N)$ memory. Experimental results verify the theoretical exactness and numerical stability of the proposed estimator and demonstrate its scalability on large datasets. Furthermore, the method proves effective for monitoring distributional convergence during the training of Time-series Generative Adversarial Networks (TimeGAN).

---

### OCCAM: Class-Agnostic, Training-Free, Prior-Free and Multi-Class Object Counting

Authors: Michail Spanakis, Iason Oikonomidis, Antonis Argyros
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.13871v1

Class-Agnostic object Counting (CAC) involves counting instances of objects from arbitrary classes within an image. Due to its practical importance, CAC has received increasing attention in recent years. Most existing methods assume a single object class per image, rely on extensive training of large deep learning models and address the problem by incorporating additional information, such as visual exemplars or text prompts. In this paper, we present OCCAM, the first training-free approach to CAC that operates without the need of any supplementary information. Moreover, our approach addresses the multi-class variant of the problem, as it is capable of counting the object instances in each and every class among arbitrary object classes within an image. We leverage Segment Anything Model 2 (SAM2), a foundation model, and a custom threshold-based variant of the First Integer Neighbor Clustering Hierarchy (FINCH) algorithm to achieve competitive performance on widely used benchmark datasets, FSC-147 and CARPK. We propose a synthetic multi-class dataset and F1 score as a more suitable evaluation metric. The code for our method and the proposed synthetic dataset will be made publicly available at https://mikespanak.github.io/OCCAM_counter.

---

### HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation

Authors: Qirui Chen, Jingxian Shuai, Shuangwu Chen, Shenghao Ye, Zijian Wen, Xufei Su, Jie Jin, Jiangming Li, Jun Chen, Xiaobin Tan, Jian Yang
Published: 2026-01-20
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.13864v2

Large language models (LLMs) are increasingly used for hardware and firmware code generation, but existing studies primarily evaluate functional correctness while largely overlooking security. However, LLM-generated code that appears functionally sound may embed security flaws which could induce catastrophic damages after deployment. This critical research gap motivates us to design a benchmark for assessing security awareness under realistic specifications. In this work, we introduce HardSecBench, a benchmark with 924 tasks spanning Verilog Register Transfer Level (RTL) and firmware-level C, covering 76 hardware-relevant Common Weakness Enumeration (CWE) entries. Each task includes a structured specification, a secure reference implementation, and executable tests. To automate artifact synthesis, we propose a multi-agent pipeline that decouples synthesis from verification and grounds evaluation in execution evidence, enabling reliable evaluation. We evaluate diverse LLMs and find that they often satisfy functional requirements while leaving security risks. We also find that security results vary with prompting. These findings highlight pressing challenges and offer actionable insights for future advancements in LLM-assisted hardware design. Our data and code are available at https://github.com/chenqirui2002/HardSecBench.

---

### Probabilistic Deep Discriminant Analysis for Wind Blade Segmentation

Authors: Raül Pérez-Gonzalo, Andreas Espersen, Antonio Agudo
Published: 2026-01-20
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.13852v1

Linear discriminant analysis improves class separability but struggles with non-linearly separable data. To overcome this, we introduce Deep Discriminant Analysis (DDA), which directly optimizes the Fisher criterion utilizing deep networks. To ensure stable training and avoid computational instabilities, we incorporate signed between-class variance, bound outputs with a sigmoid function, and convert multiplicative relationships into additive ones. We present two stable DDA loss functions and augment them with a probability loss, resulting in Probabilistic DDA (PDDA). PDDA effectively minimizes class overlap in output distributions, producing highly confident predictions with reduced within-class variance. When applied to wind blade segmentation, PDDA showcases notable advances in performance and consistency, critical for wind energy maintenance. To our knowledge, this is the first application of DDA to image segmentation.

---

### Inverting Self-Organizing Maps: A Unified Activation-Based Framework

Authors: Alessandro Londei, Matteo Benati, Denise Lanzieri, Vittorio Loreto
Published: 2026-01-20
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.13851v2

Self-Organizing Maps (SOMs) provide topology-preserving projections of high-dimensional data, yet their use as generative models remains largely unexplored. We show that the activation pattern of a SOM -- the squared distances to its prototypes -- can be \emph{inverted} to recover the exact input, following from a classical result in Euclidean distance geometry: a point in $D$ dimensions is uniquely determined by its distances to $D{+}1$ affinely independent references. We derive the corresponding linear system and characterize the conditions under which inversion is well-posed. Building on this mechanism, we introduce the \emph{Manifold-Aware Unified SOM Inversion and Control} (MUSIC) update rule, which modifies squared distances to selected prototypes while preserving others, producing controlled, semantically meaningful trajectories aligned with the SOM's piecewise-linear structure. Tikhonov regularization stabilizes the update and ensures smooth motion in high dimensions. Unlike variational or diffusion-based generative models, MUSIC requires no sampling, latent priors, or learned decoders: it operates entirely on prototype geometry. If no perturbation is applied, inversion recovers the exact input; when a target prototype or cluster is specified, MUSIC produces coherent semantic transitions. We validate the framework on synthetic Gaussian mixtures, MNIST digits, and the Labeled Faces in the Wild dataset. Across all settings, MUSIC trajectories maintain high classifier confidence, produce significantly sharper intermediate images than linear interpolation, and reveal an interpretable geometric structure of the learned map.

---

### Co-Initialization of Control Filter and Secondary Path via Meta-Learning for Active Noise Control

Authors: Ziyi Yang, Li Rao, Zhengding Luo, Dongyuan Shi, Qirui Huang, Woon-Seng Gan
Published: 2026-01-20
Categories: eess.AS, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2601.13849v1

Active noise control (ANC) must adapt quickly when the acoustic environment changes, yet early performance is largely dictated by initialization. We address this with a Model-Agnostic Meta-Learning (MAML) co-initialization that jointly sets the control filter and the secondary-path model for FxLMS-based ANC while keeping the runtime algorithm unchanged. The initializer is pre-trained on a small set of measured paths using short two-phase inner loops that mimic identification followed by residual-noise reduction, and is applied by simply setting the learned initial coefficients. In an online secondary path modeling FxLMS testbed, it yields lower early-stage error, shorter time-to-target, reduced auxiliary-noise energy, and faster recovery after path changes than a baseline without re-initialization. The method provides a simple fast start for feedforward ANC under environment changes, requiring a small set of paths to pre-train.

---

### Virtual Urbanism: An AI-Driven Framework for Quantifying Urban Identity. A Tokyo-Based Pilot Study Using Diffusion-Generated Synthetic Environments

Authors: Glinskaya Maria
Published: 2026-01-20
Categories: cs.AI, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2601.13846v1

This paper introduces Virtual Urbanism (VU), a multimodal AI-driven analytical framework for quantifying urban identity through the medium of synthetic urban replicas. The framework aims to advance computationally tractable urban identity metrics. To demonstrate feasibility, the pilot study Virtual Urbanism and Tokyo Microcosms is presented. A pipeline integrating Stable Diffusion and LoRA models was used to produce synthetic replicas of nine Tokyo areas rendered as dynamic synthetic urban sequences, excluding existing orientation markers to elicit core identity-forming elements. Human-evaluation experiments (I) assessed perceptual legitimacy of replicas; (II) quantified area-level identity; (III) derived core identity-forming elements. Results showed a mean identification accuracy of ~81%, confirming the validity of the replicas. Urban Identity Level (UIL) metric enabled assessment of identity levels across areas, while semantic analysis revealed culturally embedded typologies as core identity-forming elements, positioning VU as a viable framework for AI-augmented urban analysis, outlining a path toward automated, multi-parameter identity metrics.

---

### Optimal L2 Regularization in High-dimensional Continual Linear Regression

Authors: Gilad Karpel, Edward Moroshko, Ran Levinstein, Ron Meir, Daniel Soudry, Itay Evron
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.13844v2

We study generalization in an overparameterized continual linear regression setting, where a model is trained with L2 (isotropic) regularization across a sequence of tasks. We derive a closed-form expression for the expected generalization loss in the high-dimensional regime that holds for arbitrary linear teachers. We demonstrate that isotropic regularization mitigates label noise under both single-teacher and multiple i.i.d. teacher settings, whereas prior work accommodating multiple teachers either did not employ regularization or used memory-demanding methods. Furthermore, we prove that the optimal fixed regularization strength scales nearly linearly with the number of tasks $T$, specifically as $T/\ln T$. To our knowledge, this is the first such result in theoretical continual learning. Finally, we validate our theoretical findings through experiments on linear regression and neural networks, illustrating how this scaling law affects generalization and offering a practical recipe for the design of continual learning systems.

---

### DisasterVQA: A Visual Question Answering Benchmark Dataset for Disaster Scenes

Authors: Aisha Al-Mohannadi, Ayisha Firoz, Yin Yang, Muhammad Imran, Ferda Ofli
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.13839v2

Social media imagery provides a low-latency source of situational information during natural and human-induced disasters, enabling rapid damage assessment and response. While Visual Question Answering (VQA) has shown strong performance in general-purpose domains, its suitability for the complex and safety-critical reasoning required in disaster response remains unclear. We introduce DisasterVQA, a benchmark dataset designed for perception and reasoning in crisis contexts. DisasterVQA consists of 1,395 real-world images and 4,405 expert-curated question-answer pairs spanning diverse events such as floods, wildfires, and earthquakes. Grounded in humanitarian frameworks including FEMA ESF and OCHA MIRA, the dataset includes binary, multiple-choice, and open-ended questions covering situational awareness and operational decision-making tasks. We benchmark seven state-of-the-art vision-language models and find performance variability across question types, disaster categories, regions, and humanitarian tasks. Although models achieve high accuracy on binary questions, they struggle with fine-grained quantitative reasoning, object counting, and context-sensitive interpretation, particularly for underrepresented disaster scenarios. DisasterVQA provides a challenging and practical benchmark to guide the development of more robust and operationally meaningful vision-language models for disaster response. The dataset is publicly available at https://doi.org/10.5281/zenodo.18267769.

---

### FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation

Authors: Xinya Ji, Sebastian Weiss, Manuel Kansy, Jacek Naruniec, Xun Cao, Barbara Solenthaler, Derek Bradley
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.13837v2

Despite recent progress in 3D Gaussian-based head avatar modeling, efficiently generating high fidelity avatars remains a challenge. Current methods typically rely on extensive multi-view capture setups or monocular videos with per-identity optimization during inference, limiting their scalability and ease of use on unseen subjects. To overcome these efficiency drawbacks, we propose FastGHA, a feed-forward method to generate high-quality Gaussian head avatars from only a few input images while supporting real-time animation. Our approach directly learns a per-pixel Gaussian representation from the input images, and aggregates multi-view information using a transformer-based encoder that fuses image features from both DINOv3 and Stable Diffusion VAE. For real-time animation, we extend the explicit Gaussian representations with per-Gaussian features and introduce a lightweight MLP-based dynamic network to predict 3D Gaussian deformations from expression codes. Furthermore, to enhance geometric smoothness of the 3D head, we employ point maps from a pre-trained large reconstruction model as geometry supervision. Experiments show that our approach significantly outperforms existing methods in both rendering quality and inference efficiency, while supporting real-time dynamic avatar animation.

---

### FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs

Authors: Qian Chen, Jinlan Fu, Changsong Li, Min Zhang, See-Kiong Ng, Xipeng Qiu
Published: 2026-01-20
Categories: cs.CL, cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2601.13836v2

Although Multimodal Large Language Models (MLLMs) demonstrate strong omni-modal perception, their ability to forecast future events from audio-visual cues remains largely unexplored, as existing benchmarks focus mainly on retrospective understanding. To bridge this gap, we introduce FutureOmni, the first benchmark designed to evaluate omni-modal future forecasting from audio-visual environments. The evaluated models are required to perform cross-modal causal and temporal reasoning, as well as effectively leverage internal knowledge to predict future events. FutureOmni is constructed via a scalable LLM-assisted, human-in-the-loop pipeline and contains 919 videos and 1,034 multiple-choice QA pairs across 8 primary domains. Evaluations on 13 omni-modal and 7 video-only models show that current systems struggle with audio-visual future prediction, particularly in speech-heavy scenarios, with the best accuracy of 64.8% achieved by Gemini 3 Flash. To mitigate this limitation, we curate a 7K-sample instruction-tuning dataset and propose an Omni-Modal Future Forecasting (OFF) training strategy. Evaluations on FutureOmni and popular audio-visual and video-only benchmarks demonstrate that OFF enhances future forecasting and generalization. We publicly release all code (https://github.com/OpenMOSS/FutureOmni) and datasets (https://huggingface.co/datasets/OpenMOSS-Team/FutureOmni).

---

### The Role of Prosodic and Lexical Cues in Turn-Taking with Self-Supervised Speech Representations

Authors: Sam OConnor Russell, Delphine Charuau, Naomi Harte
Published: 2026-01-20
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.13835v1

Fluid turn-taking remains a key challenge in human-robot interaction. Self-supervised speech representations (S3Rs) have driven many advances, but it remains unclear whether S3R-based turn-taking models rely on prosodic cues, lexical cues or both. We introduce a vocoder-based approach to control prosody and lexical cues in speech more cleanly than prior work. This allows us to probe the voice-activity projection model, an S3R-based turn-taking model. We find that prediction on prosody-matched, unintelligible noise is similar to accuracy on clean speech. This reveals both prosodic and lexical cues support turn-taking, but either can be used in isolation. Hence, future models may only require prosody, providing privacy and potential performance benefits. When either prosodic or lexical information is disrupted, the model exploits the other without further training, indicating they are encoded in S3Rs with limited interdependence. Results are consistent in CPC-based and wav2vec2.0 S3Rs. We discuss our findings and highlight a number of directions for future work. All code is available to support future research.

---

### ELSA: Efficient LLM-Centric Split Aggregation for Privacy-Aware Hierarchical Federated Learning over the Network Edge

Authors: Xiaohong Yang, Tong Xie, Minghui Liwang, Chikai Shang, Yang Lu, Zhenzhen Jiao, Liqun Fu, Seyyedali Hosseinalipour
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.13824v2

Training large language models (LLMs) at the network edge faces fundamental challenges arising from device resource constraints, severe data heterogeneity, and heightened privacy risks. To address these challenges, we propose ELSA (Efficient LLM-centric Split Aggregation), a novel framework that systematically integrates split learning (SL) and hierarchical federated learning (HFL) for distributed LLM fine-tuning over resource-constrained edge networks. ELSA introduces three key innovations. First, it employs a task-agnostic, behavior-aware client clustering mechanism that constructs semantic fingerprints using public probe inputs and symmetric Kullback-Leibler (KL) divergence, augmented by prediction-consistency trust scoring and latency-aware edge assignment to jointly mitigate data heterogeneity, device unreliability, and communication constraints. Second, it employs a resource-aware dynamic model splitting strategy to adaptively partition the LLM into three segments across clients and edge servers, with the cloud used only for adapter aggregation, enabling an effective balance between on-device computation cost and global convergence stability. Third, it incorporates a lightweight communication scheme based on computational sketches combined with semantic subspace orthogonal perturbation (SS-OP) to reduce communication overhead while mitigating privacy leakage during model exchanges across the network. Extensive experiments across diverse NLP tasks demonstrate that ELSA consistently outperforms state-of-the-art baselines in terms of adaptability, convergence behavior, and robustness, establishing a scalable and privacy-aware solution for edge-side LLM fine-tuning under resource constraints.

---

### Device Association and Resource Allocation for Hierarchical Split Federated Learning in Space-Air-Ground Integrated Network

Authors: Haitao Zhao, Xiaoyu Tang, Bo Xu, Jinlong Sun, Linghao Zhang
Published: 2026-01-20
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2601.13817v3

6G facilitates deployment of Federated Learning (FL) in the Space-Air-Ground Integrated Network (SAGIN), yet FL confronts challenges such as resource constrained and unbalanced data distribution. To address these issues, this paper proposes a Hierarchical Split Federated Learning (HSFL) framework and derives its upper bound of loss function. To minimize the weighted sum of training loss and latency, we formulate a joint optimization problem that integrates device association, model split layer selection, and resource allocation. We decompose the original problem into several subproblems, where an iterative optimization algorithm for device association and resource allocation based on brute-force split point search is proposed. Simulation results demonstrate that the proposed algorithm can effectively balance training efficiency and model accuracy for FL in SAGIN.

---

### Discriminant Learning-based Colorspace for Blade Segmentation

Authors: Raül Pérez-Gonzalo, Andreas Espersen, Antonio Agudo
Published: 2026-01-20
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.13816v1

Suboptimal color representation often hinders accurate image segmentation, yet many modern algorithms neglect this critical preprocessing step. This work presents a novel multidimensional nonlinear discriminant analysis algorithm, Colorspace Discriminant Analysis (CSDA), for improved segmentation. Extending Linear Discriminant Analysis into a deep learning context, CSDA customizes color representation by maximizing multidimensional signed inter-class separability while minimizing intra-class variability through a generalized discriminative loss. To ensure stable training, we introduce three alternative losses that enable end-to-end optimization of both the discriminative colorspace and segmentation process. Experiments on wind turbine blade data demonstrate significant accuracy gains, emphasizing the importance of tailored preprocessing in domain-specific segmentation.

---

### DroneVLA: VLA based Aerial Manipulation

Authors: Fawad Mehboob, Monijesu James, Amir Habel, Jeffrin Sam, Miguel Altamirano Cabrera, Dzmitry Tsetserukou
Published: 2026-01-20
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.13809v2

As aerial platforms evolve from passive observers to active manipulators, the challenge shifts toward designing intuitive interfaces that allow non-expert users to command these systems naturally. This work introduces a novel concept of autonomous aerial manipulation system capable of interpreting high-level natural language commands to retrieve objects and deliver them to a human user. The system is intended to integrate a MediaPipe based on Grounding DINO and a Vision-Language-Action (VLA) model with a custom-built drone equipped with a 1-DOF gripper and an Intel RealSense RGB-D camera. VLA performs semantic reasoning to interpret the intent of a user prompt and generates a prioritized task queue for grasping of relevant objects in the scene. Grounding DINO and dynamic A* planning algorithm are used to navigate and safely relocate the object. To ensure safe and natural interaction during the handover phase, the system employs a human-centric controller driven by MediaPipe. This module provides real-time human pose estimation, allowing the drone to employ visual servoing to maintain a stable, distinct position directly in front of the user, facilitating a comfortable handover. We demonstrate the system's efficacy through real-world experiments for localization and navigation, which resulted in a 0.164m, 0.070m, and 0.084m of max, mean euclidean, and root-mean squared errors, respectively, highlighting the feasibility of VLA for aerial manipulation operations.

---

### Knowledge Graph-Assisted LLM Post-Training for Enhanced Legal Reasoning

Authors: Dezhao Song, Guglielmo Bonifazi, Frank Schilder, Jonathan Richard Schwarz
Published: 2026-01-20
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.13806v1

LLM post-training has primarily relied on large text corpora and human feedback, without capturing the structure of domain knowledge. This has caused models to struggle dealing with complex reasoning tasks, especially for high-stakes professional domains. In Law, reasoning requires deep understanding of the relations between various legal concepts, a key component missing in current LLM post-training. In this paper, we propose a knowledge graph (KG)-assisted approach for enhancing LLMs' reasoning capability in Legal that is generalizable to other high-stakes domains. We model key legal concepts by following the \textbf{IRAC} (Issue, Rule, Analysis and Conclusion) framework, and construct a KG with 12K legal cases. We then produce training data using our IRAC KG, and conduct both Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) with three state-of-the-art (SOTA) LLMs (30B, 49B and 70B), varying architecture and base model family. Our post-trained models obtained better average performance on 4/5 diverse legal benchmarks (14 tasks) than baselines. In particular, our 70B DPO model achieved the best score on 4/6 reasoning tasks, among baselines and a 141B SOTA legal LLM, demonstrating the effectiveness of our KG for enhancing LLMs' legal reasoning capability.

---

### Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis

Authors: Yushen Chen, Junzhe Liu, Yujie Tu, Zhikang Niu, Yuzhe Liang, Chunyu Qiang, Chen Zhang, Kai Yu, Xie Chen
Published: 2026-01-20
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2601.13802v2

Arabic spans over 30 spoken varieties, yet no open-source text-to-speech system unifies them. Key barriers include substantial cross-dialect lexical and phonological divergence, scarce synthesis-grade data, and the absence of a standardized multi-dialect evaluation benchmark. We present Habibi, a unified-dialectal Arabic TTS framework that addresses all three. Through a multi-step curation pipeline, we repurpose open-source ASR corpora into TTS training data covering 12+ regional dialects. A linguistically-informed curriculum learning strategy - progressing from Modern Standard Arabic to dialectal data - enables robust zero-shot synthesis without text diacritization. We further release the first standardized multi-dialect Arabic TTS benchmark, comprising over 11,000 utterances across 7 dialect subsets with manually verified transcripts. On this benchmark, our unified model matches or surpasses per-dialect specialized models. Both automatic metrics and human evaluations confirm that Habibi is highly competitive with ElevenLabs' Eleven v3 (alpha) in intelligibility, speaker similarity, and naturalness. Extensive ablations (~8,000 H100 GPU hours, 30+ configurations) validate each design choice. We open-source all checkpoints, training and inference code, and benchmark data - the first such release for multi-dialect Arabic TTS - at https://SWivid.github.io/Habibi/ .

---

### CFM: Language-aligned Concept Foundation Model for Vision

Authors: Kai Wittenmayer, Sukrut Rao, Amin Parchami-Araghi, Bernt Schiele, Jonas Fischer
Published: 2026-01-20
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.13798v3

Language-aligned vision foundation models perform strongly across diverse downstream tasks. Yet, their learned representations remain opaque, making interpreting their decision-making difficult. Recent work decompose these representations into human-interpretable concepts, but provide poor spatial grounding and are limited to image classification tasks. In this work, we propose CFM, a language-aligned concept foundation model for vision that provides fine-grained concepts, which are human-interpretable and spatially grounded in the input image. When paired with a foundation model with strong semantic representations, we get explanations for any of its downstream tasks. Examining local co-occurrence dependencies of concepts allows us to define concept relationships through which we improve concept naming and obtain richer explanations. On benchmark data, we show that CFM provides performance on classification, segmentation, and captioning that is competitive with opaque foundation models while providing fine-grained, high quality concept-based explanations. Code at https://github.com/kawi19/CFM. Interactive visualizations at https://concept-foundation-model.mpi-inf.mpg.de.

---

### PREGEN: Uncovering Latent Thoughts in Composed Video Retrieval

Authors: Gabriele Serussi, David Vainshtein, Jonathan Kouchly, Dotan Di Castro, Chaim Baskin
Published: 2026-01-20
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.13797v1

Composed Video Retrieval (CoVR) aims to retrieve a video based on a query video and a modifying text. Current CoVR methods fail to fully exploit modern Vision-Language Models (VLMs), either using outdated architectures or requiring computationally expensive fine-tuning and slow caption generation. We introduce PREGEN (PRE GENeration extraction), an efficient and powerful CoVR framework that overcomes these limitations. Our approach uniquely pairs a frozen, pre-trained VLM with a lightweight encoding model, eliminating the need for any VLM fine-tuning. We feed the query video and modifying text into the VLM and extract the hidden state of the final token from each layer. A simple encoder is then trained on these pooled representations, creating a semantically rich and compact embedding for retrieval. PREGEN significantly advances the state of the art, surpassing all prior methods on standard CoVR benchmarks with substantial gains in Recall@1 of +27.23 and +69.59. Our method demonstrates robustness across different VLM backbones and exhibits strong zero-shot generalization to more complex textual modifications, highlighting its effectiveness and semantic capabilities.

---

### PAtt: A Pattern Attention Network for ETA Prediction Using Historical Speed Profiles

Authors: ByeoungDo Kim, JunYeop Na, Kyungwook Tak, JunTae Kim, DongHyeon Kim, Duckky Kim
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.13793v1

In this paper, we propose an ETA model (Estimated Time of Arrival) that leverages an attention mechanism over historical road speed patterns. As autonomous driving and intelligent transportation systems become increasingly prevalent, the need for accurate and reliable ETA estimation has grown, playing a vital role in navigation, mobility planning, and traffic management. However, predicting ETA remains a challenging task due to the dynamic and complex nature of traffic flow. Traditional methods often combine real-time and historical traffic data in simplistic ways, or rely on complex rule-based computations. While recent deep learning models have shown potential, they often require high computational costs and do not effectively capture the spatio-temporal patterns crucial for ETA prediction. ETA prediction inherently involves spatio-temporal causality, and our proposed model addresses this by leveraging attention mechanisms to extract and utilize temporal features accumulated at each spatio-temporal point along a route. This architecture enables efficient and accurate ETA estimation while keeping the model lightweight and scalable. We validate our approach using real-world driving datasets and demonstrate that our approach outperforms existing baselines by effectively integrating road characteristics, real-time traffic conditions, and historical speed patterns in a task-aware manner.

---

### Principled Latent Diffusion for Graphs via Laplacian Autoencoders

Authors: Antoine Siraudin, Christopher Morris
Published: 2026-01-20
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.13780v3

Graph diffusion models achieve state-of-the-art performance in graph generation but suffer from quadratic complexity in the number of nodes -- and much of their capacity is wasted modeling the absence of edges in sparse graphs. Inspired by latent diffusion in other modalities, a natural idea is to compress graphs into a low-dimensional latent space and perform diffusion in that space. However, unlike images or text, graph generation requires nearly lossless reconstruction, as even a single error in decoding an adjacency matrix can render the entire sample invalid. This challenge has remained largely unaddressed. We propose LG-Flow, a latent graph diffusion framework that directly overcomes these obstacles. A permutation-equivariant autoencoder maps nodes to fixed-dimensional embeddings that enable near-lossless reconstruction of both undirected graphs and DAGs. The dimensionality of this latent representation scales linearly with the number of nodes, thereby removing the quadratic adjacency-space bottleneck in the diffusion process and enabling the training of substantially larger generative backbones. In this latent space, we train a Diffusion Transformer with flow matching, enabling efficient and expressive graph generation. Our approach achieves competitive results against state-of-the-art graph diffusion models while delivering up to a $1000\times$ speed-up. Our code is available at https://github.com/asiraudin/LG-Flow .

---

### Orthogonium : A Unified, Efficient Library of Orthogonal and 1-Lipschitz Building Blocks

Authors: Thibaut Boissin, Franck Mamalet, Valentin Lafargue, Mathieu Serrurier
Published: 2026-01-20
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.13776v1

Orthogonal and 1-Lipschitz neural network layers are essential building blocks in robust deep learning architectures, crucial for certified adversarial robustness, stable generative models, and reliable recurrent networks. Despite significant advancements, existing implementations remain fragmented, limited, and computationally demanding. To address these issues, we introduce Orthogonium , a unified, efficient, and comprehensive PyTorch library providing orthogonal and 1-Lipschitz layers. Orthogonium provides access to standard convolution features-including support for strides, dilation, grouping, and transposed-while maintaining strict mathematical guarantees. Its optimized implementations reduce overhead on large scale benchmarks such as ImageNet. Moreover, rigorous testing within the library has uncovered critical errors in existing implementations, emphasizing the importance of standardized and reliable tools. Orthogonium thus significantly lowers adoption barriers, enabling scalable experimentation and integration across diverse applications requiring orthogonality and robust Lipschitz constraints. Orthogonium is available at https://github.com/deel-ai/orthogonium.

---

### Look-Ahead-Bench: a Standardized Benchmark of Look-ahead Bias in Point-in-Time LLMs for Finance

Authors: Mostapha Benhenda
Published: 2026-01-20
Categories: cs.AI, cs.CL, cs.LG, q-fin.CP, q-fin.GN
arXiv: https://arxiv.org/abs/2601.13770v1

We introduce Look-Ahead-Bench, a standardized benchmark measuring look-ahead bias in Point-in-Time (PiT) Large Language Models (LLMs) within realistic and practical financial workflows. Unlike most existing approaches that primarily test inner lookahead knowledge via Q\\&A, our benchmark evaluates model behavior in practical scenarios. To distinguish genuine predictive capability from memorization-based performance, we analyze performance decay across temporally distinct market regimes, incorporating several quantitative baselines to establish performance thresholds. We evaluate prominent open-source LLMs -- Llama 3.1 (8B and 70B) and DeepSeek 3.2 -- against a family of Point-in-Time LLMs (Pitinf-Small, Pitinf-Medium, and frontier-level model Pitinf-Large) from PiT-Inference. Results reveal significant lookahead bias in standard LLMs, as measured with alpha decay, unlike Pitinf models, which demonstrate improved generalization and reasoning abilities as they scale in size. This work establishes a foundation for the standardized evaluation of temporal bias in financial LLMs and provides a practical framework for identifying models suitable for real-world deployment. Code is available on GitHub: https://github.com/benstaf/lookaheadbench

---

### vLinear: A Powerful Linear Model for Multivariate Time Series Forecasting

Authors: Wenzhen Yue, Ruohao Guo, Ji Shi, Zihan Hao, Shiyu Hu, Xianghua Ying
Published: 2026-01-20
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.13768v1

In this paper, we present \textbf{vLinear}, an effective yet efficient \textbf{linear}-based multivariate time series forecaster featuring two components: the \textbf{v}ecTrans module and the WFMLoss objective. Many state-of-the-art forecasters rely on self-attention or its variants to capture multivariate correlations, typically incurring $\mathcal{O}(N^2)$ computational complexity with respect to the number of variates $N$. To address this, we propose vecTrans, a lightweight module that utilizes a learnable vector to model multivariate correlations, reducing the complexity to $\mathcal{O}(N)$. Notably, vecTrans can be seamlessly integrated into Transformer-based forecasters, delivering up to 5$\times$ inference speedups and consistent performance gains. Furthermore, we introduce WFMLoss (Weighted Flow Matching Loss) as the objective. In contrast to typical \textbf{velocity-oriented} flow matching objectives, we demonstrate that a \textbf{final-series-oriented} formulation yields significantly superior forecasting accuracy. WFMLoss also incorporates path- and horizon-weighted strategies to focus learning on more reliable paths and horizons. Empirically, vLinear achieves state-of-the-art performance across 22 benchmarks and 124 forecasting settings. Moreover, WFMLoss serves as an effective plug-and-play objective, consistently improving existing forecasters. The code is available at https://anonymous.4open.science/r/vLinear.

---

### DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution

Authors: Shengda Fan, Xuyan Ye, Yankai Lin
Published: 2026-01-20
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.13761v2

Self-play with large language models has emerged as a promising paradigm for achieving self-improving artificial intelligence. However, existing self-play frameworks often suffer from optimization instability, due to (i) non-stationary objectives induced by solver-dependent reward feedback for the Questioner, and (ii) bootstrapping errors from self-generated pseudo-labels used to supervise the Solver. To mitigate these challenges, we introduce DARC (Decoupled Asymmetric Reasoning Curriculum), a two-stage framework that stabilizes the self-evolution process. First, we train the Questioner to synthesize difficulty-calibrated questions, conditioned on explicit difficulty levels and external corpora. Second, we train the Solver with an asymmetric self-distillation mechanism, where a document-augmented teacher generates high-quality pseudo-labels to supervise the student Solver that lacks document access. Empirical results demonstrate that DARC is model-agnostic, yielding an average improvement of 10.9 points across nine reasoning benchmarks and three backbone models. Moreover, DARC consistently outperforms all baselines and approaches the performance of fully supervised models without relying on human annotations. The code is available at https://github.com/RUCBM/DARC.

---

### Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering

Authors: Chak Tou Leong, Dingwei Chen, Heming Xia, Qingyu Yin, Sunbowen Lee, Jian Wang, Wenjie Li
Published: 2026-01-20
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.13752v1

Large reasoning models (LRMs) have achieved remarkable success in complex problem-solving, yet they often suffer from computational redundancy or reasoning unfaithfulness. Current methods for shaping LRM behavior typically rely on reinforcement learning or fine-tuning with gold-standard reasoning traces, a paradigm that is both computationally expensive and difficult to scale. In this paper, we reveal that LRMs possess latent \textit{reasoning beliefs} that internally track their own reasoning traits, which can be captured through simple logit probing. Building upon this insight, we propose Reasoning Belief Engineering (RELIEF), a simple yet effective framework that shapes LRM behavior by aligning the model's self-concept with a target belief blueprint. Crucially, RELIEF completely bypasses the need for reasoning-trace supervision. It internalizes desired traits by fine-tuning on synthesized, self-reflective question-answering pairs that affirm the target belief. Extensive experiments on efficiency and faithfulness tasks demonstrate that RELIEF matches or outperforms behavior-supervised and preference-based baselines while requiring lower training costs. Further analysis validates that shifting a model's reasoning belief effectively shapes its actual behavior.

---

### Towards Onboard Continuous Change Detection for Floods

Authors: Daniel Kyselica, Jonáš Herec, Oliver Kutis, Rado Pitoňák
Published: 2026-01-20
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.13751v3

Natural disaster monitoring through continuous satellite observation requires processing multi-temporal data under strict operational constraints. This paper addresses flood detection, a critical application for hazard management, by developing an onboard change detection system that operates within the memory and computational limits of small satellites. We propose History Injection mechanism for Transformer models (HiT), that maintains historical context from previous observations while reducing data storage by over 99\% of original image size. Moreover, testing on the STTORM-CD flood dataset confirms that the HiT mechanism within the Prithvi-tiny foundation model maintains detection accuracy compared to the bi-temporal baseline. The proposed HiT-Prithvi model achieved 43 FPS on Jetson Orin Nano, a representative onboard hardware used in nanosats. This work establishes a practical framework for satellite-based continuous monitoring of natural disasters, supporting real-time hazard assessment without dependency on ground-based processing infrastructure. Architecture as well as model checkpoints is available at https://github.com/zaitra/HiT-change-detection .

---

### Pro-AI Bias in Large Language Models

Authors: Benaya Trabelsi, Jonathan Shaki, Sarit Kraus
Published: 2026-01-20
Categories: cs.CL, cs.AI, cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2601.13749v1

Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in favor of artificial intelligence (AI) itself. Across three complementary experiments, we find consistent evidence of pro-AI bias. First, we show that LLMs disproportionately recommend AI-related options in response to diverse advice-seeking queries, with proprietary models doing so almost deterministically. Second, we demonstrate that models systematically overestimate salaries for AI-related jobs relative to closely matched non-AI jobs, with proprietary models overestimating AI salaries more by 10 percentage points. Finally, probing internal representations of open-weight models reveals that ``Artificial Intelligence'' exhibits the highest similarity to generic prompts for academic fields under positive, negative, and neutral framings alike, indicating valence-invariant representational centrality. These patterns suggest that LLM-generated advice and valuation can systematically skew choices and perceptions in high-stakes decisions.

---