# Research Papers — 2026-01 · bundle page 42 of 189

> Full-text markdown of papers #2051–2100 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/42
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/41.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/43.md)

### Learn and Verify: A Framework for Rigorous Verification of Physics-Informed Neural Networks

Authors: Kazuaki Tanaka, Kohei Yatabe
Published: 2026-01-27
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2601.19818v1

The numerical solution of differential equations using neural networks has become a central topic in scientific computing, with Physics-Informed Neural Networks (PINNs) emerging as a powerful paradigm for both forward and inverse problems. However, unlike classical numerical methods that offer established convergence guarantees, neural network-based approximations typically lack rigorous error bounds. Furthermore, the non-deterministic nature of their optimization makes it difficult to mathematically certify their accuracy. To address these challenges, we propose a "Learn and Verify" framework that provides computable, mathematically rigorous error bounds for the solutions of differential equations. By combining a novel Doubly Smoothed Maximum (DSM) loss for training with interval arithmetic for verification, we compute rigorous a posteriori error bounds as machine-verifiable proofs. Numerical experiments on nonlinear Ordinary Differential Equations (ODEs), including problems with time-varying coefficients and finite-time blow-up, demonstrate that the proposed framework successfully constructs rigorous enclosures of the true solutions, establishing a foundation for trustworthy scientific machine learning.

---

### Revisiting Incremental Stochastic Majorization-Minimization Algorithms with Applications to Mixture of Experts

Authors: TrungKhang Tran, TrungTin Nguyen, Gersende Fort, Tung Doan, Hien Duy Nguyen, Binh T. Nguyen, Florence Forbes, Christopher Drovandi
Published: 2026-01-27
Categories: stat.ML, cs.AI, cs.LG, math.ST, stat.ME
arXiv: https://arxiv.org/abs/2601.19811v1

Processing high-volume, streaming data is increasingly common in modern statistics and machine learning, where batch-mode algorithms are often impractical because they require repeated passes over the full dataset. This has motivated incremental stochastic estimation methods, including the incremental stochastic Expectation-Maximization (EM) algorithm formulated via stochastic approximation. In this work, we revisit and analyze an incremental stochastic variant of the Majorization-Minimization (MM) algorithm, which generalizes incremental stochastic EM as a special case. Our approach relaxes key EM requirements, such as explicit latent-variable representations, enabling broader applicability and greater algorithmic flexibility. We establish theoretical guarantees for the incremental stochastic MM algorithm, proving consistency in the sense that the iterates converge to a stationary point characterized by a vanishing gradient of the objective. We demonstrate these advantages on a softmax-gated mixture of experts (MoE) regression problem, for which no stochastic EM algorithm is available. Empirically, our method consistently outperforms widely used stochastic optimizers, including stochastic gradient descent, root mean square propagation, adaptive moment estimation, and second-order clipped stochastic optimization. These results support the development of new incremental stochastic algorithms, given the central role of softmax-gated MoE architectures in contemporary deep neural networks for heterogeneous data modeling. Beyond synthetic experiments, we also validate practical effectiveness on two real-world datasets, including a bioinformatics study of dent maize genotypes under drought stress that integrates high-dimensional proteomics with ecophysiological traits, where incremental stochastic MM yields stable gains in predictive performance.

---

### Unsupervised Learning of Efficient Exploration: Pre-training Adaptive Policies via Self-Imposed Goals

Authors: Octavio Pappalardo
Published: 2026-01-27
Categories: cs.LG, cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2601.19810v2

Unsupervised pre-training can equip reinforcement learning agents with prior knowledge and accelerate learning in downstream tasks. A promising direction, grounded in human development, investigates agents that learn by setting and pursuing their own goals. The core challenge lies in how to effectively generate, select, and learn from such goals. Our focus is on broad distributions of downstream tasks where solving every task zero-shot is infeasible. Such settings naturally arise when the target tasks lie outside of the pre-training distribution or when their identities are unknown to the agent. In this work, we (i) optimize for efficient multi-episode exploration and adaptation within a meta-learning framework, and (ii) guide the training curriculum with evolving estimates of the agent's post-adaptation performance. We present ULEE, an unsupervised meta-learning method that combines an in-context learner with an adversarial goal-generation strategy that maintains training at the frontier of the agent's capabilities. On XLand-MiniGrid benchmarks, ULEE pre-training yields improved exploration and adaptation abilities that generalize to novel objectives, environment dynamics, and map structures. The resulting policy attains improved zero-shot and few-shot performance, and provides a strong initialization for longer fine-tuning processes. It outperforms learning from scratch, DIAYN pre-training, and alternative curricula. Code is available at: https://github.com/Octavio-Pappalardo/ulee-jax

---

### Zero-Shot Stance Detection in the Wild: Dynamic Target Generation and Multi-Target Adaptation

Authors: Aohua Li, Yuanshuo Zhang, Ge Gao, Bo Chen, Xiaobing Zhao
Published: 2026-01-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.19802v3

Current stance detection research typically relies on predicting stance based on given targets and text. However, in real-world social media scenarios, targets are neither predefined nor static but rather complex and dynamic. To address this challenge, we propose a novel task: zero-shot stance detection in the wild with Dynamic Target Generation and Multi-Target Adaptation (DGTA), which aims to automatically identify multiple target-stance pairs from text without prior target knowledge. We construct a Chinese social media stance detection dataset and design multi-dimensional evaluation metrics. We explore both integrated and two-stage fine-tuning strategies for large language models (LLMs) and evaluate various baseline models. Experimental results demonstrate that fine-tuned LLMs achieve superior performance on this task: the two-stage fine-tuned Qwen2.5-7B attains the highest comprehensive target recognition score of 66.99%, while the integrated fine-tuned DeepSeek-R1-Distill-Qwen-7B achieves a stance detection F1 score of 79.26%.

---

### Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

Authors: Zhixiang Wei, Yi Li, Zhehan Kan, Xinghua Jiang, Zuwei Long, Shifeng Liu, Hongze Shen, Wei Liu, Xiaoyu Tan, Haojia Lin, Yubo Zhu, Qianyu Li et al.
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19798v1

Despite the significant advancements represented by Vision-Language Models (VLMs), current architectures often exhibit limitations in retaining fine-grained visual information, leading to coarse-grained multimodal comprehension. We attribute this deficiency to a suboptimal training paradigm inherent in prevailing VLMs, which exhibits a text-dominant optimization bias by conceptualizing visual signals merely as passive conditional inputs rather than supervisory targets. To mitigate this, we introduce Youtu-VL, a framework leveraging the Vision-Language Unified Autoregressive Supervision (VLUAS) paradigm, which fundamentally shifts the optimization objective from ``vision-as-input'' to ``vision-as-target.'' By integrating visual tokens directly into the prediction stream, Youtu-VL applies unified autoregressive supervision to both visual details and linguistic content. Furthermore, we extend this paradigm to encompass vision-centric tasks, enabling a standard VLM to perform vision-centric tasks without task-specific additions. Extensive empirical evaluations demonstrate that Youtu-VL achieves competitive performance on both general multimodal tasks and vision-centric tasks, establishing a robust foundation for the development of comprehensive generalist visual agents.

---

### Diffusion for De-Occlusion: Accessory-Aware Diffusion Inpainting for Robust Ear Biometric Recognition

Authors: Deeksha Arun, Kevin W. Bowyer, Patrick Flynn
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19795v1

Ear occlusions (arising from the presence of ear accessories such as earrings and earphones) can negatively impact performance in ear-based biometric recognition systems, especially in unconstrained imaging circumstances. In this study, we assess the effectiveness of a diffusion-based ear inpainting technique as a pre-processing aid to mitigate the issues of ear accessory occlusions in transformer-based ear recognition systems. Given an input ear image and an automatically derived accessory mask, the inpainting model reconstructs clean and anatomically plausible ear regions by synthesizing missing pixels while preserving local geometric coherence along key ear structures, including the helix, antihelix, concha, and lobule. We evaluate the effectiveness of this pre-processing aid in transformer-based recognition systems for several vision transformer models and different patch sizes for a range of benchmark datasets. Experiments show that diffusion-based inpainting can be a useful pre-processing aid to alleviate ear accessory occlusions to improve overall recognition performance.

---

### Component-Aware Pruning Framework for Neural Network Controllers via Gradient-Based Importance Estimation

Authors: Ganesh Sundaram, Jonas Ulmen, Daniel Görges
Published: 2026-01-27
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2601.19794v1

The transition from monolithic to multi-component neural architectures in advanced neural network controllers poses substantial challenges due to the high computational complexity of the latter. Conventional model compression techniques for complexity reduction, such as structured pruning based on norm-based metrics to estimate the relative importance of distinct parameter groups, often fail to capture functional significance. This paper introduces a component-aware pruning framework that utilizes gradient information to compute three distinct importance metrics during training: Gradient Accumulation, Fisher Information, and Bayesian Uncertainty. Experimental results with an autoencoder and a TD-MPC agent demonstrate that the proposed framework reveals critical structural dependencies and dynamic shifts in importance that static heuristics often miss, supporting more informed compression decisions.

---

### CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing

Authors: Shanyv Liu, Xuyang Yuan, Tao Chen, Zijun Zhan, Zhu Han, Danyang Zheng, Weishan Zhang, Shaohua Cao
Published: 2026-01-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.19793v1

Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware Strategy for Task Efficient Routing), a lightweight router for dynamic model selection in graph-based MAS. CASTER employs a Dual-Signal Router that combines semantic embeddings with structural meta-features to estimate task difficulty. During training, the router self-optimizes through a Cold Start to Iterative Evolution paradigm, learning from its own routing failures via on-policy negative feedback. Experiments using LLM-as-a-Judge evaluation across Software Engineering, Data Analysis, Scientific Discovery, and Cybersecurity demonstrate that CASTER reduces inference cost by up to 72.4% compared to strong-model baselines while matching their success rates, and consistently outperforms both heuristic routing and FrugalGPT across all domains.

---

### LVLMs and Humans Ground Differently in Referential Communication

Authors: Peter Zeng, Weiling Li, Amie J. Paige, Zhengxiang Wang, Panagiotis Kaliosis, Dimitris Samaras, Gregory Zelinsky, Susan E. Brennan, Owen Rambow
Published: 2026-01-27
Categories: cs.CL, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.19792v5

For generative AI agents to partner effectively with human users, the ability to accurately predict human intent is critical. But this ability to collaborate remains limited by a critical deficit: an inability to model common ground. We present a referential communication experiment with a factorial design involving director-matcher pairs (human-human, human-AI, AI-human, and AI-AI) that interact with multiple turns in repeated rounds to match pictures of objects not associated with any obvious lexicalized labels. We show that LVLMs cannot interactively generate and resolve referring expressions in a way that enables smooth communication, a crucial skill that underlies human language use. We release our corpus of 356 dialogues (89 pairs over 4 rounds each) along with the online pipeline for data collection and the tools for analyzing accuracy, efficiency, and lexical overlap.

---

### To Grok Grokking: Provable Grokking in Ridge Regression

Authors: Mingyue Xu, Gal Vardi, Itay Safran
Published: 2026-01-27
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.19791v4

We study grokking, the onset of generalization long after overfitting, in a classical ridge regression setting. We prove end-to-end grokking results for learning over-parameterized linear regression models using gradient descent with weight decay. Specifically, we prove that the following stages occur: (i) the model overfits the training data early during training; (ii) poor generalization persists long after overfitting has manifested; and (iii) the generalization error eventually becomes arbitrarily small. Moreover, we show, both theoretically and empirically, that grokking can be amplified or eliminated in a principled manner through proper hyperparameter tuning. To the best of our knowledge, these are the first rigorous quantitative bounds on the generalization delay (which we refer to as the "grokking time") in terms of training hyperparameters. Lastly, going beyond the linear setting, we empirically demonstrate that our quantitative bounds also capture the behavior of grokking on non-linear neural networks. Our results suggest that grokking is not an inherent failure mode of deep learning, but rather a consequence of specific training conditions, and thus does not require fundamental changes to the model architecture or learning algorithm to avoid.

---

### Knowledge-Aware Evolution for Task-Free Streaming Federated Continual Learning with Arbitrary Class Overlap

Authors: Sixing Tan, Xianmin Liu
Published: 2026-01-27
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2601.19788v2

Federated Continual Learning (FCL) leverages inter-client collaboration to better balance new knowledge acquisition and old knowledge retention on non-stationary data. However, existing FCL methods struggle to adapt to streaming scenarios where sequential and ephemerally accessible data chunks lack task identifiers and exhibit arbitrary class overlap, leading to confusion between old and new knowledge and an inability to sustain local inference on all encountered classes. To address this, we propose FedKACE with three components: 1) an adaptive mechanism that determines when to switch the inference model from the local to the global one to improve client-side inference performance; 2) a responsive gradient-balanced replay scheme that utilizes the ratio of the squared L2 gradient norms to balance client-specific knowledge between new acquisition and old retention; 3) a holistic buffer maintenance strategy that preserves highly informative and boundary-significant samples to enhance knowledge retention under class overlap.Experiments across multiple scenarios and theoretical analysis demonstrate the effectiveness of FedKACE.

---

### Rethinking Discrete Speech Representation Tokens for Accent Generation

Authors: Jinzuomu Zhong, Yi Wang, Korin Richmond, Peter Bell
Published: 2026-01-27
Categories: eess.AS, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2601.19786v2

Discrete Speech Representation Tokens (DSRTs) have become a foundational component in speech generation. While prior work has extensively studied phonetic and speaker information in DSRTs, how accent information is encoded in DSRTs remains largely unexplored. In this paper, we present the first systematic investigation of accent information in DSRTs. We propose a unified evaluation framework that measures both accessibility of accent information via a novel Accent ABX task and recoverability via cross-accent Voice Conversion (VC) resynthesis. Using this framework, we analyse DSRTs derived from several widely used speech representations. Our results reveal that: (1) choice of layers has the most significant impact on retaining accent information, (2) accent information is substantially reduced by ASR supervision; (3) naive codebook size reduction cannot effectively disentangle accent from phonetic and speaker information.

---

### GeoDiff3D: Self-Supervised 3D Scene Generation with Geometry-Constrained 2D Diffusion Guidance

Authors: Haozhi Zhu, Miaomiao Zhao, Dingyao Liu, Runze Tian, Yan Zhang, Jie Guo, Fenggen Yu
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19785v2

3D scene generation is a core technology for gaming, film/VFX, and VR/AR. Growing demand for rapid iteration, high-fidelity detail, and accessible content creation has further increased interest in this area. Existing methods broadly follow two paradigms - indirect 2D-to-3D reconstruction and direct 3D generation - but both are limited by weak structural modeling and heavy reliance on large-scale ground-truth supervision, often producing structural artifacts, geometric inconsistencies, and degraded high-frequency details in complex scenes. We propose GeoDiff3D, an efficient self-supervised framework that uses coarse geometry as a structural anchor and a geometry-constrained 2D diffusion model to provide texture-rich reference images. Importantly, GeoDiff3D does not require strict multi-view consistency of the diffusion-generated references and remains robust to the resulting noisy, inconsistent guidance. We further introduce voxel-aligned 3D feature aggregation and dual self-supervision to maintain scene coherence and fine details while substantially reducing dependence on labeled data. GeoDiff3D also trains with low computational cost and enables fast, high-quality 3D scene generation. Extensive experiments on challenging scenes show improved generalization and generation quality over existing baselines, offering a practical solution for accessible and efficient 3D scene construction.

---

### Reimagining Peer Review Process Through Multi-Agent Mechanism Design

Authors: Ahmad Farooq, Kamran Iqbal
Published: 2026-01-27
Categories: cs.MA, cs.AI, cs.CY, cs.GT, cs.SE
arXiv: https://arxiv.org/abs/2601.19778v1

The software engineering research community faces a systemic crisis: peer review is failing under growing submissions, misaligned incentives, and reviewer fatigue. Community surveys reveal that researchers perceive the process as "broken." This position paper argues that these dysfunctions are mechanism design failures amenable to computational solutions. We propose modeling the research community as a stochastic multi-agent system and applying multi-agent reinforcement learning to design incentive-compatible protocols. We outline three interventions: a credit-based submission economy, MARL-optimized reviewer assignment, and hybrid verification of review consistency. We present threat models, equity considerations, and phased pilot metrics. This vision charts a research agenda toward sustainable peer review.

---

### Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosis

Authors: Zhuohan Long, Zhijie Bao, Zhongyu Wei
Published: 2026-01-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.19773v1

Interactive medical consultation requires an agent to proactively elicit missing clinical evidence under uncertainty. Yet existing evaluations largely remain static or outcome-centric, neglecting the evidence-gathering process. In this work, we propose an interactive evaluation framework that explicitly models the consultation process using a simulated patient and a \rev{simulated reporter} grounded in atomic evidences. Based on this representation, we introduce Information Coverage Rate (ICR) to quantify how completely an agent uncovers necessary evidence during interaction. To support systematic study, we build EviMed, an evidence-based benchmark spanning diverse conditions from common complaints to rare diseases, and evaluate 10 models with varying reasoning abilities. We find that strong diagnostic reasoning does not guarantee effective information collection, and this insufficiency acts as a primary bottleneck limiting performance in interactive settings. To address this, we propose REFINE, a strategy that leverages diagnostic verification to guide the agent in proactively resolving uncertainties. Extensive experiments demonstrate that REFINE consistently outperforms baselines across diverse datasets and facilitates effective model collaboration, enabling smaller agents to achieve superior performance under strong reasoning supervision. Our code can be found at https://github.com/NanshineLoong/EID-Benchmark .

---

### PaW-ViT: A Patch-based Warping Vision Transformer for Robust Ear Verification

Authors: Deeksha Arun, Kevin W. Bowyer, Patrick Flynn
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19771v1

The rectangular tokens common to vision transformer methods for visual recognition can strongly affect performance of these methods due to incorporation of information outside the objects to be recognized. This paper introduces PaW-ViT, Patch-based Warping Vision Transformer, a preprocessing approach rooted in anatomical knowledge that normalizes ear images to enhance the efficacy of ViT. By accurately aligning token boundaries to detected ear feature boundaries, PaW-ViT obtains greater robustness to shape, size, and pose variation. By aligning feature boundaries to natural ear curvature, it produces more consistent token representations for various morphologies. Experiments confirm the effectiveness of PaW-ViT on various ViT models (ViT-T, ViT-S, ViT-B, ViT-L) and yield reasonable alignment robustness to variation in shape, size, and pose. Our work aims to solve the disconnect between ear biometric morphological variation and transformer architecture positional sensitivity, presenting a possible avenue for authentication schemes.

---

### GAVEL: Towards Rule-Based Safety Through Activation Monitoring

Authors: Shir Rozenfeld, Rahul Pankajakshan, Itay Zloczower, Eyal Lenga, Gilad Gressel, Yisroel Mirsky
Published: 2026-01-27
Categories: cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.19768v3

Large language models (LLMs) are increasingly paired with activation-based monitoring to detect and prevent harmful behaviors that may not be apparent at the surface-text level. However, existing activation safety approaches, trained on broad misuse datasets, struggle with poor precision, limited flexibility, and lack of interpretability. This paper introduces a new paradigm: rule-based activation safety, inspired by rule-sharing practices in cybersecurity. We propose modeling activations as cognitive elements (CEs), fine-grained, interpretable factors such as 'making a threat' and 'payment processing', that can be composed to capture nuanced, domain-specific behaviors with higher precision. Building on this representation, we present a practical framework that defines predicate rules over CEs and detects violations in real time. This enables practitioners to configure and update safeguards without retraining models or detectors, while supporting transparency and auditability. Our results show that compositional rule-based activation safety improves precision, supports domain customization, and lays the groundwork for scalable, interpretable, and auditable AI governance. We open source GAVEL and introduce GAVEL Studio, an interactive rule authoring and management tool. Code and datasets are available at github.com/Offensive-AI-Lab/gavel.

---

### The Effect of Architecture During Continual Learning

Authors: Allyson Hahn, Krishnan Raghavan
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19766v1

Continual learning is a challenge for models with static architecture, as they fail to adapt to when data distributions evolve across tasks. We introduce a mathematical framework that jointly models architecture and weights in a Sobolev space, enabling a rigorous investigation into the role of neural network architecture in continual learning and its effect on the forgetting loss. We derive necessary conditions for the continual learning solution and prove that learning only model weights is insufficient to mitigate catastrophic forgetting under distribution shifts. Consequently, we prove that by learning the architecture and weights simultaneously at each task, we can reduce catastrophic forgetting. To learn weights and architecture simultaneously, we formulate continual learning as a bilevel optimization problem: the upper level selects an optimal architecture for a given task, while the lower level computes optimal weights via dynamic programming over all tasks. To solve the upper level problem, we introduce a derivative-free direct search algorithm to determine the optimal architecture. Once found, we must transfer knowledge from the current architecture to the optimal one. However, the optimal architecture will result in a weights parameter space different from the current architecture (i.e., dimensions of weights matrices will not match). To bridge the dimensionality gap, we develop a low-rank transfer mechanism to map knowledge across architectures of mismatched dimensions. Empirical studies across regression and classification problems, including feedforward, convolutional, and graph neural networks, demonstrate that learning the optimal architecture and weights simultaneously yields substantially improved performance (up to two orders of magnitude), reduced forgetting, and enhanced robustness to noise compared with static architecture approaches.

---

### Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining

Authors: Yunwei Ren, Yatin Dandi, Florent Krzakala, Jason D. Lee
Published: 2026-01-27
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.19756v2

The empirical success of deep learning is often attributed to deep networks' ability to exploit hierarchical structure in data, constructing increasingly complex features across layers. Yet despite substantial progress in deep learning theory, most optimization results sill focus on networks with only two or three layers, leaving the theoretical understanding of hierarchical learning in genuinely deep models limited. This leads to a natural question: can we prove that deep networks, trained with gradient-based methods and standard input-label pairs, can efficiently exploit hierarchical structure? In this work, we consider Random Hierarchy Models -- a hierarchical context-free grammar introduced by arXiv:2307.02129 and conjectured to separate deep and shallow networks. We prove that, under mild conditions, a deep convolutional network can be efficiently trained to learn this function class. Our proof builds on a general observation: if intermediate layers can receive clean signal from the labels and the relevant features are weakly identifiable, then layerwise training each individual layer suffices to hierarchically learn the target function.

---

### Regularized $f$-Divergence Kernel Tests

Authors: Mónica Ribero, Antonin Schrab, Arthur Gretton
Published: 2026-01-27
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.19755v1

We propose a framework to construct practical kernel-based two-sample tests from the family of $f$-divergences. The test statistic is computed from the witness function of a regularized variational representation of the divergence, which we estimate using kernel methods. The proposed test is adaptive over hyperparameters such as the kernel bandwidth and the regularization parameter. We provide theoretical guarantees for statistical test power across our family of $f$-divergence estimates. While our test covers a variety of $f$-divergences, we bring particular focus to the Hockey-Stick divergence, motivated by its applications to differential privacy auditing and machine unlearning evaluation. For two-sample testing, experiments demonstrate that different $f$-divergences are sensitive to different localized differences, illustrating the importance of leveraging diverse statistics. For machine unlearning, we propose a relative test that distinguishes true unlearning failures from safe distributional variations.

---

### WaterClear-GS: Optical-Aware Gaussian Splatting for Underwater Reconstruction and Restoration

Authors: Xinrui Zhang, Yufeng Wang, Zesheng Wang, Dacheng Qi, Wenrui Ding, Shuangkang Fang
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19753v2

Underwater 3D reconstruction and appearance restoration remain challenging due to the complex optical properties of water, such as wavelength-dependent attenuation and scattering. Existing Neural Radiance Fields (NeRF)-based approaches often suffer from slow rendering and limited practicality, while vanilla 3D Gaussian Splatting (3DGS) lacks an effective mechanism to account for underwater degradation. To address this, we propose WaterClear-GS, a physics-informed reformulation of underwater Gaussian splatting that models degradation as intrinsic Gaussian attributes rather than external medium fields. Furthermore, we adopt a dual-branch optimization strategy that preserves underwater photometric consistency while encouraging a practical separation between restoration-oriented latent clean appearance and degradation. This strategy is enhanced by depth-guided geometry regularization and perception-driven image supervision, together with exposure constraints, spatially adaptive regularization, and physics-informed spectral regularization, which collectively promote spatial coherence and plausible visual appearance. Extensive experiments on standard benchmarks and our collected dataset demonstrate that WaterClear-GS achieves strong performance on both novel view synthesis (NVS) and underwater image restoration (UIR) tasks, while maintaining 160+ FPS real-time rendering. The code will be available at https://sherii888.github.io/WaterClear-GS/.

---

### Agentic Design Patterns: A System-Theoretic Framework

Authors: Minh-Dung Dao, Quy Minh Le, Hoang Thanh Lam, Duc-Trong Le, Quoc-Viet Pham, Barry O'Sullivan, Hoang D. Nguyen
Published: 2026-01-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.19752v1

With the development of foundation model (FM), agentic AI systems are getting more attention, yet their inherent issues like hallucination and poor reasoning, coupled with the frequent ad-hoc nature of system design, lead to unreliable and brittle applications. Existing efforts to characterise agentic design patterns often lack a rigorous systems-theoretic foundation, resulting in high-level or convenience-based taxonomies that are difficult to implement. This paper addresses this gap by introducing a principled methodology for engineering robust AI agents. We propose two primary contributions: first, a novel system-theoretic framework that deconstructs an agentic AI system into five core, interacting functional subsystems: Reasoning & World Model, Perception & Grounding, Action Execution, Learning & Adaptation, and Inter-Agent Communication. Second, derived from this architecture and directly mapped to a comprehensive taxonomy of agentic challenges, we present a collection of 12 agentic design patterns. These patterns - categorised as Foundational, Cognitive & Decisional, Execution & Interaction, and Adaptive & Learning - offer reusable, structural solutions to recurring problems in agent design. The utility of the framework is demonstrated by a case study on the ReAct framework, showing how the proposed patterns can rectify systemic architectural deficiencies. This work provides a foundational language and a structured methodology to standardise agentic design communication among researchers and engineers, leading to more modular, understandable, and reliable autonomous systems.

---

### Benchmarking Multimodal Large Language Models for Missing Modality Completion in Product Catalogues

Authors: Junchen Fu, Wenhao Deng, Kaiwen Zheng, Ioannis Arapakis, Yu Ye, Yongxin Ni, Joemon M. Jose, Xuri Ge
Published: 2026-01-27
Categories: cs.MM, cs.CV, cs.IR
arXiv: https://arxiv.org/abs/2601.19750v2

Missing-modality information on e-commerce platforms, such as absent product images or textual descriptions, often arises from annotation errors or incomplete metadata, impairing both product presentation and downstream applications such as recommendation systems. Motivated by the multimodal generative capabilities of recent Multimodal Large Language Models (MLLMs), this work investigates a fundamental yet underexplored question: can MLLMs generate missing modalities for products in e-commerce scenarios? We propose the Missing Modality Product Completion Benchmark (MMPCBench), which consists of two sub-benchmarks: a Content Quality Completion Benchmark and a Recommendation Benchmark. We further evaluate six state-of-the-art MLLMs from the Qwen2.5-VL and Gemma-3 model families across nine real-world e-commerce categories, focusing on image-to-text and text-to-image completion tasks. Experimental results show that while MLLMs can capture high-level semantics, they struggle with fine-grained word-level and pixel- or patch-level alignment. In addition, performance varies substantially across product categories and model scales, and we observe no trivial correlation between model size and performance, in contrast to trends commonly reported in mainstream benchmarks. We also explore Group Relative Policy Optimization (GRPO) to better align MLLMs with this task. GRPO improves image-to-text completion but does not yield gains for text-to-image completion. Overall, these findings expose the limitations of current MLLMs in real-world cross-modal generation and represent an early step toward more effective missing-modality product completion.

---

### Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation

Authors: Jiale Liu, Taiyu Zhou, Tianqi Jiang
Published: 2026-01-27
Categories: cs.AR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2601.19747v1

In the rapidly evolving field of Electronic Design Automation (EDA), the deployment of Large Language Models (LLMs) for Register-Transfer Level (RTL) design has emerged as a promising direction. However, silicon-grade correctness remains bottlenecked by: (i) limited test coverage and reliability of simulation-centric evaluation, (ii) regressions and repair hallucinations introduced by iterative debugging, and (iii) semantic drift as intent is reinterpreted across agent handoffs. In this work, we propose Veri-Sure, a multi-agent framework that establishes a design contract to align agents' intent and uses a patching mechanism guided by static dependency slicing to perform precise, localized repairs. By integrating a multi-branch verification pipeline that combines trace-driven temporal analysis with formal verification consisting of assertion-based checking and boolean equivalence proofs, Veri-Sure enables functional correctness beyond pure simulations. We also introduce VerilogEval-v2-EXT, extending the original benchmark with 53 more industrial-grade design tasks and stratified difficulty levels, and show that Veri-Sure achieves state-of-the-art verified-correct RTL code generation performance, surpassing standalone LLMs and prior agentic systems.

---

### GraphDLG: Exploring Deep Leakage from Gradients in Federated Graph Learning

Authors: Shuyue Wei, Wantong Chen, Tongyu Wei, Chen Gong, Yongxin Tong, Lizhen Cui
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19745v1

Federated graph learning (FGL) has recently emerged as a promising privacy-preserving paradigm that enables distributed graph learning across multiple data owners. A critical privacy concern in federated learning is whether an adversary can recover raw data from shared gradients, a vulnerability known as deep leakage from gradients (DLG). However, most prior studies on the DLG problem focused on image or text data, and it remains an open question whether graphs can be effectively recovered, particularly when the graph structure and node features are uniquely entangled in GNNs. In this work, we first theoretically analyze the components in FGL and derive a crucial insight: once the graph structure is recovered, node features can be obtained through a closed-form recursive rule. Building on this analysis, we propose GraphDLG, a novel approach to recover raw training graphs from shared gradients in FGL, which can utilize randomly generated graphs or client-side training graphs as auxiliaries to enhance recovery. Extensive experiments demonstrate that GraphDLG outperforms existing solutions by successfully decoupling the graph structure and node features, achieving improvements of over 5.46% (by MSE) for node feature reconstruction and over 25.04% (by AUC) for graph structure reconstruction.

---

### Interpretable and backpropagation-free Green Learning for efficient multi-task echocardiographic segmentation and classification

Authors: Jyun-Ping Kao, Jiaxin Yang, C. -C. Jay Kuo, Jonghye Woo
Published: 2026-01-27
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.19743v3

Echocardiography is a cornerstone for managing heart failure (HF), with Left Ventricular Ejection Fraction (LVEF) being a critical metric for guiding therapy. However, manual LVEF assessment suffers from high inter-observer variability, while existing Deep Learning (DL) models are often computationally intensive and data-hungry "black boxes" that impede clinical trust and adoption. Here, we propose a backpropagation-free multi-task Green Learning (MTGL) framework that performs simultaneous Left Ventricle (LV) segmentation and LVEF classification. Our framework integrates an unsupervised VoxelHop encoder for hierarchical spatio-temporal feature extraction with a multi-level regression decoder and an XG-Boost classifier. On the EchoNet-Dynamic dataset, our MTGL model achieves state-of-the-art classification and segmentation performance, attaining a classification accuracy of 94.3% and a Dice Similarity Coefficient (DSC) of 0.912, significantly outperforming several advanced 3D DL models. Crucially, our model achieves this with over an order of magnitude fewer parameters, demonstrating exceptional computational efficiency. This work demonstrates that the GL paradigm can deliver highly accurate, efficient, and interpretable solutions for complex medical image analysis, paving the way for more sustainable and trustworthy artificial intelligence in clinical practice.

---

### TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching

Authors: Runjia Zeng, Qifan Wang, Qiang Guan, Ruixiang Tang, Lifu Huang, Zhenting Wang, Xueling Zhang, Cheng Han, Dongfang Liu
Published: 2026-01-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.19739v1

Fine tuning has been regarded as a de facto approach for adapting large language models (LLMs) to downstream tasks, but the high training memory consumption inherited from LLMs makes this process inefficient. Among existing memory efficient approaches, activation-related optimization has proven particularly effective, as activations consistently dominate overall memory consumption. Although prior arts offer various activation optimization strategies, their data-agnostic nature ultimately results in ineffective and unstable fine tuning. In this paper, we propose TokenSeek, a universal plugin solution for various transformer-based models through instance-aware token seeking and ditching, achieving significant fine-tuning memory savings (e.g., requiring only 14.8% of the memory on Llama3.2 1B) with on-par or even better performance. Furthermore, our interpretable token seeking process reveals the underlying reasons for its effectiveness, offering valuable insights for future research on token efficiency. Homepage: https://runjia.tech/iclr_tokenseek/

---

### Quantum Circuit Pre-Synthesis: Learning Local Edits to Reduce $T$-count

Authors: Daniele Lizzio Bosco, Lukasz Cincio, Giuseppe Serra, M. Cerezo
Published: 2026-01-27
Categories: quant-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.19738v1

Compiling quantum circuits into Clifford+$T$ gates is a central task for fault-tolerant quantum computing using stabilizer codes. In the near term, $T$ gates will dominate the cost of fault tolerant implementations, and any reduction in the number of such expensive gates could mean the difference between being able to run a circuit or not. While exact synthesis is exponentially hard in the number of qubits, local synthesis approaches are commonly used to compile large circuits by decomposing them into substructures. However, composing local methods leads to suboptimal compilations in key metrics such as $T$-count or circuit depth, and their performance strongly depends on circuit representation. In this work, we address this challenge by proposing \textsc{Q-PreSyn}, a strategy that, given a set of local edits preserving circuit equivalence, uses a RL agent to identify effective sequences of such actions and thereby obtain circuit representations that yield a reduced $T$-count upon synthesis. Experimental results of our proposed strategy, applied on top of well-known synthesis algorithms, show up to a $20\%$ reduction in $T$-count on circuits with up to 25 qubits, without introducing any additional approximation error prior to synthesis.

---

### Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise

Authors: Hongxu Chen, Ke Wei, Xiaoming Yuan, Luo Luo
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19730v1

The empirical evidence indicates that stochastic optimization with heavy-tailed gradient noise is more appropriate to characterize the training of machine learning models than that with standard bounded gradient variance noise. Most existing works on this phenomenon focus on the convergence of optimization errors, while the analysis for generalization bounds under the heavy-tailed gradient noise remains limited. In this paper, we develop a general framework for establishing generalization bounds under heavy-tailed noise. Specifically, we introduce a truncation argument to achieve the generalization error bound based on the algorithmic stability under the assumption of bounded $p$th centered moment with $p\in(1,2)$. Building on this framework, we further provide the stability and generalization analysis for several popular stochastic algorithms under heavy-tailed noise, including clipped and normalized stochastic gradient descent, as well as their mini-batch and momentum variants.

---

### RvB: Automating AI System Hardening via Iterative Red-Blue Games

Authors: Lige Huang, Zicheng Liu, Jie Zhang, Lewen Yan, Dongrui Liu, Jing Shao
Published: 2026-01-27
Categories: cs.CR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.19726v1

The dual offensive and defensive utility of Large Language Models (LLMs) highlights a critical gap in AI security: the lack of unified frameworks for dynamic, iterative adversarial adaptation hardening. To bridge this gap, we propose the Red Team vs. Blue Team (RvB) framework, formulated as a training-free, sequential, imperfect-information game. In this process, the Red Team exposes vulnerabilities, driving the Blue Team to learning effective solutions without parameter updates. We validate our framework across two challenging domains: dynamic code hardening against CVEs and guardrail optimization against jailbreaks. Our empirical results show that this interaction compels the Blue Team to learn fundamental defensive principles, leading to robust remediations that are not merely overfitted to specific exploits. RvB achieves Defense Success Rates of 90\% and 45\% across the respective tasks while maintaining near 0\% False Positive Rates, significantly surpassing baselines. This work establishes the iterative adversarial interaction framework as a practical paradigm that automates the continuous hardening of AI systems.

---

### Component-Level Lesioning of Language Models Reveals Clinically Aligned Aphasia Phenotypes

Authors: Yifan Wang, Jichen Zheng, Jingyuan Sun, Yunhao Zhang, Chunyu Ye, Jixing Li, Chengqing Zong, Shaonan Wang
Published: 2026-01-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.19723v1

Large language models (LLMs) increasingly exhibit human-like linguistic behaviors and internal representations that they could serve as computational simulators of language cognition. We ask whether LLMs can be systematically manipulated to reproduce language-production impairments characteristic of aphasia following focal brain lesions. Such models could provide scalable proxies for testing rehabilitation hypotheses, and offer a controlled framework for probing the functional organization of language. We introduce a clinically grounded, component-level framework that simulates aphasia by selectively perturbing functional components in LLMs, and apply it to both modular Mixture-of-Experts models and dense Transformers using a unified intervention interface. Our pipeline (i) identifies subtype-linked components for Broca's and Wernicke's aphasia, (ii) interprets these components with linguistic probing tasks, and (iii) induces graded impairments by progressively perturbing the top-k subtype-linked components, evaluating outcomes with Western Aphasia Battery (WAB) subtests summarized by Aphasia Quotient (AQ). Across architectures and lesioning strategies, subtype-targeted perturbations yield more systematic, aphasia-like regressions than size-matched random perturbations, and MoE modularity supports more localized and interpretable phenotype-to-component mappings. These findings suggest that modular LLMs, combined with clinically informed component perturbations, provide a promising platform for simulating aphasic language production and studying how distinct language functions degrade under targeted disruptions.

---

### Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action

Authors: Gong Gao, Weidong Zhao, Xianhui Liu, Ning Jia
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19720v2

Existing value-based online reinforcement learning (RL) algorithms suffer from slow policy exploitation due to ineffective exploration and delayed policy updates. To address these challenges, we propose an algorithm called Instant Retrospect Action (IRA). Specifically, we propose Q-Representation Discrepancy Evolution (RDE) to facilitate Q-network representation learning, enabling discriminative representations for neighboring state-action pairs. In addition, we adopt an explicit method to policy constraints by enabling Greedy Action Guidance (GAG). This is achieved through backtracking historical actions, which effectively enhances the policy update process. Our proposed method relies on providing the learning algorithm with accurate $k$-nearest-neighbor action value estimates and learning to design a fast-adaptable policy through policy constraints. We further propose the Instant Policy Update (IPU) mechanism, which enhances policy exploitation by systematically increasing the frequency of policy updates. We further discover that the early-stage training conservatism of the IRA method can alleviate the overestimation bias problem in value-based RL. Experimental results show that IRA can significantly improve the learning efficiency and final performance of online RL algorithms on eight MuJoCo continuous control tasks.The code is available at https://github.com/2706853499/IRA.

---

### Rethinking Divisive Hierarchical Clustering from a Distributional Perspective

Authors: Kaifeng Zhang, Kai Ming Ting, Tianrun Liang, Qiuran Zhao
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19718v1

We uncover that current objective-based Divisive Hierarchical Clustering (DHC) methods produce a dendrogram that does not have three desired properties i.e., no unwarranted splitting, group similar clusters into a same subset, ground-truth correspondence. This shortcoming has their root cause in using a set-oriented bisecting assessment criterion. We show that this shortcoming can be addressed by using a distributional kernel, instead of the set-oriented criterion; and the resultant clusters achieve a new distribution-oriented objective to maximize the total similarity of all clusters (TSC). Our theoretical analysis shows that the resultant dendrogram guarantees a lower bound of TSC. The empirical evaluation shows the effectiveness of our proposed method on artificial and Spatial Transcriptomics (bioinformatics) datasets. Our proposed method successfully creates a dendrogram that is consistent with the biological regions in a Spatial Transcriptomics dataset, whereas other contenders fail.

---

### DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization

Authors: Yitong Yang, Xuexin Liu, Yinglin Wang, Jing Wang, Hao Dou, Changshuo Wang, Shuting He
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19717v1

3D style transfer enables the creation of visually expressive 3D content, enriching the visual appearance of 3D scenes and objects. However, existing VGG- and CLIP-based methods struggle to model multi-view consistency within the model itself, while diffusion-based approaches can capture such consistency but rely on denoising directions, leading to unstable training. To address these limitations, we propose DiffStyle3D, a novel diffusion-based paradigm for 3DGS style transfer that directly optimizes in the latent space. Specifically, we introduce an Attention-Aware Loss that performs style transfer by aligning style features in the self-attention space, while preserving original content through content feature alignment. Inspired by the geometric invariance of 3D stylization, we propose a Geometry-Guided Multi-View Consistency method that integrates geometric information into self-attention to enable cross-view correspondence modeling. Based on geometric information, we additionally construct a geometry-aware mask to prevent redundant optimization in overlapping regions across views, which further improves multi-view consistency. Extensive experiments show that DiffStyle3D outperforms state-of-the-art methods, achieving higher stylization quality and visual realism.

---

### Hyperbolic Additive Margin Softmax with Hierarchical Information for Speaker Verification

Authors: Zhihua Fang, Liang He
Published: 2026-01-27
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.19709v1

Speaker embedding learning based on Euclidean space has achieved significant progress, but it is still insufficient in modeling hierarchical information within speaker features. Hyperbolic space, with its negative curvature geometric properties, can efficiently represent hierarchical information within a finite volume, making it more suitable for the feature distribution of speaker embeddings. In this paper, we propose Hyperbolic Softmax (H-Softmax) and Hyperbolic Additive Margin Softmax (HAM-Softmax) based on hyperbolic space. H-Softmax incorporates hierarchical information into speaker embeddings by projecting embeddings and speaker centers into hyperbolic space and computing hyperbolic distances. HAM-Softmax further enhances inter-class separability by introducing margin constraint on this basis. Experimental results show that H-Softmax and HAM-Softmax achieve average relative EER reductions of 27.84% and 14.23% compared with standard Softmax and AM-Softmax, respectively, demonstrating that the proposed methods effectively improve speaker verification performance and at the same time preserve the capability of hierarchical structure modeling. The code will be released at https://github.com/PunkMale/HAM-Softmax.

---

### Scalable Exploration for High-Dimensional Continuous Control via Value-Guided Flow

Authors: Yunyue Wei, Chenhui Zuo, Yanan Sui
Published: 2026-01-27
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2601.19707v1

Controlling high-dimensional systems in biological and robotic applications is challenging due to expansive state-action spaces, where effective exploration is critical. Commonly used exploration strategies in reinforcement learning are largely undirected with sharp degradation as action dimensionality grows. Many existing methods resort to dimensionality reduction, which constrains policy expressiveness and forfeits system flexibility. We introduce Q-guided Flow Exploration (Qflex), a scalable reinforcement learning method that conducts exploration directly in the native high-dimensional action space. During training, Qflex traverses actions from a learnable source distribution along a probability flow induced by the learned value function, aligning exploration with task-relevant gradients rather than isotropic noise. Our proposed method substantially outperforms representative online reinforcement learning baselines across diverse high-dimensional continuous-control benchmarks. Qflex also successfully controls a full-body human musculoskeletal model to perform agile, complex movements, demonstrating superior scalability and sample efficiency in very high-dimensional settings. Our results indicate that value-guided flows offer a principled and practical route to exploration at scale.

---

### SAM Audio Judge: A Unified Multimodal Framework for Perceptual Evaluation of Audio Separation

Authors: Helin Wang, Bowen Shi, Andros Tjandra, John Hoffman, Yi-Chiao Wu, Apoorv Vyas, Najim Dehak, Ann Lee, Wei-Ning Hsu
Published: 2026-01-27
Categories: eess.AS, cs.AI
arXiv: https://arxiv.org/abs/2601.19702v1

The performance evaluation remains a complex challenge in audio separation, and existing evaluation metrics are often misaligned with human perception, course-grained, relying on ground truth signals. On the other hand, subjective listening tests remain the gold standard for real-world evaluation, but they are expensive, time-consuming, and difficult to scale. This paper addresses the growing need for automated systems capable of evaluating audio separation without human intervention. The proposed evaluation metric, SAM Audio Judge (SAJ), is a multimodal fine-grained reference-free objective metric, which shows highly alignment with human perceptions. SAJ supports three audio domains (speech, music and general sound events) and three prompt inputs (text, visual and span), covering four different dimensions of evaluation (recall, percision, faithfulness, and overall). SAM Audio Judge also shows potential applications in data filtering, pseudo-labeling large datasets and reranking in audio separation models. We release our code and pre-trained models at: https://github.com/facebookresearch/sam-audio.

---

### Generalizable Multimodal Large Language Model Editing via Invariant Trajectory Learning

Authors: Jiajie Su, Haoyuan Wang, Xiaohua Feng, Yunshan Ma, Xiaobo Xia, Yuyuan Li, Xiaolin Zheng, Jianmao Xiao, Chaochao Chen
Published: 2026-01-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.19700v2

Knowledge editing emerges as a crucial technique for efficiently correcting incorrect or outdated knowledge in large language models (LLM). Existing editing methods rely on a rigid mapping from parameter or module modifications to output, which causes the generalization limitation in Multimodal LLM (MLLM). In this paper, we reformulate MLLM editing as an out-of-distribution (OOD) generalization problem, where the goal is to discern semantic shift with factual shift and thus achieve robust editing among diverse cross-modal prompting. The key challenge of this OOD problem lies in identifying invariant causal trajectories that generalize accurately while suppressing spurious correlations. To address it, we propose ODEdit, a plug-and-play invariant learning based framework that optimizes the tripartite OOD risk objective to simultaneously enhance editing reliability, locality, and generality.We further introduce an edit trajectory invariant learning method, which integrates a total variation penalty into the risk minimization objective to stabilize edit trajectories against environmental variations. Theoretical analysis and extensive experiments demonstrate the effectiveness of ODEdit.

---

### AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion

Authors: Tianyue Jiang, Yanli Wang, Yanlin Wang, Daya Guo, Ensheng Shi, Yuchi Ma, Jiachi Chen, Zibin Zheng
Published: 2026-01-27
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.19697v2

Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context and domain knowledge. While retrieval-augmented generation (RAG) approaches have shown promise by retrieving relevant code snippets as cross-file context, they suffer from two fundamental problems: misalignment between the query and the target code in the retrieval process, and the inability of existing retrieval methods to effectively utilize the inference information. To address these challenges, we propose AlignCoder, a repository-level code completion framework that introduces a query enhancement mechanism and a reinforcement learning based retriever training method. Our approach generates multiple candidate completions to construct an enhanced query that bridges the semantic gap between the initial query and the target code. Additionally, we employ reinforcement learning to train an AlignRetriever that learns to leverage inference information in the enhanced query for more accurate retrieval. We evaluate AlignCoder on two widely-used benchmarks (CrossCodeEval and RepoEval) across five backbone code LLMs, demonstrating an 18.1% improvement in EM score compared to baselines on the CrossCodeEval benchmark. The results show that our framework achieves superior performance and exhibits high generalizability across various code LLMs and programming languages.

---

### Self-Supervised Weight Templates for Scalable Vision Model Initialization

Authors: Yucheng Xie, Fu Feng, Ruixiao Shi, Jing Wang, Yong Rui, Xin Geng
Published: 2026-01-27
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.19694v1

The increasing scale and complexity of modern model parameters underscore the importance of pre-trained models. However, deployment often demands architectures of varying sizes, exposing limitations of conventional pre-training and fine-tuning. To address this, we propose SWEET, a self-supervised framework that performs constraint-based pre-training to enable scalable initialization in vision tasks. Instead of pre-training a fixed-size model, we learn a shared weight template and size-specific weight scalers under Tucker-based factorization, which promotes modularity and supports flexible adaptation to architectures with varying depths and widths. Target models are subsequently initialized by composing and reweighting the template through lightweight weight scalers, whose parameters can be efficiently learned from minimal training data. To further enhance flexibility in width expansion, we introduce width-wise stochastic scaling, which regularizes the template along width-related dimensions and encourages robust, width-invariant representations for improved cross-width generalization. Extensive experiments on \textsc{classification}, \textsc{detection}, \textsc{segmentation} and \textsc{generation} tasks demonstrate the state-of-the-art performance of SWEET for initializing variable-sized vision models.

---

### DSVM-UNet : Enhancing VM-UNet with Dual Self-distillation for Medical Image Segmentation

Authors: Renrong Shao, Dongyang Li, Dong Xia, Lin Shao, Jiangdong Lu, Fen Zheng, Lulu Zhang
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19690v2

Vision Mamba models have been extensively researched in various fields, which address the limitations of previous models by effectively managing long-range dependencies with a linear-time overhead. Several prospective studies have further designed Vision Mamba based on UNet(VM-UNet) for medical image segmentation. These approaches primarily focus on optimizing architectural designs by creating more complex structures to enhance the model's ability to perceive semantic features. In this paper, we propose a simple yet effective approach to improve the model by Dual Self-distillation for VM-UNet (DSVM-UNet) without any complex architectural designs. To achieve this goal, we develop double self-distillation methods to align the features at both the global and local levels. Extensive experiments conducted on the ISIC2017, ISIC2018, and Synapse benchmarks demonstrate that our approach achieves state-of-the-art performance while maintaining computational efficiency. Code is available at https://github.com/RoryShao/DSVM-UNet.git.

---

### Video-KTR: Reinforcing Video Reasoning via Key Token Attribution

Authors: Ziyue Wang, Sheng Jin, Zhongrong Zuo, Jiawei Wu, Han Qiu, Qi She, Hao Zhang, Xudong Jiang
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19686v1

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection, neglecting fine-grained links among visual inputs, temporal dynamics, and linguistic outputs, limiting both accuracy and interpretability. We propose Video-KTR, a modality-aware policy shaping framework that performs selective, token-level RL by combining three attribution signals: (1) visual-aware tokens identified via counterfactual masking to reveal perceptual dependence; (2) temporal-aware tokens detected through frame shuffling to expose temporal sensitivity; and (3) high-entropy tokens signaling predictive uncertainty. By reinforcing only these key tokens, Video-KTR focuses learning on semantically informative, modality-sensitive content while filtering out low-value tokens. Across five challenging benchmarks, Video-KTR achieves state-of-the-art or highly competitive results, achieving 42.7\% on Video-Holmes (surpassing GPT-4o) with consistent gains on both reasoning and general video understanding tasks. Ablation studies verify the complementary roles of the attribution signals and the robustness of targeted token-level updates. Overall, Video-KTR improves accuracy and interpretability, offering a simple, drop-in extension to RL for complex video reasoning. Our code and models are available at https://github.com/zywang0104/Video-KTR.

---

### SharpNet: Enhancing MLPs to Represent Functions with Controlled Non-differentiability

Authors: Hanting Niu, Junkai Deng, Fei Hou, Wencheng Wang, Ying He
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19683v2

Multi-layer perceptrons (MLPs) are a standard tool for learning and function approximation, but they inherently produce globally smooth outputs. Consequently, they struggle to represent functions that are continuous yet intentionally non-differentiable (i.e., functions with prescribed $C^0$ sharp features) without ad hoc post-processing. We present SharpNet, a modified MLP architecture that encodes user-specified sharp features by augmenting the network with an auxiliary feature function defined as the solution to Poisson's equation with jump Neumann boundary conditions. This feature function is evaluated via an efficient local integral and is fully differentiable with respect to the feature locations, allowing us to jointly optimize both the feature locations and the MLP parameters to recover the target function or geometry. This construction provides precise control over where non-differentiability occurs, enforcing the desired $C^0$ behavior at feature locations while preserving smoothness elsewhere. We validate SharpNet on 2D problems and 3D CAD reconstruction, and compare it with several state-of-the-art baselines. In both settings, SharpNet accurately recovers sharp edges and corners while remaining smooth away from them, whereas existing methods tend to blur gradient discontinuities. Qualitative and quantitative results demonstrate the effectiveness of our approach. Our project page, code and models are publicly available at https://sharpnettech.github.io.

---

### A new Image Similarity Metric for a Perceptual and Transparent Geometric and Chromatic Assessment

Authors: Antonio Di Marino, Vincenzo Bevilacqua, Emanuel Di Nardo, Angelo Ciaramella, Ivanoe De Falco, Giovanna Sannino
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19680v1

In the literature, several studies have shown that state-of-the-art image similarity metrics are not perceptual metrics; moreover, they have difficulty evaluating images, especially when texture distortion is also present. In this work, we propose a new perceptual metric composed of two terms. The first term evaluates the dissimilarity between the textures of two images using Earth Mover's Distance. The second term evaluates the chromatic dissimilarity between two images in the Oklab perceptual color space. We evaluated the performance of our metric on a non-traditional dataset, called Berkeley-Adobe Perceptual Patch Similarity, which contains a wide range of complex distortions in shapes and colors. We have shown that our metric outperforms the state of the art, especially when images contain shape distortions, confirming also its greater perceptiveness. Furthermore, although deep black-box metrics could be very accurate, they only provide similarity scores between two images, without explaining their main differences and similarities. Our metric, on the other hand, provides visual explanations to support the calculated score, making the similarity assessment transparent and justified.

---

### LoPRo: Enhancing Low-Rank Quantization via Permuted Block-Wise Rotation

Authors: Hongyaoxing Gu, Lijuan Hu, Liye Yu, Haowei Li, Fangfang Liu
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19675v1

Post-training quantization (PTQ) enables effective model compression while preserving relatively high accuracy. Current weight-only PTQ methods primarily focus on the challenging sub-3-bit regime, where approaches often suffer significant accuracy degradation, typically requiring fine-tuning to achieve competitive performance. In this work, we revisit the fundamental characteristics of weight quantization and analyze the challenges in quantizing the residual matrix under low-rank approximation. We propose LoPRo, a novel fine-tuning-free PTQ algorithm that enhances residual matrix quantization by applying block-wise permutation and Walsh-Hadamard transformations to rotate columns of similar importance, while explicitly preserving the quantization accuracy of the most salient column blocks. Furthermore, we introduce a mixed-precision fast low-rank decomposition based on rank-1 sketch (R1SVD) to further minimize quantization costs. Experiments demonstrate that LoPRo outperforms existing fine-tuning-free PTQ methods at both 2-bit and 3-bit quantization, achieving accuracy comparable to fine-tuning baselines. Specifically, LoPRo achieves state-of-the-art quantization accuracy on LLaMA-2 and LLaMA-3 series models while delivering up to a 4$\times$ speedup. In the MoE model Mixtral-8x7B, LoPRo completes quantization within 2.5 hours, simultaneously reducing perplexity by 0.4$\downarrow$ and improving accuracy by 8\%$\uparrow$. Moreover, compared to other low-rank quantization methods, LoPRo achieves superior accuracy with a significantly lower rank, while maintaining high inference efficiency and minimal additional latency.

---

### Cross-Domain Offshore Wind Power Forecasting: Transfer Learning Through Meteorological Clusters

Authors: Dominic Weisser, Chloé Hashimoto-Cullen, Benjamin Guedj
Published: 2026-01-27
Categories: cs.LG, cs.AI, stat.AP, stat.ME
arXiv: https://arxiv.org/abs/2601.19674v2

Ambitious decarbonisation targets are rapidly increasing the commission of new offshore wind farms. For these newly commissioned plants to run, accurate power forecasts are needed from the onset. These allow grid stability, good reserve management and efficient energy trading. Despite machine learning models having strong performances, they tend to require large volumes of site-specific data that new farms do not yet have. To overcome this data scarcity, we propose a novel transfer learning framework that clusters power output according to covariate meteorological features. Rather than training a single, general-purpose model, we thus forecast with an ensemble of expert models, each trained on a cluster. As these pre-trained models each specialise in a distinct weather pattern, they adapt efficiently to new sites and capture transferable, climate-dependent dynamics. Our contributions are two-fold - we propose this novel framework and comprehensively evaluate it on eight offshore wind farms, achieving accurate cross-domain forecasting with under five months of site-specific data. Our experiments achieve a MAE of 3.52\%, providing empirical verification that reliable forecasts do not require a full annual cycle. Beyond power forecasting, this climate-aware transfer learning method opens new opportunities for offshore wind applications such as early-stage wind resource assessment, where reducing data requirements can significantly accelerate project development whilst effectively mitigating its inherent risks.

---

### A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models

Authors: Iwona Christop, Mateusz Czyżnikiewicz, Paweł Skórzewski, Łukasz Bondaruk, Jakub Kubiak, Marcin Lewandowski, Marek Kubis
Published: 2026-01-27
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.19673v1

The present benchmarks for testing the audio modality of multimodal large language models concentrate on testing various audio tasks such as speaker diarization or gender identification in isolation. Whether a multimodal model can answer the questions that require reasoning skills to combine audio tasks of different categories, cannot be verified with their use. To address this issue, we propose Audio Reasoning Tasks (ART), a new benchmark for assessing the ability of multimodal models to solve problems that require reasoning over audio signal.

---

### ProToken: Token-Level Attribution for Federated Large Language Models

Authors: Waris Gill, Ahmad Humayun, Ali Anwar, Muhammad Ali Gulzar
Published: 2026-01-27
Categories: cs.LG, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2601.19672v2

Federated Learning (FL) enables collaborative training of Large Language Models (LLMs) across distributed data sources while preserving privacy. However, when federated LLMs are deployed in critical applications, it remains unclear which client(s) contributed to specific generated responses, hindering debugging, malicious client identification, fair reward allocation, and trust verification. We present ProToken, a novel Provenance methodology for Token-level attribution in federated LLMs that addresses client attribution during autoregressive text generation while maintaining FL privacy constraints. ProToken leverages two key insights to enable provenance at each token: (1) transformer architectures concentrate task-specific signals in later blocks, enabling strategic layer selection for computational tractability, and (2) gradient-based relevance weighting filters out irrelevant neural activations, focusing attribution on neurons that directly influence token generation. We evaluate ProToken across 16 configurations spanning four LLM architectures (Gemma, Llama, Qwen, SmolLM) and four domains (medical, financial, mathematical, coding). ProToken achieves 98% average attribution accuracy in correctly localizing responsible client(s), and maintains high accuracy when the number of clients are scaled, validating its practical viability for real-world deployment settings.

---

### Grasynda: Graph-based Synthetic Time Series Generation

Authors: Luis Amorim, Moises Santos, Paulo J. Azevedo, Carlos Soares, Vitor Cerqueira
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19668v1

Data augmentation is a crucial tool in time series forecasting, especially for deep learning architectures that require a large training sample size to generalize effectively. However, extensive datasets are not always available in real-world scenarios. Although many data augmentation methods exist, their limitations include the use of transformations that do not adequately preserve data properties. This paper introduces Grasynda, a novel graph-based approach for synthetic time series generation that: (1) converts univariate time series into a network structure using a graph representation, where each state is a node and each transition is represented as a directed edge; and (2) encodes their temporal dynamics in a transition probability matrix. We performed an extensive evaluation of Grasynda as a data augmentation method for time series forecasting. We use three neural network variations on six benchmark datasets. The results indicate that Grasynda consistently outperforms other time series data augmentation methods, including ones used in state-of-the-art time series foundation models. The method and all experiments are publicly available.

---

### SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking

Authors: Adam Remaki, Christel Gérardin, Eulàlia Farré-Maduell, Martin Krallinger, Xavier Tannier
Published: 2026-01-27
Categories: cs.CL, cs.AI, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2601.19667v3

We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in supervised biomedical entity linking (BEL): the scarcity of expert-annotated training data. SynCABEL leverages large language models to generate context-rich synthetic training examples for all candidate concepts in a target knowledge base, providing broad supervision without manual annotation. We demonstrate that SynCABEL, when combined with decoder-only models and guided inference, establishes new state-of-the-art results across three widely used multilingual benchmarks: MedMentions for English, QUAERO for French, and SPACCC for Spanish. Evaluating data efficiency, we show that SynCABEL reaches the performance of full human supervision using up to 60% less annotated data, substantially reducing reliance on labor-intensive and costly expert labeling. Finally, acknowledging that standard evaluation based on exact code matching often underestimates clinically valid predictions due to ontology redundancy, we introduce an LLM-as-a-judge protocol. This analysis reveals that SynCABEL significantly improves the rate of clinically valid predictions. Our synthetic datasets, models, and code are released to support reproducibility and future research.

---