# Research Papers — 2026-02 · bundle page 173 of 210

> Full-text markdown of papers #8601–8650 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/173
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/172.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/174.md)

### REDistill: Robust Estimator Distillation for Balancing Robustness and Efficiency

Authors: Ondrej Tybl, Lukas Neumann
Published: 2026-02-04
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.04677v1

Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student by aligning their predictive distributions. However, conventional KD formulations - typically based on Kullback-Leibler divergence - assume that the teacher provides reliable soft targets. In practice, teacher predictions are often noisy or overconfident, and existing correction-based approaches rely on ad-hoc heuristics and extensive hyper-parameter tuning, which hinders generalization. We introduce REDistill (Robust Estimator Distillation), a simple yet principled framework grounded in robust statistics. REDistill replaces the standard KD objective with a power divergence loss, a generalization of KL divergence that adaptively downweights unreliable teacher output while preserving informative logit relationships. This formulation provides a unified and interpretable treatment of teacher noise, requires only logits, integrates seamlessly into existing KD pipelines, and incurs negligible computational overhead. Extensive experiments on CIFAR-100 and ImageNet-1k demonstrate that REDistill consistently improves student accuracy in diverse teacher-student architectures. Remarkably, it achieves these gains without model-specific hyper-parameter tuning, underscoring its robustness and strong generalization to unseen teacher-student pairs.

---

### Generalized Schrödinger Bridge on Graphs

Authors: Panagiotis Theodoropoulos, Juno Nam, Evangelos Theodorou, Jaemoo Choi
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04675v2

Transportation on graphs is a fundamental challenge across many domains, where decisions must respect topological and operational constraints. Despite the need for actionable policies, existing graph-transport methods lack this expressivity. They rely on restrictive assumptions, fail to generalize across sparse topologies, and scale poorly with graph size and time horizon. To address these issues, we introduce Generalized Schrödinger Bridge on Graphs (GSBoG), a novel scalable data-driven framework for learning executable controlled continuous-time Markov chain (CTMC) policies on arbitrary graphs under state cost augmented dynamics. Notably, GSBoG learns trajectory-level policies, avoiding dense global solvers and thereby enhancing scalability. This is achieved via a likelihood optimization approach, satisfying the endpoint marginals, while simultaneously optimizing intermediate behavior under state-dependent running costs. Extensive experimentation on challenging real-world graph topologies shows that GSBoG reliably learns accurate, topology-respecting policies while optimizing application-specific intermediate state costs, highlighting its broad applicability and paving new avenues for cost-aware dynamical transport on general graphs.

---

### Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility

Authors: Eun Cheol Choi, Lindsay E. Young, Emilio Ferrara
Published: 2026-02-04
Categories: cs.SI, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.04674v2

Large language models (LLMs) are increasingly used as proxies for human judgment in computational social science, yet their ability to reproduce patterns of susceptibility to misinformation remains unclear. We test whether LLM-simulated survey respondents, prompted with participant profiles drawn from social survey data measuring network, demographic, attitudinal and behavioral features, can reproduce human patterns of misinformation belief and sharing. Using three online surveys as baselines, we evaluate whether LLM outputs match observed response distributions and recover feature-outcome associations present in the original survey data. LLM-generated responses capture broad distributional tendencies and show modest correlation with human responses, but consistently overstate the association between belief and sharing. Linear models fit to simulated responses exhibit substantially higher explained variance and place disproportionate weight on attitudinal and behavioral features, while largely ignoring personal network characteristics, relative to models fit to human responses. Analyses of model-generated reasoning and LLM training data suggest that these distortions reflect systematic biases in how misinformation-related concepts are represented. Our findings suggest that LLM-based survey simulations are better suited for diagnosing systematic divergences from human judgment than for substituting it.

---

### AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation

Authors: Jin-Chuan Shi, Binhong Ye, Tao Liu, Junzhe He, Yangjinhui Xu, Xiaoyang Liu, Zeju Li, Hao Chen, Chunhua Shen
Published: 2026-02-04
Categories: cs.CV, cs.GR, cs.RO
arXiv: https://arxiv.org/abs/2602.04672v4

Reconstructing dynamic hand-object interactions from monocular videos is critical for dexterous manipulation data collection and creating realistic digital twins for robotics and VR. However, current methods face two prohibitive barriers: (1) reliance on neural rendering often yields fragmented, non-simulation-ready geometries under heavy occlusion, and (2) dependence on brittle Structure-from-Motion (SfM) initialization leads to frequent failures on in-the-wild footage. To overcome these limitations, we introduce AGILE, a robust framework that shifts the paradigm from reconstruction to agentic generation for interaction learning. First, we employ an agentic pipeline where a Vision-Language Model (VLM) guides a generative model to synthesize a complete, watertight object mesh with high-fidelity texture, independent of video occlusions. Second, bypassing fragile SfM entirely, we propose a robust anchor-and-track strategy. We initialize the object pose at a single interaction onset frame using a foundation model and propagate it temporally by leveraging the strong visual similarity between our generated asset and video observations. Finally, a contact-aware optimization integrates semantic, geometric, and interaction stability constraints to enforce physical plausibility. Extensive experiments on HO3D, DexYCB, ARCTIC, and in-the-wild videos reveal that AGILE outperforms baselines in global geometric accuracy while demonstrating exceptional robustness on challenging sequences where prior arts frequently collapse. By prioritizing physical validity, our method produces simulation-ready assets validated via real-to-sim retargeting for robotic applications. Project page: https://agile-hoi.github.io.

---

### Delving into Muon and Beyond: Deep Analysis and Extensions

Authors: Xianbiao Qi, Marco Chen, Jiaquan Ye, Yelin He, Rong Xiao
Published: 2026-02-04
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.04669v1

The Muon optimizer has recently attracted considerable attention for its strong empirical performance and use of orthogonalized updates on matrix-shaped parameters, yet its underlying mechanisms and relationship to adaptive optimizers such as Adam remain insufficiently understood. In this work, we aim to address these questions through a unified spectral perspective. Specifically, we view Muon as the p = 0 endpoint of a family of spectral transformations of the form U \boldsymbolΣ^{p} V' , and consider additional variants with p = 1/2 , p = 1/4 , and p = 1 . These transformations are applied to both first-moment updates, as in momentum SGD, and to root-mean-square (RMS) normalized gradient updates as in Adam. To enable efficient computation, we develop a coupled Newton iteration that avoids explicit singular value decomposition. Across controlled experiments, we find that RMS-normalized updates yield more stable optimization than first-moment updates. Moreover, while spectral compression provides strong stabilization benefits under first-moment updates, the Muon update (p = 0) does not consistently outperform Adam. These results suggest that Muon is best understood as an effective form of spectral normalization, but not a universally superior optimization method. Our source code will be released at https://github.com/Ocram7/BeyondMuon.

---

### Causal explanations of outliers in systems with lagged time-dependencies

Authors: Philipp Alexander Schwarz, Johannes Oberpriller, Sven Klaassen
Published: 2026-02-04
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.04667v1

Root-cause analysis in controlled time dependent systems poses a major challenge in applications. Especially energy systems are difficult to handle as they exhibit instantaneous as well as delayed effects and if equipped with storage, do have a memory. In this paper we adapt the causal root-cause analysis method of Budhathoki et al. (2022) to general time-dependent systems, as it can be regarded as a strictly causal definition of the term "root-cause". Particularly, we discuss two truncation approaches to handle the infinite dependency graphs present in time-dependent systems. While one leaves the causal mechanisms intact, the other approximates the mechanisms at the start nodes. The effectiveness of the different approaches is benchmarked using a challenging data generation process inspired by a problem in factory energy management: the avoidance of peaks in the power consumption. We show that given enough lags our extension is able to localize the root-causes in the feature and time domain. Further the effect of mechanism approximation is discussed.

---

### Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

Authors: Jaemoo Choi, Yuchen Zhu, Wei Guo, Petr Molodyk, Bo Yuan, Jinbin Bai, Yi Xin, Molei Tao, Yongxin Chen
Published: 2026-02-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.04663v3

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide a systematic analysis of the RL design space by disentangling three factors: i) policy-gradient objectives, ii) likelihood estimators, and iii) rollout sampling schemes. We show that adopting an evidence lower bound (ELBO) based model likelihood estimator, computed only from the final generated sample, is the dominant factor enabling effective, efficient, and stable RL optimization, outweighing the impact of the specific policy-gradient loss functional. We validate our findings across multiple reward benchmarks using SD 3.5 Medium, and observe consistent trends across all tasks. Our method improves the GenEval score from 0.24 to 0.95 in 90 GPU hours, which is 4.6 times more efficient than FlowGRPO and $2\times$ more efficient than the SOTA method without reward hacking.

---

### Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

Authors: Jaemoo Choi, Yuchen Zhu, Wei Guo, Petr Molodyk, Bo Yuan, Jinbin Bai, Yi Xin, Molei Tao, Yongxin Chen
Published: 2026-02-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.04663v2

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide a systematic analysis of the RL design space by disentangling three factors: i) policy-gradient objectives, ii) likelihood estimators, and iii) rollout sampling schemes. We show that adopting an evidence lower bound (ELBO) based model likelihood estimator, computed only from the final generated sample, is the dominant factor enabling effective, efficient, and stable RL optimization, outweighing the impact of the specific policy-gradient loss functional. We validate our findings across multiple reward benchmarks using SD 3.5 Medium, and observe consistent trends across all tasks. Our method improves the GenEval score from 0.24 to 0.95 in 90 GPU hours, which is $4.6\times$ more efficient than FlowGRPO and $2\times$ more efficient than the SOTA method DiffusionNFT without reward hacking.

---

### Approaches to Semantic Textual Similarity in Slovak Language: From Algorithms to Transformers

Authors: Lukas Radosky, Miroslav Blstak, Matej Krajcovic, Ivan Polasek
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.04659v1

Semantic textual similarity (STS) plays a crucial role in many natural language processing tasks. While extensively studied in high-resource languages, STS remains challenging for under-resourced languages such as Slovak. This paper presents a comparative evaluation of sentence-level STS methods applied to Slovak, including traditional algorithms, supervised machine learning models, and third-party deep learning tools. We trained several machine learning models using outputs from traditional algorithms as features, with feature selection and hyperparameter tuning jointly guided by artificial bee colony optimization. Finally, we evaluated several third-party tools, including fine-tuned model by CloudNLP, OpenAI's embedding models, GPT-4 model, and pretrained SlovakBERT model. Our findings highlight the trade-offs between different approaches.

---

### TRIO: Token Reduction via Inference-Objective Guidance for Efficient Vision-Language Models

Authors: Haokui Zhang, Congyang Ou, Dawei Yan, Peng Wang, Qingsen Yan, Yu Zhang, Ying Li, Rong Xiao
Published: 2026-02-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.04657v3

Recently, reducing redundant visual tokens in vision-language models (VLMs) to accelerate VLM inference has emerged as a hot topic. However, most existing methods rely on heuristics constructed based on inter-visual-token similarity or cross-modal visual-text similarity, which gives rise to certain limitations in compression performance and practical deployment. In contrast, we propose TRIO from the perspective of inference objectives, which transforms visual token compression into preserving output result invariance and selects tokens primarily by their importance to this goal. Specifically, vision tokens are reordered with the guidance of token-level gradient saliency generated by our designed layer-local proxy loss, a coarse constraint from the current layer to the final result. Then the most valuable vision tokens are selected following the non-maximum suppression (NMS) principle.The proposed TRIO is training-free and compatible with FlashAttention, friendly to practical application and deployment. It can be deployed independently as an encoder-free method, or combined with encoder compression approaches like VisionZip for use as an encoder-involved method. On LLaVA-Next-7B, TRIO retains just 11.1\% of visual tokens but maintains 97.2\% of the original performance, with a 2.75$\times$ prefill speedup, 2.14$\times$ inference speedup, 6.22$\times$ lower FLOPs, and 6.05$\times$ reduced KV Cache overhead.Our code is available at https://github.com/ocy1/TRIO.

---

### Inference-Time Backdoors via Chat Templates: From LLM Supply Chains to Agentic System Compromise

Authors: Ariel Fogel, Omer Hofman, Eilon Cohen, Roman Vainshtein
Published: 2026-02-04
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.04653v4

Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor attacks, in which adversaries embed hidden behaviors that activate under specific conditions. Previous work has assumed that adversaries have access to training pipelines or deployment infrastructure. We propose a novel attack surface requiring neither: the "chat template". Chat templates are executable programs invoked at every inference call, often implemented in Jinja2, that occupy a privileged position between user input and model processing. We show that an adversary who distributes a model with a maliciously modified template can implant an inference-time backdoor without modifying model weights, poisoning training data, or controlling runtime infrastructure. We evaluate this attack across three deployment tiers. At the LLM level, triggered backdoors reduce factual accuracy from 90% to 15% on average and induce attacker-controlled URL emission with success rates exceeding 80%, while benign inputs show no measurable degradation; these results hold across eighteen models. At the agent level, template backdoors hijack tool-use across two benchmarks spanning 3,868 episodes, bypassing every tested injection defense offered by the benchmarks while remaining fully dormant absent the trigger. At the multi-agent system level, we demonstrate how a single poisoned artifact compromises a real-world agentic deployment and propagates supply-chain code poisoning downstream. The poisoned artifacts evade all security scans on the largest open model distribution platform; and because the payload is rendered by the template before user input is processed, it is architecturally unreachable by input-level defenses such as prompt injection guardrails. These results establish chat templates as a reliable and undefended attack in the open-weight AI supply chain.

---

### SAFE: Stable Alignment Finetuning with Entropy-Aware Predictive Control for Reinforcement Learning from Human Feedback (RLHF)

Authors: Dipan Maity
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04651v2

Proximal Policy Optimization (PPO) has been positioned by recent literature as the canonical method for the RL part of Reinforcement Learning from Human Feedback (RLHF). PPO performs well empirically but has a heuristic motivation and handles the KL-divergence constraint used in LM-RLHF in an ad-hoc manner and suffers form reward oscillations, entropy collapse, value function drift, and sudden policy divergence that require frequent restarts and extensive hyperparameter tuning. In this paper, we develop a new pure on policy actor-critic RL method for the LM-RLHF setting. We present SAFE (Stable Alignment Finetuning with Entropy-aware control),a novel RLHF algorithm that combines a Double Soft-Min Critic for pessimistic value estimation with a new multi-layer stabilization framework combining entropy-gated KL regulation, and PID-controlled adaptive thresholds. Unlike standard PPO's symmetric KL penalties, SAFE distinguishes high-entropy exploration from low-entropy mode collapse and adjusts penalties dynamically based on reward velocity. Experiments on a 3B parameter model show SAFE achieves +5.15\% training-average reward than PPO (0.725 vs 0.689), negligible reward crashes, and superior KL control than ppo . Our method adds minimal computational overhead and provides an interpretable, crash-resistant RLHF framework that maintains aggressive learning speed while ensuring stable long-horizon optimization suitable for production deployment. Code is available at https://github.com/ryyzn9/SAFE

---

### Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models

Authors: Ariel Rodrigez, Alejandro Lancho, Amir Weiss
Published: 2026-02-04
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2602.04650v1

The increasingly crowded radio frequency (RF) spectrum forces communication signals to coexist, creating heterogeneous interferers whose structure often departs from Gaussian models. Recovering the interference-contaminated signal of interest in such settings is a central challenge, especially in single-channel RF processing. Existing data-driven methods often assume that the interference type is known, yielding ensembles of specialized models that scale poorly with the number of interferers. We show that detect-then-separate (DTS) strategies admit an analytical justification: within a Gaussian mixture framework, a plug-in maximum a posteriori detector followed by type-conditioned optimal estimation achieves asymptotic minimum mean-square error optimality under a mild temporal-diversity condition. This makes DTS a principled benchmark, but its reliance on multiple type-specific models limits scalability. Motivated by this, we propose a unified joint model (UJM), in which a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal. Using tailored UNet architectures for baseband (complex-valued) RF signals, we compare DTS and UJM on synthetic and recorded interference types, showing that a capacity-matched UJM can match oracle-aided DTS performance across diverse signal-to-interference-and-noise ratios, interference types, and constellation orders, including mismatched training and testing type-uncertainty proportions. These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader regimes.

---

### Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models

Authors: Binghai Wang, Yantao Liu, Yuxuan Liu, Tianyi Tang, Shenzhi Wang, Chang Gao, Chujie Zheng, Yichang Zhang, Le Yu, Shixuan Liu, Tao Gui, Qi Zhang et al.
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.04649v1

Generative Reward Models (GenRMs) and LLM-as-a-Judge exhibit deceptive alignment by producing correct judgments for incorrect reasons, as they are trained and evaluated to prioritize Outcome Accuracy, which undermines their ability to generalize during RLHF. We introduce Rationale Consistency, a fine-grained metric that quantifies the alignment between the model's reasoning process and human judgment. Our evaluation of frontier models reveals that rationale consistency effectively discriminates among state-of-the-art models and detects deceptive alignment, while outcome accuracy falls short in both respects. To mitigate this gap, we introduce a hybrid signal that combines rationale consistency with outcome accuracy for GenRM training. Our training method achieves state-of-the-art performance on RM-Bench (87.1%) and JudgeBench (82%), surpassing outcome-only baselines by an average of 5%. Using RM during RLHF, our method effectively improves performance as demonstrated on Arena Hard v2, notably yielding a 7% improvement in creative writing tasks. Further analysis confirms that our method escapes the deceptive alignment trap, effectively reversing the decline in rationale consistency observed in outcome-only training.

---

### SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction

Authors: Yanan He, Yunshi Wen, Xin Wang, Tengfei Ma
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04643v2

Time-series anomaly prediction aims to forecast future system failures before they fully emerge, making latent predictive models such as JEPA a promising framework for capturing precursor dynamics. However, directly applying continuous self-distillation to time-series data is often unstable and can lead to representation collapse, while also struggling to model precursors evolving at different temporal scales. To address this, we propose \textbf{SC-JEPA}, a new JEPA-based framework to model time-series anomaly prediction in a discretized predictive state space. It introduces a soft codebook bottleneck to stabilize latent predictive learning and encourage regime-level structure in the learned representations. Building on this stabilized latent space, we further design a multi-resolution predictive objective to capture precursor patterns at different temporal scales. Experiments on five real-world benchmarks show that SC-JEPA achieves strong and consistent early-warning performance.

---

### Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering Agents

Authors: Tse-Hsun, Chen
Published: 2026-02-04
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.04640v1

Software Engineering (SE) agents have shown promising abilities in supporting various SE tasks. Current SE agents remain fundamentally reactive, making decisions mainly based on conversation history and the most recent response. However, this reactive design provides no explicit structure or persistent state within the agent's memory, making long-horizon reasoning challenging. As a result, SE agents struggle to maintain a coherent understanding across reasoning steps, adapt their hypotheses as new evidence emerges, or incorporate execution feedback into the mental reasoning model of the system state. In this position paper, we argue that, to further advance SE agents, we need to move beyond reactive behavior toward a structured, state-aware, and execution-grounded reasoning. We outline how explicit structure, persistent and evolving state, and the integration of execution-grounded feedback can help SE agents perform more coherent and reliable reasoning in long-horizon tasks. We also provide an initial roadmap for developing next-generation SE agents that can more effectively perform real-world tasks.

---

### RIGA-Fold: A General Framework for Protein Inverse Folding via Recurrent Interaction and Geometric Awareness

Authors: Sisi Yuan, Jiehuang Chen, Junchuang Cai, Dong Xu, Xueliang Li, Zexuan Zhu, Junkai Ji
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04637v1

Protein inverse folding, the task of predicting amino acid sequences for desired structures, is pivotal for de novo protein design. However, existing GNN-based methods typically suffer from restricted receptive fields that miss long-range dependencies and a "single-pass" inference paradigm that leads to error accumulation. To address these bottlenecks, we propose RIGA-Fold, a framework that synergizes Recurrent Interaction with Geometric Awareness. At the micro-level, we introduce a Geometric Attention Update (GAU) module where edge features explicitly serve as attention keys, ensuring strictly SE(3)-invariant local encoding. At the macro-level, we design an attention-based Global Context Bridge that acts as a soft gating mechanism to dynamically inject global topological information. Furthermore, to bridge the gap between structural and sequence modalities, we introduce an enhanced variant, RIGA-Fold*, which integrates trainable geometric features with frozen evolutionary priors from ESM-2 and ESM-IF via a dual-stream architecture. Finally, a biologically inspired ``predict-recycle-refine'' strategy is implemented to iteratively denoise sequence distributions. Extensive experiments on CATH 4.2, TS50, and TS500 benchmarks demonstrate that our geometric framework is highly competitive, while RIGA-Fold* significantly outperforms state-of-the-art baselines in both sequence recovery and structural consistency.

---

### WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning

Authors: Zelai Xu, Zhexuan Xu, Ruize Zhang, Chunyang Zhu, Shi Yu, Weilin Liu, Quanlu Zhang, Wenbo Ding, Chao Yu, Yu Wang
Published: 2026-02-04
Categories: cs.AI, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2602.04634v3

Recent advancements in Large Language Models (LLMs) have largely focused on depth scaling, where a single agent solves long-horizon problems with multi-turn reasoning and tool use. However, as tasks grow broader, the key bottleneck shifts from individual competence to organizational capability. In this work, we explore a complementary dimension of width scaling with multi-agent systems to address broad information seeking. Existing multi-agent systems often rely on hand-crafted workflows and turn-taking interactions that fail to parallelize work effectively. To bridge this gap, we propose WideSeek-R1, a lead-agent-subagent framework trained via multi-agent reinforcement learning (MARL) to synergize scalable orchestration and parallel execution. By utilizing a shared LLM with isolated contexts and specialized tools, WideSeek-R1 jointly optimizes the lead agent and parallel subagents on a curated dataset of 20k broad information-seeking tasks. Extensive experiments show that WideSeek-R1-4B achieves an item F1 score of 40.0% on the WideSearch benchmark, which is comparable to the performance of single-agent DeepSeek-R1-671B. Furthermore, WideSeek-R1-4B exhibits consistent performance gains as the number of parallel subagents increases, highlighting the effectiveness of width scaling.

---

### Mapping the Web of Science, a large-scale graph and text-based dataset with LLM embeddings

Authors: Tim Kunt, Annika Buchholz, Imene Khebouri, Thorsten Koch, Ida Litzel, Thi Huong Vu
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.04630v1

Large text data sets, such as publications, websites, and other text-based media, inherit two distinct types of features: (1) the text itself, its information conveyed through semantics, and (2) its relationship to other texts through links, references, or shared attributes. While the latter can be described as a graph structure and can be handled by a range of established algorithms for classification and prediction, the former has recently gained new potential through the use of LLM embedding models. Demonstrating these possibilities and their practicability, we investigate the Web of Science dataset, containing ~56 million scientific publications through the lens of our proposed embedding method, revealing a self-structured landscape of texts.

---

### A labeled dataset of simulated phlebotomy procedures for medical AI: polygon annotations for object detection and human-object interaction

Authors: Raúl Jiménez Cruz, César Torres-Huitzil, Marco Franceschetti, Ronny Seiger, Luciano García-Bañuelos, Barbara Weber
Published: 2026-02-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.04624v1

This data article presents a dataset of 11,884 labeled images documenting a simulated blood extraction (phlebotomy) procedure performed on a training arm. Images were extracted from high-definition videos recorded under controlled conditions and curated to reduce redundancy using Structural Similarity Index Measure (SSIM) filtering. An automated face-anonymization step was applied to all videos prior to frame selection. Each image contains polygon annotations for five medically relevant classes: syringe, rubber band, disinfectant wipe, gloves, and training arm. The annotations were exported in a segmentation format compatible with modern object detection frameworks (e.g., YOLOv8), ensuring broad usability. This dataset is partitioned into training (70%), validation (15%), and test (15%) subsets and is designed to advance research in medical training automation and human-object interaction. It enables multiple applications, including phlebotomy tool detection, procedural step recognition, workflow analysis, conformance checking, and the development of educational systems that provide structured feedback to medical trainees. The data and accompanying label files are publicly available on Zenodo.

---

### QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning

Authors: Doyeon Lee, Eunyi Lyou, Hyunsoo Cho, Sookyung Kim, Joonseok Lee, Jaemoo Choi
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04620v3

GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approximations, however, they can lead to brittle optimization behavior, as global importance-ratio clipping and group-wise normalization fail to regulate samples whose importance ratios fall outside the clipping range. We propose Query-Adaptive Trust-Region policy Optimization (QUATRO), which directly enforces trust-region constraints through a principled optimization. This yields a clear and interpretable objective that enables explicit control over policy updates and stable, entropy-controlled optimization, with a stabilizer terms arising intrinsically from the exact trust-region formulation. Empirically verified on diverse mathematical reasoning benchmarks, QUATRO shows stable training under increased policy staleness and aggressive learning rates, maintaining well-controlled entropy throughout training.

---

### QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning

Authors: Doyeon Lee, Eunyi Lyou, Hyunsoo Cho, Sookyung Kim, Joonseok Lee, Jaemoo Choi
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04620v2

GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approximations, however, they can lead to brittle optimization behavior, as global importance-ratio clipping and group-wise normalization fail to regulate samples whose importance ratios fall outside the clipping range. We propose Query-Adaptive Trust-Region policy Optimization (QUATRO), which directly enforces trust-region constraints through a principled optimization. This yields a clear and interpretable objective that enables explicit control over policy updates and stable, entropy-controlled optimization, with a stabilizer terms arising intrinsically from the exact trust-region formulation. Empirically verified on diverse mathematical reasoning benchmarks, QUATRO shows stable training under increased policy staleness and aggressive learning rates, maintaining well-controlled entropy throughout training.

---

### LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation

Authors: Ruixiao Yang, Yuanhe Tian, Xu Yang, Huiqi Li, Yan Song
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.04617v1

Radiology Report Generation (RRG) aims to produce accurate and coherent diagnostics from medical images. Although large vision language models (LVLM) improve report fluency and accuracy, they exhibit hallucinations, generating plausible yet image-ungrounded pathological details. Existing methods primarily rely on external knowledge guidance to facilitate the alignment between generated text and visual information. However, these approaches often ignore the inherent decoding priors and vision-language alignment biases in pretrained models and lack robustness due to reliance on constructed guidance. In this paper, we propose Layer-wise Expert-aligned Decoding (LEAD), a novel method to inherently modify the LVLM decoding trajectory. A multiple experts module is designed for extracting distinct pathological features which are integrated into each decoder layer via a gating mechanism. This layer-wise architecture enables the LLM to consult expert features at every inference step via a learned gating function, thereby dynamically rectifying decoding biases and steering the generation toward factual consistency. Experiments conducted on multiple public datasets demonstrate that the LEAD method yields effective improvements in clinical accuracy metrics and mitigates hallucinations while preserving high generation quality.

---

### A Human-Centered Privacy Approach (HCP) to AI

Authors: Luyi Sun, Wei Xu, Zaifeng Gao
Published: 2026-02-04
Categories: cs.HC, cs.AI, cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.04616v1

As the paradigm of Human-Centered AI (HCAI) gains prominence, its benefits to society are accompanied by significant ethical concerns, one of which is the protection of individual privacy. This chapter provides a comprehensive overview of privacy within HCAI, proposing a human-centered privacy (HCP) framework, providing integrated solution from technology, ethics, and human factors perspectives. The chapter begins by mapping privacy risks across each stage of AI development lifecycle, from data collection to deployment and reuse, highlighting the impact of privacy risks on the entire system. The chapter then introduces privacy-preserving techniques such as federated learning and dif erential privacy. Subsequent chapters integrate the crucial user perspective by examining mental models, alongside the evolving regulatory and ethical landscapes as well as privacy governance. Next, advice on design guidelines is provided based on the human-centered privacy framework. After that, we introduce practical case studies across diverse fields. Finally, the chapter discusses persistent open challenges and future research directions, concluding that a multidisciplinary approach, merging technical, design, policy, and ethical expertise, is essential to successfully embed privacy into the core of HCAI, thereby ensuring these technologies advance in a manner that respects and ensures human autonomy, trust and dignity.

---

### Translation Heads: Disentangling meaning from language in LLM-based machine translation

Authors: Théo Lasnier, Armel Zebaze, Djamé Seddah, Rachel Bawden, Benoît Sagot
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.04613v2

Mechanistic Interpretability (MI) seeks to explain how neural networks implement their capabilities, but the scale of Large Language Models (LLMs) has limited prior MI work in Machine Translation (MT) to word-level analyses. We study sentence-level MT from a mechanistic perspective by analyzing attention heads to understand how LLMs internally encode and distribute translation functions. We decompose MT into two subtasks: producing text in the target language (i.e. target language identification) and preserving the input sentence's meaning (i.e. sentence equivalence). Across three families of open-source models and 20 translation directions, we find that distinct, sparse sets of attention heads specialize in each subtask. Based on this insight, we construct subtask-specific steering vectors and show that modifying just 1% of the relevant heads enables instruction-free MT performance comparable to instruction-based prompting, while ablating these heads selectively disrupts their corresponding translation functions.

---

### Targeted Synthetic Control Method

Authors: Yuxin Wang, Dennis Frauen, Emil Javurek, Konstantin Hess, Yuchen Ma, Stefan Feuerriegel
Published: 2026-02-04
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.04611v3

The synthetic control method (SCM) estimates causal effects in panel data with a single-treated unit by constructing a counterfactual outcome as a weighted combination of untreated control units that matches the pre-treatment trajectory. In this paper, we introduce the targeted synthetic control (TSC) method, a new two-stage estimator that directly estimates the counterfactual outcome. Specifically, our TSC method (1) yields a targeted debiasing estimator, in the sense that the targeted updating refines the initial weights to produce more stable weights; and (2) ensures that the final counterfactual estimation is a convex combination of observed control outcomes to enable direct interpretation of the synthetic control weights. TSC is flexible and can be instantiated with arbitrary machine learning models. Methodologically, TSC starts from an initial set of synthetic-control weights via a one-dimensional targeted update through the weight-tilting submodel, which calibrates the weights to reduce bias of weights estimation arising from pre-treatment fit. Furthermore, TSC avoids key shortcomings of existing methods (e.g., the augmented SCM), which can produce unbounded counterfactual estimates. Across extensive synthetic and real-world experiments, TSC consistently improves estimation accuracy over state-of-the-art SCM baselines.

---

### Resilient Load Forecasting under Climate Change: Adaptive Conditional Neural Processes for Few-Shot Extreme Load Forecasting

Authors: Chenxi Hu, Yue Ma, Yifan Wu, Yunhe Hou
Published: 2026-02-04
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2602.04609v1

Extreme weather can substantially change electricity consumption behavior, causing load curves to exhibit sharp spikes and pronounced volatility. If forecasts are inaccurate during those periods, power systems are more likely to face supply shortfalls or localized overloads, forcing emergency actions such as load shedding and increasing the risk of service disruptions and public-safety impacts. This problem is inherently difficult because extreme events can trigger abrupt regime shifts in load patterns, while relevant extreme samples are rare and irregular, making reliable learning and calibration challenging. We propose AdaCNP, a probabilistic forecasting model for data-scarce condition. AdaCNP learns similarity in a shared embedding space. For each target data, it evaluates how relevant each historical context segment is to the current condition and reweights the context information accordingly. This design highlights the most informative historical evidence even when extreme samples are rare. It enables few-shot adaptation to previously unseen extreme patterns. AdaCNP also produces predictive distributions for risk-aware decision-making without expensive fine-tuning on the target domain. We evaluate AdaCNP on real-world power-system load data and compare it against a range of representative baselines. The results show that AdaCNP is more robust during extreme periods, reducing the mean squared error by 22\% relative to the strongest baseline while achieving the lowest negative log-likelihood, indicating more reliable probabilistic outputs. These findings suggest that AdaCNP can effectively mitigate the combined impact of abrupt distribution shifts and scarce extreme samples, providing a more trustworthy forecasting for resilient power system operation under extreme events.

---

### Jacobian Regularization Stabilizes Long-Term Integration of Neural Differential Equations

Authors: Maya Janvier, Julien Salomon, Etienne Meunier
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04608v1

Hybrid models and Neural Differential Equations (NDE) are getting increasingly important for the modeling of physical systems, however they often encounter stability and accuracy issues during long-term integration. Training on unrolled trajectories is known to limit these divergences but quickly becomes too expensive due to the need for computing gradients over an iterative process. In this paper, we demonstrate that regularizing the Jacobian of the NDE model via its directional derivatives during training stabilizes long-term integration in the challenging context of short training rollouts. We design two regularizations, one for the case of known dynamics where we can directly derive the directional derivatives of the dynamic and one for the case of unknown dynamics where they are approximated using finite differences. Both methods, while having a far lower cost compared to long rollouts during training, are successful in improving the stability of long-term simulations for several ordinary and partial differential equations, opening up the door to training NDE methods for long-term integration of large scale systems.

---

### Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection

Authors: Junhao Liu, Haonan Yu, Zhenyu Yan, Xin Zhang
Published: 2026-02-04
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.04607v1

As Large Language Models (LLMs) scale to handle massive context windows, achieving surgical feature-level interpretation is essential for high-stakes tasks like legal auditing and code debugging. However, existing local model-agnostic explanation methods face a critical dilemma in these scenarios: feature-based methods suffer from attribution dilution due to high feature dimensionality, thus failing to provide faithful explanations. In this paper, we propose Focus-LIME, a coarse-to-fine framework designed to restore the tractability of surgical interpretation. Focus-LIME utilizes a proxy model to curate the perturbation neighborhood, allowing the target model to perform fine-grained attribution exclusively within the optimized context. Empirical evaluations on long-context benchmarks demonstrate that our method makes surgical explanations practicable and provides faithful explanations to users.

---

### RexBERT: Context Specialized Bidirectional Encoders for E-commerce

Authors: Rahul Bajaj, Anuj Garg
Published: 2026-02-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.04605v1

Encoder-only transformers remain indispensable in retrieval, classification, and ranking systems where latency, stability, and cost are paramount. Most general purpose encoders, however, are trained on generic corpora with limited coverage of specialized domains. We introduce RexBERT, a family of BERT-style encoders designed specifically for e-commerce semantics. We make three contributions. First, we release Ecom-niverse, a 350 billion token corpus curated from diverse retail and shopping sources. We describe a modular pipeline that isolates and extracts e-commerce content from FineFineWeb and other open web resources, and characterize the resulting domain distribution. Second, we present a reproducible pretraining recipe building on ModernBERT's architectural advances. The recipe consists of three phases: general pre-training, context extension, and annealed domain specialization. Third, we train RexBERT models ranging from 17M to 400M parameters and evaluate them on token classification, semantic similarity, and general natural language understanding tasks using e-commerce datasets. Despite having 2-3x fewer parameters, RexBERT outperforms larger general-purpose encoders and matches or surpasses modern long-context models on domain-specific benchmarks. Our results demonstrate that high quality in-domain data combined with a principled training approach provides a stronger foundation for e-commerce applications than indiscriminate scaling alone.

---

### Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays

Authors: Lucile Favero, Juan Antonio Pérez-Ortiz, Tanja Käser, Nuria Oliver
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.04604v1

Automated Essay Scoring systems have traditionally focused on holistic scores, limiting their pedagogical usefulness, especially in the case of complex essay genres such as argumentative writing. In educational contexts, teachers and learners require interpretable, trait-level feedback that aligns with instructional goals and established rubrics. In this paper, we study trait-based Automatic Argumentative Essay Scoring using two complementary modeling paradigms designed for realistic educational deployment: (1) structured in-context learning with small open-source LLMs, and (2) a supervised, encoder-based BigBird model with a CORAL-style ordinal regression formulation, optimized for long-sequence understanding. We conduct a systematic evaluation on the ASAP++ dataset, which includes essay scores across five quality traits, offering strong coverage of core argumentation dimensions. LLMs are prompted with designed, rubric-aligned in-context examples, along with feedback and confidence requests, while we explicitly model ordinality in scores with the BigBird model via the rank-consistent CORAL framework. Our results show that explicitly modeling score ordinality substantially improves agreement with human raters across all traits, outperforming LLMs and nominal classification and regression-based baselines. This finding reinforces the importance of aligning model objectives with rubric semantics for educational assessment. At the same time, small open-source LLMs achieve a competitive performance without task-specific fine-tuning, particularly for reasoning-oriented traits, while enabling transparent, privacy-preserving, and locally deployable assessment scenarios. Our findings provide methodological, modeling, and practical insights for the design of AI-based educational systems that aim to deliver interpretable, rubric-aligned feedback for argumentative writing.

---

### Stochastic Decision Horizons for Survival-Based Constrained Reinforcement Learning

Authors: Nikola Milosevic, Leonard Franz, Daniel Haeufle, Georg Martius, Nico Scherf, Pavel Kolev
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04599v3

We propose stochastic decision horizons (SDH), a theoretically grounded framework for survival-based constrained reinforcement learning from per-step violation signals. Rather than treating violations as expenditure of a cumulative budget, SDH shortens the effective decision horizon when violations occur, reducing current reward credit and future bootstrapping. We show that this construction represents a geometric-horizon survival constraint and, for a fixed Lagrange multiplier, remains the same SDH problem up to a constant reward offset that acts as an implicit incentive for survival. Using control as inference, we derive two off-policy and replay-compatible, regularized algorithms with post-violation semantics. Absorbing-state ends the decision process, so only surviving decisions pay policy KL, yielding AS-SAC. Virtual termination stops reward credit while the process continues, retaining ordinary discounted KL and yielding VT-MPO. To connect SDH with cumulative-cost CMDPs, we introduce violation-depth profiles. Under exponential-tail single-scale profiles, the SDH statistic determines cumulative cost; departures from this form mark where the connection breaks. Experiments validate both the method and this predicted scope. On the 90-muscle H2190 humanoid in Hyfydy, VT-MPO matches the EWA reference in peak gait realism, with its highest observed gait-match checkpoint at 21M environment steps versus 90M for EWA and markedly more stable training. On Safety Gymnasium, violation-depth profiles predict the regimes in which SDH achieves strong reward-violation trade-offs.

---

### Stochastic Decision Horizons for Constrained Reinforcement Learning

Authors: Nikola Milosevic, Leonard Franz, Daniel Haeufle, Georg Martius, Nico Scherf, Pavel Kolev
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04599v2

We propose stochastic decision horizons (SDH), a theoretically grounded framework for solving constrained RL problems with every-step constraint satisfaction, a desirable property in many real-world applications. In SDH, a constraint violation yields an effective shortening of horizon via a state-action continuation probability. Using Control as Inference, we develop the first off-policy and regularized algorithms for RL with instantaneous constraints. We identify two principled semantics for what counts as a decision after a violation. Absorbing-state semantics end the decision process, so only surviving decisions pay entropy cost, yielding max-entropy AS-SAC. Virtual-termination keeps the decision process alive while stopping reward credit, yielding KL-regularized VT-MPO. To connect SDH with CMDPs, we track how violations accumulate along trajectories (their violation-depth profile). SDH effectively weights each trajectory by the exponential of its total violation; this matches an additive CMDP budget exactly when violations occur at a single characteristic scale, and we pinpoint where it cannot: when rare, deep violations mix with frequent, shallow ones. Experiments validate the theory. On the 90-muscle H2190 humanoid (Hyfydy), VT-MPO matches state-of-the-art gait realism with $4\times$ fewer environment steps and substantially more stable training. On Safety Gymnasium, violation-depth profiles correctly identify the regimes in which SDH delivers strong reward-violation trade-offs. Experiments validate the theory. On the 90-muscle H2190 humanoid (Hyfydy), VT-MPO matches state-of-the-art gait realism with 4x fewer environment steps and substantially more stable training. On Safety Gymnasium, violation-depth profiles correctly identify the regimes in which SDH delivers strong reward-violation trade-offs.

---

### Uncertainty Decomposition for Bayes-Filtered Transformers via Bayesian Predictive Inference

Authors: Sandra Fortini, Kenyon Ng, Sonia Petrone, Judith Rousseau, Susan Wei
Published: 2026-02-04
Categories: stat.ML, cs.LG, stat.ME
arXiv: https://arxiv.org/abs/2602.04596v2

Bayes-filtered transformers are transformers meta-learned on sequences from a prior predictive distribution to approximate the corresponding posterior predictive distribution. They output total predictive uncertainty in a single forward pass but never explicitly represent a posterior distribution, making the standard route to separating aleatoric from epistemic uncertainty unavailable. We address this challenge through the lens of Bayesian predictive inference (BPI). Our main result is a predictive Central Limit Theorem (CLT) for supervised settings under conditions that are among the weakest known in the BPI literature. The CLT characterises the posterior of the limiting predictive distribution given an observed context as asymptotically Gaussian; the variance of this Gaussian quantifies epistemic uncertainty. We apply the framework to TabPFN, a Bayes-filtered transformer that is a state-of-the-art foundation model for tabular prediction. The resulting credible bands achieve near-nominal frequentist coverage as context length grows, and the decomposition largely matches standard desiderata: epistemic uncertainty shrinks with context length and is highest in sparsely observed regions within the span of the context data, while aleatoric uncertainty dominates near decision boundaries where classes overlap.

---

### VILLAIN at AVerImaTeC: Verifying Image-Text Claims via Multi-Agent Collaboration

Authors: Jaeyoon Jung, Yejun Yoon, Kunwoo Park
Published: 2026-02-04
Categories: cs.CL, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2602.04587v2

This paper describes VILLAIN, a multimodal fact-checking system that verifies image-text claims through prompt-based multi-agent collaboration. For the AVerImaTeC shared task, VILLAIN employs vision-language model agents across multiple stages of fact-checking. Textual and visual evidence is retrieved from the knowledge store enriched through additional web collection. To identify key information and address inconsistencies among evidence items, modality-specific and cross-modal agents generate analysis reports. In the subsequent stage, question-answer pairs are produced based on these reports. Finally, the Verdict Prediction agent produces the verification outcome based on the image-text claim and the generated question-answer pairs. Our system ranked first on the leaderboard across all evaluation metrics. The source code is publicly available at https://github.com/ssu-humane/VILLAIN.

---

### ImmuVis: Hyperconvolutional Foundation Model for Imaging Mass Cytometry

Authors: Dawid Uchal, Marcin Możejko, Krzysztof Gogolewski, Piotr Kupidura, Szymon Łukasik, Jakub Giezgała, Tomasz Nocoń, Kacper Pietrzyk, Robert Pieniuta, Mateusz Sulimowicz, Michal Orzyłowski, Tomasz Siłkowski et al.
Published: 2026-02-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.04585v2

We present ImmuVis, a family of efficient foundation models for imaging mass cytometry (IMC), a high-throughput multiplex imaging technology that handles molecular marker measurements as image channels and enables large-scale spatial tissue profiling. Unlike natural images, multiplex imaging lacks a fixed channel space, as real-world marker sets vary across studies, violating a core assumption of standard vision backbones. To address this, ImmuVis introduces marker-adaptive hyperconvolutions that generate convolutional kernels from learned marker embeddings, enabling a single model to operate on arbitrary measured marker subsets without retraining. We pretrain ImmuVis on the largest dataset to date, IMC17M (28 cohorts, 24,405 images, 265 markers, over 17M patches), using self-supervised masked reconstruction. ImmuVis outperforms state-of-the-art baselines and ablations in virtual staining and downstream classification tasks at substantially lower compute cost than transformer-based alternatives, and is the sole model that provides calibrated uncertainty via a heteroscedastic likelihood objective. These results position ImmuVis as a practical framework for real-world IMC modeling.

---

### SalFormer360: a transformer-based saliency estimation model for 360-degree videos

Authors: Mahmoud Z. A. Wahba, Francesco Barbato, Sara Baldoni, Federica Battisti
Published: 2026-02-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.04584v2

Saliency estimation has received growing attention in recent years due to its importance in a wide range of applications. In the context of 360-degree video, it has been particularly valuable for tasks such as viewport prediction and immersive content optimization. In this paper, we propose SalFormer360, a novel saliency estimation model for 360-degree videos built on a transformer-based architecture. Our approach is based on the combination of an existing encoder architecture, SegFormer, and a custom decoder. The SegFormer model was originally developed for 2D segmentation tasks, and it has been fine-tuned to adapt it to 360-degree content. To further enhance prediction accuracy in our model, we incorporated Viewing Center Bias to reflect user attention in 360-degree environments. Extensive experiments on the three largest benchmark datasets for saliency estimation demonstrate that SalFormer360 outperforms existing state-of-the-art methods. In terms of Pearson Correlation Coefficient, our model achieves 8.4% higher performance on Sport360, 2.5% on PVS-HM, and 18.6% on VR-EyeTracking compared to previous state-of-the-art.

---

### PEPR: Privileged Event-based Predictive Regularization for Domain Generalization

Authors: Gabriele Magrini, Federico Becattini, Niccolò Biondi, Pietro Pala
Published: 2026-02-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.04583v2

Deep neural networks for visual perception are highly susceptible to domain shift, which poses a critical challenge for real-world deployment under conditions that differ from the training data. To address this domain generalization challenge, we propose a cross-modal framework under the learning using privileged information (LUPI) paradigm for training a robust, single-modality RGB model. We leverage event cameras as a source of privileged information, available only during training. The two modalities exhibit complementary characteristics: the RGB stream is semantically dense but domain-dependent, whereas the event stream is sparse yet more domain-invariant. Direct feature alignment between them is therefore suboptimal, as it forces the RGB encoder to mimic the sparse event representation, thereby losing semantic detail. To overcome this, we introduce Privileged Event-based Predictive Regularization (PEPR), which reframes LUPI as a predictive problem in a shared latent space. Instead of enforcing direct cross-modal alignment, we train the RGB encoder with PEPR to predict event-based latent features, distilling robustness without sacrificing semantic richness. The resulting standalone RGB model consistently improves robustness to day-to-night and other domain shifts, outperforming alignment-based baselines across object detection and semantic segmentation.

---

### Real-time processing of analog signals on accelerated neuromorphic hardware

Authors: Yannik Stradmann, Johannes Schemmel, Mihai A. Petrovici, Laura Kriener
Published: 2026-02-04
Categories: cs.NE
arXiv: https://arxiv.org/abs/2602.04582v2

Sensory processing with neuromorphic systems is typically done by using either event-based sensors or translating input signals to spikes before presenting them to the neuromorphic processor. Here, we offer an alternative approach: direct analog signal injection eliminates superfluous and power-intensive analog-to-digital and digital-to-analog conversions, making it particularly suitable for efficient near-sensor processing. We demonstrate this by using the accelerated BrainScaleS-2 mixed-signal neuromorphic research platform and interfacing it directly to microphones and a servo-motor-driven actuator. Utilizing BrainScaleS-2's 1000-fold acceleration factor, we employ a spiking neural network to transform interaural time differences into a spatial code and thereby predict the location of sound sources. Our primary contributions are the first demonstrations of direct, continuous-valued sensor data injection into the analog compute units of the BrainScaleS-2 ASIC, and actuator control using its embedded microprocessors. This enables a fully on-chip processing pipeline$\unicode{x2014}$from sensory input handling, via spiking neural network processing to physical action. We showcase this by programming the system to localize and align a servo motor with the spatial direction of transient noise peaks in real-time.

---

### Trust The Typical

Authors: Debargha Ganguly, Sreehari Sankar, Biyao Zhang, Vikash Singh, Kanan Gupta, Harshini Kavuru, Alan Luo, Weicong Chen, Warren Morningstar, Raghu Machiraju, Vipin Chaudhary
Published: 2026-02-04
Categories: cs.CL, cs.AI, cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2602.04581v1

Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust safety comes not from enumerating what is harmful, but from deeply understanding what is safe. We introduce Trust The Typical (T3), a framework that operationalizes this principle by treating safety as an out-of-distribution (OOD) detection problem. T3 learns the distribution of acceptable prompts in a semantic space and flags any significant deviation as a potential threat. Unlike prior methods, it requires no training on harmful examples, yet achieves state-of-the-art performance across 18 benchmarks spanning toxicity, hate speech, jailbreaking, multilingual harms, and over-refusal, reducing false positive rates by up to 40x relative to specialized safety models. A single model trained only on safe English text transfers effectively to diverse domains and over 14 languages without retraining. Finally, we demonstrate production readiness by integrating a GPU-optimized version into vLLM, enabling continuous guardrailing during token generation with less than 6% overhead even under dense evaluation intervals on large-scale workloads.

---

### AIANO: Enhancing Information Retrieval with AI-Augmented Annotation

Authors: Sameh Khattab, Marie Bauer, Lukas Heine, Till Rostalski, Jens Kleesiek, Julian Friedrich
Published: 2026-02-04
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2602.04579v1

The rise of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) has rapidly increased the need for high-quality, curated information retrieval datasets. These datasets, however, are currently created with off-the-shelf annotation tools that make the annotation process complex and inefficient. To streamline this process, we developed a specialized annotation tool - AIANO. By adopting an AI-augmented annotation workflow that tightly integrates human expertise with LLM assistance, AIANO enables annotators to leverage AI suggestions while retaining full control over annotation decisions. In a within-subject user study ($n = 15$), participants created question-answering datasets using both a baseline tool and AIANO. AIANO nearly doubled annotation speed compared to the baseline while being easier to use and improving retrieval accuracy. These results demonstrate that AIANO's AI-augmented approach accelerates and enhances dataset creation for information retrieval tasks, advancing annotation capabilities in retrieval-intensive domains.

---

### Semantic Self-Distillation for Language Model Uncertainty

Authors: Edward Phillips, Sean Wu, Fredrik K. Gustafsson, Boyan Gao, David A. Clifton
Published: 2026-02-04
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.04577v3

Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been proposed as a useful proxy for model uncertainty, but the associated computational cost prohibits its use in latency-critical applications. We show that sampled semantic distributions can be distilled into lightweight student models which estimate a prompt-conditioned density before the language model generates an answer token. The student model predicts a semantic distribution over possible answers; the entropy of this distribution provides a prompt-level uncertainty signal, and the probability density allows answer-level reliability evaluation. Across experiments on TriviaQA and MMLU, we find our student models perform competitively relative to the teacher's sampled semantic dispersion on a hallucination prediction task, whilst offering additional uncertainty primitives for out-of-domain detection and multiple-choice answer selection. We term this technique Semantic Self-Distillation (SSD), which can serve as a general framework for distilling predictive uncertainty in complex output spaces beyond language.

---

### Semantic Self-Distillation for Language Model Uncertainty

Authors: Edward Phillips, Sean Wu, Fredrik K. Gustafsson, Boyan Gao, David A. Clifton
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.04577v2

Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been proposed as a useful proxy for model uncertainty, but the associated computational cost prohibits its use in latency-critical applications. We show that sampled semantic distributions can be distilled into lightweight student models which estimate a prompt-conditioned density before the language model generates an answer token. The student model predicts a semantic distribution over possible answers; the entropy of this distribution provides a prompt-level uncertainty signal, and the probability density allows answer-level reliability evaluation. Across experiments on TriviaQA and MMLU, we find our student models perform competitively relative to sampling-based semantic dispersion baselines on a hallucination prediction task, whilst offering additional uncertainty primitives for out-of-domain detection and multiple-choice answer selection. We term this technique Semantic Self-Distillation (SSD), which can serve as a general framework for distilling predictive uncertainty in complex output spaces beyond language.

---

### Vibe AIGC: A New Paradigm for Content Generation via Agentic Orchestration

Authors: Jiaheng Liu, Yuanxing Zhang, Shihao Li, Xinping Lei
Published: 2026-02-04
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.04575v2

For the past decade, the trajectory of generative artificial intelligence (AI) has been dominated by a model-centric paradigm driven by scaling laws. Despite significant leaps in visual fidelity, this approach has encountered a ``usability ceiling'' manifested as the Intent-Execution Gap (i.e., the fundamental disparity between a creator's high-level intent and the stochastic, black-box nature of current single-shot models). In this paper, inspired by the Vibe Coding, we introduce the \textbf{Vibe AIGC}, a new paradigm for content generation via agentic orchestration, which represents the autonomous synthesis of hierarchical multi-agent workflows. Under this paradigm, the user's role transcends traditional prompt engineering, evolving into a Commander who provides a Vibe, a high-level representation encompassing aesthetic preferences, functional logic, and etc. A centralized Meta-Planner then functions as a system architect, deconstructing this ``Vibe'' into executable, verifiable, and adaptive agentic pipelines. By transitioning from stochastic inference to logical orchestration, Vibe AIGC bridges the gap between human imagination and machine execution. We contend that this shift will redefine the human-AI collaborative economy, transforming AI from a fragile inference engine into a robust system-level engineering partner that democratizes the creation of complex, long-horizon digital assets.

---

### Probabilistic Label Spreading: Efficient and Consistent Estimation of Soft Labels with Epistemic Uncertainty on Graphs

Authors: Jonathan Klees, Tobias Riedlinger, Peter Stehr, Bennet Böddecker, Daniel Kondermann, Matthias Rottmann
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04574v1

Safe artificial intelligence for perception tasks remains a major challenge, partly due to the lack of data with high-quality labels. Annotations themselves are subject to aleatoric and epistemic uncertainty, which is typically ignored during annotation and evaluation. While crowdsourcing enables collecting multiple annotations per image to estimate these uncertainties, this approach is impractical at scale due to the required annotation effort. We introduce a probabilistic label spreading method that provides reliable estimates of aleatoric and epistemic uncertainty of labels. Assuming label smoothness over the feature space, we propagate single annotations using a graph-based diffusion method. We prove that label spreading yields consistent probability estimators even when the number of annotations per data point converges to zero. We present and analyze a scalable implementation of our method. Experimental results indicate that, compared to baselines, our approach substantially reduces the annotation budget required to achieve a desired label quality on common image datasets and achieves a new state of the art on the Data-Centric Image Classification benchmark.

---

### From Competition to Collaboration: Designing Sustainable Mechanisms Between LLMs and Online Forums

Authors: Niv Fono, Yftah Ziser, Omer Ben-Porat
Published: 2026-02-04
Categories: cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2602.04572v2

While Generative AI (GenAI) systems draw users away from (Q&A) forums, they also depend on the very data those forums produce to improve their performance. Addressing this paradox, we propose a framework of sequential interaction, in which a GenAI system proposes questions to a forum that can publish some of them. Our framework captures several intricacies of such a collaboration, including non-monetary exchanges, asymmetric information, and incentive misalignment. We bring the framework to life through comprehensive, data-driven simulations using real Stack Exchange data and commonly used LLMs. We demonstrate the incentive misalignment empirically, yet show that players can achieve roughly half of the utility in an ideal full-information scenario. Our results highlight the potential for sustainable collaboration that preserves effective knowledge sharing between AI systems and human knowledge platforms.

---

### Can LLMs capture stable human-generated sentence entropy measures?

Authors: Estrella Pivel-Villanueva, Elisabeth Frederike Sterner, Franziska Knolle
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.04570v1

Predicting upcoming words is a core mechanism of language comprehension and may be quantified using Shannon entropy. There is currently no empirical consensus on how many human responses are required to obtain stable and unbiased entropy estimates at the word level. Moreover, large language models (LLMs) are increasingly used as substitutes for human norming data, yet their ability to reproduce stable human entropy remains unclear. Here, we address both issues using two large publicly available cloze datasets in German 1 and English 2. We implemented a bootstrap-based convergence analysis that tracks how entropy estimates stabilize as a function of sample size. Across both languages, more than 97% of sentences reached stable entropy estimates within the available sample sizes. 90% of sentences converged after 111 responses in German and 81 responses in English, while low-entropy sentences (<1) required as few as 20 responses and high-entropy sentences (>2.5) substantially more. These findings provide the first direct empirical validation for common norming practices and demonstrate that convergence critically depends on sentence predictability. We then compared stable human entropy values with entropy estimates derived from several LLMs, including GPT-4o, using both logit-based probability extraction and sampling-based frequency estimation, GPT2-xl/german-GPT-2, RoBERTa Base/GottBERT, and LLaMA 2 7B Chat. GPT-4o showed the highest correspondence with human data, although alignment depended strongly on the extraction method and prompt design. Logit-based estimates minimized absolute error, whereas sampling-based estimates were better in capturing the dispersion of human variability. Together, our results establish practical guidelines for human norming and show that while LLMs can approximate human entropy, they are not interchangeable with stable human-derived distributions.

---

### Dual Mind World Model Inspired Network Digital Twin for Access Scheduling

Authors: Hrishikesh Dutta, Roberto Minerva, Noel Crespi
Published: 2026-02-04
Categories: cs.NI, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2602.04566v1

Emerging networked systems such as industrial IoT and real-time cyber-physical infrastructures demand intelligent scheduling strategies capable of adapting to dynamic traffic, deadlines, and interference constraints. In this work, we present a novel Digital Twin-enabled scheduling framework inspired by Dual Mind World Model (DMWM) architecture, for learning-informed and imagination-driven network control. Unlike conventional rule-based or purely data-driven policies, the proposed DMWM combines short-horizon predictive planning with symbolic model-based rollout, enabling the scheduler to anticipate future network states and adjust transmission decisions accordingly. We implement the framework in a configurable simulation testbed and benchmark its performance against traditional heuristics and reinforcement learning baselines under varied traffic conditions. Our results show that DMWM achieves superior performance in bursty, interference-limited, and deadline-sensitive environments, while maintaining interpretability and sample efficiency. The proposed design bridges the gap between network-level reasoning and low-overhead learning, marking a step toward scalable and adaptive NDT-based network optimization.

---

### Understanding Degradation with Vision Language Model

Authors: Guanzhou Lan, Chenyi Liao, Yuqi Yang, Qianli Ma, Zhigang Wang, Dong Wang, Bin Zhao, Xuelong Li
Published: 2026-02-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.04565v1

Understanding visual degradations is a critical yet challenging problem in computer vision. While recent Vision-Language Models (VLMs) excel at qualitative description, they often fall short in understanding the parametric physics underlying image degradations. In this work, we redefine degradation understanding as a hierarchical structured prediction task, necessitating the concurrent estimation of degradation types, parameter keys, and their continuous physical values. Although these sub-tasks operate in disparate spaces, we prove that they can be unified under one autoregressive next-token prediction paradigm, whose error is bounded by the value-space quantization grid. Building on this insight, we introduce DU-VLM, a multimodal chain-of-thought model trained with supervised fine-tuning and reinforcement learning using structured rewards. Furthermore, we show that DU-VLM can serve as a zero-shot controller for pre-trained diffusion models, enabling high-fidelity image restoration without fine-tuning the generative backbone. We also introduce \textbf{DU-110k}, a large-scale dataset comprising 110,000 clean-degraded pairs with grounded physical annotations. Extensive experiments demonstrate that our approach significantly outperforms generalist baselines in both accuracy and robustness, exhibiting generalization to unseen distributions.

---

### Textual Planning with Explicit Latent Transitions

Authors: Eliezer Shlomi, Ido Levy, Eilam Shapira, Michael Katz, Guy Uziel, Segev Shlomov, Nir Mashkif, Roi Reichart, Sarah Keren
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.04557v1

Planning with LLMs is bottlenecked by token-by-token generation and repeated full forward passes, making multi-step lookahead and rollout-based search expensive in latency and compute. We propose EmbedPlan, which replaces autoregressive next-state generation with a lightweight transition model operating in a frozen language embedding space. EmbedPlan encodes natural language state and action descriptions into vectors, predicts the next-state embedding, and retrieves the next state by nearest-neighbor similarity, enabling fast planning computation without fine-tuning the encoder. We evaluate next-state prediction across nine classical planning domains using six evaluation protocols of increasing difficulty: interpolation, plan-variant, extrapolation, multi-domain, cross-domain, and leave-one-out. Results show near-perfect interpolation performance but a sharp degradation when generalization requires transfer to unseen problems or unseen domains; plan-variant evaluation indicates generalization to alternative plans rather than memorizing seen trajectories. Overall, frozen embeddings support within-domain dynamics learning after observing a domain's transitions, while transfer across domain boundaries remains a bottleneck.

---