# Research Papers — 2026-02 · bundle page 153 of 210

> Full-text markdown of papers #7601–7650 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/153
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/152.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/154.md)

### Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction

Authors: Bo Du, Xiaochen Ma, Xuekang Zhu, Zhe Yang, Chaogun Niu, Chenfan Qu, Mingqi Fang, Zhenming Wang, Jingjing Liu, Jian Liu, Ji-Zhe Zhou
Published: 2026-02-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06676v4

Fake Image Detection (FID), aiming at unified detection across four image forensic subdomains, is critical in real-world forensic scenarios. Compared with ensemble approaches, monolithic FID models are theoretically more promising, but to date, consistently yield inferior performance in practice. In this work, we identify the intrinsic distinctness of artifacts across subdomains, a critical barrier we term the ``Ji-Zhe phenomenon". Driven by this phenomenon, we diagnose the cause of this underperformance for the first time: the collapse of the artifact feature space. The core challenge for developing a practical monolithic FID model thus boils down to the ``unified-yet-discriminative" reconstruction of the artifact feature space. To address this paradoxical challenge, we hypothesize that high-level semantics can serve as a structural prior for the reconstruction, and further propose Semantic-Induced Constrained Adaptation (SICA), the first monolithic FID paradigm. Extensive experiments on our OpenMMSec dataset demonstrate that SICA outperforms 15 state-of-the-art methods and reconstructs the target unified-yet-discriminative artifact feature space in a near-orthogonal manner, thus firmly validating our hypothesis. The code and dataset are available at: https://github.com/venus-guangjian/SICA_OpenMMSec.

---

### Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation

Authors: Hoang Pham, The-Anh Ta, Long Tran-Thanh
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06675v1

Pruning at Initialisation methods discover sparse, trainable subnetworks before training, but their theoretical mechanisms remain elusive. Existing analyses are often limited to finite-width statistics, lacking a rigorous characterisation of the global sparsity patterns that emerge as networks grow large. In this work, we connect discrete pruning heuristics to graph limit theory via graphons, establishing the graphon limit of PaI masks. We introduce a Factorised Saliency Model that encompasses popular pruning criteria and prove that, under regularity conditions, the discrete masks generated by these algorithms converge to deterministic bipartite graphons. This limit framework establishes a novel topological taxonomy for sparse networks: while unstructured methods (e.g., Random, Magnitude) converge to homogeneous graphons representing uniform connectivity, data-driven methods (e.g., SNIP, GraSP) converge to heterogeneous graphons that encode implicit feature selection. Leveraging this continuous characterisation, we derive two fundamental theoretical results: (i) a Universal Approximation Theorem for sparse networks that depends only on the intrinsic dimension of active coordinate subspaces; and (ii) a Graphon-NTK generalisation bound demonstrating how the limit graphon modulates the kernel geometry to align with informative features. Our results transform the study of sparse neural networks from combinatorial graph problems into a rigorous framework of continuous operators, offering a new mechanism for analysing expressivity and generalisation in sparse neural networks.

---

### CytoCrowd: A Multi-Annotator Benchmark Dataset for Cytology Image Analysis

Authors: Yonghao Si, Xingyuan Zeng, Zhao Chen, Libin Zheng, Caleb Chen Cao, Lei Chen, Jian Yin
Published: 2026-02-06
Categories: cs.CV, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2602.06674v2

High-quality annotated datasets are crucial for advancing machine learning in medical image analysis. However, a critical gap exists: most datasets either offer a single, clean ground truth, which hides real-world expert disagreement, or they provide multiple annotations without a separate gold standard for objective evaluation. To bridge this gap, we introduce CytoCrowd, a new public benchmark for cytology analysis. The dataset features 446 high-resolution images, each with two key components: (1) raw, conflicting annotations from four independent pathologists, and (2) a separate, high-quality gold-standard ground truth established by a senior expert. This dual structure makes CytoCrowd a versatile resource. It serves as a benchmark for standard computer vision tasks, such as object detection and classification, using the ground truth. Simultaneously, it provides a realistic testbed for evaluating annotation aggregation algorithms that must resolve expert disagreements. We provide comprehensive baseline results for both tasks. Our experiments demonstrate the challenges presented by CytoCrowd and establish its value as a resource for developing the next generation of models for medical image analysis. The dataset is publicly available at https://github.com/YHSI5358/CytoCrowd-Datasets.

---

### CytoCrowd: A Multi-Annotator Benchmark Dataset for Cytology Image Analysis

Authors: Yonghao Si, Xingyuan Zeng, Zhao Chen, Libin Zheng, Caleb Chen Cao, Lei Chen, Jian Yin
Published: 2026-02-06
Categories: cs.CV, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2602.06674v1

High-quality annotated datasets are crucial for advancing machine learning in medical image analysis. However, a critical gap exists: most datasets either offer a single, clean ground truth, which hides real-world expert disagreement, or they provide multiple annotations without a separate gold standard for objective evaluation. To bridge this gap, we introduce CytoCrowd, a new public benchmark for cytology analysis. The dataset features 446 high-resolution images, each with two key components: (1) raw, conflicting annotations from four independent pathologists, and (2) a separate, high-quality gold-standard ground truth established by a senior expert. This dual structure makes CytoCrowd a versatile resource. It serves as a benchmark for standard computer vision tasks, such as object detection and classification, using the ground truth. Simultaneously, it provides a realistic testbed for evaluating annotation aggregation algorithms that must resolve expert disagreements. We provide comprehensive baseline results for both tasks. Our experiments demonstrate the challenges presented by CytoCrowd and establish its value as a resource for developing the next generation of models for medical image analysis.

---

### compar:IA: The French Government's LLM arena to collect French-language human prompts and preference data

Authors: Lucie Termignon, Simonas Zilinskas, Hadrien Pélissier, Aurélien Barrot, Nicolas Chesnais, Elie Gavoty
Published: 2026-02-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.06669v1

Large Language Models (LLMs) often show reduced performance, cultural alignment, and safety robustness in non-English languages, partly because English dominates both pre-training data and human preference alignment datasets. Training methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) require human preference data, which remains scarce and largely non-public for many languages beyond English. To address this gap, we introduce compar:IA, an open-source digital public service developed inside the French government and designed to collect large-scale human preference data from a predominantly French-speaking general audience. The platform uses a blind pairwise comparison interface to capture unconstrained, real-world prompts and user judgments across a diverse set of language models, while maintaining low participation friction and privacy-preserving automated filtering. As of 2026-02-07, compar:IA has collected over 600,000 free-form prompts and 250,000 preference votes, with approximately 89% of the data in French. We release three complementary datasets -- conversations, votes, and reactions -- under open licenses, and present initial analyses, including a French-language model leaderboard and user interaction patterns. Beyond the French context, compar:IA is evolving toward an international digital public good, offering reusable infrastructure for multilingual model training, evaluation, and the study of human-AI interaction.

---

### Not All Layers Need Tuning: Selective Layer Restoration Recovers Diversity

Authors: Bowen Zhang, Meiyi Wang, Harold Soh
Published: 2026-02-06
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.06665v1

Post-training improves instruction-following and helpfulness of large language models (LLMs) but often reduces generation diversity, which leads to repetitive outputs in open-ended settings, a phenomenon known as mode collapse. Motivated by evidence that LLM layers play distinct functional roles, we hypothesize that mode collapse can be localized to specific layers and that restoring a carefully chosen range of layers to their pre-trained weights can recover diversity while maintaining high output quality. To validate this hypothesis and decide which layers to restore, we design a proxy task -- Constrained Random Character(CRC) -- with an explicit validity set and a natural diversity objective. Results on CRC reveal a clear diversity-validity trade-off across restoration ranges and identify configurations that increase diversity with minimal quality loss. Based on these findings, we propose Selective Layer Restoration (SLR), a training-free method that restores selected layers in a post-trained model to their pre-trained weights, yielding a hybrid model with the same architecture and parameter count, incurring no additional inference cost. Across three different tasks (creative writing, open-ended question answering, and multi-step reasoning) and three different model families (Llama, Qwen, and Gemma), we find SLR can consistently and substantially improve output diversity while maintaining high output quality.

---

### PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks

Authors: Junxian Li, Kai Liu, Leyang Chen, Weida Wang, Zhixin Wang, Jiaqi Xu, Fan Li, Renjing Pei, Linghe Kong, Yulun Zhang
Published: 2026-02-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06663v2

Unified multimodal models (UMMs) have shown impressive capabilities in generating natural images and supporting multimodal reasoning. However, their potential in supporting computer-use planning tasks, which are closely related to our lives, remain underexplored. Image generation and editing in computer-use tasks require capabilities like spatial reasoning and procedural understanding, and it is still unknown whether UMMs have these capabilities to finish these tasks or not. Therefore, we propose PlanViz, a new benchmark designed to evaluate image generation and editing for computer-use tasks. To achieve the goal of our evaluation, we focus on sub-tasks which frequently involve in daily life and require planning. Specifically, three representative sub-tasks are designed: route planning, work diagramming, and web&UI displaying. We address challenges in data quality ensuring by curating human-annotated questions and reference images, and a quality control process. For detailed and exact evaluation, a task-adaptive score, PlanScore, is proposed. The score helps understanding the correctness, visual quality and efficiency of generated images. Through experiments, we highlight key limitations and opportunities for future research on this topic.

---

### Multimodal Generative Retrieval Model with Staged Pretraining for Food Delivery on Meituan

Authors: Boyu Chen, Tai Guo, Weiyu Cui, Yuqing Li, Xingxing Wang, Chuan Shi, Cheng Yang
Published: 2026-02-06
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.06654v1

Multimodal retrieval models are becoming increasingly important in scenarios such as food delivery, where rich multimodal features can meet diverse user needs and enable precise retrieval. Mainstream approaches typically employ a dual-tower architecture between queries and items, and perform joint optimization of intra-tower and inter-tower tasks. However, we observe that joint optimization often leads to certain modalities dominating the training process, while other modalities are neglected. In addition, inconsistent training speeds across modalities can easily result in the one-epoch problem. To address these challenges, we propose a staged pretraining strategy, which guides the model to focus on specialized tasks at each stage, enabling it to effectively attend to and utilize multimodal features, and allowing flexible control over the training process at each stage to avoid the one-epoch problem. Furthermore, to better utilize the semantic IDs that compress high-dimensional multimodal embeddings, we design both generative and discriminative tasks to help the model understand the associations between SIDs, queries, and item features, thereby improving overall performance. Extensive experiments on large-scale real-world Meituan data demonstrate that our method achieves improvements of 3.80%, 2.64%, and 2.17% on R@5, R@10, and R@20, and 5.10%, 4.22%, and 2.09% on N@5, N@10, and N@20 compared to mainstream baselines. Online A/B testing on the Meituan platform shows that our approach achieves a 1.12% increase in revenue and a 1.02% increase in click-through rate, validating the effectiveness and superiority of our method in practical applications.

---

### RAPID: Reconfigurable, Adaptive Platform for Iterative Design

Authors: Zi Yin, Fanhong Li, Shurui Zheng, Jia Liu
Published: 2026-02-06
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2602.06653v1

Developing robotic manipulation policies is iterative and hypothesis-driven: researchers test tactile sensing, gripper geometries, and sensor placements through real-world data collection and training. Yet even minor end-effector changes often require mechanical refitting and system re-integration, slowing iteration. We present RAPID, a full-stack reconfigurable platform designed to reduce this friction. RAPID is built around a tool-free, modular hardware architecture that unifies handheld data collection and robot deployment, and a matching software stack that maintains real-time awareness of the underlying hardware configuration through a driver-level Physical Mask derived from USB events. This modular hardware architecture reduces reconfiguration to seconds and makes systematic multi-modal ablation studies practical, allowing researchers to sweep diverse gripper and sensing configurations without repeated system bring-up. The Physical Mask exposes modality presence as an explicit runtime signal, enabling auto-configuration and graceful degradation under sensor hot-plug events, so policies can continue executing when sensors are physically added or removed. System-centric experiments show that RAPID reduces the setup time for multi-modal configurations by two orders of magnitude compared to traditional workflows and preserves policy execution under runtime sensor hot-unplug events. The hardware designs, drivers, and software stack are open-sourced at https://rapid-kit.github.io/ .

---

### Same Answer, Different Representations: Hidden instability in VLMs

Authors: Farooq Ahmad Wani, Alessandro Suglia, Rohit Saxena, Aryo Pradipta Gema, Wai-Chung Kwan, Fazl Barez, Maria Sofia Bucarelli, Fabrizio Silvestri, Pasquale Minervini
Published: 2026-02-06
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.06652v2

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is insufficient. We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness (spatial consistency of vision tokens), alongside standard label-based metrics. Applying this framework to modern VLMs across the SEEDBench, MMMU, and POPE datasets reveals three distinct failure modes. First, models frequently preserve predicted answers while undergoing substantial internal representation drift; for perturbations such as text overlays, this drift approaches the magnitude of inter-image variability, indicating that representations move to regions typically occupied by unrelated inputs despite unchanged outputs. Second, robustness does not improve with scale; larger models achieve higher accuracy but exhibit equal or greater sensitivity, consistent with sharper yet more fragile decision boundaries. Third, we find that perturbations affect tasks differently: they harm reasoning when they disrupt how models combine coarse and fine visual cues, but on the hallucination benchmarks, they can reduce false positives by making models generate more conservative answers.

---

### Same Answer, Different Representations: Hidden instability in VLMs

Authors: Farooq Ahmad Wani, Alessandro Suglia, Rohit Saxena, Aryo Pradipta Gema, Wai-Chung Kwan, Fazl Barez, Maria Sofia Bucarelli, Fabrizio Silvestri, Pasquale Minervini
Published: 2026-02-06
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.06652v1

The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processing. In this work, we argue that this assumption is insufficient. We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness (spatial consistency of vision tokens), alongside standard label-based metrics. Applying this framework to modern VLMs across the SEEDBench, MMMU, and POPE datasets reveals three distinct failure modes. First, models frequently preserve predicted answers while undergoing substantial internal representation drift; for perturbations such as text overlays, this drift approaches the magnitude of inter-image variability, indicating that representations move to regions typically occupied by unrelated inputs despite unchanged outputs. Second, robustness does not improve with scale; larger models achieve higher accuracy but exhibit equal or greater sensitivity, consistent with sharper yet more fragile decision boundaries. Third, we find that perturbations affect tasks differently: they harm reasoning when they disrupt how models combine coarse and fine visual cues, but on the hallucination benchmarks, they can reduce false positives by making models generate more conservative answers.

---

### Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought

Authors: Jianfeng Si, Lin Sun, Weihong Lin, Xiangzheng Zhang
Published: 2026-02-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06650v1

Large Language Models (LLMs) face a fundamental safety-helpfulness trade-off due to static, one-size-fits-all safety policies that lack runtime controllabilityxf, making it difficult to tailor responses to diverse application needs. %As a result, models may over-refuse benign requests or under-constrain harmful ones. We present \textbf{PACT} (Prompt-configured Action via Chain-of-Thought), a framework for dynamic safety control through explicit, risk-aware reasoning. PACT operates under a hierarchical policy architecture: a non-overridable global safety policy establishes immutable boundaries for critical risks (e.g., child safety, violent extremism), while user-defined policies can introduce domain-specific (non-global) risk categories and specify label-to-action behaviors to improve utility in real-world deployment settings. The framework decomposes safety decisions into structured Classify$\rightarrow$Act paths that route queries to the appropriate action (comply, guide, or reject) and render the decision-making process transparent. Extensive experiments demonstrate that PACT achieves near state-of-the-art safety performance under global policy evaluation while attaining the best controllability under user-specific policy evaluation, effectively mitigating the safety-helpfulness trade-off. We will release the PACT model suite, training data, and evaluation protocols to facilitate reproducible research in controllable safety alignment.

---

### Reading Between the Waves: Robust Topic Segmentation Using Inter-Sentence Audio Features

Authors: Steffen Freisinger, Philipp Seeberger, Tobias Bocklet, Korbinian Riedhammer
Published: 2026-02-06
Categories: cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2602.06647v1

Spoken content, such as online videos and podcasts, often spans multiple topics, which makes automatic topic segmentation essential for user navigation and downstream applications. However, current methods do not fully leverage acoustic features, leaving room for improvement. We propose a multi-modal approach that fine-tunes both a text encoder and a Siamese audio encoder, capturing acoustic cues around sentence boundaries. Experiments on a large-scale dataset of YouTube videos show substantial gains over text-only and multi-modal baselines. Our model also proves more resilient to ASR noise and outperforms a larger text-only baseline on three additional datasets in Portuguese, German, and English, underscoring the value of learned acoustic features for robust topic segmentation.

---

### Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrations

Authors: Ruiqian Nai, Boyuan Zheng, Junming Zhao, Haodong Zhu, Sicong Dai, Zunhao Chen, Yihang Hu, Yingdong Hu, Tong Zhang, Chuan Wen, Yang Gao
Published: 2026-02-06
Categories: cs.RO, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.06643v2

Current approaches for humanoid whole-body manipulation, primarily relying on teleoperation or visual sim-to-real reinforcement learning, are hindered by hardware logistics and complex reward engineering. Consequently, demonstrated autonomous skills remain limited and are typically restricted to controlled environments. In this paper, we present the Humanoid Manipulation Interface (HuMI), a portable and efficient framework for learning diverse whole-body manipulation tasks across various environments. HuMI enables robot-free data collection by capturing rich whole-body motion using portable hardware. This data drives a hierarchical learning pipeline that translates human motions into dexterous and feasible humanoid skills. Extensive experiments across five whole-body tasks--including kneeling, squatting, tossing, walking, and bimanual manipulation--demonstrate that HuMI achieves a 3x increase in data collection efficiency compared to teleoperation and attains a 70% success rate in unseen environments.

---

### Temperature Scaling Attack Disrupting Model Confidence in Federated Learning

Authors: Kichang Lee, Jaeho Jin, JaeYeon Park, Songkuk Kim, JeongGil Ko
Published: 2026-02-06
Categories: cs.LG, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2602.06638v3

Predictive confidence serves as a foundational control signal in mission-critical systems, directly governing risk-aware logic such as escalation, abstention, and conservative fallback. While prior federated learning attacks predominantly target accuracy or implant backdoors, we identify confidence calibration as a distinct attack objective. We present the Temperature Scaling Attack (TSA), a training-time attack that degrades calibration while preserving accuracy. By injecting temperature scaling with learning rate-temperature coupling during local training, TSA shifts model confidence while keeping predictive accuracy and common optimization signals close to benign training. We provide a convergence analysis under non-IID settings, showing that the coupling controls the primary update scale while leaving a bounded temperature-induced residual, yielding the standard non-convex FL convergence structure with an additional residual term. Across three benchmarks, TSA substantially shifts calibration (e.g., 145% error increase on CIFAR-100) with <2% accuracy change, and remains effective under robust aggregation and post-hoc calibration defenses. Case studies further show up to a 7.2x increase in missed verifications in healthcare and severe confidence-gating failures in autonomous driving, even when accuracy is unchanged. Overall, our results establish calibration integrity as a critical attack surface in federated learning.

---

### Temperature Scaling Attack Disrupting Model Confidence in Federated Learning

Authors: Kichang Lee, Jaeho Jin, JaeYeon Park, Songkuk Kim, JeongGil Ko
Published: 2026-02-06
Categories: cs.LG, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2602.06638v2

Predictive confidence serves as a foundational control signal in mission-critical systems, directly governing risk-aware logic such as escalation, abstention, and conservative fallback. While prior federated learning attacks predominantly target accuracy or implant backdoors, we identify confidence calibration as a distinct attack objective. We present the Temperature Scaling Attack (TSA), a training-time attack that degrades calibration while preserving accuracy. By injecting temperature scaling with learning rate-temperature coupling during local training, malicious updates maintain benign-like optimization behavior, evading accuracy-based monitoring and similarity-based detection. We provide a convergence analysis under non-IID settings, showing that this coupling preserves standard convergence bounds while systematically distorting confidence. Across three benchmarks, TSA substantially shifts calibration (e.g., 145% error increase on CIFAR-100) with <2 accuracy change, and remains effective under robust aggregation and post-hoc calibration defenses. Case studies further show that confidence manipulation can cause up to 7.2x increases in missed critical cases (healthcare) or false alarms (autonomous driving), even when accuracy is unchanged. Overall, our results establish calibration integrity as a critical attack surface in federated learning.

---

### Graph-Based Nearest-Neighbor Search without the Spread

Authors: Jeff Giliberti, Sariel Har-Peled, Jonas Sauer, Ali Vakilian
Published: 2026-02-06
Categories: cs.CG, cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2602.06633v1

$\renewcommand{\Re}{\mathbb{R}}$Recent work showed how to construct nearest-neighbor graphs of linear size, on a given set $P$ of $n$ points in $\Re^d$, such that one can answer approximate nearest-neighbor queries in logarithmic time in the spread. Unfortunately, the spread might be unbounded in $n$, and an interesting theoretical question is how to remove the dependency on the spread. Here, we show how to construct an external linear-size data structure that, combined with the linear-size graph, allows us to answer ANN queries in logarithmic time in $n$.

---

### Trust Regions Sell, But Who's Buying? Overlap Geometry as an Alternative Trust Region for Policy Optimization

Authors: Gaurish Trivedi, Alakh Sharma, Kartikey Singh Bhandari, Yash Sinha, Pratik Narang, Dhruv Kumar, Jagat Sesh Challa
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06627v1

Standard trust-region methods constrain policy updates via Kullback-Leibler (KL) divergence. However, KL controls only an average divergence and does not directly prevent rare, large likelihood-ratio excursions that destabilize training--precisely the failure mode that motivates heuristics such as PPO's clipping. We propose overlap geometry as an alternative trust region, constraining distributional overlap via the Bhattacharyya coefficient (closely related to the Hellinger/Renyi-1/2 geometry). This objective penalizes separation in the ratio tails, yielding tighter control over likelihood-ratio excursions without relying on total variation bounds that can be loose in tail regimes. We derive Bhattacharyya-TRPO (BTRPO) and Bhattacharyya-PPO (BPPO), enforcing overlap constraints via square-root ratio updates: BPPO clips the square-root ratio q = sqrt(r), and BTRPO applies a quadratic Hellinger/Bhattacharyya penalty. Empirically, overlap-based updates improve robustness and aggregate performance as measured by RLiable under matched training budgets, suggesting overlap constraints as a practical, principled alternative to KL for stable policy optimization.

---

### FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge

Authors: Bo Yang, Lanfei Feng, Yunkui Chen, Yu Zhang, Xiao Xu, Shijian Li
Published: 2026-02-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06625v2

Existing LLM-as-a-Judge systems suffer from three fundamental limitations: limited adaptivity to task- and domain-specific evaluation criteria, systematic biases driven by non-semantic cues such as position, length, format, and model provenance, and evaluation inconsistency that leads to contradictory judgments across different evaluation modes (e.g., pointwise versus pairwise). To address these issues, we propose FairJudge, an adaptive, debiased, and consistent LLM-as-a-Judge. Unlike prior approaches that treat the judge as a static evaluator, FairJudge models judging behavior itself as a learnable and regularized policy. From a data-centric perspective, we construct a high-information-density judging dataset that explicitly injects supervision signals aligned with evaluation behavior. Building on this dataset, we adopt a curriculum-style SFT-DPO-GRPO training paradigm that progressively aligns rubric adherence, bias mitigation, and cross-mode consistency, while avoiding catastrophic forgetting. Experimental results on multiple internal and public benchmarks show that FairJudge consistently improves agreement and F1, reduces non-semantic biases, and outperforms substantially larger instruction-tuned LLMs. All resources will be publicly released after acceptance to facilitate future research.

---

### Do Prompts Guarantee Safety? Mitigating Toxicity from LLM Generations through Subspace Intervention

Authors: Himanshu Singh, Ziwei Xu, A. V. Subramanyam, Mohan Kankanhalli
Published: 2026-02-06
Categories: cs.CL, cs.CR
arXiv: https://arxiv.org/abs/2602.06623v1

Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often subtle and context-dependent, making it difficult to detect at the token level or through coarse sentence-level signals. Moreover, efforts to mitigate toxicity often face a trade-off between safety and the coherence, or fluency of the generated text. In this work, we present a targeted subspace intervention strategy for identifying and suppressing hidden toxic patterns from underlying model representations, while preserving overall ability to generate safe fluent content. On the RealToxicityPrompts, our method achieves strong mitigation performance compared to existing baselines, with minimal impact on inference complexity. Across multiple LLMs, our approach reduces toxicity of state-of-the-art detoxification systems by 8-20%, while maintaining comparable fluency. Through extensive quantitative and qualitative analyses, we show that our approach achieves effective toxicity reduction without impairing generative performance, consistently outperforming existing baselines.

---

### Infinite-dimensional generative diffusions via Doob's h-transform

Authors: Thorben Pieper-Sethmacher, Daniel Paulin
Published: 2026-02-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.06621v2

This paper introduces a rigorous framework for defining generative diffusion models in infinite dimensions via Doob's h-transform. Rather than relying on time reversal of a noising process, a reference diffusion is forced towards the target distribution by an exponential change of measure. Compared to existing methodology, this approach readily generalises to the infinite-dimensional setting, hence offering greater flexibility in the diffusion model. The construction is derived rigorously under verifiable conditions, and bounds with respect to the target measure are established. We show that the forced process under the changed measure can be approximated by minimising a score-matching objective and validate our method on both synthetic and real data.

---

### Infinite-dimensional generative diffusions via Doob's h-transform

Authors: Thorben Pieper-Sethmacher, Daniel Paulin
Published: 2026-02-06
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.06621v1

This paper introduces a rigorous framework for defining generative diffusion models in infinite dimensions via Doob's h-transform. Rather than relying on time reversal of a noising process, a reference diffusion is forced towards the target distribution by an exponential change of measure. Compared to existing methodology, this approach readily generalises to the infinite-dimensional setting, hence offering greater flexibility in the diffusion model. The construction is derived rigorously under verifiable conditions, and bounds with respect to the target measure are established. We show that the forced process under the changed measure can be approximated by minimising a score-matching objective and validate our method on both synthetic and real data.

---

### CauCLIP: Bridging the Sim-to-Real Gap in Surgical Video Understanding via Causality-Inspired Vision-Language Modeling

Authors: Yuxin He, An Li, Cheng Xue
Published: 2026-02-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06619v1

Surgical phase recognition is a critical component for context-aware decision support in intelligent operating rooms, yet training robust models is hindered by limited annotated clinical videos and large domain gaps between synthetic and real surgical data. To address this, we propose CauCLIP, a causality-inspired vision-language framework that leverages CLIP to learn domain-invariant representations for surgical phase recognition without access to target domain data. Our approach integrates a frequency-based augmentation strategy to perturb domain-specific attributes while preserving semantic structures, and a causal suppression loss that mitigates non-causal biases and reinforces causal surgical features. These components are combined in a unified training framework that enables the model to focus on stable causal factors underlying surgical workflows. Experiments on the SurgVisDom hard adaptation benchmark demonstrate that our method substantially outperforms all competing approaches, highlighting the effectiveness of causality-guided vision-language models for domain-generalizable surgical video understanding.

---

### Confundo: Learning to Generate Robust Poison for Practical RAG Systems

Authors: Haoyang Hu, Zhejun Jiang, Yueming Lyu, Junyuan Zhang, Yi Liu, Ka-Ho Chow
Published: 2026-02-06
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2602.06616v1

Retrieval-augmented generation (RAG) is increasingly deployed in real-world applications, where its reference-grounded design makes outputs appear trustworthy. This trust has spurred research on poisoning attacks that craft malicious content, inject it into knowledge sources, and manipulate RAG responses. However, when evaluated in practical RAG systems, existing attacks suffer from severely degraded effectiveness. This gap stems from two overlooked realities: (i) content is often processed before use, which can fragment the poison and weaken its effect, and (ii) users often do not issue the exact queries anticipated during attack design. These factors can lead practitioners to underestimate risks and develop a false sense of security. To better characterize the threat to practical systems, we present Confundo, a learning-to-poison framework that fine-tunes a large language model as a poison generator to achieve high effectiveness, robustness, and stealthiness. Confundo provides a unified framework supporting multiple attack objectives, demonstrated by manipulating factual correctness, inducing biased opinions, and triggering hallucinations. By addressing these overlooked challenges, Confundo consistently outperforms a wide range of purpose-built attacks across datasets and RAG configurations by large margins, even in the presence of defenses. Beyond exposing vulnerabilities, we also present a defensive use case that protects web content from unauthorized incorporation into RAG systems via scraping, with no impact on user experience.

---

### DAVE: Distribution-aware Attribution via ViT Gradient Decomposition

Authors: Adam Wróbel, Siddhartha Gairola, Jacek Tabor, Bernt Schiele, Bartosz Zieliński, Dawid Rymarczyk
Published: 2026-02-06
Categories: cs.CV, cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2602.06613v1

Vision Transformers (ViTs) have become a dominant architecture in computer vision, yet producing stable and high-resolution attribution maps for these models remains challenging. Architectural components such as patch embeddings and attention routing often introduce structured artifacts in pixel-level explanations, causing many existing methods to rely on coarse patch-level attributions. We introduce DAVE \textit{(\underline{D}istribution-aware \underline{A}ttribution via \underline{V}iT Gradient D\underline{E}composition)}, a mathematically grounded attribution method for ViTs based on a structured decomposition of the input gradient. By exploiting architectural properties of ViTs, DAVE isolates locally equivariant and stable components of the effective input--output mapping. It separates these from architecture-induced artifacts and other sources of instability.

---

### Adaptive-CaRe: Adaptive Causal Regularization for Robust Outcome Prediction

Authors: Nithya Bhasker, Fiona R. Kolbinger, Susu Hu, Gitta Kutyniok, Stefanie Speidel
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06611v1

Accurate prediction of outcomes is crucial for clinical decision-making and personalized patient care. Supervised machine learning algorithms, which are commonly used for outcome prediction in the medical domain, optimize for predictive accuracy, which can result in models latching onto spurious correlations instead of robust predictors. Causal structure learning methods on the other hand have the potential to provide robust predictors for the target, but can be too conservative because of algorithmic and data assumptions, resulting in loss of diagnostic precision. Therefore, we propose a novel model-agnostic regularization strategy, Adaptive-CaRe, for generalized outcome prediction in the medical domain. Adaptive-CaRe strikes a balance between both predictive value and causal robustness by incorporating a penalty that is proportional to the difference between the estimated statistical contribution and estimated causal contribution of the input features for model predictions. Our experiments on synthetic data establish the efficacy of the proposed Adaptive-CaRe regularizer in finding robust predictors for the target while maintaining competitive predictive accuracy. With experiments on a standard causal benchmark, we provide a blueprint for navigating the trade-off between predictive accuracy and causal robustness by tweaking the regularization strength, $λ$. Validation using real-world dataset confirms that the results translate to practical, real-domain settings. Therefore, Adaptive-CaRe provides a simple yet effective solution to the long-standing trade-off between predictive accuracy and causal robustness in the medical domain. Future work would involve studying alternate causal structure learning frameworks and complex classification models to provide deeper insights at a larger scale.

---

### Green Optimization: Energy-aware Design of Metaheuristics by Using Machine Learning Surrogates to Cope with Real Problems

Authors: Tomohiro Harada, Enrique Alba, Gabriel Luque
Published: 2026-02-06
Categories: cs.NE
arXiv: https://arxiv.org/abs/2602.06610v2

Addressing real-world optimization challenges requires not only advanced metaheuristics but also continuous refinement of their internal mechanisms. This paper explores the integration of machine learning in the form of neural surrogate models into metaheuristics through a recent lens: energy consumption. While surrogates are widely used to reduce the computational cost of expensive objective functions, their combined impact on energy efficiency, algorithmic performance, and solution accuracy remains largely unquantified. We provide a critical investigation into this intersection, aiming to advance the design of energy-aware, surrogate-assisted search algorithms. Our experiments reveal substantial benefits: employing a state-of-the-art pre-trained surrogate can reduce energy consumption by up to 98\%, execution time by approximately 98%, and memory usage by around 99\%. Moreover, increasing the training dataset size further enhances these gains by lowering the per-use computational cost, while static pre-training versus continuous (iterative) retraining have relatively different advantages depending on whether we aim at time/energy or accuracy and general cost across problems, respectively. Surrogates also have a negative impact on costs and accuracy at times, and then they cannot be blindly adopted. These findings support a more holistic approach to surrogate-assisted optimization, integrating energy with time and predictive accuracy into performance assessments.

---

### The challenge of generating and evolving real-life like synthetic test data without accessing real-world raw data -- a Systematic Review

Authors: Maj-Annika Tammisto, Faiz Ali Shah, Daniel Rodriguez, Dietmar Pfahl
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06609v1

Background: High-level system testing of applications that use data from e-Government services as input requires test data that is real-life-like but where the privacy of personal information is guaranteed. Applications with such strong requirement include information exchange between countries, medicine, banking, etc. This review aims to synthesize the current state-of-the-practice in this domain. Objectives: The objective of this Systematic Review is to identify existing approaches for creating and evolving synthetic test data without using real-life raw data. Methods: We followed well-known methodologies for conducting systematic literature reviews, including the ones from Kitchenham as well as guidelines for analysing the limitations of our review and its threats to validity. Results: A variety of methods and tools exist for creating privacy-preserving test data. Our search found 1,013 publications in IEEE Xplore, ACM Digital Library, and SCOPUS. We extracted data from 75 of those publications and identified 37 approaches that answer our research question partly. A common prerequisite for using these methods and tools is direct access to real-life data for data anonymization or synthetic test data generation. Nine existing synthetic test data generation approaches were identified that were closest to answering our research question. Nevertheless, further work would be needed to add the ability to evolve synthetic test data to the existing approaches. Conclusions: None of the publications really covered our requirements completely, only partially. Synthetic test data evolution is a field that has not received much attention from researchers but needs to be explored in Digital Government Solutions, especially since new legal regulations are being placed in force in many countries.

---

### The hidden risks of temporal resampling in clinical reinforcement learning

Authors: Thomas Frost, Hrisheekesh Vaidya, Steve Harris
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06603v3

Reinforcement learning (RL) is a type of artificial intelligence for making optimal choices. In healthcare, researchers generally use offline RL (ORL), where models are trained and evaluated from retrospective observational data. To accommodate inherently irregular clinical records, researchers often resample the data into uniform time intervals before training (known as binning). However, discretised data presents the model with a fictional representation of clinical scenarios, especially where unpredictable decision timings are common. As these models lack robust trial evidence, we chose to explore the effects of this further by conducting an in silico clinical trial using 30 virtual patients with type 1 diabetes from the FDA-approved UVA/Padova simulator. The simulator was modified to include stochastic intervals between decisions and used to generate a training dataset for offline RL. We trained three ORL algorithms on both the unprocessed dataset and equivalent datasets resampled at 10-minute, 2-hour, and 4-hour intervals. When deployed back into the simulated environment, temporal resampling was found to reduce model performance by up to 60% relative to unprocessed data, with 4-hour binning causing all agents to perform worse than the dataset's baseline. Retrospective evaluation on resampled data actively obscured this effect, predicting 1.5-3x better returns than agents achieved in practice. We recommend that future research in this area prioritises datasets with natural clinical timings between decisions, which may be a necessary step before these models can be safely deployed into patient care.

---

### Scaling Speech Tokenizers with Diffusion Autoencoders

Authors: Yuancheng Wang, Zhenyu Tang, Yun Wang, Arthur Hinsvark, Yingru Liu, Yinghao Li, Kainan Peng, Junyi Ao, Mingbo Ma, Mike Seltzer, Qing He, Xubo Liu
Published: 2026-02-06
Categories: cs.SD, cs.AI, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2602.06602v1

Speech tokenizers are foundational to speech language models, yet existing approaches face two major challenges: (1) balancing trade-offs between encoding semantics for understanding and acoustics for reconstruction, and (2) achieving low bit rates and low token rates. We propose Speech Diffusion Tokenizer (SiTok), a diffusion autoencoder that jointly learns semantic-rich representations through supervised learning and enables high-fidelity audio reconstruction with diffusion. We scale SiTok to 1.6B parameters and train it on 2 million hours of speech. Experiments show that SiTok outperforms strong baselines on understanding, reconstruction and generation tasks, at an extremely low token rate of $12.5$ Hz and a bit-rate of 200 bits-per-second.

---

### Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning

Authors: Zhuoyuan Hao, Zhuo Li, Wu Li, Fangming Liu, Min Zhang, Jing Li
Published: 2026-02-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06600v1

Test-time compute allocation in large reasoning models (LRMs) is widely used and has applications in mathematical problem solving, code synthesis, and planning. Recent work has addressed this problem by scaling self-consistency and parallel thinking, adding generic ``thinking tokens'' and prompting models to re-read the question before answering. Unfortunately, these approaches either inject task-agnostic tokens or mandate heuristics that do not explain -- and often ignore -- the \emph{spontaneous} repetition that many LRMs exhibit at the head of their internal chains. In contrast, we analyze and harness the model's tendency to restate the question, which we term the \emph{Echo of Prompt (EOP)}, as a front-loaded, compute-shaping mechanism. We formalize its probabilistic cost by casting echo removal as rejection-based conditioning and defining the \emph{Echo Likelihood Gap} $Δ\mathcal{L}$ as a computable proxy. This provides the missing theoretical link that links early repetition to likelihood gains and downstream accuracy. However, it does not by itself specify how to exploit EOP. Consequently, we develop \emph{Echo-Distilled SFT (ED-SFT)} to instill an ``echo-then-reason'' pattern through supervised finetuning, and \emph{Echoic Prompting (EP)} to re-ground the model mid-trace without training. While promising, quantifying benefits beyond verbosity is non-trivial. Therefore, we conduct length and suffix-controlled likelihood analyses together with layer-wise attention studies, showing that EOP increases answer to answer-prefix attention in middle layers, consistent with an \emph{attention refocusing} mechanism. We evaluate on GSM8K, MathQA, Hendrycks-MATH, AIME24, and MATH-500 under identical decoding settings and budgets, and find consistent gains over baselines. Code is available at https://github.com/hhh2210/echoes-as-anchors.

---

### Sample-Efficient Policy Space Response Oracles with Joint Experience Best Response

Authors: Ariyan Bighashdel, Thiago D. Simão, Frans A. Oliehoek
Published: 2026-02-06
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.06599v1

Multi-agent reinforcement learning (MARL) offers a scalable alternative to exact game-theoretic analysis but suffers from non-stationarity and the need to maintain diverse populations of strategies that capture non-transitive interactions. Policy Space Response Oracles (PSRO) address these issues by iteratively expanding a restricted game with approximate best responses (BRs), yet per-agent BR training makes it prohibitively expensive in many-agent or simulator-expensive settings. We introduce Joint Experience Best Response (JBR), a drop-in modification to PSRO that collects trajectories once under the current meta-strategy profile and reuses this joint dataset to compute BRs for all agents simultaneously. This amortizes environment interaction and improves the sample efficiency of best-response computation. Because JBR converts BR computation into an offline RL problem, we propose three remedies for distribution-shift bias: (i) Conservative JBR with safe policy improvement, (ii) Exploration-Augmented JBR that perturbs data collection and admits theoretical guarantees, and (iii) Hybrid BR that interleaves JBR with periodic independent BR updates. Across benchmark multi-agent environments, Exploration-Augmented JBR achieves the best accuracy-efficiency trade-off, while Hybrid BR attains near-PSRO performance at a fraction of the sample cost. Overall, JBR makes PSRO substantially more practical for large-scale strategic learning while preserving equilibrium robustness.

---

### DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters

Authors: Haoran Zhang, Haixuan Liu, Yong Liu, Yunzhong Qiu, Yuxuan Wang, Jianmin Wang, Mingsheng Long
Published: 2026-02-06
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.06597v1

While generative modeling on time series facilitates more capable and flexible probabilistic forecasting, existing generative time series models do not address the multi-dimensional properties of time series data well. The prevalent architecture of Diffusion Transformers (DiT), which relies on simplistic conditioning controls and a single-stream Transformer backbone, tends to underutilize cross-variate dependencies in covariate-aware forecasting. Inspired by Multimodal Diffusion Transformers that integrate textual guidance into video generation, we propose Diffusion Transformers for Time Series (DiTS), a general-purpose architecture that frames endogenous and exogenous variates as distinct modalities. To better capture both inter-variate and intra-variate dependencies, we design a dual-stream Transformer block tailored for time-series data, comprising a Time Attention module for autoregressive modeling along the temporal dimension and a Variate Attention module for cross-variate modeling. Unlike the common approach for images, which flattens 2D token grids into 1D sequences, our design leverages the low-rank property inherent in multivariate dependencies, thereby reducing computational costs. Experiments show that DiTS achieves state-of-the-art performance across benchmarks, regardless of the presence of future exogenous variate observations, demonstrating unique generative forecasting strengths over traditional deterministic deep forecasting models.

---

### Personality as Relational Infrastructure: User Perceptions of Personality-Trait-Infused LLM Messaging

Authors: Dominik P. Hofer, David Haag, Rania Islambouli, Jan D. Smeddinck
Published: 2026-02-06
Categories: cs.HC, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.06596v2

Digital behaviour change systems increasingly rely on repeated, system-initiated messages to support users in everyday contexts. LLMs enable these messages to be personalised consistently across interactions, yet it remains unclear whether such personalisation improves individual messages or instead shapes users' perceptions through patterns of exposure. We explore this question in the context of LLM-generated JITAIs, which are short, context-aware messages delivered at moments deemed appropriate to support behaviour change, using physical activity as an application domain. In a controlled retrospective study, 90 participants evaluated messages generated using four LLM strategies: baseline prompting, few-shot prompting, fine-tuned models, and retrieval augmented generation, each implemented with and without Big Five Personality Traits to produce personality-aligned communication across multiple scenarios. Using ordinal multilevel models with within-between decomposition, we distinguish trial-level effects, whether personality information improves evaluations of individual messages, from person-level exposure effects, whether participants receiving higher proportions of personality-informed messages exhibit systematically different overall perceptions. Results showed no trial-level associations, but participants who received higher proportions of BFPT-informed messages rated the messages as more personalised, appropriate, and reported less negative affect. We use Communication Accommodation Theory for post-hoc analysis. These results suggest that personality-based personalisation in behaviour change systems may operate primarily through aggregate exposure rather than per-message optimisation, with implications for how adaptive systems are designed and evaluated in sustained human-AI interaction. In-situ longitudinal studies are needed to validate these findings in real-world contexts.

---

### Energy-Aware Metaheuristics

Authors: Enrique Alba, Tomohiro Harada, Gabriel Luque
Published: 2026-02-06
Categories: cs.NE
arXiv: https://arxiv.org/abs/2602.06595v5

This paper presents a principled framework for designing energy-aware metaheuristics that operate under fixed energy budgets. We introduce a unified operator-level model that quantifies both numerical gain and energy usage, and define a robust Expected Improvement per Joule (EI/J) score that guides adaptive selection among operator variants during the search. The resulting energy-aware solvers dynamically choose between operators to self-control exploration and exploitation, aiming to maximize fitness gain under limited energy. We instantiate this framework with three representative metaheuristics - steady-state GA, PSO, and ILS - each equipped with both lightweight and heavy operator variants. Experiments on three heterogeneous combinatorial problems (Knapsack, NK-landscapes, and Error-Correcting Codes) show that the energy-aware variants consistently reach comparable fitness while requiring substantially less energy than their non-energy-aware baselines. EI/J values stabilize early and yield clear operator-selection patterns, with each solver reliably self-identifying the most improvement-per-Joule - efficient operator across problems.

---

### AgentStepper: Interactive Debugging of Software Development Agents

Authors: Robert Hutter, Michael Pradel
Published: 2026-02-06
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2602.06593v1

Software development agents powered by large language models (LLMs) have shown great promise in automating tasks like environment setup, issue solving, and program repair. Unfortunately, understanding and debugging such agents remain challenging due to their complex and dynamic nature. Developers must reason about trajectories of LLM queries, tool calls, and code modifications, but current techniques reveal little of this intermediate process in a comprehensible format. The key insight of this paper is that debugging software development agents shares many similarities with conventional debugging of software programs, yet requires a higher level of abstraction that raises the level from low-level implementation details to high-level agent actions. Drawing on this insight, we introduce AgentStepper, the first interactive debugger for LLM-based software engineering agents. AgentStepper enables developers to inspect, control, and interactively manipulate agent trajectories. AgentStepper represents trajectories as structured conversations among an LLM, the agent program, and tools. It supports breakpoints, stepwise execution, and live editing of prompts and tool invocations, while capturing and displaying intermediate repository-level code changes. Our evaluation applies AgentStepper to three state-of-the-art software development agents, ExecutionAgent, SWE-Agent, and RepairAgent, showing that integrating the approach into existing agents requires minor code changes (39-42 edited lines). Moreover, we report on a user study with twelve participants, indicating that AgentStepper improves the ability of participants to interpret trajectories (64% vs. 67% mean performance) and identify bugs in the agent's implementation (17% vs. 60% success rate), while reducing perceived workload (e.g., frustration reduced from 5.4/7.0 to 2.4/7.0) compared to conventional tools.

---

### ProtoQuant: Quantization of Prototypical Parts For General and Fine-Grained Image Classification

Authors: Mikołaj Janusz, Adam Wróbel, Bartosz Zieliński, Dawid Rymarczyk
Published: 2026-02-06
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.06592v1

Prototypical parts-based models offer a "this looks like that" paradigm for intrinsic interpretability, yet they typically struggle with ImageNet-scale generalization and often require computationally expensive backbone finetuning. Furthermore, existing methods frequently suffer from "prototype drift," where learned prototypes lack tangible grounding in the training distribution and change their activation under small perturbations. We present ProtoQuant, a novel architecture that achieves prototype stability and grounded interpretability through latent vector quantization. By constraining prototypes to a discrete learned codebook within the latent space, we ensure they remain faithful representations of the training data without the need to update the backbone. This design allows ProtoQuant to function as an efficient, interpretable head that scales to large-scale datasets. We evaluate ProtoQuant on ImageNet and several fine-grained benchmarks (CUB-200, Cars-196). Our results demonstrate that ProtoQuant achieves competitive classification accuracy while generalizing to ImageNet and comparable interpretability metrics to other prototypical-parts-based methods.

---

### An Integer Linear Programming Approach to Geometrically Consistent Partial-Partial Shape Matching

Authors: Viktoria Ehm, Paul Roetzer, Florian Bernard, Daniel Cremers
Published: 2026-02-06
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06590v1

The task of establishing correspondences between two 3D shapes is a long-standing challenge in computer vision. While numerous studies address full-full and partial-full 3D shape matching, only a limited number of works have explored the partial-partial setting, very likely due to its unique challenges: we must compute accurate correspondences while at the same time find the unknown overlapping region. Nevertheless, partial-partial 3D shape matching reflects the most realistic setting, as in many real-world cases, such as 3D scanning, shapes are only partially observable. In this work, we introduce the first integer linear programming approach specifically designed to address the distinctive challenges of partial-partial shape matching. Our method leverages geometric consistency as a strong prior, enabling both robust estimation of the overlapping region and computation of neighbourhood-preserving correspondences. We empirically demonstrate that our approach achieves high-quality matching results both in terms of matching error and smoothness. Moreover, we show that our method is more scalable than previous formalisms.

---

### Degradation of Feature Space in Continual Learning

Authors: Chiara Lanza, Roberto Pereira, Marco Miozzo, Eduard Angelats, Paolo Dini
Published: 2026-02-06
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2602.06586v1

Centralized training is the standard paradigm in deep learning, enabling models to learn from a unified dataset in a single location. In such setup, isotropic feature distributions naturally arise as a mean to support well-structured and generalizable representations. In contrast, continual learning operates on streaming and non-stationary data, and trains models incrementally, inherently facing the well-known plasticity-stability dilemma. In such settings, learning dynamics tends to yield increasingly anisotropic feature space. This arises a fundamental question: should isotropy be enforced to achieve a better balance between stability and plasticity, and thereby mitigate catastrophic forgetting? In this paper, we investigate whether promoting feature-space isotropy can enhance representation quality in continual learning. Through experiments using contrastive continual learning techniques on CIFAR-10 and CIFAR-100 data, we find that isotropic regularization fails to improve, and can in fact degrade, model accuracy in continual settings. Our results highlight essential differences in feature geometry between centralized and continual learning, suggesting that isotropy, while beneficial in centralized setups, may not constitute an appropriate inductive bias for non-stationary learning scenarios.

---

### Target noise: A pre-training based neural network initialization for efficient high resolution learning

Authors: Shaowen Wang, Tariq Alkhalifah
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06585v1

Weight initialization plays a crucial role in the optimization behavior and convergence efficiency of neural networks. Most existing initialization methods, such as Xavier and Kaiming initializations, rely on random sampling and do not exploit information from the optimization process itself. We propose a simple, yet effective, initialization strategy based on self-supervised pre-training using random noise as the target. Instead of directly training the network from random weights, we first pre-train it to fit random noise, which leads to a structured and non-random parameter configuration. We show that this noise-driven pre-training significantly improves convergence speed in subsequent tasks, without requiring additional data or changes to the network architecture. The proposed method is particularly effective for implicit neural representations (INRs) and Deep Image Prior (DIP)-style networks, which are known to exhibit a strong low-frequency bias during optimization. After noise-based pre-training, the network is able to capture high-frequency components much earlier in training, leading to faster and more stable convergence. Although random noise contains no semantic information, it serves as an effective self-supervised signal (considering its white spectrum nature) for shaping the initialization of neural networks. Overall, this work demonstrates that noise-based pre-training offers a lightweight and general alternative to traditional random initialization, enabling more efficient optimization of deep neural networks.

---

### Inference-Time Rethinking with Latent Thought Vectors for Math Reasoning

Authors: Deqian Kong, Minglu Zhao, Aoyang Qin, Bo Pang, Chenxin Tao, David Hartmann, Edouardo Honig, Dehong Xu, Amit Kumar, Matt Sarte, Chuan Li, Jianwen Xie et al.
Published: 2026-02-06
Categories: cs.CL, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.06584v1

Standard chain-of-thought reasoning generates a solution in a single forward pass, committing irrevocably to each token and lacking a mechanism to recover from early errors. We introduce Inference-Time Rethinking, a generative framework that enables iterative self-correction by decoupling declarative latent thought vectors from procedural generation. We factorize reasoning into a continuous latent thought vector (what to reason about) and a decoder that verbalizes the trace conditioned on this vector (how to reason). Beyond serving as a declarative buffer, latent thought vectors compress the reasoning structure into a continuous representation that abstracts away surface-level token variability, making gradient-based optimization over reasoning strategies well-posed. Our prior model maps unstructured noise to a learned manifold of valid reasoning patterns, and at test time we employ a Gibbs-style procedure that alternates between generating a candidate trace and optimizing the latent vector to better explain that trace, effectively navigating the latent manifold to refine the reasoning strategy. Training a 0.2B-parameter model from scratch on GSM8K, our method with 30 rethinking iterations surpasses baselines with 10 to 15 times more parameters, including a 3B counterpart. This result demonstrates that effective mathematical reasoning can emerge from sophisticated inference-time computation rather than solely from massive parameter counts.

---

### Efficient Online Variational Estimation via Monte Carlo Sampling

Authors: Mathis Chagneux, Mathias Müller, Pierre Gloaguen, Sylvain Le Corff, Jimmy Olsson
Published: 2026-02-06
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.06579v1

This article addresses online variational estimation in parametric state-space models. We propose a new procedure for efficiently computing the evidence lower bound and its gradient in a streaming-data setting, where observations arrive sequentially. The algorithm allows for the simultaneous training of the model parameters and the distribution of the latent states given the observations. It is based on i.i.d. Monte Carlo sampling, coupled with a well-chosen deep architecture, enabling both computational efficiency and flexibility. The performance of the method is illustrated on both synthetic data and real-world air-quality data. The proposed approach is theoretically motivated by the existence of an asymptotic contrast function and the ergodicity of the underlying Markov chain, and applies more generally to the computation of additive expectations under posterior distributions in state-space models.

---

### Exploring Sparsity and Smoothness of Arbitrary Lp Norms in Adversarial Attacks

Authors: Christof Duhme, Florian Eilers, Xiaoyi Jiang
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06578v2

Adversarial attacks against deep neural networks are commonly constructed under $\ell_p$ norm constraints, most often using $p=1$, $p=2$ or $p=\infty$, and potentially regularized for specific demands such as sparsity or smoothness. These choices are typically made without a systematic investigation of how the norm parameter $p$ influences the structural and perceptual properties of adversarial perturbations. In this work, we study how the choice of $p$ affects sparsity and smoothness of adversarial attacks generated under $\ell_p$ norm constraints for values of $p \in (1,2)$. To enable a quantitative analysis, we adopt two established sparsity measures from the literature and introduce three smoothness measures. In particular, we propose a general framework for deriving smoothness measures based on smoothing operations and additionally introduce a smoothness measure based on first-order Taylor approximations. Using these measures, we conduct a comprehensive empirical evaluation across multiple real-world image datasets and a diverse set of model architectures, including both convolutional and transformer-based networks. We show that the choice of $\ell_1$ or $\ell_2$ is suboptimal in most cases and the optimal $p$ value is dependent on the specific task. In our experiments, using $\ell_p$ norms with $p\in (1.3, 1.5)$ yields the best trade-off between sparse and smooth attacks. These findings highlight the importance of principled norm selection when designing and evaluating adversarial attacks.

---

### Exploring Sparsity and Smoothness of Arbitrary $\ell_p$ Norms in Adversarial Attacks

Authors: Christof Duhme, Florian Eilers, Xiaoyi Jiang
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06578v1

Adversarial attacks against deep neural networks are commonly constructed under $\ell_p$ norm constraints, most often using $p=1$, $p=2$ or $p=\infty$, and potentially regularized for specific demands such as sparsity or smoothness. These choices are typically made without a systematic investigation of how the norm parameter \( p \) influences the structural and perceptual properties of adversarial perturbations. In this work, we study how the choice of \( p \) affects sparsity and smoothness of adversarial attacks generated under \( \ell_p \) norm constraints for values of $p \in (1,2)$. To enable a quantitative analysis, we adopt two established sparsity measures from the literature and introduce three smoothness measures. In particular, we propose a general framework for deriving smoothness measures based on smoothing operations and additionally introduce a smoothness measure based on first-order Taylor approximations. Using these measures, we conduct a comprehensive empirical evaluation across multiple real-world image datasets and a diverse set of model architectures, including both convolutional and transformer-based networks. We show that the choice of $\ell_1$ or $\ell_2$ is suboptimal in most cases and the optimal $p$ value is dependent on the specific task. In our experiments, using $\ell_p$ norms with $p\in (1.3, 1.5)$ yields the best trade-off between sparse and smooth attacks. These findings highlight the importance of principled norm selection when designing and evaluating adversarial attacks.

---

### Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks

Authors: Florian Eilers, Christof Duhme, Xiaoyi Jiang
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06577v2

Complex-valued neural networks (CVNNs) are rising in popularity for all kinds of applications. To safely use CVNNs in practice, analyzing their robustness against outliers is crucial. One well known technique to understand the behavior of deep neural networks is to investigate their behavior under adversarial attacks, which can be seen as worst case minimal perturbations. We design Phase Attacks, a kind of attack specifically targeting the phase information of complex-valued inputs. Additionally, we derive complex-valued versions of commonly used adversarial attacks. We show that in some scenarios CVNNs are more robust than RVNNs and that both are very susceptible to phase changes with the Phase Attacks decreasing the model performance more, than equally strong regular attacks, which can attack both phase and magnitude.

---

### Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks

Authors: Florian Eilers, Christof Duhme, Xiaoyi Jiang
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06577v1

Complex-valued neural networks (CVNNs) are rising in popularity for all kinds of applications. To safely use CVNNs in practice, analyzing their robustness against outliers is crucial. One well known technique to understand the behavior of deep neural networks is to investigate their behavior under adversarial attacks, which can be seen as worst case minimal perturbations. We design Phase Attacks, a kind of attack specifically targeting the phase information of complex-valued inputs. Additionally, we derive complex-valued versions of commonly used adversarial attacks. We show that in some scenarios CVNNs are more robust than RVNNs and that both are very susceptible to phase changes with the Phase Attacks decreasing the model performance more, than equally strong regular attacks, which can attack both phase and magnitude.

---

### Think Proprioceptively: State-Grounded Visual Token Selection for VLA Policies

Authors: Fangyuan Wang, Peng Zhou, Jiaming Qi, Shipeng Lyu, Chengyang He, David Navarro-Alarcon, Guodong Guo
Published: 2026-02-06
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.06575v2

Vision-language-action (VLA) models typically inject proprioception only as a late conditioning signal, preventing robot state from grounding instruction understanding or directing visual attention. We introduce ThinkProprio, which discretizes proprioception into VLM-vocabulary tokens and uses them jointly with the instruction to gate visual patches before VLM computation, steering the model toward action-relevant evidence while discarding redundant tokens early. We find that proprioception added as a passive conditioning signal leaves performance essentially unchanged; its value emerges when token-form state acts as an active query that, with the instruction, selects which visual patches the VLM processes. Systematic ablations show that VLM-vocabulary tokens outperform learned projectors as the state encoding, and that retaining only about \SI{12}{\percent} of the visual tokens surpasses on CALVIN ABC$\to$D. Across CALVIN, LIBERO, and real-world manipulation, ThinkProprio reduces end-to-end inference latency while improving the matched full-token baseline.

---

### Transformer-based Parameter Fitting of Models derived from Bloch-McConnell Equations for CEST MRI Analysis

Authors: Christof Duhme, Chris Lippe, Verena Hoerr, Xiaoyi Jiang
Published: 2026-02-06
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.06574v1

Chemical exchange saturation transfer (CEST) MRI is a non-invasive imaging modality for detecting metabolites. It offers higher resolution and sensitivity compared to conventional magnetic resonance spectroscopy (MRS). However, quantification of CEST data is challenging because the measured signal results from a complex interplay of many physiological variables. Here, we introduce a transformer-based neural network to fit parameters such as metabolite concentrations, exchange and relaxation rates of a physical model derived from Bloch-McConnell equations to in-vitro CEST spectra. We show that our self-supervised trained neural network clearly outperforms the solution of classical gradient-based solver.

---

### Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making

Authors: Baichuan-M3 Team, :, Chengfeng Dou, Fan Yang, Fei Li, Jiyuan Jia, Qiang Ju, Shuai Wang, Tianpeng Li, Xiangrong Zeng, Yijie Zhou, Hongda Zhang et al.
Published: 2026-02-06
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.06570v1

We introduce Baichuan-M3, a medical-enhanced large language model engineered to shift the paradigm from passive question-answering to active, clinical-grade decision support. Addressing the limitations of existing systems in open-ended consultations, Baichuan-M3 utilizes a specialized training pipeline to model the systematic workflow of a physician. Key capabilities include: (i) proactive information acquisition to resolve ambiguity; (ii) long-horizon reasoning that unifies scattered evidence into coherent diagnoses; and (iii) adaptive hallucination suppression to ensure factual reliability. Empirical evaluations demonstrate that Baichuan-M3 achieves state-of-the-art results on HealthBench, the newly introduced HealthBench-Hallu and ScanBench, significantly outperforming GPT-5.2 in clinical inquiry, advisory and safety. The models are publicly available at https://huggingface.co/collections/baichuan-inc/baichuan-m3.

---

### SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs

Authors: Niccolo Avogaro, Nayanika Debnath, Li Mi, Thomas Frick, Junling Wang, Zexue He, Hang Hua, Konrad Schindler, Mattia Rigotti
Published: 2026-02-06
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.06566v3

Despite recent successes, test-time scaling -- i.e., dynamically expanding the token budget during inference as needed -- remains brittle for vision-language models (VLMs). Unstructured visual reasoning chains entangle perception and reasoning, leading to long, disorganized contexts where small perceptual mistakes may cascade into completely wrong answers. Reasoning also requires expensive reinforcement learning with hand-crafted rewards. Here, we introduce SPARC (Separating Perception And Reasoning Circuits), a modular framework that explicitly decouples visual perception from reasoning. Inspired by sequential sensory-to-cognitive processing in the brain, SPARC implements a two-stage pipeline where the model first performs explicit visual search to localize question-relevant regions, then conditions its reasoning on those regions to produce the final answer. This separation enables independent test-time scaling with asymmetric compute allocation (e.g., prioritizing perceptual processing under distribution shift), and supports selective optimization (e.g., improving the perceptual stage alone when it is the bottleneck for end-to-end performance). It also accommodates compressed contexts by running global search at lower image resolutions and allocating high-resolution processing only to selected regions, thereby reducing visual token count and compute. SPARC outperforms monolithic baselines and strong visual-grounding approaches across challenging visual reasoning tasks, such as improving Qwen3VL 4B on the $V^*$ VQA benchmark by 6.7 points and surpassing "thinking with images" by 4.6 points in an OOD setting with a $200\times$ lower token budget.

---