# Research Papers — 2025-10 · bundle page 130 of 217

> Full-text markdown of papers #6451–6500 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-10/page/130
[← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/129.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-10/page/131.md)

### Causal Disentanglement Learning for Accurate Anomaly Detection in Multivariate Time Series

Authors: Wonah Kim, Jeonghyeon Park, Dongsan Jun, Jungkyu Han, Sejin Chun
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11084v1

Disentangling complex causal relationships is important for accurate detection of anomalies. In multivariate time series analysis, dynamic interactions among data variables over time complicate the interpretation of causal relationships. Traditional approaches assume statistical independence between variables in unsupervised settings, whereas recent methods capture feature correlations through graph representation learning. However, their representations fail to explicitly infer the causal relationships over different time periods. To solve the problem, we propose Causally Disentangled Representation Learning for Anomaly Detection (CDRL4AD) to detect anomalies and identify their causal relationships in multivariate time series. First, we design the causal process as model input, the temporal heterogeneous graph, and causal relationships. Second, our representation identifies causal relationships over different time periods and disentangles latent variables to infer the corresponding causal factors. Third, our experiments on real-world datasets demonstrate that CDRL4AD outperforms state-of-the-art methods in terms of accuracy and root cause analysis. Fourth, our model analysis validates hyperparameter sensitivity and the time complexity of CDRL4AD. Last, we conduct a case study to show how our approach assists human experts in diagnosing the root causes of anomalies.

---

### Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling

Authors: Tianyi Tan, Yinan Zheng, Ruiming Liang, Zexu Wang, Kexin Zheng, Jinliang Zheng, Jianxiong Li, Xianyuan Zhan, Jingjing Liu
Published: 2025-10-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.11083v1

Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced generative models, removing the dependency on over-engineered architectures for representation fusion. However, brute-force implementation by simply stacking transformer blocks lacks a dedicated mechanism for modeling interactive behaviors that are common in real driving scenarios. The scarcity of interactive driving data further exacerbates this problem, leaving conventional imitation learning methods ill-equipped to capture high-value interactive behaviors. We propose Flow Planner, which tackles these problems through coordinated innovations in data modeling, model architecture, and learning scheme. Specifically, we first introduce fine-grained trajectory tokenization, which decomposes the trajectory into overlapping segments to decrease the complexity of whole trajectory modeling. With a sophisticatedly designed architecture, we achieve efficient temporal and spatial fusion of planning and scene information, to better capture interactive behaviors. In addition, the framework incorporates flow matching with classifier-free guidance for multi-modal behavior generation, which dynamically reweights agent interactions during inference to maintain coherent response strategies, providing a critical boost for interactive scenario understanding. Experimental results on the large-scale nuPlan dataset and challenging interactive interPlan dataset demonstrate that Flow Planner achieves state-of-the-art performance among learning-based approaches while effectively modeling interactive behaviors in complex driving scenarios.

---

### Argumentation-Based Explainability for Legal AI: Comparative and Regulatory Perspectives

Authors: Andrada Iulia Prajescu, Roberto Confalonieri
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.11079v1

Artificial Intelligence (AI) systems are increasingly deployed in legal contexts, where their opacity raises significant challenges for fairness, accountability, and trust. The so-called ``black box problem'' undermines the legitimacy of automated decision-making, as affected individuals often lack access to meaningful explanations. In response, the field of Explainable AI (XAI) has proposed a variety of methods to enhance transparency, ranging from example-based and rule-based techniques to hybrid and argumentation-based approaches. This paper promotes computational models of arguments and their role in providing legally relevant explanations, with particular attention to their alignment with emerging regulatory frameworks such as the EU General Data Protection Regulation (GDPR) and the Artificial Intelligence Act (AIA). We analyze the strengths and limitations of different explanation strategies, evaluate their applicability to legal reasoning, and highlight how argumentation frameworks -- by capturing the defeasible, contestable, and value-sensitive nature of law -- offer a particularly robust foundation for explainable legal AI. Finally, we identify open challenges and research directions, including bias mitigation, empirical validation in judicial settings, and compliance with evolving ethical and legal standards, arguing that computational argumentation is best positioned to meet both technical and normative requirements of transparency in the law domain.

---

### ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer

Authors: Yuan Tian, Min Zhou, Yitong Chen, Fang Li, Lingzi Qi, Shuo Wang, Xieyang Xu, Yu Yu, Shiqiong Xu, Chaoyu Lei, Yankai Jiang, Rongzhao Zhang et al.
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11073v1

Patient face images provide a convenient mean for evaluating eye diseases, while also raising privacy concerns. Here, we introduce ROFI, a deep learning-based privacy protection framework for ophthalmology. Using weakly supervised learning and neural identity translation, ROFI anonymizes facial features while retaining disease features (over 98\% accuracy, $κ> 0.90$). It achieves 100\% diagnostic sensitivity and high agreement ($κ> 0.90$) across eleven eye diseases in three cohorts, anonymizing over 95\% of images. ROFI works with AI systems, maintaining original diagnoses ($κ> 0.80$), and supports secure image reversal (over 98\% similarity), enabling audits and long-term care. These results show ROFI's effectiveness of protecting patient privacy in the digital medicine era.

---

### PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System

Authors: Huayi Wang, Wentao Zhang, Runyi Yu, Tao Huang, Junli Ren, Feiyu Jia, Zirui Wang, Xiaojie Niu, Xiao Chen, Jiahe Chen, Qifeng Chen, Jingbo Wang et al.
Published: 2025-10-13
Categories: cs.RO, cs.AI, cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2510.11072v1

Deploying humanoid robots to interact with real-world environments--such as carrying objects or sitting on chairs--requires generalizable, lifelike motions and robust scene perception. Although prior approaches have advanced each capability individually, combining them in a unified system is still an ongoing challenge. In this work, we present a physical-world humanoid-scene interaction system, PhysHSI, that enables humanoids to autonomously perform diverse interaction tasks while maintaining natural and lifelike behaviors. PhysHSI comprises a simulation training pipeline and a real-world deployment system. In simulation, we adopt adversarial motion prior-based policy learning to imitate natural humanoid-scene interaction data across diverse scenarios, achieving both generalization and lifelike behaviors. For real-world deployment, we introduce a coarse-to-fine object localization module that combines LiDAR and camera inputs to provide continuous and robust scene perception. We validate PhysHSI on four representative interactive tasks--box carrying, sitting, lying, and standing up--in both simulation and real-world settings, demonstrating consistently high success rates, strong generalization across diverse task goals, and natural motion patterns.

---

### A Black-Box Debiasing Framework for Conditional Sampling

Authors: Han Cui, Jingbo Liu
Published: 2025-10-13
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2510.11071v1

Conditional sampling is a fundamental task in Bayesian statistics and generative modeling. Consider the problem of sampling from the posterior distribution $P_{X|Y=y^*}$ for some observation $y^*$, where the likelihood $P_{Y|X}$ is known, and we are given $n$ i.i.d. samples $D=\{X_i\}_{i=1}^n$ drawn from an unknown prior distribution $π_X$. Suppose that $f(\hatπ_{X^n})$ is the distribution of a posterior sample generated by an algorithm (e.g. a conditional generative model or the Bayes rule) when $\hatπ_{X^n}$ is the empirical distribution of the training data. Although averaging over the randomness of the training data $D$, we have $\mathbb{E}_D\left(\hatπ_{X^n}\right)= π_X$, we do not have $\mathbb{E}_D\left\{f(\hatπ_{X^n})\right\}= f(π_X)$ due to the nonlinearity of $f$, leading to a bias. In this paper we propose a black-box debiasing scheme that improves the accuracy of such a naive plug-in approach. For any integer $k$ and under boundedness of the likelihood and smoothness of $f$, we generate samples $\hat{X}^{(1)},\dots,\hat{X}^{(k)}$ and weights $w_1,\dots,w_k$ such that $\sum_{i=1}^kw_iP_{\hat{X}^{(i)}}$ is a $k$-th order approximation of $f(π_X)$, where the generation process treats $f$ as a black-box. Our generation process achieves higher accuracy when averaged over the randomness of the training data, without degrading the variance, which can be interpreted as improving memorization without compromising generalization in generative models.

---

### Efficient Test-Time Adaptation through Latent Subspace Coefficients Search

Authors: Xinyu Luo, Jie Liu, Kecheng Chen, Yihua Shao, Junyi Yang, Bo Ding, Nicu Sebe, Arindam Basu, Haoliang Li
Published: 2025-10-13
Categories: cs.LG, eess.AS, eess.IV
arXiv: https://arxiv.org/abs/2510.11068v4

Real-world deployment often exposes vision models to distribution shifts, making test-time adaptation (TTA) important for reliable prediction. Existing TTA methods can be difficult to deploy on edge devices because they require backpropagation, activation storage, or test-time batches, which increase computation, memory, and state. We propose \textbf{ELaTTA} (\textit{Efficient Latent Test-Time Adaptation}), a forward-only, gradient-free framework for single-instance TTA. ELaTTA freezes the pretrained model and adapts each test input by searching a low-dimensional coefficient vector in a principal latent subspace computed offline from a source-domain cache. The basis is stored once and source data are discarded before deployment. At test time, CMA-ES performs covariance-adaptive Gaussian search, ranks candidate corrections by prediction entropy, and selects the best candidate within a fixed evaluation budget. On five visual benchmarks spanning corruption, natural, rendition, sketch, and cross-domain shifts, ELaTTA provides strong accuracy under strict and continual single-instance protocols. In the strict single-instance comparison, MEMO requires \emph{64.7$\times$} the computation and \emph{12.4$\times$} the peak memory of ELaTTA. A complementary keyword-spotting experiment shows that the same coefficient-search design transfers beyond vision. We further demonstrate ViT-Base adaptation on a Raspberry Pi 5, confirming the feasibility of deploying ELaTTA on an edge device.

---

### LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation

Authors: Chang Liu, Henghui Ding, Kaining Ying, Lingyi Hong, Ning Xu, Linjie Yang, Yuchen Fan, Mingqi Gao, Jingkun Chen, Yunqi Miao, Gengshen Wu, Zhijin Qin et al.
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11063v1

This report presents an overview of the 7th Large-scale Video Object Segmentation (LSVOS) Challenge held in conjunction with ICCV 2025. Besides the two traditional tracks of LSVOS that jointly target robustness in realistic video scenarios: Classic VOS (VOS), and Referring VOS (RVOS), the 2025 edition features a newly introduced track, Complex VOS (MOSEv2). Building upon prior insights, MOSEv2 substantially increases difficulty, introducing more challenging but realistic scenarios including denser small objects, frequent disappear/reappear events, severe occlusions, adverse weather and lighting, etc., pushing long-term consistency and generalization beyond curated benchmarks. The challenge retains standard ${J}$, $F$, and ${J\&F}$ metrics for VOS and RVOS, while MOSEv2 adopts ${J\&\dot{F}}$ as the primary ranking metric to better evaluate objects across scales and disappearance cases. We summarize datasets and protocols, highlight top-performing solutions, and distill emerging trends, such as the growing role of LLM/MLLM components and memory-aware propagation, aiming to chart future directions for resilient, language-aware video segmentation in the wild.

---

### Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs

Authors: Yujie Zhao, Lanxiang Hu, Yang Wang, Minmin Hou, Hao Zhang, Ke Ding, Jishen Zhao
Published: 2025-10-13
Categories: cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2510.11062v5

Multi-agent systems (MAS) and reinforcement learning (RL) are widely used to enhance the agentic capabilities of large language models (LLMs). MAS improves task performance through role-based orchestration, while RL uses environmental rewards to learn stronger policies, such as GRPO-style optimization. However, applying on-policy RL to MAS remains underexplored and presents unique challenges. Algorithmically, standard GRPO grouping assumptions break down because prompts vary by role and by turn. System-wise, the training stack must support MAS-workflow rollouts and on-policy updates for both single-policy and multi-policy models. We propose AT-GRPO, which includes (i) an agent- and turn-wise grouped RL algorithm tailored to MAS and (ii) a training system that supports both single- and multi-policy regimes. Across game, planning, coding, and math tasks, AT-GRPO delivers substantial gains. On long-horizon planning, it increases accuracy from a 14.0 to 47.0 percent single-agent RL baseline to 96.0 to 99.5 percent. It also improves reasoning performance, with average gains of 3.87 to 7.62 percent on coding tasks and 9.0 to 17.93 percent on math. Code and environments are available at: https://github.com/pettingllms-ai/PettingLLMs.

---

### Robust Photoplethysmography Signal Denoising via Mamba Networks

Authors: I Chiu, Yu-Tung Liu, Kuan-Chen Wang, Hung-Yu Wei, Yu Tsao
Published: 2025-10-13
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2510.11058v2

Photoplethysmography (PPG) is widely used in wearable health monitoring, but its reliability is often degraded by noise and motion artifacts, limiting downstream applications such as heart rate (HR) estimation. This paper presents a deep learning framework for PPG denoising with an emphasis on preserving physiological information. In this framework, we propose DPNet, a Mamba-based denoising backbone designed for effective temporal modeling. To further enhance denoising performance, the framework also incorporates a scale-invariant signal-to-distortion ratio (SI-SDR) loss to promote waveform fidelity and an auxiliary HR predictor (HRP) that provides physiological consistency through HR-based supervision. Experiments on the BIDMC dataset show that our method achieves strong robustness against both synthetic noise and real-world motion artifacts, outperforming conventional filtering and existing neural models. Our method can effectively restore PPG signals while maintaining HR accuracy, highlighting the complementary roles of SI-SDR loss and HR-guided supervision. These results demonstrate the potential of our approach for practical deployment in wearable healthcare systems.

---

### Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models

Authors: Youngrok Park, Hojung Jung, Sangmin Bae, Se-Young Yun
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.11057v1

Diffusion models have achieved remarkable success as generative models. However, even a well-trained model can accumulate errors throughout the generation process. These errors become particularly problematic when arbitrary guidance is applied to steer samples toward desired properties, which often breaks sample fidelity. In this paper, we propose a general solution to address the off-manifold phenomenon observed in diffusion models. Our approach leverages a time predictor to estimate deviations from the desired data manifold at each timestep, identifying that a larger time gap is associated with reduced generation quality. We then design a novel guidance mechanism, `Temporal Alignment Guidance' (TAG), attracting the samples back to the desired manifold at every timestep during generation. Through extensive experiments, we demonstrate that TAG consistently produces samples closely aligned with the desired manifold at each timestep, leading to significant improvements in generation quality across various downstream tasks.

---

### From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance

Authors: Runze Xia, Yupeng Ji, Yuxi Zhou, Haodong Liu, Teng Zhang, Piji Li
Published: 2025-10-13
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2510.11056v3

Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge this gap, we propose a two-stage reasoning distillation framework to transfer reasoning capabilities from a powerful teacher LLM to a lightweight, deployment-friendly student model. In the first stage, we address the limitations of general-purpose LLMs by constructing a domain-adapted teacher model. This is achieved through a three-step process: domain-adaptive pre-training to inject platform knowledge, supervised fine-tuning to elicit reasoning skills, and preference optimization with a multi-dimensional reward model to ensure the generation of reliable and preference-aligned reasoning paths. This teacher can then automatically annotate massive query-service pairs from search logs with both relevance labels and reasoning chains. In the second stage, to address the challenges of architectural heterogeneity in standard distillation, we introduce Contrastive Reasoning Self-Distillation (CRSD). By modeling the behavior of the same student model under ``standard'' and ``reasoning-augmented'' inputs as a teacher-student relationship, CRSD enables the lightweight model to internalize the teacher's complex decision-making mechanisms without needing the explicit reasoning path at inference. Offline evaluations and online A/B testing in the Meituan search advertising system demonstrate that our framework achieves significant improvements across multiple metrics, validating its effectiveness and practical value.

---

### Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States

Authors: Qinglin Zhu, Yizhen Yao, Runcong Zhao, Yanzheng Xiang, Amrutha Saseendran, Chen Jin, Philip Teare, Bin Liang, Yulan He, Lin Gui
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11052v2

Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as LlaDA and Dream, mitigate this by generating in parallel, yet they suffer from two core limitations: information loss, as predictive distributions for non-finalized tokens are discarded at each step, and premature commitment, where local decisions are made without sufficient global coordination. We introduce Latent Refinement Decoding (LRD), a two-stage framework with Latent Refinement and a Predictive Feedback Loop. The first stage maintains masked positions as distributional mixtures of predicted tokens and the mask embedding, allowing the model to establish more globally consistent beliefs. The second stage progressively finalizes confident tokens while retaining uncertain ones for iterative feedback. KL-divergence dynamics provide a principled and reliable criterion for convergence and early stopping. Experiments across coding (HumanEval +6.3, MBPP +2.6) and reasoning (GSM8K +2.9, MATH500 +3.8) show that LRD improves accuracy while delivering speedups of up to 10.6x, making it a strong and versatile alternative for parallel sequence generation.

---

### Zero-shot Face Editing via ID-Attribute Decoupled Inversion

Authors: Yang Hou, Minggu Wang, Jianjun Zhao
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11050v1

Recent advancements in text-guided diffusion models have shown promise for general image editing via inversion techniques, but often struggle to maintain ID and structural consistency in real face editing tasks. To address this limitation, we propose a zero-shot face editing method based on ID-Attribute Decoupled Inversion. Specifically, we decompose the face representation into ID and attribute features, using them as joint conditions to guide both the inversion and the reverse diffusion processes. This allows independent control over ID and attributes, ensuring strong ID preservation and structural consistency while enabling precise facial attribute manipulation. Our method supports a wide range of complex multi-attribute face editing tasks using only text prompts, without requiring region-specific input, and operates at a speed comparable to DDIM inversion. Comprehensive experiments demonstrate its practicality and effectiveness.

---

### Conformal Inference for Time Series over Graphs

Authors: Sonakshi Dua, Gonzalo Mateos, Sundeep Prabhakar Chepuri
Published: 2025-10-13
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2510.11049v1

Trustworthy decision making in networked, dynamic environments calls for innovative uncertainty quantification substrates in predictive models for graph time series. Existing conformal prediction (CP) methods have been applied separately to multivariate time series and static graphs, but they either ignore the underlying graph topology or neglect temporal dynamics. To bridge this gap, here we develop a CP-based sequential prediction region framework tailored for graph time series. A key technical innovation is to leverage the graph structure and thus capture pairwise dependencies across nodes, while providing user-specified coverage guarantees on the predictive outcomes. We formally establish that our scheme yields an exponential shrinkage in the volume of the ellipsoidal prediction set relative to its graph-agnostic counterpart. Using real-world datasets, we demonstrate that the novel uncertainty quantification framework maintains desired empirical coverage while achieving markedly smaller (up to 80% reduction) prediction regions than existing approaches.

---

### Benchmarking Deep Learning Models for Laryngeal Cancer Staging Using the LaryngealCT Dataset

Authors: Nivea Roy, Son Tran, Atul Sajjanhar, K. Devaraja, Prakashini Koteshwara, Yong Xiang, Divya Rao
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11047v2

Laryngeal cancer imaging research lacks standardised public datasets to enable reproducible deep learning (DL) model development. We present LaryngealCT, a curated benchmark of 1,029 computed tomography (CT) scans aggregated from six collections from The Cancer Imaging Archive (TCIA). Uniform 1 mm isotropic volumes of interest encompassing the larynx were extracted using a weakly supervised parameter search framework validated by clinical experts. Six 3D DL architectures (custom 3D CNN, ResNet18,50,101, DenseNet121 and MedicalNet-pretrained ResNet50) were benchmarked on (i) early (Tis,T1,T2) vs. advanced (T3,T4) and (ii) T4 vs. non-T4 classification tasks. On the independent test set, the 3D CNN achieved the strongest overall performance across global and per-class metrics (Accuracy 0.854, F1-macro 0.841) in early vs. advanced classification. In the T4 task, AU-ROC values exceeded 0.82 for most models, but sensitivity for T4 disease remained limited (less than or equal to 0.412), with ResNet101 showing the most promising calibrated T4 recall (0.706. Model explainability assessed using GradCAMpp with thyroid cartilage overlays for T4 classification task revealed anatomically plausible peri-cartilage activations, although spatial overlap was modest. Through open-source data, pretrained models, and integrated explainability tools, LaryngealCT offers a reproducible foundation for AI-driven research to support future clinical decision-making in laryngeal oncology.

---

### Enabling Doctor-Centric Medical AI with LLMs through Workflow-Aligned Tasks and Benchmarks

Authors: Wenya Xie, Qingying Xiao, Yu Zheng, Xidong Wang, Junying Chen, Ke Ji, Anningzhe Gao, Prayag Tiwari, Xiang Wan, Feng Jiang, Benyou Wang
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11040v1

The rise of large language models (LLMs) has transformed healthcare by offering clinical guidance, yet their direct deployment to patients poses safety risks due to limited domain expertise. To mitigate this, we propose repositioning LLMs as clinical assistants that collaborate with experienced physicians rather than interacting with patients directly. We conduct a two-stage inspiration-feedback survey to identify real-world needs in clinical workflows. Guided by this, we construct DoctorFLAN, a large-scale Chinese medical dataset comprising 92,000 Q&A instances across 22 clinical tasks and 27 specialties. To evaluate model performance in doctor-facing applications, we introduce DoctorFLAN-test (550 single-turn Q&A items) and DotaBench (74 multi-turn conversations). Experimental results with over ten popular LLMs demonstrate that DoctorFLAN notably improves the performance of open-source LLMs in medical contexts, facilitating their alignment with physician workflows and complementing existing patient-oriented models. This work contributes a valuable resource and framework for advancing doctor-centered medical LLM development

---

### XGrasp: Gripper-Aware Grasp Detection with Multi-Gripper Data Generation

Authors: Yeonseo Lee, Jungwook Mun, Hyosup Shin, Guebin Hwang, Junhee Nam, Taeyeop Lee, Sungho Jo
Published: 2025-10-13
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2510.11036v2

Real-world robotic systems frequently require diverse end-effectors for different tasks, however most existing grasp detection methods are optimized for a single gripper type, demanding retraining or optimization for each novel gripper configuration. This gripper-specific retraining paradigm is neither scalable nor practical. We propose XGrasp, a real-time gripper-aware grasp detection framework that generalizes to novel gripper configurations without additional training or optimization. To resolve data scarcity, we augment existing single-gripper datasets with multi-gripper annotations by incorporating the physical characteristics and closing trajectories of diverse grippers. Each gripper is represented as a two-channel 2D image encoding its static shape (Gripper Mask) and dynamic closing trajectory (Gripper Path). XGrasp employs a hierarchical two-stage architecture consisting of a Grasp Point Predictor (GPP) and an Angle-Width Predictor (AWP). In the AWP, contrastive learning with a quality-aware anchor builds a gripper-agnostic embedding space, enabling generalization to novel grippers without additional training. Experimental results demonstrate that XGrasp outperforms existing gripper-aware methods in both grasp success rate and inference speed across diverse gripper types. Project page: https://sites.google.com/view/xgrasp

---

### LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Models

Authors: Yiwei Liu, Yucheng Li, Xiao Li, Gong Cheng
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.11031v1

Joint logical-numerical reasoning remains a major challenge for language models, yet existing datasets rely on fixed rule sets and offer limited control over task complexity, constraining their generalizability for evaluation and training. We present LogiNumSynth, a flexible natural language problem synthesizer that synthesizes tasks requiring proficiency in joint logical reasoning (e.g., rule-based reasoning) and numerical reasoning (e.g., arithmetic computation). LogiNumSynth supports fine-grained control over reasoning world richness, logical reasoning depth, and the complexity of numerical computations, enabling flexible data synthesis across difficulty levels. We demonstrate three key contributions: (1) Synthesizer -- synthesizing fully controllable joint reasoning tasks over natural language; (2) Evaluation & Process Analysis -- evaluating both process accuracy and answer accuracy; (3) Targeted Training -- using synthesized data to enhance LLMs' reasoning performance. Experiments with multiple LLMs highlight persistent weaknesses in logical-numerical reasoning, showing that LogiNumSynth can serve as both a diagnostic tool and a source of targeted supervision for advancing integrated reasoning skills.

---

### Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts

Authors: Yanning Hou, Ke Xu, Junfa Li, Yanran Ruan, Jianfeng Qiu
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11028v1

Recently, the powerful generalization ability exhibited by foundation models has brought forth new solutions for zero-shot anomaly segmentation tasks. However, guiding these foundation models correctly to address downstream tasks remains a challenge. This paper proposes a novel two-stage framework, for zero-shot anomaly segmentation tasks in industrial anomaly detection. This framework excellently leverages the powerful anomaly localization capability of CLIP and the boundary perception ability of SAM.(1) To mitigate SAM's inclination towards object segmentation, we propose the Co-Feature Point Prompt Generation (PPG) module. This module collaboratively utilizes CLIP and SAM to generate positive and negative point prompts, guiding SAM to focus on segmenting anomalous regions rather than the entire object. (2) To further optimize SAM's segmentation results and mitigate rough boundaries and isolated noise, we introduce the Cascaded Prompts for SAM (CPS) module. This module employs hybrid prompts cascaded with a lightweight decoder of SAM, achieving precise segmentation of anomalous regions. Across multiple datasets, consistent experimental validation demonstrates that our approach achieves state-of-the-art zero-shot anomaly segmentation results. Particularly noteworthy is our performance on the Visa dataset, where we outperform the state-of-the-art methods by 10.3\% and 7.7\% in terms of {$F_1$-max} and AP metrics, respectively.

---

### Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

Authors: Ganlin Yang, Tianyi Zhang, Haoran Hao, Weiyun Wang, Yibin Liu, Dehui Wang, Guanzhou Chen, Zijian Cai, Junting Chen, Weijie Su, Wengang Zhou, Yu Qiao et al.
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11027v2

While significant research has focused on developing embodied reasoning capabilities using Vision-Language Models (VLMs) or integrating advanced VLMs into Vision-Language-Action (VLA) models for end-to-end robot control, few studies directly address the critical gap between upstream VLM-based reasoning and downstream VLA policy learning. In this work, we take an initial step toward bridging embodied reasoning with VLA policy learning by introducing Vlaser - a Vision-Language-Action Model with synergistic embodied reasoning capability, which is a foundational vision-language model designed to integrate high-level reasoning with low-level control for embodied agents. Built upon the high-quality Vlaser-6M dataset, Vlaser achieves state-of-the-art performance across a range of embodied reasoning benchmarks - including spatial reasoning, embodied grounding, embodied QA, and task planning. Furthermore, we systematically examine how different VLM initializations affect supervised VLA fine-tuning, offering novel insights into mitigating the domain shift between internet-scale pre-training data and embodied-specific policy learning data. Based on these insights, our approach achieves state-of-the-art results on the WidowX benchmark and competitive performance on the Google Robot benchmark.

---

### GIR-Bench: Versatile Benchmark for Generating Images with Reasoning

Authors: Hongxiang Li, Yaowei Li, Bin Lin, Yuwei Niu, Yuhang Yang, Xiaoshuang Huang, Jiayin Cai, Xiaolong Jiang, Yao Hu, Long Chen
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11026v2

Unified multimodal models integrate the reasoning capacity of large language models with both image understanding and generation, showing great promise for advanced multimodal intelligence. However, the community still lacks a rigorous reasoning-centric benchmark to systematically evaluate the alignment between understanding and generation, and their generalization potential in complex visual tasks. To this end, we introduce GIR-Bench, a comprehensive benchmark that evaluates unified models across three complementary perspectives. Firstly, we investigate understanding-generation consistency (GIR-Bench-UGC), asking whether models can consistently leverage the same knowledge in both understanding and generation tasks. Secondly, we investigate whether models can perform reasoning-centric text-to-image generation that requires applying logical constraints and implicit knowledge to generate faithful visual content (GIR-Bench-T2I). Thirdly, we evaluate whether models can handle multi-step reasoning in editing (GIR-Bench-Edit). For each subset, we carefully design different task-specific evaluation pipelines tailored for each task. This enables fine-grained and interpretable evaluation while mitigating biases from the prevalent MLLM-as-a-Judge paradigm. Extensive ablations over various unified models and generation-only systems have shown that: Although unified models are more capable of reasoning-driven visual tasks, they still exhibit a persistent gap between understanding and generation. The data and code for GIR-Bench are available at https://github.com/HKUST-LongGroup/GIR-Bench.

---

### GeoVLMath: Enhancing Geometry Reasoning in Vision-Language Models via Cross-Modal Reward for Auxiliary Line Creation

Authors: Shasha Guo, Liang Pang, Xi Wang, Yanling Wang, Huawei Shen, Jing Zhang
Published: 2025-10-13
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2510.11020v2

Auxiliary lines are essential for solving complex geometric problems but remain challenging for large vision-language models (LVLMs). Recent attempts construct auxiliary lines via code-driven rendering, a strategy that relies on accurate and executable code generation to produce visual renderings of the auxiliary lines for subsequent reasoning. However, in complex solid geometry settings, such a strong dependence on precise specifications substantially restricts the robustness of this strategy. Alternatively, we turn to a simpler and more stable solution, representing auxiliary-line constructions as structured textual descriptions. To bridge the gap between textual descriptions and spatial structure, we propose a reinforcement learning framework that enhances diagram-text alignment. The core is a cross-modal reward model that evaluates how well the generated auxiliary-line description matches the ground-truth auxiliary-line diagram. The reward signal drives a GRPO-based RL stage to yield informative auxiliary-line descriptions for the reasoning. To support the training and evaluation, we develop a scalable data pipeline and construct AuxSolidMath, a dataset of 3,018 real-exam geometry problems with paired diagrams and aligned textual fields. Based on this framework, we derive GeoVLMath, an LVLM for solving complex solid geometry.

---

### The Easy Path to Robustness: Coreset Selection using Sample Hardness

Authors: Pranav Ramesh, Arjun Roy, Deepak Ravikumar, Kaushik Roy, Gopalakrishnan Srinivasan
Published: 2025-10-13
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2510.11018v1

Designing adversarially robust models from a data-centric perspective requires understanding which input samples are most crucial for learning resilient features. While coreset selection provides a mechanism for efficient training on data subsets, current algorithms are designed for clean accuracy and fall short in preserving robustness. To address this, we propose a framework linking a sample's adversarial vulnerability to its \textit{hardness}, which we quantify using the average input gradient norm (AIGN) over training. We demonstrate that \textit{easy} samples (with low AIGN) are less vulnerable and occupy regions further from the decision boundary. Leveraging this insight, we present EasyCore, a coreset selection algorithm that retains only the samples with low AIGN for training. We empirically show that models trained on EasyCore-selected data achieve significantly higher adversarial accuracy than those trained with competing coreset methods under both standard and adversarial training. As AIGN is a model-agnostic dataset property, EasyCore is an efficient and widely applicable data-centric method for improving adversarial robustness. We show that EasyCore achieves up to 7\% and 5\% improvement in adversarial accuracy under standard training and TRADES adversarial training, respectively, compared to existing coreset methods.

---

### High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation

Authors: Runyang Feng, Hyung Jin Chang, Tze Ho Elden Tse, Boeun Kim, Yi Chang, Yixing Gao
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11017v1

Modeling high-resolution spatiotemporal representations, including both global dynamic contexts (e.g., holistic human motion tendencies) and local motion details (e.g., high-frequency changes of keypoints), is essential for video-based human pose estimation (VHPE). Current state-of-the-art methods typically unify spatiotemporal learning within a single type of modeling structure (convolution or attention-based blocks), which inherently have difficulties in balancing global and local dynamic modeling and may bias the network to one of them, leading to suboptimal performance. Moreover, existing VHPE models suffer from quadratic complexity when capturing global dependencies, limiting their applicability especially for high-resolution sequences. Recently, the state space models (known as Mamba) have demonstrated significant potential in modeling long-range contexts with linear complexity; however, they are restricted to 1D sequential data. In this paper, we present a novel framework that extends Mamba from two aspects to separately learn global and local high-resolution spatiotemporal representations for VHPE. Specifically, we first propose a Global Spatiotemporal Mamba, which performs 6D selective space-time scan and spatial- and temporal-modulated scan merging to efficiently extract global representations from high-resolution sequences. We further introduce a windowed space-time scan-based Local Refinement Mamba to enhance the high-frequency details of localized keypoint motions. Extensive experiments on four benchmark datasets demonstrate that the proposed model outperforms state-of-the-art VHPE approaches while achieving better computational trade-offs.

---

### Instruction-aware User Embedding via Synergistic Language and Representation Modeling

Authors: Ziyi Gao, Yike Xu, Jiahao Yuan, Baokun Wang, Jinyong Wen, Xiaotong Lin, Yun Liu, Xing Fu, Yu Cheng, Yongchao Liu, Weiqiang Wang, Zhongle Xie
Published: 2025-10-13
Categories: cs.LG
arXiv: https://arxiv.org/abs/2510.11016v1

User representation modeling has become increasingly crucial for personalized applications, yet existing approaches struggle with generalizability across domains and sensitivity to noisy behavioral signals. We present InstructUE, an instruction-aware user embedding foundation model that leverages large language models (LLMs) to generate general and instruction-aware user representations. InstructUE introduces a multi-encoder architecture with a lightweight adapter that efficiently processes heterogeneous data from six different sources while preserving their structural characteristics. Additionally, it proposes a novel contrastive-autoregressive training framework that bridges language and representation spaces through a curated UserQA dataset. The contrastive-autoregressive training framework simultaneously leverages autoregressive learning to capture domain knowledge in language space and contrastive learning to align user-text embeddings in representation space, thereby enhancing the instruction-awareness and noise-robustness of user embeddings. Through extensive experiments on real-world applications, we demonstrate that InstructUE significantly outperforms existing methods across multiple domains including user prediction, marketing, and recommendation scenarios. Our results show that instruction-aware user modeling can effectively achieve instruction-guided denoising of user information in specific scenarios, paving the way for more generalizable and robust user representation learning.

---

### MatterDoor: Sampling Zero-shot Spatio-semantic Priors using Generative Models

Authors: Subhransu S. Bhattacharjee, Hao Lu, Dylan Campbell, Rahul Shome
Published: 2025-10-13
Categories: cs.RO, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2510.11014v2

Autonomous robots often view rooms only partially, through a doorway, where the walls and scene structure hide the geometry and task-relevant semantics needed for safe navigation and goal-directed action. We ask whether off-the-shelf pretrained generative vision models can derive this missing structure as zero-shot offline priors for robot reasoning. Such priors should support spatio-semantic queries over unobserved structure, estimating the target object likelihood in hidden regions and the probability that those regions are occupied. Given an egocentric RGB observation and target query, our pipeline uses VLM-guided outpainting, monocular depth estimation, and semantic segmentation to sample semantically labeled 3D point cloud hypotheses of the hidden room. We introduce MatterDoor, a Matterport3D-derived benchmark of doorway-occluded indoor scenes, and evaluate the resulting priors with generative metrics and simulated Stretch robot object-reaching tasks. Our results suggest that useful spatio-semantic priors for planning can be derived without problem-specific fine-tuning.

---

### COCO-Tree: Compositional Hierarchical Concept Trees for Enhanced Reasoning in Vision Language Models

Authors: Sanchit Sinha, Guangzhi Xiong, Aidong Zhang
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11012v1

Compositional reasoning remains a persistent weakness of modern vision language models (VLMs): they often falter when a task hinges on understanding how multiple objects, attributes, and relations interact within an image. Multiple research works have attempted to improve compositionality performance by creative tricks such as improving prompt structure, chain of thought reasoning, etc. A more recent line of work attempts to impart additional reasoning in VLMs using well-trained Large Language Models (LLMs), which are far superior in linguistic understanding than VLMs to compensate for the limited linguistic prowess of VLMs. However, these approaches are either resource-intensive or do not provide an interpretable reasoning process. In this paper, we present 'COCO-Tree' - a novel approach that augments VLM outputs with carefully designed neurosymbolic concept trees learned from LLMs to improve VLM's linguistic reasoning. COCO-Tree's beam search-inspired reasoning process boosts compositionality performance and provides a rationale behind VLM predictions. Empirical results on four compositionality benchmarks, Winoground, EqBench, ColorSwap, and SugarCrepe, in seven different open-source VLMs with varying sizes, demonstrate that COCO-Tree significantly improves compositional generalization by 5-10% over baselines.

---

### GrASP: A Generalizable Address-based Semantic Prefetcher for Scalable Transactional and Analytical Workloads

Authors: Farzaneh Zirak, Farhana Choudhury, Renata Borovica-Gajic
Published: 2025-10-13
Categories: cs.DB, cs.LG
arXiv: https://arxiv.org/abs/2510.11011v1

Data prefetching--loading data into the cache before it is requested--is essential for reducing I/O overhead and improving database performance. While traditional prefetchers focus on sequential patterns, recent learning-based approaches, especially those leveraging data semantics, achieve higher accuracy for complex access patterns. However, these methods often struggle with today's dynamic, ever-growing datasets and require frequent, timely fine-tuning. Privacy constraints may also restrict access to complete datasets, necessitating prefetchers that can learn effectively from samples. To address these challenges, we present GrASP, a learning-based prefetcher designed for both analytical and transactional workloads. GrASP enhances prefetching accuracy and scalability by leveraging logical block address deltas and combining query representations with result encodings. It frames prefetching as a context-aware multi-label classification task, using multi-layer LSTMs to predict delta patterns from embedded context. This delta modeling approach enables GrASP to generalize predictions from small samples to larger, dynamic datasets without requiring extensive retraining. Experiments on real-world datasets and industrial benchmarks demonstrate that GrASP generalizes to datasets 250 times larger than the training data, achieving up to 45% higher hit ratios, 60% lower I/O time, and 55% lower end-to-end query execution latency than existing baselines. On average, GrASP attains a 91.4% hit ratio, a 90.8% I/O time reduction, and a 57.1% execution latency reduction.

---

### Macroeconomic Forecasting and Machine Learning

Authors: Ta-Chung Chi, Ting-Han Fan, Raffaele M. Ghigliazza, Domenico Giannone, Zixuan, Wang
Published: 2025-10-13
Categories: econ.EM, stat.ML
arXiv: https://arxiv.org/abs/2510.11008v1

We forecast the full conditional distribution of macroeconomic outcomes by systematically integrating three key principles: using high-dimensional data with appropriate regularization, adopting rigorous out-of-sample validation procedures, and incorporating nonlinearities. By exploiting the rich information embedded in a large set of macroeconomic and financial predictors, we produce accurate predictions of the entire profile of macroeconomic risk in real time. Our findings show that regularization via shrinkage is essential to control model complexity, while introducing nonlinearities yields limited improvements in predictive accuracy. Out-of-sample validation plays a critical role in selecting model architecture and preventing overfitting.

---

### Frequency Domain Unlocks New Perspectives for Abdominal Medical Image Segmentation

Authors: Kai Han, Siqi Ma, Chengxuan Qian, Jun Chen, Chongwen Lyu, Yuqing Song, Zhe Liu
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11005v1

Accurate segmentation of tumors and adjacent normal tissues in medical images is essential for surgical planning and tumor staging. Although foundation models generally perform well in segmentation tasks, they often struggle to focus on foreground areas in complex, low-contrast backgrounds, where some malignant tumors closely resemble normal organs, complicating contextual differentiation. To address these challenges, we propose the Foreground-Aware Spectrum Segmentation (FASS) framework. First, we introduce a foreground-aware module to amplify the distinction between background and the entire volume space, allowing the model to concentrate more effectively on target areas. Next, a feature-level frequency enhancement module, based on wavelet transform, extracts discriminative high-frequency features to enhance boundary recognition and detail perception. Eventually, we introduce an edge constraint module to preserve geometric continuity in segmentation boundaries. Extensive experiments on multiple medical datasets demonstrate superior performance across all metrics, validating the effectiveness of our framework, particularly in robustness under complex conditions and fine structure recognition. Our framework significantly enhances segmentation of low-contrast images, paving the way for applications in more diverse and complex medical imaging scenarios.

---

### Automating Structural Engineering Workflows with Large Language Model Agents

Authors: Haoran Liang, Yufa Zhou, Mohammad Talebi Kalaleh, Qipei Mei
Published: 2025-10-13
Categories: cs.MA, cs.AI, cs.CE, cs.CL
arXiv: https://arxiv.org/abs/2510.11004v1

We introduce $\textbf{MASSE}$, the first Multi-Agent System for Structural Engineering, effectively integrating large language model (LLM)-based agents with real-world engineering workflows. Structural engineering is a fundamental yet traditionally stagnant domain, with core workflows remaining largely unchanged for decades despite its substantial economic impact and global market size. Recent advancements in LLMs have significantly enhanced their ability to perform complex reasoning, long-horizon planning, and precise tool utilization -- capabilities well aligned with structural engineering tasks such as interpreting design codes, executing load calculations, and verifying structural capacities. We present a proof-of-concept showing that most real-world structural engineering workflows can be fully automated through a training-free LLM-based multi-agent system. MASSE enables immediate deployment in professional environments, and our comprehensive validation on real-world case studies demonstrates that it can reduce expert workload from approximately two hours to mere minutes, while enhancing both reliability and accuracy in practical engineering scenarios.

---

### FBS Model-based Maintenance Record Accumulation for Failure-Cause Inference in Manufacturing Systems

Authors: Takuma Fujiu, Sho Okazaki, Kohei Kaminishi, Yuji Nakata, Shota Hamamoto, Kenshin Yokose, Tatsunori Hara, Yasushi Umeda, Jun Ota
Published: 2025-10-13
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2510.11003v1

In manufacturing systems, identifying the causes of failures is crucial for maintaining and improving production efficiency. In knowledge-based failure-cause inference, it is important that the knowledge base (1) explicitly structures knowledge about the target system and about failures, and (2) contains sufficiently long causal chains of failures. In this study, we constructed Diagnostic Knowledge Ontology and proposed a Function-Behavior-Structure (FBS) model-based maintenance-record accumulation method based on it. Failure-cause inference using the maintenance records accumulated by the proposed method showed better agreement with the set of candidate causes enumerated by experts, especially in difficult cases where the number of related cases is small and the vocabulary used differs. In the future, it will be necessary to develop inference methods tailored to these maintenance records, build a user interface, and carry out validation on larger and more diverse systems. Additionally, this approach leverages the understanding and knowledge of the target in the design phase to support knowledge accumulation and problem solving during the maintenance phase, and it is expected to become a foundation for knowledge sharing across the entire engineering chain in the future.

---

### DND: Boosting Large Language Models with Dynamic Nested Depth

Authors: Tieyuan Chen, Xiaodong Chen, Haoxing Chen, Zhenzhong Lan, Weiyao Lin, Jianguo Li
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.11001v3

We introduce Dynamic Nested Depth (DND), a novel method that improves performance for off-the-shelf LLMs by selecting critical tokens to reprocess in a nested depth manner. Specifically, at the end of the given transformer layer, DND identifies more critical tokens with a router and feeds them back for an extra round of processing, effectively ``reviewing" difficult tokens while avoiding redundant computation for easier ones. The dynamic selection mechanism is tailored for precise control via two novel strategies: a router controlling loss to enhance token selection distinguishability, and a threshold control scheme to ensure selection stability. We demonstrate the effectiveness of DND by directly integrating it into pre-trained dense and MoE models during a post-training phase. On diverse benchmarks, this approach boosts the performances of the dense Qwen3-1.7B by 1.88% and the MoE Qwen3-30B-A3B by 0.87%, all with a minimal parameter and computing increase.

---

### ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation

Authors: Ruihang Xu, Dewei Zhou, Fan Ma, Yi Yang
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.11000v3

Multi-instance image generation (MIG) remains a significant challenge for modern diffusion models due to key limitations in achieving precise control over object layout and preserving the identity of multiple distinct subjects. To address these limitations, we introduce ContextGen, a novel Diffusion Transformer framework for multi-instance generation that is guided by both layout and reference images. Our approach integrates two key technical contributions: a Contextual Layout Anchoring (CLA) mechanism that incorporates the composite layout image into the generation context to robustly anchor the objects in their desired positions, and Identity Consistency Attention (ICA), an innovative attention mechanism that leverages contextual reference images to ensure the identity consistency of multiple instances. To address the absence of a large-scale, high-quality dataset for this task, we introduce IMIG-100K, the first dataset to provide detailed layout and identity annotations specifically designed for Multi-Instance Generation. Extensive experiments demonstrate that ContextGen sets a new state-of-the-art, outperforming existing methods especially in layout control and identity fidelity.

---

### ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios

Authors: Mahika Phutane, Hayoung Jung, Matthew Kim, Tanushree Mitra, Aditya Vashistha
Published: 2025-10-13
Categories: cs.CL, cs.AI, cs.CY, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2510.10998v2

Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hiring, particularly against people with disabilities (PwD). However, existing research remains largely Western-centric, overlooking how intersecting forms of marginalization--such as gender and caste--shape experiences of PwD in the Global South. We conduct a comprehensive audit of six LLMs across 2,820 hiring scenarios spanning diverse disability, gender, nationality, and caste profiles. To capture subtle intersectional harms and biases, we introduce ABLEIST (Ableism, Inspiration, Superhumanization, and Tokenism), a set of five ableism-specific and three intersectional harm metrics grounded in disability studies literature. Our results reveal significant increases in ABLEIST harms towards disabled candidates--harms that many state-of-the-art models failed to detect. These harms were further amplified by sharp increases in intersectional harms (e.g., Tokenism) for gender and caste-marginalized disabled candidates, highlighting critical blind spots in current safety tools and the need for intersectional safety evaluations of frontier models in high-stakes domains like hiring.

---

### Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety

Authors: Wei-Chieh Huang, Henry Peng Zou, Yaozu Wu, Dongyuan Li, Yankai Chen, Weizhi Zhang, Yangning Li, Angelo Zangari, Jizhou Guo, Chunyu Miao, Liancheng Fang, Langzhou He et al.
Published: 2025-10-13
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2510.10994v2

Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential to address complex issues through planning and research cycles, existing frameworks are deficient in sufficient evaluation procedures and stage-specific protections. They typically treat evaluation as exact match accuracy of question-answering, but overlook crucial aspects of report quality such as credibility, coherence, breadth, depth, and safety. This oversight may result in hazardous or malicious sources being integrated into the final report. To address this, we introduce DeepResearchGuard, a framework featuring four-stage safeguards with open-domain evaluation, and DRSafeBench, a novel stage-wise safety benchmark. Evaluating across GPT-4o, o4-mini, Gemini-2.5-flash, DeepSeek-v3, GPT-5, DeepResearchGuard improves defense success rates by 16.53% while reducing over-refusal to 6%. Through extensive experiments, we show that DRSafeBench enables comprehensive open-domain evaluation and stage-aware defenses that effectively block harmful content propagation, while systematically improving report quality without excessive over-refusal rates.

---

### Perspective-aware 3D Gaussian Inpainting with Multi-view Consistency

Authors: Yuxin Cheng, Binxiao Huang, Taiqiang Wu, Wenyong Zhou, Chenchen Ding, Zhengwu Liu, Graziano Chesi, Ngai Wong
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10993v1

3D Gaussian inpainting, a critical technique for numerous applications in virtual reality and multimedia, has made significant progress with pretrained diffusion models. However, ensuring multi-view consistency, an essential requirement for high-quality inpainting, remains a key challenge. In this work, we present PAInpainter, a novel approach designed to advance 3D Gaussian inpainting by leveraging perspective-aware content propagation and consistency verification across multi-view inpainted images. Our method iteratively refines inpainting and optimizes the 3D Gaussian representation with multiple views adaptively sampled from a perspective graph. By propagating inpainted images as prior information and verifying consistency across neighboring views, PAInpainter substantially enhances global consistency and texture fidelity in restored 3D scenes. Extensive experiments demonstrate the superiority of PAInpainter over existing methods. Our approach achieves superior 3D inpainting quality, with PSNR scores of 26.03 dB and 29.51 dB on the SPIn-NeRF and NeRFiller datasets, respectively, highlighting its effectiveness and generalization capability.

---

### A Survey on Agentic Multimodal Large Language Models

Authors: Huanjin Yao, Ruifei Zhang, Jiaxing Huang, Jingyi Zhang, Yibo Wang, Bo Fang, Ruolin Zhu, Yongcheng Jing, Shunyu Liu, Guanbin Li, Dacheng Tao
Published: 2025-10-13
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.10991v1

With the recent emergence of revolutionary autonomous agentic systems, research community is witnessing a significant shift from traditional static, passive, and domain-specific AI agents toward more dynamic, proactive, and generalizable agentic AI. Motivated by the growing interest in agentic AI and its potential trajectory toward AGI, we present a comprehensive survey on Agentic Multimodal Large Language Models (Agentic MLLMs). In this survey, we explore the emerging paradigm of agentic MLLMs, delineating their conceptual foundations and distinguishing characteristics from conventional MLLM-based agents. We establish a conceptual framework that organizes agentic MLLMs along three fundamental dimensions: (i) Agentic internal intelligence functions as the system's commander, enabling accurate long-horizon planning through reasoning, reflection, and memory; (ii) Agentic external tool invocation, whereby models proactively use various external tools to extend their problem-solving capabilities beyond their intrinsic knowledge; and (iii) Agentic environment interaction further situates models within virtual or physical environments, allowing them to take actions, adapt strategies, and sustain goal-directed behavior in dynamic real-world scenarios. To further accelerate research in this area for the community, we compile open-source training frameworks, training and evaluation datasets for developing agentic MLLMs. Finally, we review the downstream applications of agentic MLLMs and outline future research directions for this rapidly evolving field. To continuously track developments in this rapidly evolving field, we will also actively update a public repository at https://github.com/HJYao00/Awesome-Agentic-MLLMs.

---

### Secret-Protected Evolution for Differentially Private Synthetic Text Generation

Authors: Tianze Wang, Zhaoyu Chen, Jian Du, Yingtai Xiao, Linjun Zhang, Qiang Yan
Published: 2025-10-13
Categories: cs.CR, cs.CL, cs.NE
arXiv: https://arxiv.org/abs/2510.10990v1

Text data has become extremely valuable on large language models (LLMs) and even lead to general artificial intelligence (AGI). A lot of high-quality text in the real world is private and cannot be freely used due to privacy concerns. Therefore, differentially private (DP) synthetic text generation has been proposed, aiming to produce high-utility synthetic data while protecting sensitive information. However, existing DP synthetic text generation imposes uniform guarantees that often overprotect non-sensitive content, resulting in substantial utility loss and computational overhead. Therefore, we propose Secret-Protected Evolution (SecPE), a novel framework that extends private evolution with secret-aware protection. Theoretically, we show that SecPE satisfies $(\mathrm{p}, \mathrm{r})$-secret protection, constituting a relaxation of Gaussian DP that enables tighter utility-privacy trade-offs, while also substantially reducing computational complexity relative to baseline methods. Empirically, across the OpenReview, PubMed, and Yelp benchmarks, SecPE consistently achieves lower Fréchet Inception Distance (FID) and higher downstream task accuracy than GDP-based Aug-PE baselines, while requiring less noise to attain the same level of protection. Our results highlight that secret-aware guarantees can unlock more practical and effective privacy-preserving synthetic text generation.

---

### Adversarial Robustness in One-Stage Learning-to-Defer

Authors: Yannis Montreuil, Letian Yu, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi
Published: 2025-10-13
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2510.10988v4

Learning-to-Defer (L2D) enables hybrid decision-making by routing inputs either to a predictor or to external experts. While promising, L2D is highly vulnerable to adversarial perturbations, which can not only flip predictions but also manipulate deferral decisions. Prior robustness analyses focus solely on two-stage settings, leaving open the end-to-end (one-stage) case where predictor and allocation are trained jointly. We introduce the first framework for adversarial robustness in one-stage L2D, covering both classification and regression. Our approach formalizes attacks, proposes cost-sensitive adversarial surrogate losses, and establishes theoretical guarantees including $\mathcal{H}$, $(\mathcal{R }, \mathcal{F})$, and Bayes consistency. Experiments on benchmark datasets confirm that our methods improve robustness against untargeted and targeted attacks while preserving clean performance.

---

### DITTO: A Spoofing Attack Framework on Watermarked LLMs via Knowledge Distillation

Authors: Hyeseon An, Shinwoo Park, Suyeon Woo, Yo-Sub Han
Published: 2025-10-13
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2510.10987v3

The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a sophisticated attack that allows a malicious model to generate text containing the authentic-looking watermark of a trusted, victim model. This enables the seamless misattribution of harmful content, such as disinformation, to reputable sources. The key to our attack is repurposing watermark radioactivity, the unintended inheritance of data patterns during fine-tuning, from a discoverable trait into an attack vector. By distilling knowledge from a watermarked teacher model, our framework allows an attacker to steal and replicate the watermarking signal of the victim model. This work reveals a critical security gap in text authorship verification and calls for a paradigm shift towards technologies capable of distinguishing authentic watermarks from expertly imitated ones. Our code is available at https://github.com/hsannn/ditto.git.

---

### Mixup Helps Understanding Multimodal Video Better

Authors: Xiaoyu Ma, Ding Ding, Hao Chen
Published: 2025-10-13
Categories: cs.CV
arXiv: https://arxiv.org/abs/2510.10986v1

Multimodal video understanding plays a crucial role in tasks such as action recognition and emotion classification by combining information from different modalities. However, multimodal models are prone to overfitting strong modalities, which can dominate learning and suppress the contributions of weaker ones. To address this challenge, we first propose Multimodal Mixup (MM), which applies the Mixup strategy at the aggregated multimodal feature level to mitigate overfitting by generating virtual feature-label pairs. While MM effectively improves generalization, it treats all modalities uniformly and does not account for modality imbalance during training. Building on MM, we further introduce Balanced Multimodal Mixup (B-MM), which dynamically adjusts the mixing ratios for each modality based on their relative contributions to the learning objective. Extensive experiments on several datasets demonstrate the effectiveness of our methods in improving generalization and multimodal robustness.

---

### A Constrained Multi-Fidelity Bayesian Optimization Method

Authors: Jingyi Wang, Nai-Yuan Chiang, Tucker Hartland, J. Luc Peterson, Jerome Solberg, Cosmin G. Petra
Published: 2025-10-13
Categories: math.NA, stat.ML
arXiv: https://arxiv.org/abs/2510.10984v1

Recently, multi-fidelity Bayesian optimization (MFBO) has been successfully applied to many engineering design optimization problems, where the cost of high-fidelity simulations and experiments can be prohibitive. However, challenges remain for constrained optimization problems using the MFBO framework, particularly in efficiently identifying the feasible region defined by the constraints. In this paper, we propose a constrained multi-fidelity Bayesian optimization (CMFBO) method with novel acquisition functions. Specifically, we design efficient acquisition functions that 1) have analytically closed-form expressions; 2) are straightforward to implement; and 3) do not require feasible initial samples, an important feature often missing in commonly used acquisition functions such as expected constrained improvement (ECI). We demonstrate the effectiveness of our algorithms on synthetic test problems using different combinations of acquisition functions. Then, we apply the proposed method to a data-driven inertial confinement fusion (ICF) design problem, and a high-current joint design problem using finite element simulations with computational contact mechanics.

---

### Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization

Authors: Zihan Wang, Zhiyong Ma, Zhongkui Ma, Shuofeng Liu, Akide Liu, Derui Wang, Minhui Xue, Guangdong Bai
Published: 2025-10-13
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2510.10982v2

Recent AI regulations increasingly emphasize the need for mechanisms that preserve the utility of data for AI innovation while preventing misuse, particularly by enforcing purpose limitation in downstream AI applications. In practice, enforcing this principle remains challenging, as released data can be trivially fed into arbitrary models beyond its declared intent. Existing approaches attempt to mitigate this risk by either perturbing data or retraining models to limit unintended use. These strategies, however, offer no protection against inference by unknown or externally trained models, or fundamentally rely on control over the training or deployment. In this work, we introduce non-transferable examples (NTEs), recoded data that act as a task-level "ciphertext" decodable only by a designated model. Whereas adversarial examples exploit directions of high model sensitivity, NTEs leverage the complementary insensitive subspace. We propose a training-free, data-agnostic method that recodes data within a model-specific low-sensitivity subspace, preserving outputs for the authorized model while degrading unauthorized ones through subspace misalignment. We establish formal bounds certifying authorized-model fidelity and showing that unauthorized degradation scales with measurable spectral misalignment between models. Empirically, NTEs preserve performance across diverse vision backbones and state-of-the-art vision-language models under common preprocessing, while unauthorized models collapse even under adaptive reconstruction attacks. These results establish NTEs as a practical means to preserve intended data utility while preventing unauthorized exploitation. Our project is available at https://trusted-system-lab.github.io/model-specificity

---

### In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learning

Authors: Tomoya Wakayama, Taiji Suzuki
Published: 2025-10-13
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2510.10981v3

This paper develops a finite-sample statistical theory for in-context learning (ICL), analyzed within a meta-learning framework that accommodates mixtures of diverse task types. We introduce a principled risk decomposition that separates the total ICL risk into two orthogonal components: Bayes Gap and Posterior Variance. The Bayes Gap quantifies how well the trained model approximates the Bayes-optimal in-context predictor. For a uniform-attention Transformer, we derive a non-asymptotic upper bound on this gap, which explicitly clarifies the dependence on the number of pretraining prompts and their context length. The Posterior Variance is a model-independent risk representing the intrinsic task uncertainty. Our key finding is that this term is determined solely by the difficulty of the true underlying task, while the uncertainty arising from the task mixture vanishes exponentially fast with only a few in-context examples. Together, these results provide a unified view of ICL: the Transformer selects the optimal meta-algorithm during pretraining and rapidly converges to the optimal algorithm for the true task at test time.

---

### On the Optimal Representation Efficiency of Barlow Twins: An Information-Geometric Interpretation

Authors: Di Zhang
Published: 2025-10-13
Categories: cs.LG, cs.CV, cs.IT, math.ST, stat.ML
arXiv: https://arxiv.org/abs/2510.10980v1

Self-supervised learning (SSL) has achieved remarkable success by learning meaningful representations without labeled data. However, a unified theoretical framework for understanding and comparing the efficiency of different SSL paradigms remains elusive. In this paper, we introduce a novel information-geometric framework to quantify representation efficiency. We define representation efficiency $η$ as the ratio between the effective intrinsic dimension of the learned representation space and its ambient dimension, where the effective dimension is derived from the spectral properties of the Fisher Information Matrix (FIM) on the statistical manifold induced by the encoder. Within this framework, we present a theoretical analysis of the Barlow Twins method. Under specific but natural assumptions, we prove that Barlow Twins achieves optimal representation efficiency ($η= 1$) by driving the cross-correlation matrix of representations towards the identity matrix, which in turn induces an isotropic FIM. This work provides a rigorous theoretical foundation for understanding the effectiveness of Barlow Twins and offers a new geometric perspective for analyzing SSL algorithms.

---

### Revisiting Model Interpolation for Efficient Reasoning

Authors: Taiqiang Wu, Runming Yang, Tao Liu, Jiahao Wang, Ngai Wong
Published: 2025-10-13
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2510.10977v2

Model merging, typically on Instruct and Thinking models, has shown remarkable performance for efficient reasoning. In this paper, we systematically revisit the simplest merging method that interpolates two weights directly. Particularly, we observe that model interpolation follows a three-stage evolutionary paradigm with distinct behaviors on the reasoning trajectory. These dynamics provide a principled guide for navigating the performance-cost trade-off. Empirical results demonstrate that a strategically interpolated model surprisingly surpasses sophisticated model merging baselines on both efficiency and effectiveness. We further validate our findings with extensive ablation studies on model layers, modules, and decoding strategies. Ultimately, this work demystifies model interpolation and offers a practical framework for crafting models with precisely targeted reasoning capabilities. Code is available at \href{https://github.com/wutaiqiang/MI}{Github}.

---

### Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph

Authors: Wentao Wang, Heqing Zou, Tianze Luo, Rui Huang, Yutian Zhao, Zhuochen Wang, Hansheng Zhang, Chengwei Qin, Yan Wang, Lin Zhao, Huaijian Zhang
Published: 2025-10-13
Categories: cs.AI
arXiv: https://arxiv.org/abs/2510.10976v1

Recent progress in Multimodal Large Language Models (MLLMs) has demonstrated strong semantic understanding capabilities, but struggles to perform precise spatio-temporal understanding. Existing spatio-temporal methods primarily focus on the video itself, while overlooking the physical information within the video, such as multi-object layouts and motion. Such limitations restrict the use of MLLMs in downstream applications that demand high precision, including embodied intelligence and VR. To address this issue, we present Video-STR, a novel graph-based reinforcement method for precise Video Spatio-Temporal Reasoning. Building upon the capacity of Reinforcement Learning with Verifiable Reward (RLVR) to improve model abilities, we introduce a reasoning mechanism using graph-based Group Relative Policy Optimization (GRPO) method to guide the model in inferring the underlying spatio-temporal topology of scenarios during the thinking process. To resolve the lack of spatio-temporal training data, we construct the STV-205k dataset with 205k question-answering pairs, covering dynamic multi-object scenes in both indoor and outdoor environments, to support the model training. Experiments show that Video-STR achieves state-of-the-art results on various benchmarks, outperforming the base model by 13% on STI-Bench, and demonstrating the effectiveness of our approach and dataset. Code, model, and data will be released.

---

### Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning

Authors: Zhiwen Ruan, Yixia Li, He Zhu, Yun Chen, Peng Li, Yang Liu, Guanhua Chen
Published: 2025-10-13
Categories: cs.CL
arXiv: https://arxiv.org/abs/2510.10974v1

Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. However, standard SFT uniformly penalizes all tokens, neglecting that only a small subset of critical tokens determines reasoning correctness. This uniform supervision often causes reduced output diversity and limited generalization. We propose Critical Token Fine-tuning (CFT), a simple yet effective approach that updates only tokens identified as functionally indispensable via counterfactual perturbations. By focusing gradient signals on these decisive reasoning steps while preserving the diversity of non-critical tokens, CFT can enhance both generation and diversity. Extensive experiments on five models across three families (Qwen, OLMo, LLaMA) and eleven mathematical reasoning benchmarks show that CFT, despite fine-tuning on less than 12% of tokens, consistently outperforms standard SFT. Moreover, CFT enables test-time scaling through improved sampling diversity and provides a stronger initialization for reinforcement learning, sustaining performance gains in later training stages while maintaining higher entropy for better exploration. These results highlight CFT as a practical and general framework for efficient and robust LLM fine-tuning.

---