# Research Papers — 2025-11 · bundle page 47 of 197

> Full-text markdown of papers #2301–2350 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2025-11/page/47
[← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/46.md)
[Next bundle →](https://aipod.dev/papers/archive/2025-11/page/48.md)

### Mitigating Participation Imbalance Bias in Asynchronous Federated Learning

Authors: Xiangyu Chang, Manyi Yao, Srikanth V. Krishnamurthy, Christian R. Shelton, Anirban Chakraborty, Ananthram Swami, Samet Oymak, Amit Roy-Chowdhury
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.19066v1

In Asynchronous Federated Learning (AFL), the central server immediately updates the global model with each arriving client's contribution. As a result, clients perform their local training on different model versions, causing information staleness (delay). In federated environments with non-IID local data distributions, this asynchronous pattern amplifies the adverse effect of client heterogeneity (due to different data distribution, local objectives, etc.), as faster clients contribute more frequent updates, biasing the global model. We term this phenomenon heterogeneity amplification. Our work provides a theoretical analysis that maps AFL design choices to their resulting error sources when heterogeneity amplification occurs. Guided by our analysis, we propose ACE (All-Client Engagement AFL), which mitigates participation imbalance through immediate, non-buffered updates that use the latest information available from all clients. We also introduce a delay-aware variant, ACED, to balance client diversity against update staleness. Experiments on different models for different tasks across diverse heterogeneity and delay settings validate our analysis and demonstrate the robust performance of our approaches.

---

### Understanding, Accelerating, and Improving MeanFlow Training

Authors: Jin-Young Kim, Hyojun Go, Lea Bogensperger, Julius Erbach, Nikolai Kalischek, Federico Tombari, Konrad Schindler, Dominik Narnhofer
Published: 2025-11-24
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2511.19065v2

MeanFlow promises high-quality generative modeling in few steps, by jointly learning instantaneous and average velocity fields. Yet, the underlying training dynamics remain unclear. We analyze the interaction between the two velocities and find: (i) well-established instantaneous velocity is a prerequisite for learning average velocity; (ii) learning of instantaneous velocity benefits from average velocity when the temporal gap is small, but degrades as the gap increases; and (iii) task-affinity analysis indicates that smooth learning of large-gap average velocities, essential for one-step generation, depends on the prior formation of accurate instantaneous and small-gap average velocities. Guided by these observations, we design an effective training scheme that accelerates the formation of instantaneous velocity, then shifts emphasis from short- to long-interval average velocity. Our enhanced MeanFlow training yields faster convergence and significantly better few-step generation: With the same DiT-XL backbone, our method reaches an impressive FID of 2.87 on 1-NFE ImageNet 256x256, compared to 3.43 for the conventional MeanFlow baseline. Alternatively, our method matches the performance of the MeanFlow baseline with 2.5x shorter training time, or with a smaller DiT-L backbone.

---

### Logic of Montage

Authors: Hayami Takahashi, Kensuke Takahashi
Published: 2025-11-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.19063v1

In expressing emotions, as an expression form separate from natural language, we propose an alternative form that complements natural language, acting as a proxy or window for emotional states. First, we set up an expression form "Effect of Contradictory Structure." "Effect of Contradictory Structure" is not static but dynamic. Effect in "Effect of Contradictory Structure" is unpleasant or pleasant, and the orientation to avoid that unpleasantness is considered pseudo-expression of will. Second, "Effect of Contradictory Structure" can be overlapped with each other. This overlapping operation is called "montage." A broader "Structure" that includes related "Effect of Contradictory Structure" and "Effect of Structure" are set up. Montage produces "Effect of Structure". In montage, it is necessary to set something like "strength," so we adopted Deleuze and Deleuze/Guattari's word "intensity" and set it as an element of our model. We set up a general theoretical framework - Word Import Between Systems (Models) and justified the import of "intensity" through Austin's use of the word "force." "Effect of Structure" process is demonstrated using the example of proceeding to the next level of education.

---

### Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation

Authors: Qiyang Yu, Yu Fang, Tianrui Li, Xuemei Cao, Yan Chen, Jianghao Li, Fan Min, Yi Zhang
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19062v1

Prompt-free image segmentation aims to generate accurate masks without manual guidance. Typical pre-trained models, notably Segmentation Anything Model (SAM), generate prompts directly at a single granularity level. However, this approach has two limitations: (1) Localizability, lacking mechanisms for autonomous region localization; (2) Scalability, limited fine-grained modeling at high resolution. To address these challenges, we introduce Granular Computing-driven SAM (Grc-SAM), a coarse-to-fine framework motivated by Granular Computing (GrC). First, the coarse stage adaptively extracts high-response regions from features to achieve precise foreground localization and reduce reliance on external prompts. Second, the fine stage applies finer patch partitioning with sparse local swin-style attention to enhance detail modeling and enable high-resolution segmentation. Third, refined masks are encoded as latent prompt embeddings for the SAM decoder, replacing handcrafted prompts with an automated reasoning process. By integrating multi-granularity attention, Grc-SAM bridges granular computing with vision transformers. Extensive experimental results demonstrate Grc-SAM outperforms baseline methods in both accuracy and scalability. It offers a unique granular computational perspective for prompt-free segmentation.

---

### LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Space

Authors: Hai Wu, Shuai Tang, Jiale Wang, Longkun Zou, Mingyue Guo, Rongqin Liang, Ke Chen, Yaowei Wang
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19057v1

Perception of Low-Altitude Aircraft (LAA) in 3D space enables precise 3D object localization and behavior understanding. However, datasets tailored for 3D LAA perception remain scarce. To address this gap, we present LAA3D, a large-scale dataset designed to advance 3D detection and tracking of low-altitude aerial vehicles. LAA3D contains 15,000 real images and 600,000 synthetic frames, captured across diverse scenarios, including urban and suburban environments. It covers multiple aerial object categories, including electric Vertical Take-Off and Landing (eVTOL) aircraft, Micro Aerial Vehicles (MAVs), and Helicopters. Each instance is annotated with 3D bounding box, class label, and instance identity, supporting tasks such as 3D object detection, 3D multi-object tracking (MOT), and 6-DoF pose estimation. Besides, we establish the LAA3D Benchmark, integrating multiple tasks and methods with unified evaluation protocols for comparison. Furthermore, we propose MonoLAA, a monocular 3D detection baseline, achieving robust 3D localization from zoom cameras with varying focal lengths. Models pretrained on synthetic images transfer effectively to real-world data with fine-tuning, demonstrating strong sim-to-real generalization. Our LAA3D provides a comprehensive foundation for future research in low-altitude 3D object perception.

---

### Large Language Model-Assisted Planning of Electric Vehicle Charging Infrastructure with Real-World Case Study

Authors: Xinda Zheng, Canchen Jiang, Hao Wang
Published: 2025-11-24
Categories: eess.SY, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2511.19055v1

The growing demand for electric vehicle (EV) charging infrastructure presents significant planning challenges, requiring efficient strategies for investment and operation to deliver cost-effective charging services. However, the potential benefits of EV charging assignment, particularly in response to varying spatial-temporal patterns of charging demand, remain under-explored in infrastructure planning. This paper proposes an integrated approach that jointly optimizes investment decisions and charging assignments while accounting for spatial-temporal demand dynamics and their interdependencies. To support efficient model development, we leverage a large language model (LLM) to assist in generating and refining the mathematical formulation from structured natural-language descriptions, significantly reducing the modeling burden. The resulting optimization model enables optimal joint decision-making for investment and operation. Additionally, we propose a distributed optimization algorithm based on the Alternating Direction Method of Multipliers (ADMM) to address computational complexity in high-dimensional scenarios, which can be executed on standard computing platforms. We validate our approach through a case study using 1.5 million real-world travel records from Chengdu, China, demonstrating a 30% reduction in total cost compared to a baseline without EV assignment.

---

### Beyond Reward Margin: Rethinking and Resolving Likelihood Displacement in Diffusion Models via Video Generation

Authors: Ruojun Xu, Yu Kai, Xuhua Ren, Jiaxiang Cheng, Bing Ma, Tianxiang Zheng, Qinhlin Lu
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19049v1

Direct Preference Optimization (DPO) has shown promising results in aligning generative outputs with human preferences by distinguishing between chosen and rejected samples. However, a critical limitation of DPO is likelihood displacement, where the probabilities of chosen samples paradoxically decrease during training, undermining the quality of generation. Although this issue has been investigated in autoregressive models, its impact within diffusion-based models remains largely unexplored. This gap leads to suboptimal performance in tasks involving video generation. To address this, we conduct a formal analysis of DPO loss through updating policy within the diffusion framework, which describes how the updating of specific training samples influences the model's predictions on other samples. Using this tool, we identify two main failure modes: (1) Optimization Conflict, which arises from small reward margins between chosen and rejected samples, and (2) Suboptimal Maximization, caused by large reward margins. Informed by these insights, we introduce a novel solution named Policy-Guided DPO (PG-DPO), combining Adaptive Rejection Scaling (ARS) and Implicit Preference Regularization (IPR) to effectively mitigate likelihood displacement. Experiments show that PG-DPO outperforms existing methods in both quantitative metrics and qualitative evaluations, offering a robust solution for improving preference alignment in video generation tasks.

---

### MedSAM3: Delving into Segment Anything with Medical Concepts

Authors: Anglin Liu, Xu R. Cao, Yifan Shen, Yi Lu, Xiang Li, Qianqian Chen, Jintai Chen
Published: 2025-11-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.19046v2

Medical image segmentation is fundamental for biomedical discovery. Existing methods lack generalizability and demand extensive, time-consuming manual annotation for new clinical application. Here, we propose MedSAM-3, a text promptable medical segmentation model for medical image and video segmentation. By fine-tuning the Segment Anything Model (SAM) 3 architecture on medical images paired with semantic conceptual labels, our MedSAM-3 enables medical Promptable Concept Segmentation (PCS), allowing precise targeting of anatomical structures via open-vocabulary text descriptions rather than solely geometric prompts. We further introduce the MedSAM-3 Agent, a framework that integrates Multimodal Large Language Models (MLLMs) to perform complex reasoning and iterative refinement in an agent-in-the-loop workflow. Comprehensive experiments across diverse medical imaging modalities, including X-ray, MRI, Ultrasound, CT, and video, demonstrate that our approach significantly outperforms existing specialist and foundation models. We will release our code and model at https://github.com/Joey-S-Liu/MedSAM3.

---

### Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings

Authors: Zimo Yan, Zheng Xie, Chang Liu, Yuan Wang
Published: 2025-11-24
Categories: cs.LG, math.PR
arXiv: https://arxiv.org/abs/2511.19037v1

Message passing graph neural networks are widely used for learning on graphs, yet their expressive power is limited by the one-dimensional Weisfeiler-Lehman test and can fail to distinguish structurally different nodes. We provide rigorous theory for a Laplacian positional encoding that is invariant to eigenvector sign flips and to basis rotations within eigenspaces. We prove that this encoding yields node identifiability from a constant number of observations and establishes a sample-complexity separation from architectures constrained by the Weisfeiler-Lehman test. The analysis combines a monotone link between shortest-path and diffusion distance, spectral trilateration with a constant set of anchors, and quantitative spectral injectivity with logarithmic embedding size. As an instantiation, pairing this encoding with a neural-process style decoder yields significant gains on a drug-drug interaction task on chemical graphs, improving both the area under the ROC curve and the F1 score and demonstrating the practical benefits of resolving theoretical expressiveness limitations with principled positional information.

---

### Changes in Gaza: DINOv3-Powered Multi-Class Change Detection for Damage Assessment in Conflict Zones

Authors: Kai Zheng, Zhenkai Wu, Fupeng Wei, Miaolan Zhou, Kai Lie, Haitao Guo, Lei Ding, Wei Zhang, Hang-Cheng Dong
Published: 2025-11-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.19035v2

Accurately and swiftly assessing damage from conflicts is crucial for humanitarian aid and regional stability. In conflict zones, damaged zones often share similar architectural styles, with damage typically covering small areas and exhibiting blurred boundaries. These characteristics lead to limited data, annotation difficulties, and significant recognition challenges, including high intra-class similarity and ambiguous semantic changes. To address these issues, we introduce a pre-trained DINOv3 model and propose a multi-scale cross-attention difference siamese network (MC-DiSNet). The powerful visual representation capability of the DINOv3 backbone enables robust and rich feature extraction from bi-temporal remote sensing images. The multi-scale cross-attention mechanism allows for precise localization of subtle semantic changes, while the difference siamese structure enhances inter-class feature discrimination, enabling fine-grained semantic change detection. Furthermore, a simple yet powerful lightweight decoder is designed to generate clear detection maps while maintaining high efficiency. We also release a new Gaza-change dataset containing high-resolution satellite image pairs from 2023-2024 with pixel-level semantic change annotations. It is worth emphasizing that our annotations only include semantic pixels of changed areas. We evaluated our method on the Gaza-Change and two classical datasets: the SECOND and Landsat-SCD datasets. Experimental results demonstrate that our proposed approach effectively addresses the MCD task, and its outstanding performance paves the way for practical applications in rapid damage assessment across conflict zones.

---

### ReEXplore: Improving MLLMs for Embodied Exploration with Contextualized Retrospective Experience Replay

Authors: Gengyuan Zhang, Mingcong Ding, Jingpei Wu, Ruotong Liao, Volker Tresp
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19033v1

Embodied exploration is a target-driven process that requires embodied agents to possess fine-grained perception and knowledge-enhanced decision making. While recent attempts leverage MLLMs for exploration due to their strong perceptual and reasoning abilities, we find that MLLM-based embodied agents remain suboptimal in exploring new environments: (i) they rely on profound but stale pre-trained knowledge, (ii) training-based approaches such as imitation learning or reinforcement learning are expensive for long-horizon tasks with sparse outcome rewards, and (iii) frontier-based exploration yields a large, visually nuanced action space that is difficult for MLLMs to make reliable decisions. We address these challenges with ReEXplore, a training-free framework that performs retrospective experience replay to inject distilled, abstract experience at inference time, and hierarchical frontier selection to decompose frontier ranking into coarse-to-fine decisions. Our approach enables robust, traceable, and efficient exploration. Across multiple embodied exploration benchmarks, ReEXplore yields great improvements over strong MLLM baselines, up to 3x higher performance in both success rate and in navigation efficiency under open-source backbones.

---

### Diagnosing Corruption-Induced Reliability Failures in Vision-Language Models

Authors: Xiangjie Sui, Songyang Li, Hanwei Zhu, Baoliang Chen, Yuming Fang, Xin Sun
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19032v2

Visual corruptions can change vision--language model (VLM) behavior in ways that top-1 accuracy does not capture. A model may keep the same answer while losing distributional support, or improve accuracy through unstable wrong-to-correct changes. We introduce Bench-C, a controlled multiple-choice testbed for studying these effects. It selects semantically diverse samples whose predictions respond to corruption, and evaluates them under 19 corruption types and five severity levels. To measure how corruption changes the option distribution, we introduce the Robustness Alignment Score (RAS), which combines confidence-correctness alignment with uncertainty direction. We further separate originally correct samples from originally wrong samples, and track whether changes are temporary or persistent across severity. Experiments across 13 VLMs reveal a counterintuitive pattern: mild corruptions can improve top-1 accuracy while degrading prediction structure. These failures include silent degradation, erroneous overconfidence, and severity-dependent persistence. Bench-C therefore supports robustness evaluation that goes beyond final answers and attributes where reliability changes occur. Code and data are available at https://github.com/xiangjieSui/Bench-C.

---

### Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling

Authors: Long Tang, Guoquan Zhen, Jie Hao, Jianbo Zhang, Huiyu Duan, Liang Yuan, Guangtao Zhai
Published: 2025-11-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.19024v1

Blind image quality assessment (BIQA) plays a crucial role in evaluating and optimizing visual experience. Most existing BIQA approaches fuse shallow and deep features extracted from backbone networks, while overlooking the unequal contributions to quality prediction. Moreover, while various vision encoder backbones are widely adopted in BIQA, the effective quality decoding architectures remain underexplored. To address these limitations, this paper investigates the contributions of shallow and deep features to BIQA, and proposes a effective quality feature decoding framework via GCN-enhanced \underline{l}ayer\underline{i}nteraction and MoE-based \underline{f}eature d\underline{e}coupling, termed \textbf{(Life-IQA)}. Specifically, the GCN-enhanced layer interaction module utilizes the GCN-enhanced deepest-layer features as query and the penultimate-layer features as key, value, then performs cross-attention to achieve feature interaction. Moreover, a MoE-based feature decoupling module is proposed to decouple fused representations though different experts specialized for specific distortion types or quality dimensions. Extensive experiments demonstrate that Life-IQA shows more favorable balance between accuracy and cost than a vanilla Transformer decoder and achieves state-of-the-art performance on multiple BIQA benchmarks.The code is available at: \href{https://github.com/TANGLONG2/Life-IQA/tree/main}{\texttt{Life-IQA}}.

---

### OrdMoE: Preference Alignment via Hierarchical Expert Group Ranking in Multimodal Mixture-of-Experts LLMs

Authors: Yuting Gao, Weihao Chen, Lan Wang, Ruihan Xu, Qingpei Guo
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.19023v1

Preference learning has recently emerged as a pivotal strategy for post-training alignment of Multimodal Large Language Models (MLLMs). However, existing approaches predominantly rely on external human-annotated preference data, which is costly and labor-intensive to collect. In this work, we propose OrdMoE, a novel preference alignment framework that bypasses the reliance on external human preferences entirely by leveraging intrinsic signals within Mixture-of-Experts (MoE) architectures. Specifically, we observe that the router's expert selection scores implicitly encode a quality-aware ranking of responses (i.e. higher-scoring experts consistently generate higher-quality outputs). Building on this insight, OrdMoE constructs an internal preference hierarchy by grouping experts into ranked tiers based on their per-token routing scores and activating each tier separately to produce a sequence of responses with increasing quality. This yields a zero-cost, self-supervised preference ordering over generated responses, which can be directly optimized using standard preference learning objectives. Extensive experiments across multiple multimodal benchmarks demnstrate that OrdMoE significantly enhances both alignment and overall performance of multimodal Mixture-of-Experts LLMs, achieving competitive results without requiring any human-annotated preference data.

---

### Dynamic Granularity Matters: Rethinking Vision Transformers Beyond Fixed Patch Splitting

Authors: Qiyang Yu, Yu Fang, Tianrui Li, Xuemei Cao, Yan Chen, Jianghao Li, Fan Min
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19021v1

Vision Transformers (ViTs) have demonstrated strong capabilities in capturing global dependencies but often struggle to efficiently represent fine-grained local details. Existing multi-scale approaches alleviate this issue by integrating hierarchical or hybrid features; however, they rely on fixed patch sizes and introduce redundant computation. To address these limitations, we propose Granularity-driven Vision Transformer (Grc-ViT), a dynamic coarse-to-fine framework that adaptively adjusts visual granularity based on image complexity. It comprises two key stages: (1) Coarse Granularity Evaluation module, which assesses visual complexity using edge density, entropy, and frequency-domain cues to estimate suitable patch and window sizes; (2) Fine-grained Refinement module, which refines attention computation according to the selected granularity, enabling efficient and precise feature learning. Two learnable parameters, α and \b{eta}, are optimized end-to-end to balance global reasoning and local perception. Comprehensive evaluations demonstrate that Grc-ViT enhances fine-grained discrimination while achieving a superior trade-off between accuracy and computational efficiency.

---

### 3D Dynamic Radio Map Prediction Using Vision Transformers for Low-Altitude Wireless Networks

Authors: Nguyen Duc Minh Quang, Chang Liu, Huy-Trung Nguyen, Shuangyang Li, Derrick Wing Kwan Ng, Wei Xiang
Published: 2025-11-24
Categories: cs.LG
arXiv: https://arxiv.org/abs/2511.19019v2

Low-altitude wireless networks (LAWN) are rapidly expanding with the growing deployment of unmanned aerial vehicles (UAVs) for logistics, surveillance, and emergency response. Reliable connectivity remains a critical yet challenging task due to three-dimensional (3D) mobility, time-varying user density, and limited power budgets. The transmit power of base stations (BSs) fluctuates dynamically according to user locations and traffic demands, leading to a highly non-stationary 3D radio environment. Radio maps (RMs) have emerged as an effective means to characterize spatial power distributions and support radio-aware network optimization. However, most existing works construct static or offline RMs, overlooking real-time power variations and spatio-temporal dependencies in multi-UAV networks. To overcome this limitation, we propose a 3D dynamic radio map (3D-DRM) framework that learns and predicts the spatio-temporal evolution of received power. Specially, a Vision Transformer (ViT) encoder extracts high-dimensional spatial representations from 3D RMs, while a Transformer-based module models sequential dependencies to predict future power distributions. Experiments unveil that 3D-DRM accurately captures fast-varying power dynamics and substantially outperforms baseline models in both RM reconstruction and short-term prediction.

---

### Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention

Authors: Junbo Zhang, Ran Chen, Qianli Zhou, Xinyang Deng, Wen Jiang
Published: 2025-11-24
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2511.19009v2

Large language models (LLMs) demonstrate powerful capabilities across various natural language processing tasks,yet their inherent safety vulnerabilities undermine the reliable application of LLMs in real-world scenarios. To enhance LLM safety, various jailbreak defense methods have been proposed to guard against harmful outputs. However, improvements in model safety often come at the cost of severe over-refusal, failing to strike a good balance between safety and usability. This phenomenon is a critical reliability degradation issue in LLM intelligent systems, failing to strike a good balance between safety defense effectiveness and system usability reliability. In this paper, we first analyze the causes of over-refusal from a representation perspective, revealing that LLMs are unable to effectively distinguish between over-refusal samples and malicious samples. Based on this, we propose to mitigate overrefusal by intervening in the safety representation space of LLMs. Our method incorporates two core strategies: (1) OverlapAware Loss Weighting, which determines the erasure weight for malicious samples by quantifying their similarity to overrefusal samples in the representation space, and (2) ContextAware Augmentation, which supplements the necessary context for rejection decisions by adding harmful prefixes before rejection responses. Experiments demonstrate that our method achieves a better trade-off between mitigating over-refusal and maintaining safety, compared with existing approaches. This paper also aims to encourage researchers to consider the reliability of defending methods against jailbreak attacks from both the perspectives of safety and over-refusal.

---

### Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding

Authors: Di Wu, Liting Jiang, Ruiyu Fang, Bianjing, Hongyan Xie, Haoxiang Su, Hao Huang, Zhongjiang He, Shuangyong Song, Xuelong Li
Published: 2025-11-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.19005v1

Spoken Language Understanding (SLU) consists of two sub-tasks: intent detection (ID) and slot filling (SF). Given its broad range of real-world applications, enhancing SLU for practical deployment is increasingly critical. Profile-based SLU addresses ambiguous user utterances by incorporating context awareness (CA), user profiles (UP), and knowledge graphs (KG) to support disambiguation, thereby advancing SLU research toward real-world applicability. However, existing SLU datasets still fall short in representing real-world scenarios. Specifically, (1) CA uses one-hot vectors for representation, which is overly idealized, and (2) models typically focuses solely on predicting intents and slot labels, neglecting the reasoning process that could enhance performance and interpretability. To overcome these limitations, we introduce VRSLU, a novel SLU dataset that integrates both Visual images and explicit Reasoning. For over-idealized CA, we use GPT-4o and FLUX.1-dev to generate images reflecting users' environments and statuses, followed by human verification to ensure quality. For reasoning, GPT-4o is employed to generate explanations for predicted labels, which are then refined by human annotators to ensure accuracy and coherence. Additionally, we propose an instructional template, LR-Instruct, which first predicts labels and then generates corresponding reasoning. This two-step approach helps mitigate the influence of reasoning bias on label prediction. Experimental results confirm the effectiveness of incorporating visual information and highlight the promise of explicit reasoning in advancing SLU.

---

### A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation

Authors: Wentao Qu, Guofeng Mei, Yang Wu, Yongshun Gong, Xiaoshui Huang, Liang Xiao
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.19004v2

Text-to-LiDAR generation can customize 3D data with rich structures and diverse scenes for downstream tasks. However, the scarcity of Text-LiDAR pairs often causes insufficient training priors, generating overly smooth 3D scenes. Moreover, low-quality text descriptions may degrade generation quality and controllability. In this paper, we propose a Text-to-LiDAR Diffusion Model for scene generation, named T2LDM, with a Self-Conditioned Representation Guidance (SCRG). Specifically, SCRG, by aligning to the real representations, provides the soft supervision with reconstruction details for the Denoising Network (DN) in training, while decoupled in inference. In this way, T2LDM can perceive rich geometric structures from data distribution, generating detailed objects in scenes. Meanwhile, we construct a content-composable Text-LiDAR benchmark, T2nuScenes, along with a controllability metric. Based on this, we analyze the effects of different text prompts for LiDAR generation quality and controllability, providing practical prompt paradigms and insights. Furthermore, a directional position prior is designed to mitigate street distortion, further improving scene fidelity. Additionally, by learning a conditional encoder via frozen DN, T2LDM can support multiple conditional tasks, including Sparse-to-Dense, Dense-to-Sparse, and Semantic-to-LiDAR generation. Extensive experiments in unconditional and conditional generation demonstrate that T2LDM outperforms existing methods, achieving state-of-the-art scene generation.

---

### Enhancing low energy reconstruction and classification in KM3NeT/ORCA with transformers

Authors: Iván Mozún Mateo
Published: 2025-11-24
Categories: hep-ex, astro-ph.IM, cs.AI
arXiv: https://arxiv.org/abs/2511.18999v2

The current KM3NeT/ORCA neutrino telescope, still under construction, has not yet reached its full potential in neutrino reconstruction capability. When training any deep learning model, no explicit information about the physics or the detector is provided, thus they remain unknown to the model. This study leverages the strengths of transformers by incorporating attention masks inspired by the physics and detector design, making the model understand both the telescope design and the neutrino physics measured on it. The study also shows the efficacy of transformers on retaining valuable information between detectors when doing fine-tuning from one configurations to another.

---

### AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization

Authors: Christos Koutlis, Symeon Papadopoulos
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18993v1

With the rapid advancement of sophisticated synthetic audio-visual content, e.g., for subtle malicious manipulations, ensuring the integrity of digital media has become paramount. This work presents a novel approach to temporal localization of deepfakes by leveraging Audio-Visual Speech Representation Reconstruction (AuViRe). Specifically, our approach reconstructs speech representations from one modality (e.g., lip movements) based on the other (e.g., audio waveform). Cross-modal reconstruction is significantly more challenging in manipulated video segments, leading to amplified discrepancies, thereby providing robust discriminative cues for precise temporal forgery localization. AuViRe outperforms the state of the art by +8.9 AP@0.95 on LAV-DF, +9.6 AP@0.5 on AV-Deepfake1M, and +5.1 AUC on an in-the-wild experiment. Code available at https://github.com/mever-team/auvire.

---

### Classification EM-PCA for clustering and embedding

Authors: Zineddine Tighidet, Lazhar Labiod, Mohamed Nadif
Published: 2025-11-24
Categories: stat.ML, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2511.18992v1

The mixture model is undoubtedly one of the greatest contributions to clustering. For continuous data, Gaussian models are often used and the Expectation-Maximization (EM) algorithm is particularly suitable for estimating parameters from which clustering is inferred. If these models are particularly popular in various domains including image clustering, they however suffer from the dimensionality and also from the slowness of convergence of the EM algorithm. However, the Classification EM (CEM) algorithm, a classifying version, offers a fast convergence solution while dimensionality reduction still remains a challenge. Thus we propose in this paper an algorithm combining simultaneously and non-sequentially the two tasks --Data embedding and Clustering-- relying on Principal Component Analysis (PCA) and CEM. We demonstrate the interest of such approach in terms of clustering and data embedding. We also establish different connections with other clustering approaches.

---

### View-Consistent Diffusion Representations for 3D-Consistent Video Generation

Authors: Duolikun Danier, Ge Gao, Steven McDonagh, Changjian Li, Hakan Bilen, Oisin Mac Aodha
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18991v1

Video generation models have made significant progress in generating realistic content, enabling applications in simulation, gaming, and film making. However, current generated videos still contain visual artifacts arising from 3D inconsistencies, e.g., objects and structures deforming under changes in camera pose, which can undermine user experience and simulation fidelity. Motivated by recent findings on representation alignment for diffusion models, we hypothesize that improving the multi-view consistency of video diffusion representations will yield more 3D-consistent video generation. Through detailed analysis on multiple recent camera-controlled video diffusion models we reveal strong correlations between 3D-consistent representations and videos. We also propose ViCoDR, a new approach for improving the 3D consistency of video models by learning multi-view consistent diffusion representations. We evaluate ViCoDR on camera controlled image-to-video, text-to-video, and multi-view generation models, demonstrating significant improvements in the 3D consistency of the generated videos. Project page: https://danier97.github.io/ViCoDR.

---

### Rethinking Plant Disease Diagnosis: Bridging the Academic-Practical Gap with Vision Transformers and Zero-Shot Learning

Authors: Wassim Benabbas, Mohammed Brahimi, Samir Akhrouf, Bilal Fortas
Published: 2025-11-24
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2511.18989v1

Recent advances in deep learning have enabled significant progress in plant disease classification using leaf images. Much of the existing research in this field has relied on the PlantVillage dataset, which consists of well-centered plant images captured against uniform, uncluttered backgrounds. Although models trained on this dataset achieve high accuracy, they often fail to generalize to real-world field images, such as those submitted by farmers to plant diagnostic systems. This has created a significant gap between published studies and practical application requirements, highlighting the necessity of investigating and addressing this issue. In this study, we investigate whether attention-based architectures and zero-shot learning approaches can bridge the gap between curated academic datasets and real-world agricultural conditions in plant disease classification. We evaluate three model categories: Convolutional Neural Networks (CNNs), Vision Transformers, and Contrastive Language-Image Pre-training (CLIP)-based zero-shot models. While CNNs exhibit limited robustness under domain shift, Vision Transformers demonstrate stronger generalization by capturing global contextual features. Most notably, CLIP models classify diseases directly from natural language descriptions without any task-specific training, offering strong adaptability and interpretability. These findings highlight the potential of zero-shot learning as a practical and scalable domain adaptation strategy for plant health diagnosis in diverse field environments.

---

### Dynamic Mixture of Experts Against Severe Distribution Shifts

Authors: Donghu Kim
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.18987v1

The challenge of building neural networks that can continuously learn and adapt to evolving data streams is central to the fields of continual learning (CL) and reinforcement learning (RL). This lifelong learning problem is often framed in terms of the plasticity-stability dilemma, focusing on issues like loss of plasticity and catastrophic forgetting. Unlike neural networks, biological brains maintain plasticity through capacity growth, inspiring researchers to explore similar approaches in artificial networks, such as adding capacity dynamically. Prior solutions often lack parameter efficiency or depend on explicit task indices, but Mixture-of-Experts (MoE) architectures offer a promising alternative by specializing experts for distinct distributions. This paper aims to evaluate a DynamicMoE approach for continual and reinforcement learning environments and benchmark its effectiveness against existing network expansion methods.

---

### UMCL: Unimodal-generated Multimodal Contrastive Learning for Cross-compression-rate Deepfake Detection

Authors: Ching-Yi Lai, Chih-Yu Jian, Pei-Cheng Chuang, Chia-Ming Lee, Chih-Chung Hsu, Chiou-Ting Hsu, Chia-Wen Lin
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18983v1

In deepfake detection, the varying degrees of compression employed by social media platforms pose significant challenges for model generalization and reliability. Although existing methods have progressed from single-modal to multimodal approaches, they face critical limitations: single-modal methods struggle with feature degradation under data compression in social media streaming, while multimodal approaches require expensive data collection and labeling and suffer from inconsistent modal quality or accessibility in real-world scenarios. To address these challenges, we propose a novel Unimodal-generated Multimodal Contrastive Learning (UMCL) framework for robust cross-compression-rate (CCR) deepfake detection. In the training stage, our approach transforms a single visual modality into three complementary features: compression-robust rPPG signals, temporal landmark dynamics, and semantic embeddings from pre-trained vision-language models. These features are explicitly aligned through an affinity-driven semantic alignment (ASA) strategy, which models inter-modal relationships through affinity matrices and optimizes their consistency through contrastive learning. Subsequently, our cross-quality similarity learning (CQSL) strategy enhances feature robustness across compression rates. Extensive experiments demonstrate that our method achieves superior performance across various compression rates and manipulation types, establishing a new benchmark for robust deepfake detection. Notably, our approach maintains high detection accuracy even when individual features degrade, while providing interpretable insights into feature relationships through explicit alignment.

---

### MOCLIP: A Foundation Model for Large-Scale Nanophotonic Inverse Design

Authors: S. Rodionov, A. Burguete-Lopez, M. Makarenko, Q. Wang, F. Getman, A. Fratalocchi
Published: 2025-11-24
Categories: physics.optics, cs.AI
arXiv: https://arxiv.org/abs/2511.18980v2

Foundation models (FM) are transforming artificial intelligence by enabling generalizable, data-efficient solutions across different domains for a broad range of applications. However, the lack of large and diverse datasets limits the development of FM in nanophotonics. This work presents MOCLIP (Metasurface Optics Contrastive Learning Pretrained), a nanophotonic foundation model that integrates metasurface geometry and spectra within a shared latent space. MOCLIP employs contrastive learning to align geometry and spectral representations using an experimentally acquired dataset with a sample density comparable to ImageNet-1K. The study demonstrates MOCLIP inverse design capabilities for high-throughput zero-shot prediction at a rate of 0.2 million samples per second, enabling the design of a full 4-inch wafer populated with high-density metasurfaces in minutes. It also shows generative latent-space optimization reaching 97 percent accuracy. Finally, we introduce an optical information storage concept that uses MOCLIP to achieve a density of 0.1 Gbit per square millimeter at the resolution limit, exceeding commercial optical media by a factor of six. These results position MOCLIP as a scalable and versatile platform for next-generation photonic design and data-driven applications.

---

### Zero-shot segmentation of skin tumors in whole-slide images with vision-language foundation models

Authors: Santiago Moreno, Pablo Meseguer, Rocío del Amor, Valery Naranjo
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18978v1

Accurate annotation of cutaneous neoplasm biopsies represents a major challenge due to their wide morphological variability, overlapping histological patterns, and the subtle distinctions between benign and malignant lesions. Vision-language foundation models (VLMs), pre-trained on paired image-text corpora, learn joint representations that bridge visual features and diagnostic terminology, enabling zero-shot localization and classification of tissue regions without pixel-level labels. However, most existing VLM applications in histopathology remain limited to slide-level tasks or rely on coarse interactive prompts, and they struggle to produce fine-grained segmentations across gigapixel whole-slide images (WSIs). In this work, we introduce a zero-shot visual-language segmentation pipeline for whole-slide images (ZEUS), a fully automated, zero-shot segmentation framework that leverages class-specific textual prompt ensembles and frozen VLM encoders to generate high-resolution tumor masks in WSIs. By partitioning each WSI into overlapping patches, extracting visual embeddings, and computing cosine similarities against text prompts, we generate a final segmentation mask. We demonstrate competitive performance on two in-house datasets, primary spindle cell neoplasms and cutaneous metastases, highlighting the influence of prompt design, domain shifts, and institutional variability in VLMs for histopathology. ZEUS markedly reduces annotation burden while offering scalable, explainable tumor delineation for downstream diagnostic workflows.

---

### FastForward Pruning: Efficient LLM Pruning via Single-Step Reinforcement Learning

Authors: Xin Yuan, Siqi Li, Jiateng Wei, Chengrui Zhu, Yanming Wu, Qingpeng Li, Jiajun Lv, Xiaoke Lan, Jun Chen, Yong Liu
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.18977v1

Pruning is an effective method for compressing Large Language Models, but finding an optimal, non-uniform layer-wise sparsity allocation remains a key challenge. While heuristic methods are fast but yield suboptimal performance, more powerful search-based approaches like Reinforcement Learning are often hindered by prohibitive computational costs on large-scale models. To overcome this efficiency barrier, we propose FastForward Pruning. Its core is a decoupled, single-step RL framework that separates policy optimization from the complex budget satisfaction problem. Such a decoupling is crucial for efficiently searching the vast policy space of LLMs. This curriculum-based strategy begins with low-cost, simple tasks and gradually increases in complexity, significantly reducing the search's computational overhead. Evaluated on the LLaMA, Mistral, and OPT model families, our framework discovers pruning policies that achieve superior performance over strong heuristic baselines. Crucially, when compared to other search-based algorithms, our method achieves competitive or superior results at a fraction of the computational cost, demonstrating a clear advantage in search efficiency.

---

### Peregrine: One-Shot Fine-Tuning for FHE Inference of General Deep CNNs

Authors: Huaming Ling, Ying Wang, Si Chen, Junfeng Fan
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18976v1

We address two fundamental challenges in adapting general deep CNNs for FHE-based inference: approximating non-linear activations such as ReLU with low-degree polynomials while minimizing accuracy degradation, and overcoming the ciphertext capacity barrier that constrains high-resolution image processing on FHE inference. Our contributions are twofold: (1) a single-stage fine-tuning (SFT) strategy that directly converts pre-trained CNNs into FHE-friendly forms using low-degree polynomials, achieving competitive accuracy with minimal training overhead; and (2) a generalized interleaved packing (GIP) scheme that is compatible with feature maps of virtually arbitrary spatial resolutions, accompanied by a suite of carefully designed homomorphic operators that preserve the GIP-form encryption throughout computation. These advances enable efficient, end-to-end FHE inference across diverse CNN architectures. Experiments on CIFAR-10, ImageNet, and MS COCO demonstrate that the FHE-friendly CNNs obtained via our SFT strategy achieve accuracy comparable to baselines using ReLU or SiLU activations. Moreover, this work presents the first demonstration of FHE-based inference for YOLO architectures in object detection leveraging low-degree polynomial activations.

---

### CataractCompDetect: Intraoperative Complication Detection in Cataract Surgery

Authors: Bhuvan Sachdeva, Sneha Kumari, Rudransh Agarwal, Shalaka Kumaraswamy, Niharika Singri Prasad, Simon Mueller, Raphael Lechtenboehmer, Maximilian W. M. Wintergerst, Thomas Schultz, Kaushik Murali, Mohit Jain
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18968v1

Cataract surgery is one of the most commonly performed surgeries worldwide, yet intraoperative complications such as iris prolapse, posterior capsule rupture (PCR), and vitreous loss remain major causes of adverse outcomes. Automated detection of such events could enable early warning systems and objective training feedback. In this work, we propose CataractCompDetect, a complication detection framework that combines phase-aware localization, SAM 2-based tracking, complication-specific risk scoring, and vision-language reasoning for final classification. To validate CataractCompDetect, we curate CataComp, the first cataract surgery video dataset annotated for intraoperative complications, comprising 53 surgeries, including 23 with clinical complications. On CataComp, CataractCompDetect achieves an average F1 score of 70.63%, with per-complication performance of 81.8% (Iris Prolapse), 60.87% (PCR), and 69.23% (Vitreous Loss). These results highlight the value of combining structured surgical priors with vision-language reasoning for recognizing rare but high-impact intraoperative events. Our dataset and code will be publicly released upon acceptance.

---

### LLM-CSEC: Empirical Evaluation of Security in C/C++ Code Generated by Large Language Models

Authors: Muhammad Usman Shahid, Chuadhry Mujeeb Ahmed, Rajiv Ranjan
Published: 2025-11-24
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2511.18966v1

The security of code generated by large language models (LLMs) is a significant concern, as studies indicate that such code often contains vulnerabilities and lacks essential defensive programming constructs. This work focuses on examining and evaluating the security of LLM-generated code, particularly in the context of C/C++. We categorized known vulnerabilities using the Common Weakness Enumeration (CWE) and, to study their criticality, mapped them to CVEs. We used ten different LLMs for code generation and analyzed the outputs through static analysis. The amount of CWEs present in AI-generated code is concerning. Our findings highlight the need for developers to be cautious when using LLM-generated code. This study provides valuable insights to advance automated code generation and encourage further research in this domain.

---

### Synthesizing Visual Concepts as Vision-Language Programs

Authors: Antonia Wüst, Wolfgang Stammer, Hikaru Shindo, Lukas Helff, Devendra Singh Dhami, Kristian Kersting
Published: 2025-11-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.18964v1

Vision-Language models (VLMs) achieve strong performance on multimodal tasks but often fail at systematic visual reasoning tasks, leading to inconsistent or illogical outputs. Neuro-symbolic methods promise to address this by inducing interpretable logical rules, though they exploit rigid, domain-specific perception modules. We propose Vision-Language Programs (VLP), which combine the perceptual flexibility of VLMs with systematic reasoning of program synthesis. Rather than embedding reasoning inside the VLM, VLP leverages the model to produce structured visual descriptions that are compiled into neuro-symbolic programs. The resulting programs execute directly on images, remain consistent with task constraints, and provide human-interpretable explanations that enable easy shortcut mitigation. Experiments on synthetic and real-world datasets demonstrate that VLPs outperform direct and structured prompting, particularly on tasks requiring complex logical reasoning.

---

### AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention

Authors: Lei Xiao, Jifeng Li, Juntao Gao, Feiyang Ye, Yan Jin, Jingjing Qian, Jing Zhang, Yong Wu, Xiaoyuan Yu
Published: 2025-11-24
Categories: cs.LG, cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2511.18960v4

Vision-Language-Action (VLA) models have shown remarkable progress in embodied tasks recently, but most methods process visual observations independently at each timestep. This history-agnostic design treats robot manipulation as a Markov Decision Process, even though real-world robotic control is inherently partially observable and requires reasoning over past interactions. To address this mismatch, we reformulate VLA policy learning from a Partially Observable Markov Decision Process perspective and propose AVA-VLA, a framework that conditions action generation on a recurrent state that serves as a neural approximation to the agent's belief over task history. Built on this recurrent state, we introduce Active Visual Attention (AVA), which dynamically reweights visual tokens in the current observation to focus on regions most relevant given both the instruction and execution history. Extensive experiments show that AVA-VLA achieves state-of-the-art performance on standard robotic benchmarks, including LIBERO and CALVIN, and transfers effectively to real-world dual-arm manipulation tasks. These results demonstrate the effectiveness of temporally grounded active visual processing for improving VLA performance in robotic sequential decision-making. The project page is available at https://liauto-dsr.github.io/AVA-VLA-Page.

---

### Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation

Authors: Qisen Chai, Yansong Wang, Junjie Huang, Tao Jia
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.18958v2

As graph-structured data grow increasingly large, evaluating their robustness under adversarial attacks becomes computationally expensive and difficult to scale. To address this challenge, we propose to compress graphs into compact representations that preserve both topological structure and robustness profile, enabling efficient and reliable evaluation. We propose Cutter, a dual-agent reinforcement learning framework composed of a Vital Detection Agent (VDA) and a Redundancy Detection Agent (RDA), which collaboratively identify structurally vital and redundant nodes for guided compression. Cutter incorporates three key strategies to enhance learning efficiency and compression quality: trajectory-level reward shaping to transform sparse trajectory returns into dense, policy-equivalent learning signals; prototype-based shaping to guide decisions using behavioral patterns from both high- and low-return trajectories; and cross-agent imitation to enable safer and more transferable exploration. Experiments on multiple real-world graphs demonstrate that Cutter generates compressed graphs that retain essential static topological properties and exhibit robustness degradation trends highly consistent with the original graphs under various attack scenarios, thereby significantly improving evaluation efficiency without compromising assessment fidelity.

---

### Eevee: Towards Close-up High-resolution Video-based Virtual Try-on

Authors: Jianhao Zeng, Yancheng Bai, Ruidong Chen, Xuanpu Zhang, Lei Sun, Dongyang Jin, Ryan Xu, Nannan Zhang, Dan Song, Xiangxiang Chu
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18957v2

Video virtual try-on technology provides a cost-effective solution for creating marketing videos in fashion e-commerce. However, its practical adoption is hindered by two critical limitations. First, the reliance on a single garment image as input in current virtual try-on datasets limits the accurate capture of realistic texture details. Second, most existing methods focus solely on generating full-shot virtual try-on videos, neglecting the business's demand for videos that also provide detailed close-ups. To address these challenges, we introduce a high-resolution dataset for video-based virtual try-on. This dataset offers two key features. First, it provides more detailed information on the garments, which includes high-fidelity images with detailed close-ups and textual descriptions; Second, it uniquely includes full-shot and close-up try-on videos of real human models. Furthermore, accurately assessing consistency becomes significantly more critical for the close-up videos, which demand high-fidelity preservation of garment details. To facilitate such fine-grained evaluation, we propose a new garment consistency metric VGID (Video Garment Inception Distance) that quantifies the preservation of both texture and structure. Our experiments validate these contributions. We demonstrate that by utilizing the detailed images from our dataset, existing video generation models can extract and incorporate texture features, significantly enhancing the realism and detail fidelity of virtual try-on results. Furthermore, we conduct a comprehensive benchmark of recent models. The benchmark effectively identifies the texture and structural preservation problems among current methods.

---

### Active Inference is a Subtype of Variational Inference

Authors: Wouter W. L. Nuijten, Mykola Lukashchuk
Published: 2025-11-24
Categories: cs.AI
arXiv: https://arxiv.org/abs/2511.18955v1

Automated decision-making under uncertainty requires balancing exploitation and exploration. Classical methods treat these separately using heuristics, while Active Inference unifies them through Expected Free Energy (EFE) minimization. However, EFE minimization is computationally expensive, limiting scalability. We build on recent theory recasting EFE minimization as variational inference, formally unifying it with Planning-as-Inference and showing the epistemic drive as a unique entropic contribution. Our main contribution is a novel message-passing scheme for this unified objective, enabling scalable Active Inference in factored-state MDPs and overcoming high-dimensional planning intractability.

---

### Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation

Authors: Juntao Gao, Feiyang Ye, Jing Zhang, Wenjing Qian
Published: 2025-11-24
Categories: cs.RO, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2511.18950v1

Vision-Language-Action (VLA) models have emerged as a powerful paradigm in Embodied AI. However, the significant computational overhead of processing redundant visual tokens remains a critical bottleneck for real-time robotic deployment. While standard token pruning techniques can alleviate this, these task-agnostic methods struggle to preserve task-critical visual information. To address this challenge, simultaneously preserving both the holistic context and fine-grained details for precise action, we propose Compressor-VLA, a novel hybrid instruction-conditioned token compression framework designed for efficient, task-oriented compression of visual information in VLA models. The proposed Compressor-VLA framework consists of two token compression modules: a Semantic Task Compressor (STC) that distills holistic, task-relevant context, and a Spatial Refinement Compressor (SRC) that preserves fine-grained spatial details. This compression is dynamically modulated by the natural language instruction, allowing for the adaptive condensation of task-relevant visual information. Experimentally, extensive evaluations demonstrate that Compressor-VLA achieves a competitive success rate on the LIBERO benchmark while reducing FLOPs by 59% and the visual token count by over 3x compared to its baseline. The real-robot deployments on a dual-arm robot platform validate the model's sim-to-real transferability and practical applicability. Moreover, qualitative analyses reveal that our instruction guidance dynamically steers the model's perceptual focus toward task-relevant objects, thereby validating the effectiveness of our approach.

---

### Leveraging Adversarial Learning for Pathological Fidelity in Virtual Staining

Authors: José Teixeira, Pascal Klöckner, Diana Montezuma, Melis Erdal Cesur, João Fraga, Hugo M. Horlings, Jaime S. Cardoso, Sara P. Oliveira
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18946v1

In addition to evaluating tumor morphology using H&E staining, immunohistochemistry is used to assess the presence of specific proteins within the tissue. However, this is a costly and labor-intensive technique, for which virtual staining, as an image-to-image translation task, offers a promising alternative. Although recent, this is an emerging field of research with 64% of published studies just in 2024. Most studies use publicly available datasets of H&E-IHC pairs from consecutive tissue sections. Recognizing the training challenges, many authors develop complex virtual staining models based on conditional Generative Adversarial Networks, but ignore the impact of adversarial loss on the quality of virtual staining. Furthermore, overlooking the issues of model evaluation, they claim improved performance based on metrics such as SSIM and PSNR, which are not sufficiently robust to evaluate the quality of virtually stained images. In this paper, we developed CSSP2P GAN, which we demonstrate to achieve heightened pathological fidelity through a blind pathological expert evaluation. Furthermore, while iteratively developing our model, we study the impact of the adversarial loss and demonstrate its crucial role in the quality of virtually stained images. Finally, while comparing our model with reference works in the field, we underscore the limitations of the currently used evaluation metrics and demonstrate the superior performance of CSSP2P GAN.

---

### MIST: Mutual Information Estimation Via Supervised Training

Authors: German Gritsai, Megan Richards, Maxime Méloux, Kyunghyun Cho, Maxime Peyrard
Published: 2025-11-24
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2511.18945v4

We propose a fully data-driven approach to designing mutual information (MI) estimators. Since any MI estimator is a function of the observed sample from two random variables, we parameterize this function with a neural network (MIST) and train it end-to-end to predict MI values. Training is performed on a large meta-dataset of 625,000 synthetic joint distributions with known ground-truth MI. To handle variable sample sizes and dimensions, we employ a two-dimensional attention scheme ensuring permutation invariance across input samples. To quantify uncertainty, we optimize a quantile regression loss, enabling the estimator to approximate the sampling distribution of MI rather than return a single point estimate. This research program departs from prior work by taking a fully empirical route, trading universal theoretical guarantees for flexibility and efficiency. Empirically, the learned estimators largely outperform classical baselines across sample sizes and dimensions, including on joint distributions unseen during training. The resulting quantile-based intervals are well-calibrated and more reliable than bootstrap-based confidence intervals, while inference is orders of magnitude faster than existing neural baselines. Beyond immediate empirical gains, this framework yields trainable, fully differentiable estimators that can be embedded into larger learning pipelines. Moreover, exploiting MI's invariance to invertible transformations, meta-datasets can be adapted to arbitrary data modalities via normalizing flows, enabling flexible training for diverse target meta-distributions.

---

### VeCoR -- Velocity Contrastive Regularization for Flow Matching

Authors: Zong-Wei Hong, Jing-lun Li, Lin-Ze Li, Shen Zhang, Yao Tang
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18942v2

Flow Matching (FM) has recently emerged as a principled and efficient alternative to diffusion models. Standard FM encourages the learned velocity field to follow a target direction; however, it may accumulate errors along the trajectory and drive samples off the data manifold, leading to perceptual degradation, especially in lightweight or low-step configurations. To enhance stability and generalization, we extend FM into a balanced attract-repel scheme that provides explicit guidance on both "where to go" and "where not to go." To be formal, we propose \textbf{Velocity Contrastive Regularization (VeCoR)}, a complementary training scheme for flow-based generative modeling that augments the standard FM objective with contrastive, two-sided supervision. VeCoR not only aligns the predicted velocity with a stable reference direction (positive supervision) but also pushes it away from inconsistent, off-manifold directions (negative supervision). This contrastive formulation transforms FM from a purely attractive, one-sided objective into a two-sided training signal, regularizing trajectory evolution and improving perceptual fidelity across datasets and backbones. On ImageNet-1K 256$\times$256, VeCoR yields 22\% and 35\% relative FID reductions on SiT-XL/2 and REPA-SiT-XL/2 backbones, respectively, and achieves further FID gains (32\% relative) on MS-COCO text-to-image generation, demonstrating consistent improvements in stability, convergence, and image quality, particularly in low-step and lightweight settings. Project page: https://p458732.github.io/VeCoR_Project_Page/

---

### Geometry-Aware Deep Congruence Networks for Manifold Learning in Cross-Subject Motor Imagery

Authors: Sanjeev Manivannan, Chandra Shekar Lakshminarayan
Published: 2025-11-24
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2511.18940v3

Cross-subject motor imagery decoding remains a fundamental challenge in EEG-based brain-computer interfaces due to substantial inter-subject variability. Recent approaches have leveraged Riemannian geometry by representing EEG signals as covariance matrices on the symmetric positive definite (SPD) manifold. However, existing methods primarily focus on manifold-based representations while largely overlooking subject-specific variations in covariance dispersion and orientation. In this work, we address these challenges through geometry-aware congruence transformations and propose three complementary models: (i) Discriminative Congruence Transform (DCT), (ii) Deep Linear DCT (DLDCT), and (iii) Deep DCT-UNet (DDCT-UNet). The proposed models are evaluated both as manifold alignment modules for downstream classifiers and as end-to-end discriminative architectures optimized via cross-entropy with a custom logistic regression head. Experiments on challenging cross-subject motor imagery benchmarks demonstrate consistent improvements in transductive decoding performance, achieving 2-3% higher accuracy than strong baselines. These results highlight the effectiveness of geometry-aware congruence learning for mitigating inter-subject variability in EEG decoding.

---

### Knowledge-based Graphical Method for Safety Signal Detection in Clinical Trials

Authors: Francois Vandenhende, Anna Georgiou, Michalis Georgiou, Theodoros Psaras, Ellie Karekla, Elena Hadjicosta
Published: 2025-11-24
Categories: cs.CL
arXiv: https://arxiv.org/abs/2511.18937v1

We present a graphical, knowledge-based method for reviewing treatment-emergent adverse events (AEs) in clinical trials. The approach enhances MedDRA by adding a hidden medical knowledge layer (Safeterm) that captures semantic relationships between terms in a 2-D map. Using this layer, AE Preferred Terms can be regrouped automatically into similarity clusters, and their association to the trial disease may be quantified. The Safeterm map is available online and connected to aggregated AE incidence tables from ClinicalTrials.gov. For signal detection, we compute treatment-specific disproportionality metrics using shrinkage incidence ratios. Cluster-level EBGM values are then derived through precision-weighted aggregation. Two visual outputs support interpretation: a semantic map showing AE incidence and an expectedness-versus-disproportionality plot for rapid signal detection. Applied to three legacy trials, the automated method clearly recovers all expected safety signals. Overall, augmenting MedDRA with a medical knowledge layer improves clarity, efficiency, and accuracy in AE interpretation for clinical trials.

---

### SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression

Authors: Santhosh G S, Saurav Prakash, Balaraman Ravindran
Published: 2025-11-24
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2511.18936v1

Large Language Models (LLMs) face a significant bottleneck during autoregressive inference due to the massive memory footprint of the Key-Value (KV) cache. Existing compression techniques like token eviction, quantization, or other low-rank methods often risk information loss, have fixed limits, or introduce significant computational overhead from explicit decompression steps. In this work, we introduce SWAN, a novel, fine-tuning-free framework that eliminates this overhead. Our method uses an offline orthogonal matrix to rotate and prune the KV-cache, which is then used directly in the attention computation without any reconstruction. Our extensive experiments demonstrate that SWAN, augmented with a small dense buffer, offers a robust trade-off, maintaining performance close to the uncompressed baseline even at aggressive 50-60% memory savings per-token on KV-cache. A key advantage is its runtime-tunable compression level, allowing operators to dynamically adjust the memory footprint, a flexibility absent in methods requiring fixed offline configurations. This combination of a decompression-free design, high performance under compression, and adaptability makes SWAN a practical and efficient solution for serving LLMs with long contexts.

---

### Skeletons Matter: Dynamic Data Augmentation for Text-to-Query

Authors: Yuchen Ji, Bo Xu, Jie Shi, Jiaqing Liang, Deqing Yang, Yu Mao, Hai Chen, Yanghua Xiao
Published: 2025-11-24
Categories: cs.CL, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2511.18934v1

The task of translating natural language questions into query languages has long been a central focus in semantic parsing. Recent advancements in Large Language Models (LLMs) have significantly accelerated progress in this field. However, existing studies typically focus on a single query language, resulting in methods with limited generalizability across different languages. In this paper, we formally define the Text-to-Query task paradigm, unifying semantic parsing tasks across various query languages. We identify query skeletons as a shared optimization target of Text-to-Query tasks, and propose a general dynamic data augmentation framework that explicitly diagnoses model-specific weaknesses in handling these skeletons to synthesize targeted training data. Experiments on four Text-to-Query benchmarks demonstrate that our method achieves state-of-the-art performance using only a small amount of synthesized data, highlighting the efficiency and generality of our approach and laying a solid foundation for unified research on Text-to-Query tasks. We release our code at https://github.com/jjjycaptain/Skeletron.

---

### Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations

Authors: Ryan Wong, Hosea David Yu Fei Ng, Dhananjai Sharma, Glenn Jun Jie Ng, Kavishvaran Srinivasan
Published: 2025-11-24
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2511.18933v1

Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level, model-level, and training-time interventions, followed by three proposed defense strategies. First, a Prompt-Level Defense Framework detects and neutralizes adversarial inputs through sanitization, paraphrasing, and adaptive system guarding. Second, a Logit-Based Steering Defense reinforces refusal behavior through inference-time vector steering in safety-sensitive layers. Third, a Domain-Specific Agent Defense employs the MetaGPT framework to enforce structured, role-based collaboration and domain adherence. Experiments on benchmark datasets show substantial reductions in attack success rate, achieving full mitigation under the agent-based defense. Overall, this study highlights how jailbreaks pose a significant security threat to LLMs and identifies key intervention points for prevention, while noting that defense strategies often involve trade-offs between safety, performance, and scalability. Code is available at: https://github.com/Kuro0911/CS5446-Project

---

### Look It Up: Analysing Internal Web Search Capabilities of Modern LLMs

Authors: Sahil Kale
Published: 2025-11-24
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2511.18931v2

Modern large language models increasingly integrate internal web-based retrieval to provide real-time answers, yet it remains unclear how effectively these systems identify information need, trigger retrieval, and use retrieved evidence. To understand these parameters better, we evaluate the necessity and effectiveness of internal web search through an external lens in closed-source LLMs, without access to model parameters or internal configuration. Our evaluation method comprises a static split of 783 temporally anchored factual queries answerable from pre-cutoff knowledge, designed to test whether retrieval is invoked based on factual uncertainty, and a dynamic split of 288 post-cutoff queries that require up-to-date information, designed to evaluate retrieval effectiveness under unavoidable information need. We experiment across four models across two model families and scales. Across models, enabling retrieval yields substantial accuracy gains on the static split, but systematically degrades confidence calibration. On the dynamic split, models frequently invoke retrieval yet remain below 70 percent accuracy, with failures dominated by query formulation and source selection errors rather than integration of retrieved content. While retrieval is inexpensive to invoke and can be selectively beneficial, repeated retrieval attempts rarely recover from early failures, and confidence becomes inflated once retrieval is available. Overall, internal web-based retrieval functions effectively as a low-latency verification mechanism, but falls short as a reliable IR pipeline, highlighting the need for improved retrieval triggering, query formulation, and evidence-aware confidence calibration in web-enabled LLMs.

---

### Learning Solution Operators for Partial Differential Equations via Monte Carlo-Type Approximation

Authors: Salah Eddine Choutri, Prajwal Chauhan, Othmane Mazhar, Saif Eddin Jabari
Published: 2025-11-24
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2511.18930v1

The Monte Carlo-type Neural Operator (MCNO) introduces a lightweight architecture for learning solution operators for parametric PDEs by directly approximating the kernel integral using a Monte Carlo approach. Unlike Fourier Neural Operators, MCNO makes no spectral or translation-invariance assumptions. The kernel is represented as a learnable tensor over a fixed set of randomly sampled points. This design enables generalization across multiple grid resolutions without relying on fixed global basis functions or repeated sampling during training. Experiments on standard 1D PDE benchmarks show that MCNO achieves competitive accuracy with low computational cost, providing a simple and practical alternative to spectral and graph-based neural operators.

---

### Human-Centric Open-Future Task Discovery: Formulation, Benchmark, and Scalable Tree-Based Search

Authors: Zijian Song, Xiaoxin Lin, Tao Pu, Zhenlong Yuan, Guangrun Wang, Liang Lin
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18929v3

Recent progress in robotics and embodied AI is largely driven by Large Multimodal Models (LMMs). However, a key challenge remains underexplored: how can we advance LMMs to discover tasks that assist humans in open-future scenarios, where human intentions are highly concurrent and dynamic. In this work, we formalize the problem of Human-centric Open-future Task Discovery (HOTD), focusing particularly on identifying tasks that reduce human effort across plausible futures. To facilitate this study, we propose HOTD-Bench, which features over 2K real-world videos, a semi-automated annotation pipeline, and a simulation-based protocol tailored for open-set future evaluation. Additionally, we propose the Collaborative Multi-Agent Search Tree (CMAST) framework, which decomposes complex reasoning through a multi-agent system and structures the reasoning process through a scalable search tree module. In our experiments, CMAST achieves the best performance on the HOTD-Bench, significantly surpassing existing LMMs. It also integrates well with existing LMMs, consistently improving performance.

---

### FineXtrol: Controllable Motion Generation via Fine-Grained Text

Authors: Keming Shen, Bizhu Wu, Junliang Chen, Xiaoqin Wang, Linlin Shen
Published: 2025-11-24
Categories: cs.CV
arXiv: https://arxiv.org/abs/2511.18927v1

Recent works have sought to enhance the controllability and precision of text-driven motion generation. Some approaches leverage large language models (LLMs) to produce more detailed texts, while others incorporate global 3D coordinate sequences as additional control signals. However, the former often introduces misaligned details and lacks explicit temporal cues, and the latter incurs significant computational cost when converting coordinates to standard motion representations. To address these issues, we propose FineXtrol, a novel control framework for efficient motion generation guided by temporally-aware, precise, user-friendly, and fine-grained textual control signals that describe specific body part movements over time. In support of this framework, we design a hierarchical contrastive learning module that encourages the text encoder to produce more discriminative embeddings for our novel control signals, thereby improving motion controllability. Quantitative results show that FineXtrol achieves strong performance in controllable motion generation, while qualitative analysis demonstrates its flexibility in directing specific body part movements.

---