# Research Papers — 2025-11 · bundle page 49 of 197 > Full-text markdown of papers #2401–2450 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/49 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/48.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/50.md) ### PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation Authors: Huadai Liu, Kaicheng Luo, Wen Wang, Qian Chen, Peiwen Sun, Rongjie Huang, Xiangang Li, Jieping Ye, Wei Xue Published: 2025-11-24 Categories: cs.SD, cs.CV, eess.AS, eess.IV arXiv: https://arxiv.org/abs/2511.18833v4 Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accuracy; yet existing methods suffer from objective entanglement that conflates competing goals in single loss functions and lack human preference alignment. We introduce PrismAudio, the first framework to integrate Reinforcement Learning into V2A generation with specialized Chain-of-Thought (CoT) planning. Our approach decomposes monolithic reasoning into four specialized CoT modules (Semantic, Temporal, Aesthetic, and Spatial CoT), each paired with targeted reward functions. This CoT-reward correspondence enables multidimensional RL optimization that guides the model to jointly generate better reasoning across all perspectives, solving the objective entanglement problem while preserving interpretability. To make this optimization computationally practical, we propose Fast-GRPO, which employs hybrid ODE-SDE sampling that dramatically reduces the training overhead compared to existing GRPO implementations. We also introduce AudioCanvas, a rigorous benchmark that is more distributionally balanced and covers more realistically diverse and challenging scenarios than existing datasets, with 300 single-event classes and 501 multi-event samples. Experimental results demonstrate that PrismAudio achieves state-of-the-art performance across all four perceptual dimensions on both the in-domain VGGSound test set and out-of-domain AudioCanvas benchmark. The project page is available at https://PrismAudio.github.io. --- ### Concept than Document: Context Compression via AMR-based Conceptual Entropy Authors: Kaize Shi, Xueyao Sun, Xiaohui Tao, Lin Li, Qika Lin, Guandong Xu Published: 2025-11-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18832v1 Large Language Models (LLMs) face information overload when handling long contexts, particularly in Retrieval-Augmented Generation (RAG) where extensive supporting documents often introduce redundant content. This issue not only weakens reasoning accuracy but also increases computational overhead. We propose an unsupervised context compression framework that exploits Abstract Meaning Representation (AMR) graphs to preserve semantically essential information while filtering out irrelevant text. By quantifying node-level entropy within AMR graphs, our method estimates the conceptual importance of each node, enabling the retention of core semantics. Specifically, we construct AMR graphs from raw contexts, compute the conceptual entropy of each node, and screen significant informative nodes to form a condensed and semantically focused context than raw documents. Experiments on the PopQA and EntityQuestions datasets show that our method outperforms vanilla and other baselines, achieving higher accuracy while substantially reducing context length. To the best of our knowledge, this is the first work introducing AMR-based conceptual entropy for context compression, demonstrating the potential of stable linguistic features in context engineering. --- ### VideoCompressa: Data-Efficient Video Understanding via Joint Temporal Compression and Spatial Reconstruction Authors: Shaobo Wang, Tianle Niu, Runkang Yang, Deshan Liu, Xu He, Zichen Wen, Conghui He, Xuming Hu, Linfeng Zhang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18831v1 The scalability of video understanding models is increasingly limited by the prohibitive storage and computational costs of large-scale video datasets. While data synthesis has improved data efficiency in the image domain, its extension to video remains challenging due to pervasive temporal redundancy and complex spatiotemporal dynamics. In this work, we uncover a critical insight: the primary source of inefficiency in video datasets is not inter-sample redundancy, but intra-sample frame-level redundancy. To leverage this insight, we introduce VideoCompressa, a novel framework for video data synthesis that reframes the problem as dynamic latent compression. Specifically, VideoCompressa jointly optimizes a differentiable keyframe selector-implemented as a lightweight ConvNet with Gumbel-Softmax sampling-to identify the most informative frames, and a pretrained, frozen Variational Autoencoder (VAE) to compress these frames into compact, semantically rich latent codes. These latent representations are then fed into a compression network, enabling end-to-end backpropagation. Crucially, the keyframe selector and synthetic latent codes are co-optimized to maximize retention of task-relevant information. Experiments show that our method achieves unprecedented data efficiency: on UCF101 with ConvNets, VideoCompressa surpasses full-data training by 2.34\% points using only 0.13\% of the original data, with over 5800x speedup compared to traditional synthesis method. Moreover, when fine-tuning Qwen2.5-7B-VL on HMDB51, VideoCompressa matches full-data performance using just 0.41\% of the training data-outperforming zero-shot baseline by 10.61\%. --- ### Leveraging Duration Pseudo-Embeddings in Multilevel LSTM and GCN Hypermodels for Outcome-Oriented PPM Authors: Fang Wang, Paolo Ceravolo, Ernesto Damiani Published: 2025-11-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18830v1 Existing deep learning models for Predictive Process Monitoring (PPM) struggle with temporal irregularities, particularly stochastic event durations and overlapping timestamps, limiting their adaptability across heterogeneous datasets. We propose a dual input neural network strategy that separates event and sequence attributes, using a duration-aware pseudo-embedding matrix to transform temporal importance into compact, learnable representations. This design is implemented across two baseline families: B-LSTM and B-GCN, and their duration-aware variants D-LSTM and D-GCN. All models incorporate self-tuned hypermodels for adaptive architecture selection. Experiments on balanced and imbalanced outcome prediction tasks show that duration pseudo-embedding inputs consistently improve generalization, reduce model complexity, and enhance interpretability. Our results demonstrate the benefits of explicit temporal encoding and provide a flexible design for robust, real-world PPM applications. --- ### Towards Characterizing Knowledge Distillation of PPG Heart Rate Estimation Models Authors: Kanav Arora, Girish Narayanswamy, Shwetak Patel, Richard Li Published: 2025-11-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18829v2 Heart rate estimation from photoplethysmography (PPG) signals generated by wearable devices such as smartwatches and fitness trackers has significant implications for the health and well-being of individuals. Although prior work has demonstrated deep learning models with strong performance in the heart rate estimation task, in order to deploy these models on wearable devices, these models must also adhere to strict memory and latency constraints. In this work, we explore and characterize how large pre-trained PPG models may be distilled to smaller models appropriate for real-time inference on the edge. We evaluate four distillation strategies through comprehensive sweeps of teacher and student model capacities: (1) hard distillation, (2) soft distillation, (3) decoupled knowledge distillation (DKD), and (4) feature distillation. We present a characterization of the resulting scaling laws describing the relationship between model size and performance. This early investigation lays the groundwork for practical and predictable methods for building edge-deployable models for physiological sensing. --- ### Solving a Research Problem in Mathematical Statistics with AI Assistance Authors: Edgar Dobriban Published: 2025-11-24 Categories: math.ST, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.18828v3 Over the last few months, AI models including large language models have improved greatly. There are now several documented examples where they have helped professional mathematical scientists prove new results, sometimes even helping resolve known open problems. In this short note, we add another example to the list, by documenting how we were able to solve a previously unsolved research problem in robust mathematical statistics with crucial help from GPT-5. Our problem concerns robust density estimation, where the observations are perturbed by Wasserstein-bounded contaminations. In a previous preprint (Chao and Dobriban, 2023, arxiv:2308.01853v2), we have obtained upper and lower bounds on the minimax optimal estimation error; which were, however, not sharp. Starting in October 2025, making significant use of GPT-5 Pro, we were able to derive the minimax optimal error rate (reported in version 3 of the above arxiv preprint). GPT-5 provided crucial help along the way, including by suggesting calculations that we did not think of, and techniques that were not familiar to us, such as the dynamic Benamou-Brenier formulation, for key steps in the analysis. Working with GPT-5 took a few weeks of effort, and we estimate that it could have taken several months to get the same results otherwise. At the same time, there are still areas where working with GPT-5 was challenging: it sometimes provided incorrect references, and glossed over details that sometimes took days of work to fill in. We outline our workflow and steps taken to mitigate issues. Overall, our work can serve as additional documentation for a new age of human-AI collaborative work in mathematical science. --- ### Leveraging Metaheuristic Approaches to Improve Deep Learning Systems for Anxiety Disorder Detection Authors: Mohammadreza Amiri, Monireh Hosseini Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18827v1 Despite being among the most common psychological disorders, anxiety-related conditions are still primarily identified through subjective assessments, such as clinical interviews and self-evaluation questionnaires. These conventional methods often require significant time and may vary depending on the evaluator. However, the emergence of advanced artificial intelligence techniques has created new opportunities for detecting anxiety in a more consistent and automated manner. To address the limitations of traditional approaches, this study introduces a comprehensive model that integrates deep learning architectures with optimization strategies inspired by swarm intelligence. Using multimodal and wearable-sensor datasets, the framework analyzes physiological, emotional, and behavioral signals. Swarm intelligence techniques including genetic algorithms and particle swarm optimization are incorporated to refine the feature space and optimize hyperparameters. Meanwhile, deep learning components are tasked with deriving layered and discriminative representations from sequential, multi-source inputs. Our evaluation shows that the fusion of these two computational paradigms significantly enhances detection performance compared with using deep networks alone. The hybrid model achieves notable improvements in accuracy and demonstrates stronger generalization across various individuals. Overall, the results highlight the potential of combining metaheuristic optimization with deep learning to develop scalable, objective, and clinically meaningful solutions for assessing anxiety disorders --- ### Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image Classification Authors: Aakash Gore, Anoushka Dey, Aryan Mishra Published: 2025-11-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.18826v1 Knowledge distillation has emerged as a powerful technique for model compression, enabling the transfer of knowledge from large teacher networks to compact student models. However, traditional knowledge distillation methods treat all teacher predictions equally, regardless of the teacher's confidence in those predictions. This paper proposes an uncertainty-aware dual-student knowledge distillation framework that leverages teacher prediction uncertainty to selectively guide student learning. We introduce a peer-learning mechanism where two heterogeneous student architectures, specifically ResNet-18 and MobileNetV2, learn collaboratively from both the teacher network and each other. Experimental results on ImageNet-100 demonstrate that our approach achieves superior performance compared to baseline knowledge distillation methods, with ResNet-18 achieving 83.84\% top-1 accuracy and MobileNetV2 achieving 81.46\% top-1 accuracy, representing improvements of 2.04\% and 0.92\% respectively over traditional single-student distillation approaches. --- ### Q-Save: Towards Scoring and Attribution for Generated Video Evaluation Authors: Xiele Wu, Mingtao Chen, Zicheng Zhang, Yixian Liu, Yiming Liu, Jianxiang Lu, Jin Wang, Shushi Wang, Chunyi Li, Zhichao Hu, Lliu Yuhong, Xiongkuo Min et al. Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18825v3 Evaluating AI-generated video (AIGV) quality hinges on three crucial dimensions: visual quality, dynamic quality, and text-video alignment. While numerous evaluation datasets and algorithms have been proposed, existing approaches are constrained by two limitations: the absence of systematic definitions for evaluation dimensions, and the isolated treatment of the three dimensions in separate models. Therefore, we introduce Q-Save, a holistic benchmark dataset and unified evaluation model for AIGV quality assessment. The Q-Save dataset contains nearly 10,000 video samples, each annotated with Mean Opinion Scores (MOS) and fine-grained attribution explanations across the three core dimensions. Leveraging this attribution-annotated dataset, we train the proposed Q-Save model, which adopts the SlowFast framework to balance accuracy and efficiency, and employs a three-stage training strategy with Chain-of-Thought (COT) formatted data: Supervised Fine-Tuning (SFT), Grouped Relative Policy Optimization (GRPO), and a final SFT round for stability, to jointly perform quality scoring and attribution generation. Experimental results demonstrate that Q-Save achieves superior performance in AIGV quality prediction while providing interpretable justifications. Code and dataset will be released upon publication. --- ### Assessing the alignment between infants' visual and linguistic experience using multimodal language models Authors: Alvin Wei Ming Tan, Jane Yang, Tarun Sepuri, Khai Loong Aw, Robert Z. Sparks, Zi Yin, Virginia A. Marchman, Michael C. Frank, Bria Long Published: 2025-11-24 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2511.18824v1 Figuring out which objects or concepts words refer to is a central language learning challenge for young children. Most models of this process posit that children learn early object labels from co-occurrences of words and their referents that occur when someone around them talks about an object in the immediate physical environment. But how aligned in time are children's visual and linguistic experiences during everyday learning? To date, answers to this question have been limited by the need for labor-intensive manual annotations of vision-language co-occurrences. Here, we evaluate the use of contrastive language-image pretraining (CLIP) models to automatically characterize vision-language alignment in egocentric videos taken from the infant perspective in home environments. After validating CLIP alignment scores using human alignment judgments, we apply this metric to a large corpus of infant-perspective videos. We show that idealized aligned moments for learning (e.g., "look at the ball" with a ball present in the child's view) are relatively rare in children's everyday experiences compared to modern machine learning datasets, and highlight variability in alignment both within and across children. These findings suggest that infrequent alignment is a constraint for models describing early word learning and offer a new method for investigating children's multimodal environment. --- ### VideoPerceiver: Enhancing Fine-Grained Temporal Perception in Video Multimodal Large Language Models Authors: Fufangchen Zhao, Liao Zhang, Daiqi Shi, Yuanjun Gao, Chen Ye, Yang Cai, Jian Gao, Danfeng Yan Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18823v1 We propose VideoPerceiver, a novel video multimodal large language model (VMLLM) that enhances fine-grained perception in video understanding, addressing VMLLMs' limited ability to reason about brief actions in short clips or rare transient events in long videos. VideoPerceiver adopts a two-stage training framework. During supervised fine-tuning (SFT), we construct "key-information-missing" videos by extracting event-action keywords from captions, identifying corresponding key frames, and replacing them with adjacent frames. We jointly encode original and modified video tokens with text tokens, aligning intermediate visual representations with keywords via an auxiliary contrastive loss to enhance sensitivity to fine-grained motion cues. In reinforcement learning (RL), both video variants are fed into the model to generate descriptions, and a novel relative reward ensures responses from complete videos outperform those from degraded inputs, explicitly training the model to recover temporally precise action details. We also curate a dataset of 80,000 videos with fine-grained actions and transient events. Experiments show VideoPerceiver substantially outperforms state-of-the-art VMLLMs on fine-grained action understanding and rare event captioning benchmarks, while maintaining strong performance on standard tasks. By prioritizing task-relevant visual features, our work redefines video-language model training for fine-grained perception. --- ### DiP: Taming Diffusion Models in Pixel Space Authors: Zhennan Chen, Junwei Zhu, Xu Chen, Jiangning Zhang, Xiaobin Hu, Hanzhen Zhao, Chengjie Wang, Jian Yang, Ying Tai Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18822v3 Diffusion models face a fundamental trade-off between generation quality and computational efficiency. Latent Diffusion Models (LDMs) offer an efficient solution but suffer from potential information loss and non-end-to-end training. In contrast, existing pixel space models bypass VAEs but are computationally prohibitive for high-resolution synthesis. To resolve this dilemma, we propose DiP, an efficient pixel space diffusion framework. DiP decouples generation into a global and a local stage: a Diffusion Transformer (DiT) backbone operates on large patches for efficient global structure construction, while a co-trained lightweight Patch Detailer Head leverages contextual features to restore fine-grained local details. This synergistic design achieves computational efficiency comparable to LDMs without relying on a VAE. DiP is accomplished with up to 10$\times$ faster inference speeds than previous method while increasing the total number of parameters by only 0.3%, and achieves an 1.79 FID score on ImageNet 256$\times$256. --- ### Unsupervised simulation of incompressible flows with physics- and equality- constrained artificial neural networks Authors: Qifeng Hu, Inanc Senocak Published: 2025-11-24 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2511.18820v2 Physics-informed neural networks (PINNs) have shown promise for solving partial differential equations, yet their success in simulating incompressible flows at high Reynolds numbers remains limited. Existing approaches rely on auxiliary labeled data, supervised pretraining, or reference solutions, and no purely unsupervised method comparable to conventional finite-difference or finite-volume solvers has been demonstrated. We attribute this gap to the absence of a mechanism for enforcing the divergence-free constraint and boundary conditions to strict tolerances. To address this, we adopt the physics- and equality-constrained artificial neural network (PECANN) framework with a conditionally adaptive augmented Lagrangian method (CA-ALM), and introduce a pressure-Poisson-based objective. The residual of the pressure Poisson equation is minimized subject to the momentum and continuity equations and boundary conditions on the primitive variables as equality constraints, with CA-ALM enforcing all constraints tightly. For advection-dominated, high-Reynolds-number flows, we further propose an adaptive vanishing entropy viscosity that stabilizes early training without influencing the converged solution. A baseline that instead uses the momentum residual as the objective proves ineffective under the same machinery, underscoring the critical role of the pressure-Poisson objective. The method is assessed on lid-driven cavity flow up to $Re=7{,}500$, three-dimensional unsteady Beltrami flow, and steady and unsteady flow past a circular cylinder with general inflow-outflow boundary conditions, including an ablation study identifying admissible outlet conditions -- all without labeled data or supervised pretraining. Notably, it captures the spontaneous onset of periodic vortex shedding in unsteady cylinder flow without external perturbations, starting from a randomly initialized network. --- ### Disc3D: Automatic Curation of High-Quality 3D Dialog Data via Discriminative Object Referring Authors: Siyuan Wei, Chunjie Wang, Xiao Liu, Xiaosheng Yan, Zhishan Zhou, Rui Huang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18817v3 3D Multi-modal Large Language Models (MLLMs) still lag behind their 2D peers, largely because large-scale, high-quality 3D scene-dialogue datasets remain scarce. Prior efforts hinge on expensive human annotation and leave two key ambiguities unresolved: viewpoint ambiguity, where spatial language presumes unknown camera poses, and object referring ambiguity, where non-exclusive descriptions blur the line between targets and distractors. We therefore present a fully automated pipeline that converts raw 3D scans into unambiguous, high-quality dialogue data at a fraction of the previous cost. By synergizing rule-based constraints with 2D MLLMs and LLMs, the pipeline enables controllable, scalable generation without human intervention. The pipeline comprises four stages: (1) meta-annotation collection harvesting object-, frame-, and scene-level captions, (2) scene graph construction with relation correction to capture proximal object relations, (3) discriminative object referring that generates exclusive and compact descriptions, and (4) multi-task data generation synthesizing diverse dialogues. Our pipeline systematically mitigates inherent flaws in source datasets and produces the final Disc3D dataset, over 2 million samples in 25K hybrid 3D scenes, spanning scene, view, and object captioning, visual grounding, and five object-centric QA tasks. Extensive experiments demonstrate that training with Disc3D yields consistent, significant improvements on both public benchmarks and our multifaceted Disc3D-QA tasks. Code, data, and models will be publicly available. --- ### SupLID: Geometrical Guidance for Out-of-Distribution Detection in Semantic Segmentation Authors: Nimeshika Udayangani, Sarah Erfani, Christopher Leckie Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18816v1 Out-of-Distribution (OOD) detection in semantic segmentation aims to localize anomalous regions at the pixel level, advancing beyond traditional image-level OOD techniques to better suit real-world applications such as autonomous driving. Recent literature has successfully explored the adaptation of commonly used image-level OOD methods--primarily based on classifier-derived confidence scores (e.g., energy or entropy)--for this pixel-precise task. However, these methods inherit a set of limitations, including vulnerability to overconfidence. In this work, we introduce SupLID, a novel framework that effectively guides classifier-derived OOD scores by exploiting the geometrical structure of the underlying semantic space, particularly using Linear Intrinsic Dimensionality (LID). While LID effectively characterizes the local structure of high-dimensional data by analyzing distance distributions, its direct application at the pixel level remains challenging. To overcome this, SupLID constructs a geometrical coreset that captures the intrinsic structure of the in-distribution (ID) subspace. It then computes OOD scores at the superpixel level, enabling both efficient real-time inference and improved spatial smoothness. We demonstrate that geometrical cues derived from SupLID serve as a complementary signal to traditional classifier confidence, enhancing the model's ability to detect diverse OOD scenarios. Designed as a post-hoc scoring method, SupLID can be seamlessly integrated with any semantic segmentation classifier at deployment time. Our results demonstrate that SupLID significantly enhances existing classifier-based OOD scores, achieving state-of-the-art performance across key evaluation metrics, including AUR, FPR, and AUP. Code is available at https://github.com/hdnugit/SupLID. --- ### DetAny4D: Detect Anything 4D Temporally in a Streaming RGB Video Authors: Jiawei Hou, Shenghao Zhang, Can Wang, Zheng Gu, Yonggen Ling, Taiping Zeng, Xiangyang Xue, Jingbo Zhang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18814v1 Reliable 4D object detection, which refers to 3D object detection in streaming video, is crucial for perceiving and understanding the real world. Existing open-set 4D object detection methods typically make predictions on a frame-by-frame basis without modeling temporal consistency, or rely on complex multi-stage pipelines that are prone to error propagation across cascaded stages. Progress in this area has been hindered by the lack of large-scale datasets that capture continuous reliable 3D bounding box (b-box) annotations. To overcome these challenges, we first introduce DA4D, a large-scale 4D detection dataset containing over 280k sequences with high-quality b-box annotations collected under diverse conditions. Building on DA4D, we propose DetAny4D, an open-set end-to-end framework that predicts 3D b-boxes directly from sequential inputs. DetAny4D fuses multi-modal features from pre-trained foundational models and designs a geometry-aware spatiotemporal decoder to effectively capture both spatial and temporal dynamics. Furthermore, it adopts a multi-task learning architecture coupled with a dedicated training strategy to maintain global consistency across sequences of varying lengths. Extensive experiments show that DetAny4D achieves competitive detection accuracy and significantly improves temporal stability, effectively addressing long-standing issues of jitter and inconsistency in 4D object detection. Data and code will be released upon acceptance. --- ### Uncertainty of Network Topology with Applications to Out-of-Distribution Detection Authors: Sing-Yuan Yeh, Chun-Hao Yang Published: 2025-11-24 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2511.18813v1 Persistent homology (PH) is a crucial concept in computational topology, providing a multiscale topological description of a space. It is particularly significant in topological data analysis, which aims to make statistical inference from a topological perspective. In this work, we introduce a new topological summary for Bayesian neural networks, termed the predictive topological uncertainty (pTU). The proposed pTU measures the uncertainty in the interaction between the model and the inputs. It provides insights from the model perspective: if two samples interact with a model in a similar way, then they are considered identically distributed. We also show that the pTU is insensitive to the model architecture. As an application, pTU is used to solve the out-of-distribution (OOD) detection problem, which is critical to ensure model reliability. Failure to detect OOD input can lead to incorrect and unreliable predictions. To address this issue, we propose a significance test for OOD based on the pTU, providing a statistical framework for this issue. The effectiveness of the framework is validated through various experiments, in terms of its statistical power, sensitivity, and robustness. --- ### Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache Authors: Yuqiu Jiang, Xiaozhen Qiao, Yifan Chen, Ye Zheng, Zhe Sun, Xuelong Li Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18811v2 Human-Object Interaction (HOI) detection is a fundamental task in computer vision, empowering machines to comprehend human-object relationships in diverse real-world scenarios. Recent advances in VLMs have significantly improved HOI detection by leveraging rich cross-modal representations. However, most existing VLM-based approaches rely heavily on additional training or prompt tuning, resulting in substantial computational overhead and limited scalability, particularly in long-tailed scenarios where rare interactions are severely underrepresented. In this paper, we propose the Adaptive Diversity Cache (ADC) module, a novel training-free and plug-and-play mechanism designed to mitigate long-tail bias in HOI detection. ADC constructs class-specific caches that accumulate high-confidence and diverse feature representations during inference. The method incorporates adaptive capacity allocation favoring rare categories and dynamic feature augmentation to enable robust prediction calibration without requiring additional training or fine-tuning. Extensive experiments on HICO-DET and V-COCO datasets show that ADC consistently improves existing HOI detectors, particularly enhancing rare category detection while preserving overall performance. These findings confirm the effectiveness of ADC as a training-free, plug-and-play solution for long-tail bias mitigation. --- ### HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representations Authors: Linxiao Cao, Ruitao Wang, Jindong Li, Zhipeng Zhou, Menglin Yang Published: 2025-11-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.18808v2 Retrieval-augmented generation (RAG) enables large language models (LLMs) to access external knowledge, helping mitigate hallucinations and enhance domain-specific expertise. Graph-based RAG enhances structural reasoning by introducing explicit relational organization that enables information propagation across semantically connected text units. However, these methods typically rely on Euclidean embeddings that capture semantic similarity but lack a geometric notion of hierarchical depth, limiting their ability to represent abstraction relationships inherent in complex knowledge graphs. To capture both fine-grained semantics and global hierarchy, we propose HyperbolicRAG, a retrieval framework that integrates hyperbolic geometry into graph-based RAG. HyperbolicRAG introduces three key designs: (1) a depth-aware representation learner that embeds nodes within a shared Poincare manifold to align semantic similarity with hierarchical containment, (2) an unsupervised contrastive regularization that enforces geometric consistency across abstraction levels, and (3) a mutual-ranking fusion mechanism that jointly exploits retrieval signals from Euclidean and hyperbolic spaces, emphasizing cross-space agreement during inference. Extensive experiments across multiple QA benchmarks demonstrate that HyperbolicRAG outperforms competitive baselines, including both standard RAG and graph-augmented baselines. --- ### TPG-INR: Target Prior-Guided Implicit 3D CT Reconstruction for Enhanced Sparse-view Imaging Authors: Qinglei Cao, Ziyao Tang, Xiaoqin Tang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18806v2 X-ray imaging, based on penetration, enables detailed visualization of internal structures. Building on this capability, existing implicit 3D reconstruction methods have adapted the NeRF model and its variants for internal CT reconstruction. However, these approaches often neglect the significance of objects' anatomical priors for implicit learning, limiting both reconstruction precision and learning efficiency, particularly in ultra-sparse view scenarios. To address these challenges, we propose a novel 3D CT reconstruction framework that employs a 'target prior' derived from the object's projection data to enhance implicit learning. Our approach integrates positional and structural encoding to facilitate voxel-wise implicit reconstruction, utilizing the target prior to guide voxel sampling and enrich structural encoding. This dual strategy significantly boosts both learning efficiency and reconstruction quality. Additionally, we introduce a CUDA-based algorithm for rapid estimation of high-quality 3D target priors from sparse-view projections. Experiments utilizing projection data from a complex abdominal dataset demonstrate that the proposed model substantially enhances learning efficiency, outperforming the current leading model, NAF, by a factor of ten. In terms of reconstruction quality, it also exceeds the most accurate model, NeRP, achieving PSNR improvements of 3.57 dB, 5.42 dB, and 5.70 dB with 10, 20, and 30 projections, respectively. The code is available at https://github.com/qlcao171/TPG-INR. --- ### PartDiffuser: Part-wise 3D Mesh Generation via Discrete Diffusion Authors: Yichen Yang, Hong Li, Haodong Zhu, Linin Yang, Guojun Lei, Sheng Xu, Baochang Zhang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18801v4 Existing autoregressive (AR) methods for generating artist-designed meshes struggle to balance global structural consistency with high-fidelity local details, and are susceptible to error accumulation. To address this, we propose PartDiffuser, a novel semi-autoregressive diffusion framework for point-cloud-to-mesh generation. The method first performs semantic segmentation on the mesh and then operates in a "part-wise" manner: it employs autoregression between parts to ensure global topology, while utilizing a parallel discrete diffusion process within each semantic part to precisely reconstruct high-frequency geometric features. PartDiffuser is based on the DiT architecture and introduces a part-aware cross-attention mechanism, using point clouds as hierarchical geometric conditioning to dynamically control the generation process, thereby effectively decoupling the global and local generation tasks. Experiments demonstrate that this method significantly outperforms state-of-the-art (SOTA) models in generating 3D meshes with rich detail, exhibiting exceptional detail representation suitable for real-world applications. --- ### ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes Authors: Zhongtao Wang, Jiaqi Dai, Qingtian Zhu, Yilong Li, Mai Su, Fei Zhu, Meng Gai, Shaorong Wang, Chengwei Pan, Yisong Chen, Guoping Wang Published: 2025-11-24 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2511.18794v2 Multi-period image collections are common in real-world applications. Cities are re-scanned for mapping, construction sites are revisited for progress tracking, and natural regions are monitored for environmental change. Such data form multi-period scenes, where geometry and appearance evolve. Reconstructing such scenes is an important yet underexplored problem. Existing pipelines rely on incompatible assumptions: static and in-the-wild methods enforce a single geometry, while dynamic ones assume smooth motion, both failing under long-term, discontinuous changes. To solve this problem, we introduce ChronoGS, a temporally modulated Gaussian representation that reconstructs all periods within a unified anchor scaffold. It's also designed to disentangle stable and evolving components, achieving temporally consistent reconstruction of multi-period scenes. To catalyze relevant research, we release ChronoScene dataset, a benchmark of real and synthetic multi-period scenes, capturing geometric and appearance variation. Experiments demonstrate that ChronoGS consistently outperforms baselines in reconstruction quality and temporal consistency. Our code and the ChronoScene dataset are publicly available at https://github.com/ZhongtaoWang/ChronoGS. --- ### NEZHA: A Zero-sacrifice and Hyperspeed Decoding Architecture for Generative Recommendations Authors: Yejing Wang, Shengyu Zhou, Jinyu Lu, Ziwei Liu, Langming Liu, Maolin Wang, Wenlin Zhang, Feng Li, Wenbo Su, Pengjie Wang, Jian Xu, Xiangyu Zhao Published: 2025-11-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.18793v2 Generative Recommendation (GR), powered by Large Language Models (LLMs), represents a promising new paradigm for industrial recommender systems. However, their practical application is severely hindered by high inference latency, which makes them infeasible for high-throughput, real-time services and limits their overall business impact. While Speculative Decoding (SD) has been proposed to accelerate the autoregressive generation process, existing implementations introduce new bottlenecks: they typically require separate draft models and model-based verifiers, requiring additional training and increasing the latency overhead. In this paper, we address these challenges with NEZHA, a novel architecture that achieves hyperspeed decoding for GR systems without sacrificing recommendation quality. Specifically, NEZHA integrates a nimble autoregressive draft head directly into the primary model, enabling efficient self-drafting. This design, combined with a specialized input prompt structure, preserves the integrity of sequence-to-sequence generation. Furthermore, to tackle the critical problem of hallucination, a major source of performance degradation, we introduce an efficient, model-free verifier based on a hash set. We demonstrate the effectiveness of NEZHA through extensive experiments on public datasets and have successfully deployed the system on Taobao since October 2025, driving the billion-level advertising revenue and serving hundreds of millions of daily active users. --- ### Scale What Counts, Mask What Matters: Evaluating Foundation Models for Zero-Shot Cross-Domain Wi-Fi Sensing Authors: Cheng Jiang, Yihe Yan, Yanxiang Wang, Chun Tung Chou, Wen Hu Published: 2025-11-24 Categories: cs.CV, cs.IT arXiv: https://arxiv.org/abs/2511.18792v1 While Wi-Fi sensing offers a compelling, privacy-preserving alternative to cameras, its practical utility has been fundamentally undermined by a lack of robustness across domains. Models trained in one setup fail to generalize to new environments, hardware, or users, a critical "domain shift" problem exacerbated by modest, fragmented public datasets. We shift from this limited paradigm and apply a foundation model approach, leveraging Masked Autoencoding (MAE) style pretraining on the largest and most heterogeneous Wi-Fi CSI datasets collection assembled to date. Our study pretrains and evaluates models on over 1.3 million samples extracted from 14 datasets, collected using 4 distinct devices across the 2.4/5/6 GHz bands and bandwidths from 20 to 160 MHz. Our large-scale evaluation is the first to systematically disentangle the impacts of data diversity versus model capacity on cross-domain performance. The results establish scaling trends on Wi-Fi CSI sensing. First, our experiments show log-linear improvements in unseen domain performance as the amount of pretraining data increases, suggesting that data scale and diversity are key to domain generalization. Second, based on the current data volume, larger model can only provide marginal gains for cross-domain performance, indicating that data, rather than model capacity, is the current bottleneck for Wi-Fi sensing generalization. Finally, we conduct a series of cross-domain evaluations on human activity recognition, human gesture recognition and user identification tasks. The results show that the large-scale pretraining improves cross-domain accuracy ranging from 2.2% to 15.7%, compared to the supervised learning baseline. Overall, our findings provide insightful direction for designing future Wi-Fi sensing systems that can eventually be robust enough for real-world deployment. --- ### Perturbing the Derivative: Doubly Wild Refitting for Model-Free Evaluation of Opaque Machine Learning Predictors Authors: Haichen Hu, David Simchi-Levi Published: 2025-11-24 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.18789v3 We study the problem of excess risk evaluation for empirical risk minimization (ERM) under convex losses. We show that by leveraging the idea of wild refitting, one can upper bound the excess risk through the so-called "wild optimism," without relying on the global structure of the underlying function class but only assuming black box access to the training algorithm and a single dataset. We begin by generating two sets of artificially modified pseudo-outcomes created by stochastically perturbing the derivatives with carefully chosen scaling. Using these pseudo-labeled datasets, we refit the black-box procedure twice to obtain two wild predictors and derive an efficient excess risk upper bound under the fixed design setting. Requiring no prior knowledge of the complexity of the underlying function class, our method is essentially model-free and holds significant promise for theoretically evaluating modern opaque deep neural networks and generative models, where traditional learning theory could be infeasible due to the extreme complexity of the hypothesis class. --- ### StereoDETR: Stereo-based Transformer for 3D Object Detection Authors: Shiyi Mu, Zichong Gu, Zhiqi Ai, Anqi Liu, Yilin Gao, Shugong Xu Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18788v1 Compared to monocular 3D object detection, stereo-based 3D methods offer significantly higher accuracy but still suffer from high computational overhead and latency. The state-of-the-art stereo 3D detection method achieves twice the accuracy of monocular approaches, yet its inference speed is only half as fast. In this paper, we propose StereoDETR, an efficient stereo 3D object detection framework based on DETR. StereoDETR consists of two branches: a monocular DETR branch and a stereo branch. The DETR branch is built upon 2D DETR with additional channels for predicting object scale, orientation, and sampling points. The stereo branch leverages low-cost multi-scale disparity features to predict object-level depth maps. These two branches are coupled solely through a differentiable depth sampling strategy. To handle occlusion, we introduce a constrained supervision strategy for sampling points without requiring extra annotations. StereoDETR achieves real-time inference and is the first stereo-based method to surpass monocular approaches in speed. It also achieves competitive accuracy on the public KITTI benchmark, setting new state-of-the-art results on pedestrian and cyclist subsets. The code is available at https://github.com/shiyi-mu/StereoDETR-OPEN. --- ### Understanding Task Transfer in Vision-Language Models Authors: Bhuvan Sachdeva, Karan Uppal, Abhinav Java, Vineeth N. Balasubramanian Published: 2025-11-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.18787v2 Vision-Language Models (VLMs) perform well on multimodal benchmarks but lag behind humans and specialized models on visual perception tasks like depth estimation or object counting. Finetuning on one task can unpredictably affect performance on others, making task-specific finetuning challenging. In this paper, we address this challenge through a systematic study of task transferability. We examine how finetuning a VLM on one perception task affects its zero-shot performance on others. We introduce Perfection Gap Factor (PGF), a normalized metric that measures change in performance as a result of task transfer. We utilize PGF to compute Task Transferability, which captures both the breadth and the magnitude of transfer induced by a source task. Using three open-weight VLMs evaluated across 13 perception tasks, we construct a task transfer graph that reveals previously unobserved relationships among perception tasks. Our analysis uncovers patterns of positive and negative transfer, identifies groups of tasks that mutually influence each other, organizes tasks into personas based on their transfer behavior and demonstrates how PGF can guide data selection for more efficient training. These findings highlight both opportunities for positive transfer and risks of negative interference, offering actionable guidance for advancing VLMs. --- ### STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution Authors: Junyang Chen, Jiangxin Dong, Long Sun, Yixin Yang, Jinshan Pan Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18786v1 We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main challenges lie in maintaining temporal stability during reconstruction and preserving structural fidelity during generation. To address these challenges, we first develop a motion-aware VAE reconstruction method that performs segment-wise reconstruction, with each segment clip exhibiting uniform motion characteristic, thereby effectively handling videos with complex camera motions. Moreover, we observe that the first-frame latent extracted by the VAE encoder in each clip, termed the anchor-frame latent, remains unaffected by temporal compression and retains richer spatial structural information than subsequent frame latents. We further develop an anchor-frame guidance approach that leverages structural information from anchor frames to constrain the generation process and improve structural fidelity of video features. Coupling these two designs enables the video diffusion model to achieve high-quality video super-resolution. Extensive experiments show that STCDiT outperforms state-of-the-art methods in terms of structural fidelity and temporal consistency. --- ### Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs Authors: Renchu Guan, Xuyang Li, Yachao Zhang, Wei Pang, Fausto Giunchiglia, Ximing Li, Yonghao Liu, Xiaoyue Feng Published: 2025-11-24 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2511.18783v1 Hypergraphs, as a generalization of traditional graphs, naturally capture high-order relationships. In recent years, hypergraph neural networks (HNNs) have been widely used to capture complex high-order relationships. However, most existing hypergraph neural network methods inherently rely on the homophily assumption, which often does not hold in real-world scenarios that exhibit significant heterophilic structures. To address this limitation, we propose \textbf{HONOR}, a novel unsupervised \textbf{H}ypergraph c\textbf{ON}trastive learning framework suitable for both hom\textbf{O}philic and hete\textbf{R}ophilic hypergraphs. Specifically, HONOR explicitly models the heterophilic relationships between hyperedges and nodes through two complementary mechanisms: a prompt-based hyperedge feature construction strategy that maintains global semantic consistency while suppressing local noise, and an adaptive attention aggregation module that dynamically captures the diverse local contributions of nodes to hyperedges. Combined with high-pass filtering, these designs enable HONOR to fully exploit heterophilic connection patterns, yielding more discriminative and robust node and hyperedge representations. Theoretically, we demonstrate the superior generalization ability and robustness of HONOR. Empirically, extensive experiments further validate that HONOR consistently outperforms state-of-the-art baselines under both homophilic and heterophilic datasets. --- ### A Novel Dual-Stream Framework for dMRI Tractography Streamline Classification with Joint dMRI and fMRI Data Authors: Haotian Yan, Bocheng Guo, Jianzhong He, Nir A. Sochen, Ofer Pasternak, Lauren J O'Donnell, Fan Zhang Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18781v1 Streamline classification is essential to identify anatomically meaningful white matter tracts from diffusion MRI (dMRI) tractography. However, current streamline classification methods rely primarily on the geometric features of the streamline trajectory, failing to distinguish between functionally distinct fiber tracts with similar pathways. To address this, we introduce a novel dual-stream streamline classification framework that jointly analyzes dMRI and functional MRI (fMRI) data to enhance the functional coherence of tract parcellation. We design a novel network that performs streamline classification using a pretrained backbone model for full streamline trajectories, while augmenting with an auxiliary network that processes fMRI signals from fiber endpoint regions. We demonstrate our method by parcellating the corticospinal tract (CST) into its four somatotopic subdivisions. Experimental results from ablation studies and comparisons with state-of-the-art methods demonstrate our approach's superior performance. --- ### ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection Authors: Ruize Ma, Minghong Cai, Yilei Jiang, Jiaming Han, Yi Feng, Yingshui Tan, Xiaoyong Zhu, Bo Zhang, Bo Zheng, Xiangyu Yue Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18780v3 Recent progress in video generative models has enabled the creation of high-quality videos from multimodal prompts that combine text and images. While these systems offer enhanced controllability, they also introduce new safety risks, as harmful content can emerge from individual modalities or their interaction. Existing safety methods are often text-only, require prior knowledge of the risk category, or operate as post-generation auditors, struggling to proactively mitigate such compositional, multimodal risks. To address this challenge, we present ConceptGuard, a unified safeguard framework for proactively detecting and mitigating unsafe semantics in multimodal video generation. ConceptGuard operates in two stages: First, a contrastive detection module identifies latent safety risks by projecting fused image-text inputs into a structured concept space; Second, a semantic suppression mechanism steers the generative process away from unsafe concepts by intervening in the prompt's multimodal conditioning. To support the development and rigorous evaluation of this framework, we introduce two novel benchmarks: ConceptRisk, a large-scale dataset for training on multimodal risks, and T2VSafetyBench-TI2V, the first benchmark adapted from T2VSafetyBench for the Text-and-Image-to-Video (TI2V) safety setting. Comprehensive experiments on both benchmarks show that ConceptGuard consistently outperforms existing baselines, achieving state-of-the-art results in both risk detection and safe video generation. Our code is available at https://github.com/Ruize-Ma/ConceptGuard. --- ### SAOT: An Enhanced Locality-Aware Spectral Transformer for Solving PDEs Authors: Chenhong Zhou, Jie Chen, Zaifeng Yang Published: 2025-11-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18777v1 Neural operators have shown great potential in solving a family of Partial Differential Equations (PDEs) by modeling the mappings between input and output functions. Fourier Neural Operator (FNO) implements global convolutions via parameterizing the integral operators in Fourier space. However, it often results in over-smoothing solutions and fails to capture local details and high-frequency components. To address these limitations, we investigate incorporating the spatial-frequency localization property of Wavelet transforms into the Transformer architecture. We propose a novel Wavelet Attention (WA) module with linear computational complexity to efficiently learn locality-aware features. Building upon WA, we further develop the Spectral Attention Operator Transformer (SAOT), a hybrid spectral Transformer framework that integrates WA's localized focus with the global receptive field of Fourier-based Attention (FA) through a gated fusion block. Experimental results demonstrate that WA significantly mitigates the limitations of FA and outperforms existing Wavelet-based neural operators by a large margin. By integrating the locality-aware and global spectral representations, SAOT achieves state-of-the-art performance on six operator learning benchmarks and exhibits strong discretization-invariant ability. --- ### Rethinking Garment Conditioning in Diffusion-based Virtual Try-On: Decouple, Don't Denoise Authors: Kihyun Na, Jinyoung Choi, Injung Kim Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18775v2 Virtual Try-On (VTON) synthesizes realistic images of a person wearing a target garment, with broad applications in e-commerce and fashion. Diffusion-based dual-UNet methods achieve strong results but double the parameters by dedicating a separate network to garment conditioning. Spatial concatenation offers a simpler single-network alternative, yet both UNet- and DiT-based instantiations report that full fine-tuning is ineffective, and the community has settled for attention-only training. We ask: why does full fine-tuning fail, and can this be resolved? Through what is, to our knowledge, the first visualization study of dual-UNet reference network behavior, we identify a unifying insight: garment conditioning must be decoupled from the denoising process. Spatial concatenation violates this by embedding the garment within the denoising target, causing three conflicts: guidance leakage, gradient competition, and train-test discrepancy. We derive three design principles to restore this decoupling and implement them as a pure recipe atop a standard architecture with no modification. The resulting model, DeCo-VTON (860M params), achieves single-network state of the art, matching the dual-UNet state of the art at half the cost while being preferred in human evaluation. --- ### Zero-Shot Context-Aware ASR for Diverse Arabic Varieties Authors: Bashar Talafha, Amin Abu Alhassan, Muhammad Abdul-Mageed Published: 2025-11-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18774v2 Zero-shot ASR for Arabic remains challenging: while multilingual models perform well on Modern Standard Arabic (MSA), error rates rise sharply on dialectal and accented speech due to linguistic mismatch and scarce labeled data. We study context-aware decoding as a lightweight test-time adaptation paradigm that conditions inference on external side information without parameter updates. For promptable encoder-decoder ASR (e.g., Whisper), we incorporate context through (i) decoder prompting with first-pass hypotheses and (ii) encoder/decoder prefixing with retrieved speech-text exemplars, complemented by simple prompt reordering and optional speaker-matched synthetic exemplars to improve robustness in informal and multi-speaker settings. To extend contextual adaptation beyond promptable architectures, we introduce proxy-guided n-best selection for CTC ASR: given one or more external proxy hypotheses, we select from a model's n-best list by minimizing text-level distance to the proxies, enabling contextual inference without direct prompting. Across ten Arabic conditions spanning MSA, accented MSA, and multiple dialects, context-aware decoding yields average relative WER reductions of 22.29% on MSA, 20.54 on accented MSA, and 9.15% on dialectal Arabic. For CTC models, proxy-guided selection reduces WER by 15.6% relative on MSA and recovers a substantial fraction of oracle n-best gains, demonstrating that context-aware inference generalizes beyond encoder-decoder ASR. --- ### Sampling Control for Imbalanced Calibration in Semi-Supervised Learning Authors: Senmao Tian, Xiang Wei, Shunli Zhang Published: 2025-11-24 Categories: cs.LG, cs.CV, stat.ML arXiv: https://arxiv.org/abs/2511.18773v1 Class imbalance remains a critical challenge in semi-supervised learning (SSL), especially when distributional mismatches between labeled and unlabeled data lead to biased classification. Although existing methods address this issue by adjusting logits based on the estimated class distribution of unlabeled data, they often handle model imbalance in a coarse-grained manner, conflating data imbalance with bias arising from varying class-specific learning difficulties. To address this issue, we propose a unified framework, SC-SSL, which suppresses model bias through decoupled sampling control. During training, we identify the key variables for sampling control under ideal conditions. By introducing a classifier with explicit expansion capability and adaptively adjusting sampling probabilities across different data distributions, SC-SSL mitigates feature-level imbalance for minority classes. In the inference phase, we further analyze the weight imbalance of the linear classifier and apply post-hoc sampling control with an optimization bias vector to directly calibrate the logits. Extensive experiments across various benchmark datasets and distribution settings validate the consistency and state-of-the-art performance of SC-SSL. --- ### Re-Key-Free, Risky-Free: Adaptable Model Usage Control Authors: Zihan Wang, Zhongkui Ma, Xinguo Feng, Chuan Yan, Dongge Liu, Ruoxi Sun, Derui Wang, Minhui Xue, Guangdong Bai Published: 2025-11-24 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.18772v2 Deep neural networks (DNNs) have become valuable intellectual property of model owners, due to the substantial resources required for their development. To protect these assets in the deployed environment, recent research has proposed model usage control mechanisms to ensure models cannot be used without proper authorization. These methods typically lock the utility of the model by embedding an access key into its parameters. However, they often assume static deployment, and largely fail to withstand continual post-deployment model updates, such as fine-tuning or task-specific adaptation. In this paper, we propose AdaLoc, to endow key-based model usage control with adaptability during model evolution. It strategically selects a subset of weights as an intrinsic access key, which enables all model updates to be confined to this key throughout the evolution lifecycle. AdaLoc enables using the access key to restore the keyed model to the latest authorized states without redistributing the entire network (i.e., adaptation), and frees the model owner from full re-keying after each model update (i.e., lock preservation). We establish a formal foundation to underpin AdaLoc, providing crucial bounds such as the errors introduced by updates restricted to the access key. Experiments across six vision and language benchmarks and six modern architectures spanning CNNs and Transformers demonstrate that AdaLoc achieves high accuracy under significant updates while retaining robust protections. Specifically, authorized usages consistently achieve strong task-specific performance, while unauthorized usage accuracy drops to near-random guessing levels (e.g., 1.02% on CIFAR-100), compared to up to 87.01% under prior key-based defenses. This shows that AdaLoc can offer a practical solution for adaptive and protected DNN deployment in evolving real-world scenarios. --- ### Unsupervised Multi-View Visual Anomaly Detection via Progressive Homography-Guided Alignment Authors: Xintao Chen, Xiaohao Xu, Bozhong Zheng, Yun Liu, Yingna Wu Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18766v1 Unsupervised visual anomaly detection from multi-view images presents a significant challenge: distinguishing genuine defects from benign appearance variations caused by viewpoint changes. Existing methods, often designed for single-view inputs, treat multiple views as a disconnected set of images, leading to inconsistent feature representations and a high false-positive rate. To address this, we introduce ViewSense-AD (VSAD), a novel framework that learns viewpoint-invariant representations by explicitly modeling geometric consistency across views. At its core is our Multi-View Alignment Module (MVAM), which leverages homography to project and align corresponding feature regions between neighboring views. We integrate MVAM into a View-Align Latent Diffusion Model (VALDM), enabling progressive and multi-stage alignment during the denoising process. This allows the model to build a coherent and holistic understanding of the object's surface from coarse to fine scales. Furthermore, a lightweight Fusion Refiner Module (FRM) enhances the global consistency of the aligned features, suppressing noise and improving discriminative power. Anomaly detection is performed by comparing multi-level features from the diffusion model against a learned memory bank of normal prototypes. Extensive experiments on the challenging RealIAD and MANTA datasets demonstrate that VSAD sets a new state-of-the-art, significantly outperforming existing methods in pixel, view, and sample-level visual anomaly proving its robustness to large viewpoint shifts and complex textures. --- ### NI-Tex: Non-isometric Image-based Garment Texture Generation Authors: Hui Shan, Ming Li, Haitao Yang, Kai Zheng, Sizhe Zheng, Yanwei Fu, Xiangru Huang Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18765v3 Existing industrial 3D garment meshes already cover most real-world clothing geometries, yet their texture diversity remains limited. To acquire more realistic textures, generative methods are often used to extract Physically-based Rendering (PBR) textures and materials from large collections of wild images and project them back onto garment meshes. However, most image-conditioned texture generation approaches require strict topological consistency between the input image and the input 3D mesh, or rely on accurate mesh deformation to match to the image poses, which significantly constrains the texture generation quality and flexibility. To address the challenging problem of non-isometric image-based garment texture generation, we construct 3D Garment Videos, a physically simulated, garment-centric dataset that provides consistent geometry and material supervision across diverse deformations, enabling robust cross-pose texture learning. We further employ Nano Banana for high-quality non-isometric image editing, achieving reliable cross-topology texture generation between non-isometric image-geometry pairs. Finally, we propose an iterative baking method via uncertainty-guided view selection and reweighting that fuses multi-view predictions into seamless, production-ready PBR textures. Through extensive experiments, we demonstrate that our feedforward dual-branch architecture generates versatile and spatially aligned PBR materials suitable for industry-level 3D garment design. --- ### VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement Authors: Xuanzhao Dong, Wenhui Zhu, Yujian Xiong, Xiwen Chen, Hao Wang, Xin Li, Jiajun Cheng, Zhipeng Wang, Shao Tang, Oana Dumitrascu, Yalin Wang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18763v1 Color fundus photography (CFP) is central to diagnosing and monitoring retinal disease, yet its acquisition variability (e.g., illumination changes) often degrades image quality, which motivates robust enhancement methods. Unpaired enhancement pipelines are typically GAN-based, however, they can distort clinically critical vasculature, altering vessel topology and endpoint integrity. Motivated by these structural alterations, we propose Vessel-Aware Optimal Transport (\textbf{VAOT}), a framework that combines an optimal-transport objective with two structure-preserving regularizers: (i) a skeleton-based loss to maintain global vascular connectivity and (ii) an endpoint-aware loss to stabilize local termini. These constraints guide learning in the unpaired setting, reducing noise while preserving vessel structure. Experimental results on synthetic degradation benchmark and downstream evaluations in vessel and lesion segmentation demonstrate the superiority of the proposed methods against several state-of-the art baselines. The code is available at https://github.com/Retinal-Research/VAOT --- ### HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs Authors: Azim Ospanov, Zijin Feng, Jiacheng Sun, Haoli Bai, Xin Shen, Farzan Farnia Published: 2025-11-24 Categories: cs.AI, cs.FL arXiv: https://arxiv.org/abs/2511.18760v2 Informal mathematics has been central to modern large language model (LLM) reasoning, offering flexibility and efficient construction of arguments. However, purely informal reasoning is prone to logical gaps and subtle errors that are difficult to detect and correct. In contrast, formal theorem proving provides rigorous, verifiable mathematical reasoning, where each inference step is checked by a trusted compiler, but lacks the exploratory freedom of informal problem-solving. This mismatch leaves current LLM-based math agents without a principled way to combine the strengths of both paradigms. In this work, we introduce Hermes, the first tool-assisted agent that explicitly interleaves informal reasoning with formally verified proofs in Lean. The framework performs intermediate formal checking to prevent reasoning drift and a memory module for proof continuity across multi-step reasoning chains, enabling both exploration and verification. We evaluate Hermes on four challenging mathematical reasoning benchmarks using LLMs of varying parameter scales, from small models to state-of-the-art systems. Across all settings, Hermes reliably improves the reasoning accuracy of base models while substantially reducing reasoning token usage and computational cost compared to reward-based approaches. On difficult datasets such as AIME and HARDMath2, Hermes@1 achieves up to a 40% accuracy improvement while using 80% fewer total inference FLOPs. When scaled at test time, Hermes@5 boosts accuracy further by 20%. The implementation and codebase are publicly available at https://github.com/aziksh-ospanov/HERMES. --- ### From Features to Reference Points: Lightweight and Adaptive Fusion for Cooperative Autonomous Driving Authors: Yongqi Zhu, Morui Zhu, Qi Chen, Deyuan Qu, Isabella Luo, Song Fu, Qing Yang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18757v2 We present RefPtsFusion, a lightweight and interpretable framework for cooperative autonomous driving. Instead of sharing large feature maps or query embeddings, vehicles exchange compact reference points, e.g., objects' positions, velocities, and size information. This approach shifts the focus from "what is seen" to "where to see", creating a sensor- and model-independent interface that works well across vehicles with heterogeneous perception models while greatly reducing communication bandwidth. To enhance the richness of shared information, we further develop a selective Top-K query fusion that selectively adds high-confidence queries from the sender. It thus achieves a strong balance between accuracy and communication cost. Experiments on the M3CAD dataset show that RefPtsFusion maintains stable perception performance while reducing communication overhead by five orders of magnitude, dropping from hundreds of MB/s to only a few KB/s at 5 FPS (frame per second), compared to traditional feature-level fusion methods. Extensive experiments also demonstrate RefPtsFusion's strong robustness and consistent transmission behavior, highlighting its potential for scalable, real-time cooperative driving systems. --- ### Robust Multimodal Sentiment Analysis of Image-Text Pairs by Distribution-Based Feature Recovery and Fusion Authors: Daiqing Wu, Dongbao Yang, Yu Zhou, Can Ma Published: 2025-11-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18751v3 As posts on social media increase rapidly, analyzing the sentiments embedded in image-text pairs has become a popular research topic in recent years. Although existing works achieve impressive accomplishments in simultaneously harnessing image and text information, they lack the considerations of possible low-quality and missing modalities. In real-world applications, these issues might frequently occur, leading to urgent needs for models capable of predicting sentiment robustly. Therefore, we propose a Distribution-based feature Recovery and Fusion (DRF) method for robust multimodal sentiment analysis of image-text pairs. Specifically, we maintain a feature queue for each modality to approximate their feature distributions, through which we can simultaneously handle low-quality and missing modalities in a unified framework. For low-quality modalities, we reduce their contributions to the fusion by quantitatively estimating modality qualities based on the distributions. For missing modalities, we build inter-modal mapping relationships supervised by samples and distributions, thereby recovering the missing modalities from available ones. In experiments, two disruption strategies that corrupt and discard some modalities in samples are adopted to mimic the low-quality and missing modalities in various real-world scenarios. Through comprehensive experiments on three publicly available image-text datasets, we demonstrate the universal improvements of DRF compared to SOTA methods under both two strategies, validating its effectiveness in robust multimodal sentiment analysis. --- ### On Instability of Minimax Optimal Optimism-Based Bandit Algorithms Authors: Samya Praharaj, Koulik Khamaru Published: 2025-11-24 Categories: stat.ML, cs.IT, cs.LG, math.ST arXiv: https://arxiv.org/abs/2511.18750v1 Statistical inference from data generated by multi-armed bandit (MAB) algorithms is challenging due to their adaptive, non-i.i.d. nature. A classical manifestation is that sample averages of arm rewards under bandit sampling may fail to satisfy a central limit theorem. Lai and Wei's stability condition provides a sufficient, and essentially necessary criterion, for asymptotic normality in bandit problems. While the celebrated Upper Confidence Bound (UCB) algorithm satisfies this stability condition, it is not minimax optimal, raising the question of whether minimax optimality and statistical stability can be achieved simultaneously. In this paper, we analyze the stability properties of a broad class of bandit algorithms that are based on the optimism principle. We establish general structural conditions under which such algorithms violate the Lai-Wei stability criterion. As a consequence, we show that widely used minimax-optimal UCB-style algorithms, including MOSS, Anytime-MOSS, Vanilla-MOSS, ADA-UCB, OC-UCB, KL-MOSS, KL-UCB++, KL-UCB-SWITCH, and Anytime KL-UCB-SWITCH, are unstable. We further complement our theoretical results with numerical simulations demonstrating that, in all these cases, the sample means fail to exhibit asymptotic normality. Overall, our findings suggest a fundamental tension between stability and minimax optimal regret, raising the question of whether it is possible to design bandit algorithms that achieve both. Understanding whether such simultaneously stable and minimax optimal strategies exist remains an important open direction. --- ### Large Language Models Require Curated Context for Reliable Political Fact-Checking -- Even with Reasoning and Web Search Authors: Matthew R. DeVerna, Kai-Cheng Yang, Harry Yaojun Yan, Filippo Menczer Published: 2025-11-24 Categories: cs.CL, cs.CY, cs.IR arXiv: https://arxiv.org/abs/2511.18749v1 Large language models (LLMs) have raised hopes for automated end-to-end fact-checking, but prior studies report mixed results. As mainstream chatbots increasingly ship with reasoning capabilities and web search tools -- and millions of users already rely on them for verification -- rigorous evaluation is urgent. We evaluate 15 recent LLMs from OpenAI, Google, Meta, and DeepSeek on more than 6,000 claims fact-checked by PolitiFact, comparing standard models with reasoning- and web-search variants. Standard models perform poorly, reasoning offers minimal benefits, and web search provides only moderate gains, despite fact-checks being available on the web. In contrast, a curated RAG system using PolitiFact summaries improved macro F1 by 233% on average across model variants. These findings suggest that giving models access to curated high-quality context is a promising path for automated fact-checking. --- ### Any4D: Open-Prompt 4D Generation from Natural Language and Images Authors: Hao Li, Qiao Sun Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18746v2 While video-generation-based embodied world models have gained increasing attention, their reliance on large-scale embodied interaction data remains a key bottleneck. The scarcity, difficulty of collection, and high dimensionality of embodied data fundamentally limit the alignment granularity between language and actions and exacerbate the challenge of long-horizon video generation--hindering generative models from achieving a \textit{"GPT moment"} in the embodied domain. There is a naive observation: \textit{the diversity of embodied data far exceeds the relatively small space of possible primitive motions}. Based on this insight, we propose \textbf{Primitive Embodied World Models} (PEWM), which restricts video generation to fixed shorter horizons, our approach \textit{1) enables} fine-grained alignment between linguistic concepts and visual representations of robotic actions, \textit{2) reduces} learning complexity, \textit{3) improves} data efficiency in embodied data collection, and \textit{4) decreases} inference latency. By equipping with a modular Vision-Language Model (VLM) planner and a Start-Goal heatmap Guidance mechanism (SGG), PEWM further enables flexible closed-loop control and supports compositional generalization of primitive-level policies over extended, complex tasks. Our framework leverages the spatiotemporal vision priors in video models and the semantic awareness of VLMs to bridge the gap between fine-grained physical interaction and high-level reasoning, paving the way toward scalable, interpretable, and general-purpose embodied intelligence. --- ### RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context Authors: Yu Lei, Shuzheng Si, Wei Wang, Yifei Wu, Gang Chen, Fanchao Qi, Maosong Sun Published: 2025-11-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.18743v1 Large language models are evolving from single-turn responders into tool-using agents capable of sustained reasoning and decision-making for deep research. Prevailing systems adopt a linear pipeline of plan to search to write to a report, which suffers from error accumulation and context rot due to the lack of explicit control over both model behavior and context. We introduce RhinoInsight, a deep research framework that adds two control mechanisms to enhance robustness, traceability, and overall quality without parameter updates. First, a Verifiable Checklist module transforms user requirements into traceable and verifiable sub-goals, incorporates human or LLM critics for refinement, and compiles a hierarchical outline to anchor subsequent actions and prevent non-executable planning. Second, an Evidence Audit module structures search content, iteratively updates the outline, and prunes noisy context, while a critic ranks and binds high-quality evidence to drafted content to ensure verifiability and reduce hallucinations. Our experiments demonstrate that RhinoInsight achieves state-of-the-art performance on deep research tasks while remaining competitive on deep search tasks. --- ### ProxT2I: Efficient Reward-Guided Text-to-Image Generation via Proximal Diffusion Authors: Zhenghan Fang, Jian Zheng, Qiaozi Gao, Xiaofeng Gao, Jeremias Sulam Published: 2025-11-24 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.18742v2 Diffusion models have emerged as a dominant paradigm for generative modeling across a wide range of domains, including prompt-conditional generation. The vast majority of samplers, however, rely on forward discretization of the reverse diffusion process and use score functions that are learned from data. Such forward and explicit discretizations can be slow and unstable, requiring a large number of sampling steps to produce good-quality samples. In this work we develop a text-to-image (T2I) diffusion model based on backward discretizations, dubbed ProxT2I, relying on learned and conditional proximal operators instead of score functions. We further leverage recent advances in reinforcement learning and policy optimization to optimize our samplers for task-specific rewards. Additionally, we develop a new large-scale and open-source dataset comprising 15 million high-quality human images with fine-grained captions, called LAION-Face-T2I-15M, for training and evaluation. Our approach consistently enhances sampling efficiency and human-preference alignment compared to score-based baselines, and achieves results on par with existing state-of-the-art and open-source text-to-image models while requiring lower compute and smaller model size, offering a lightweight yet performant solution for human text-to-image generation. --- ### A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detection Authors: Kaixiang Yang, Jiarong Liu, Yupeng Song, Shuanghua Yang, Yujue Zhou Published: 2025-11-24 Categories: cs.AI, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.18739v2 Time series anomaly detection is widely used in IoT and cyber-physical systems, yet its evaluation remains challenging due to diverse application objectives and heterogeneous metric assumptions. This study introduces a problem-oriented framework that reinterprets existing metrics based on the specific evaluation challenges they are designed to address, rather than their mathematical forms or output structures. We categorize over twenty commonly used metrics into six dimensions: 1) basic accuracy-driven evaluation; 2) timeliness-aware reward mechanisms; 3) tolerance to labeling imprecision; 4) penalties reflecting human-audit cost; 5) robustness against random or inflated scores; and 6) parameter-free comparability for cross-dataset benchmarking. Comprehensive experiments are conducted to examine metric behavior under genuine, random, and oracle detection scenarios. By comparing their resulting score distributions, we quantify each metric's discriminative ability -- its capability to distinguish meaningful detections from random noise. The results show that while most event-level metrics exhibit strong separability, several widely used metrics (e.g., NAB, Point-Adjust) demonstrate limited resistance to random-score inflation. These findings reveal that metric suitability must be inherently task-dependent and aligned with the operational objectives of IoT applications. The proposed framework offers a unified analytical perspective for understanding existing metrics and provides practical guidance for selecting or developing more context-aware, robust, and fair evaluation methodologies for time series anomaly detection. --- ### Joint learning of a network of linear dynamical systems via total variation penalization Authors: Claire Donnat, Olga Klopp, Hemant Tyagi Published: 2025-11-24 Categories: math.ST, math.OC, stat.ML arXiv: https://arxiv.org/abs/2511.18737v3 We consider the problem of joint estimation of the parameters of $m$ linear dynamical systems, given access to single realizations of their respective trajectories, each of length $T$. The linear systems are assumed to reside on the nodes of an undirected and connected graph $G = ((m), \mathcal{E})$, and the system matrices are assumed to either vary smoothly or exhibit small number of ``jumps'' across the edges. We consider a total variation penalized least-squares estimator and derive non-asymptotic bounds on the mean squared error (MSE) which hold with high probability. In particular, the bounds imply for certain choices of well connected $G$ that the MSE goes to zero as $m$ increases, even when $T$ is constant. The theoretical results are supported by extensive experiments on synthetic and real data. --- ### Thinking Ahead: Foresight Intelligence in MLLMs and World Model Authors: Zhantao Gong, Liaoyuan Fan, Qing Guo, Xun Xu, Xulei Yang, Shijie Li Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18735v3 In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events-an ability essential for applications such as autonomous driving, yet largely overlooked by existing research. To bridge this gap, we introduce FSU-QA, a new Visual Question-Answering (VQA) dataset specifically designed to elicit and evaluate Foresight Intelligence. Using FSU-QA, we conduct the first comprehensive study of state-of-the-art Vision-Language Models (VLMs) under foresight-oriented tasks, revealing that current models still struggle to reason about future situations. Beyond serving as a benchmark, FSU-QA also enables the assessment of world models by measuring the semantic coherence of their generated predictions, quantified through performance gains when VLMs are augmented with such outputs. Our experiments further demonstrate that FSU-QA can effectively enhance foresight reasoning: even small VLMs fine-tuned on FSU-QA surpass much larger, advanced models by a substantial margin. Together, these findings position FSU-QA as a principled foundation for developing next-generation models capable of truly anticipating and understanding future events. Furthermore, beyond model performance, we examine whether WM-generated predictions remain semantically consistent by using VLM-based proxy judges, and validate this evaluation protocol through shuffled control experiments. Fine-tuning models on FSU-QA leads to substantial improvements in foresight understanding, demonstrating the dataset's effectiveness and offering a principled foundation for future research. ---