# Research Papers — 2025-11 · bundle page 106 of 197 > Full-text markdown of papers #5251–5300 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/106 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/105.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/107.md) ### SenseRay-3D: Generalizable and Physics-Informed Framework for End-to-End Indoor Propagation Modeling Authors: Yu Zheng, Kezhi Wang, Wenji Xi, Gang Yu, Jiming Chen, Jie Zhang Published: 2025-11-15 Categories: cs.LG, cs.NI arXiv: https://arxiv.org/abs/2511.12092v1 Modeling indoor radio propagation is crucial for wireless network planning and optimization. However, existing approaches often rely on labor-intensive manual modeling of geometry and material properties, resulting in limited scalability and efficiency. To overcome these challenges, this paper presents SenseRay-3D, a generalizable and physics-informed end-to-end framework that predicts three-dimensional (3D) path-loss heatmaps directly from RGB-D scans, thereby eliminating the need for explicit geometry reconstruction or material annotation. The proposed framework builds a sensing-driven voxelized scene representation that jointly encodes occupancy, electromagnetic material characteristics, and transmitter-receiver geometry, which is processed by a SwinUNETR-based neural network to infer environmental path-loss relative to free-space path-loss. A comprehensive synthetic indoor propagation dataset is further developed to validate the framework and to serve as a standardized benchmark for future research. Experimental results show that SenseRay-3D achieves a mean absolute error of 4.27 dB on unseen environments and supports real-time inference at 217 ms per sample, demonstrating its scalability, efficiency, and physical consistency. SenseRay-3D paves a new path for sense-driven, generalizable, and physics-consistent modeling of indoor propagation, marking a major leap beyond our pioneering EM DeepRay framework. --- ### Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual Learning Authors: Shengqin Jiang, Tianqi Kong, Yuankai Qi, Haokui Zhang, Lina Yao, Quan Z. Sheng, Qingshan Liu, Ming-Hsuan Yang Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12090v3 Prompt-based continual learning methods fine-tune only a small set of additional learnable parameters while keeping the pre-trained model's parameters frozen. It enables efficient adaptation to new tasks while mitigating the risk of catastrophic forgetting. These methods typically attach one independent task-specific prompt to each layer of pre-trained models to locally modulate its features, ensuring that the layer's representation aligns with the requirements of the new task. However, although introducing learnable prompts independently at each layer provides high flexibility for adapting to new tasks, this overly flexible tuning could make certain layers susceptible to unnecessary updates. As all prompts till the current task are added together as a final prompt for all seen tasks, the model may easily overwrite feature representations essential to previous tasks, which increases the risk of catastrophic forgetting. To address this issue, we propose a novel hierarchical layer-grouped prompt tuning method for continual learning. It improves model stability in two ways: (i) Layers in the same group share roughly the same prompts, which are adjusted by position encoding. This helps preserve the intrinsic feature relationships and propagation pathways of the pre-trained model within each group. (ii) It utilizes a single task-specific root prompt to learn to generate sub-prompts for each layer group. In this way, all sub-prompts are conditioned on the same root prompt, enhancing their synergy and reducing independence. Extensive experiments across four benchmarks demonstrate that our method achieves favorable performance compared with several state-of-the-art methods. --- ### KrwEmd: Revising the Imperfect-Recall Abstraction from Forgetting Everything Authors: Yanchang Fu, Qiyue Yin, Shengda Liu, Pei Xu, Kaiqi Huang Published: 2025-11-15 Categories: cs.AI, cs.GT arXiv: https://arxiv.org/abs/2511.12089v1 Excessive abstraction is a critical challenge in hand abstraction-a task specific to games like Texas hold'em-when solving large-scale imperfect-information games, as it impairs AI performance. This issue arises from extreme implementations of imperfect-recall abstraction, which entirely discard historical information. This paper presents KrwEmd, the first practical algorithm designed to address this problem. We first introduce the k-recall winrate feature, which not only qualitatively distinguishes signal observation infosets by leveraging both future and, crucially, historical game information, but also quantitatively captures their similarity. We then develop the KrwEmd algorithm, which clusters signal observation infosets using earth mover's distance to measure discrepancies between their features. Experimental results demonstrate that KrwEmd significantly improves AI gameplay performance compared to existing algorithms. --- ### A Robust and Explainable Transformer-Based Framework for Phishing Email Detection Authors: Sajad U P Published: 2025-11-15 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12085v3 Phishing and related cyber threats are becoming increasingly sophisticated, with email-based phishing remaining the most persistent attack vector. These attacks exploit human vulnerabilities to deliver malware or gain unauthorized access to sensitive information. Transformer-based models enhance phishing detection through robust contextual language understanding; yet they are often regarded as black boxes due to a lack of interpretability. Moreover, recent AI-enabled attacks further undermine model resilience. To address these challenges, this work proposes a lightweight phishing detection framework based on DistilBERT, a lightweight Transformer model. Robustness to embedding-level perturbations and character-level input noise is enhanced through gradient-based adversarial training using the Fast Gradient Method (FGM), combined with stochastic character-level perturbations. To improve transparency, three prominent Explainable AI (XAI) methods, LIME (Local Interpretable Model-agnostic Explanations), SHAP (SHapley Additive exPlanations), and IG (Integrated Gradients), are integrated to interpret model decision-making. A structured rule-based prompt combines model predictions and XAI features to guide Flan-T5-Small in generating plain-language, evidence-based explanations. Experimental results demonstrate that the proposed framework outperforms a standard DistilBERT-based detection model trained without robustness enhancements in terms of accuracy and resilience. This integrated approach helps bridge the gap between model reliability and user trust, advancing transparent phishing detection. --- ### SemanticStitch: Enhancing Image Coherence through Foreground-Aware Seam Carving Authors: Ji-Ping Jin, Chen-Bin Feng, Rui Fan, Chi-Man Vong Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12084v2 Image stitching often faces challenges due to varying capture angles, positional differences, and object movements, leading to misalignments and visual discrepancies. Traditional seam carving methods neglect semantic information, causing disruptions in foreground continuity. We introduce SemanticStitch, a deep learning-based framework that incorporates semantic priors of foreground objects to preserve their integrity and enhance visual coherence. Our approach includes a novel loss function that emphasizes the semantic integrity of salient objects, significantly improving stitching quality. We also present two specialized real-world datasets to evaluate our method's effectiveness. Experimental results demonstrate substantial improvements over traditional techniques, providing robust support for practical applications. --- ### No-Regret Strategy Solving in Imperfect-Information Games via Pre-Trained Embedding Authors: Yanchang Fu, Shengda Liu, Pei Xu, Kaiqi Huang Published: 2025-11-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.12083v2 High-quality information set abstraction remains a core challenge in solving large-scale imperfect-information extensive-form games (IIEFGs)--such as no-limit Texas Hold'em--where the finite nature of spatial resources hinders solving strategies for the full game. State-of-the-art AI methods rely on pre-trained discrete clustering for abstraction, yet their hard classification irreversibly discards critical information: specifically, the quantifiable subtle differences between information sets--vital for strategy solving--thus compromising the quality of such solving. Inspired by the word embedding paradigm in natural language processing, this paper proposes the Embedding CFR algorithm, a novel approach for solving strategies in IIEFGs within an embedding space. The algorithm pre-trains and embeds the features of individual information sets into an interconnected low-dimensional continuous space, where the resulting vectors more precisely capture both the distinctions and connections between information sets. Embedding CFR introduces a strategy-solving process driven by regret accumulation and strategy updates in this embedding space, with supporting theoretical analysis verifying its ability to reduce cumulative regret. Experiments on poker show that with the same spatial overhead, Embedding CFR achieves significantly faster exploitability convergence compared to cluster-based abstraction algorithms, confirming its effectiveness. Furthermore, to our knowledge, it is the first algorithm in poker AI that pre-trains information set abstractions via low-dimensional embedding for strategy solving. --- ### Supervised Multilabel Image Classification Using Residual Networks with Probabilistic Reasoning Authors: Lokender Singh, Saksham Kumar, Chandan Kumar Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12082v1 Multilabel image categorization has drawn interest recently because of its numerous computer vision applications. The proposed work introduces a novel method for classifying multilabel images using the COCO-2014 dataset and a modified ResNet-101 architecture. By simulating label dependencies and uncertainties, the approach uses probabilistic reasoning to improve prediction accuracy. Extensive tests show that the model outperforms earlier techniques and approaches to state-of-the-art outcomes in multilabel categorization. The work also thoroughly assesses the model's performance using metrics like precision-recall score and achieves 0.794 mAP on COCO-2014, outperforming ResNet-SRN (0.771) and Vision Transformer baselines (0.785). The novelty of the work lies in integrating probabilistic reasoning into deep learning models to effectively address the challenges presented by multilabel scenarios. --- ### From Scaling to Structured Expressivity: Rethinking Transformers for CTR Prediction Authors: Bencheng Yan, Yuejie Lei, Zhiyuan Zeng, Zheye Deng, Di Wang, Kaiyi Lin, Pengjie Wang, Chuan Yu, Jian Xu, Bo Zheng Published: 2025-11-15 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2511.12081v2 Despite massive investments in scale, deep models for click-through rate (CTR) prediction often exhibit rapidly diminishing returns -- a stark contrast to the {predictable scaling laws} seen in large language models (LLMs). We identify the root cause as a {fundamental} \textit{structural misalignment}: {standard} Transformers assume sequential compositionality, whereas CTR data demand combinatorial reasoning over {heterogeneous} fields. To restore alignment, we introduce the \textbf{Field-Aware Transformer (FAT)}. {By reconstructing the standard Transformer block with field-centric parameters, FAT achieves \textit{structured expressivity}, {fundamentally shifting the model complexity dependence from the total vocabulary size $n$ with the number of fields $F$ ($n \gg F$).}} Crucially, to decouple model capacity from field cardinality, FAT employs a {Basis-Composed Hypernetwork} to synthesize field-specific parameters from shared bases, further reducing parameter complexity. {Theoretically, we ground this scaling behavior through a formal scaling law based on Rademacher complexity. Empirically, FAT outperforms exisiting state-of-the-art methods with up to \textbf{+4.38\%} AUC improvement, and delivers \textbf{+2.33\%} CTR and \textbf{+0.66\%} RPM in live production.} Our work establishes that scalable recommendation arises not from size alone, but from \textit{structured expressivity} -- architectural coherence with data semantics. --- ### Point Cloud Quantization through Multimodal Prompting for 3D Understanding Authors: Hongxuan Li, Wencheng Zhu, Huiying Xu, Xinzhong Zhu, Pengfei Zhu Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12079v2 Vector quantization has emerged as a powerful tool in large-scale multimodal models, unifying heterogeneous representations through discrete token encoding. However, its effectiveness hinges on robust codebook design. Current prototype-based approaches relying on trainable vectors or clustered centroids fall short in representativeness and interpretability, even as multimodal alignment demonstrates its promise in vision-language models. To address these limitations, we propose a simple multimodal prompting-driven quantization framework for point cloud analysis. Our methodology is built upon two core insights: 1) Text embeddings from pre-trained models inherently encode visual semantics through many-to-one contrastive alignment, naturally serving as robust prototype priors; and 2) Multimodal prompts enable adaptive refinement of these prototypes, effectively mitigating vision-language semantic gaps. The framework introduces a dual-constrained quantization space, enforced by compactness and separation regularization, which seamlessly integrates visual and prototype features, resulting in hybrid representations that jointly encode geometric and semantic information. Furthermore, we employ Gumbel-Softmax relaxation to achieve differentiable discretization while maintaining quantization sparsity. Extensive experiments on the ModelNet40 and ScanObjectNN datasets clearly demonstrate the superior effectiveness of the proposed method. --- ### Learning to Hear by Seeing: It's Time for Vision Language Models to Understand Artistic Emotion from Sight and Sound Authors: Dengming Zhang, Weitao You, Jingxiong Li, Weishen Lin, Wenda Shi, Xue Zhao, Heda Zuo, Junxian Wu, Lingyun Sun Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12077v2 Emotion understanding is critical for making Large Language Models (LLMs) more general, reliable, and aligned with humans. Art conveys emotion through the joint design of visual and auditory elements, yet most prior work is human-centered or single-modality, overlooking the emotion intentionally expressed by the artwork. Meanwhile, current Audio-Visual Language Models (AVLMs) typically require large-scale audio pretraining to endow Visual Language Models (VLMs) with hearing, which limits scalability. We present Vision Anchored Audio-Visual Emotion LLM (VAEmotionLLM), a two-stage framework that teaches a VLM to hear by seeing with limited audio pretraining and to understand emotion across modalities. In Stage 1, Vision-Guided Audio Alignment (VG-Align) distills the frozen visual pathway into a new audio pathway by aligning next-token distributions of the shared LLM on synchronized audio-video clips, enabling hearing without a large audio dataset. In Stage 2, a lightweight Cross-Modal Emotion Adapter (EmoAdapter), composed of the Emotion Enhancer and the Emotion Supervisor, injects emotion-sensitive residuals and applies emotion supervision to enhance cross-modal emotion understanding. We also construct ArtEmoBenchmark, an art-centric emotion benchmark that evaluates content and emotion understanding under audio-only, visual-only, and audio-visual inputs. VAEmotionLLM achieves state-of-the-art results on ArtEmoBenchmark, outperforming audio-only, visual-only, and audio-visual baselines. Ablations show that the proposed components are complementary. --- ### Treatment Stitching with Schrödinger Bridge for Enhancing Offline Reinforcement Learning in Adaptive Treatment Strategies Authors: Dong-Hee Shin, Deok-Joong Lee, Young-Han Son, Tae-Eui Kam Published: 2025-11-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12075v1 Adaptive treatment strategies (ATS) are sequential decision-making processes that enable personalized care by dynamically adjusting treatment decisions in response to evolving patient symptoms. While reinforcement learning (RL) offers a promising approach for optimizing ATS, its conventional online trial-and-error learning mechanism is not permissible in clinical settings due to risks of harm to patients. Offline RL tackles this limitation by learning policies exclusively from historical treatment data, but its performance is often constrained by data scarcity-a pervasive challenge in clinical domains. To overcome this, we propose Treatment Stitching (TreatStitch), a novel data augmentation framework that generates clinically valid treatment trajectories by intelligently stitching segments from existing treatment data. Specifically, TreatStitch identifies similar intermediate patient states across different trajectories and stitches their respective segments. Even when intermediate states are too dissimilar to stitch directly, TreatStitch leverages the Schrödinger bridge method to generate smooth and energy-efficient bridging trajectories that connect dissimilar states. By augmenting these synthetic trajectories into the original dataset, offline RL can learn from a more diverse dataset, thereby improving its ability to optimize ATS. Extensive experiments across multiple treatment datasets demonstrate the effectiveness of TreatStitch in enhancing offline RL performance. Furthermore, we provide a theoretical justification showing that TreatStitch maintains clinical validity by avoiding out-of-distribution transitions. --- ### MF-Speech: Achieving Fine-Grained and Compositional Control in Speech Generation via Factor Disentanglement Authors: Xinyue Yu, Youqing Fang, Pingyu Wu, Guoyang Ye, Wenbo Zhou, Weiming Zhang, Song Xiao Published: 2025-11-15 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2511.12074v2 Generating expressive and controllable human speech is one of the core goals of generative artificial intelligence, but its progress has long been constrained by two fundamental challenges: the deep entanglement of speech factors and the coarse granularity of existing control mechanisms. To overcome these challenges, we have proposed a novel framework called MF-Speech, which consists of two core components: MF-SpeechEncoder and MF-SpeechGenerator. MF-SpeechEncoder acts as a factor purifier, adopting a multi-objective optimization strategy to decompose the original speech signal into highly pure and independent representations of content, timbre, and emotion. Subsequently, MF-SpeechGenerator functions as a conductor, achieving precise, composable and fine-grained control over these factors through dynamic fusion and Hierarchical Style Adaptive Normalization (HSAN). Experiments demonstrate that in the highly challenging multi-factor compositional speech generation task, MF-Speech significantly outperforms current state-of-the-art methods, achieving a lower word error rate (WER=4.67%), superior style control (SECS=0.5685, Corr=0.68), and the highest subjective evaluation scores(nMOS=3.96, sMOS_emotion=3.86, sMOS_style=3.78). Furthermore, the learned discrete factors exhibit strong transferability, demonstrating their significant potential as a general-purpose speech representation. --- ### Informed Bootstrap Augmentation Improves EEG Decoding Authors: Woojae Jeong, Wenhui Cui, Kleanthis Avramidis, Takfarinas Medani, Shrikanth Narayanan, Richard Leahy Published: 2025-11-15 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2511.12073v1 Electroencephalography (EEG) offers detailed access to neural dynamics but remains constrained by noise and trial-by-trial variability, limiting decoding performance in data-restricted or complex paradigms. Data augmentation is often employed to enhance feature representations, yet conventional uniform averaging overlooks differences in trial informativeness and can degrade representational quality. We introduce a weighted bootstrapping approach that prioritizes more reliable trials to generate higher-quality augmented samples. In a Sentence Evaluation paradigm, weights were computed from relative ERP differences and applied during probabilistic sampling and averaging. Across conditions, weighted bootstrapping improved decoding accuracy relative to unweighted (from 68.35% to 71.25% at best), demonstrating that emphasizing reliable trials strengthens representational quality. The results demonstrate that reliability-based augmentation yields more robust and discriminative EEG representations. The code is publicly available at https://github.com/lyricists/NeuroBootstrap. --- ### ProAV-DiT: A Projected Latent Diffusion Transformer for Efficient Synchronized Audio-Video Generation Authors: Jiahui Sun, Weining Wang, Mingzhen Sun, Yirong Yang, Xinxin Zhu, Jing Liu Published: 2025-11-15 Categories: cs.MM, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2511.12072v1 Sounding Video Generation (SVG) remains a challenging task due to the inherent structural misalignment between audio and video, as well as the high computational cost of multimodal data processing. In this paper, we introduce ProAV-DiT, a Projected Latent Diffusion Transformer designed for efficient and synchronized audio-video generation. To address structural inconsistencies, we preprocess raw audio into video-like representations, aligning both the temporal and spatial dimensions between audio and video. At its core, ProAV-DiT adopts a Multi-scale Dual-stream Spatio-Temporal Autoencoder (MDSA), which projects both modalities into a unified latent space using orthogonal decomposition, enabling fine-grained spatiotemporal modeling and semantic alignment. To further enhance temporal coherence and modality-specific fusion, we introduce a multi-scale attention mechanism, which consists of multi-scale temporal self-attention and group cross-modal attention. Furthermore, we stack the 2D latents from MDSA into a unified 3D latent space, which is processed by a spatio-temporal diffusion Transformer. This design efficiently models spatiotemporal dependencies, enabling the generation of high-fidelity synchronized audio-video content while reducing computational overhead. Extensive experiments conducted on standard benchmarks demonstrate that ProAV-DiT outperforms existing methods in both generation quality and computational efficiency. --- ### Improving Graph Embeddings in Machine Learning Using Knowledge Completion with Validation in a Case Study on COVID-19 Spread Authors: Rosario Napoli, Gabriele Morabito, Antonio Celesti, Massimo Villari, Maria Fazio Published: 2025-11-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12071v1 The rise of graph-structured data has driven major advances in Graph Machine Learning (GML), where graph embeddings (GEs) map features from Knowledge Graphs (KGs) into vector spaces, enabling tasks like node classification and link prediction. However, since GEs are derived from explicit topology and features, they may miss crucial implicit knowledge hidden in seemingly sparse datasets, affecting graph structure and their representation. We propose a GML pipeline that integrates a Knowledge Completion (KC) phase to uncover latent dataset semantics before embedding generation. Focusing on transitive relations, we model hidden connections with decay-based inference functions, reshaping graph topology, with consequences on embedding dynamics and aggregation processes in GraphSAGE and Node2Vec. Experiments show that our GML pipeline significantly alters the embedding space geometry, demonstrating that its introduction is not just a simple enrichment but a transformative step that redefines graph representation quality. --- ### DCA-LUT: Deep Chromatic Alignment with 5D LUT for Purple Fringing Removal Authors: Jialang Lu, Shuning Sun, Pu Wang, Chen Wu, Feng Gao, Lina Gong, Dianjie Lu, Guijuan Zhang, Zhuoran Zheng Published: 2025-11-15 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2511.12066v1 Purple fringing, a persistent artifact caused by Longitudinal Chromatic Aberration (LCA) in camera lenses, has long degraded the clarity and realism of digital imaging. Traditional solutions rely on complex and expensive apochromatic (APO) lens hardware and the extraction of handcrafted features, ignoring the data-driven approach. To fill this gap, we introduce DCA-LUT, the first deep learning framework for purple fringing removal. Inspired by the physical root of the problem, the spatial misalignment of RGB color channels due to lens dispersion, we introduce a novel Chromatic-Aware Coordinate Transformation (CA-CT) module, learning an image-adaptive color space to decouple and isolate fringing into a dedicated dimension. This targeted separation allows the network to learn a precise ``purple fringe channel", which then guides the accurate restoration of the luminance channel. The final color correction is performed by a learned 5D Look-Up Table (5D LUT), enabling efficient and powerful% non-linear color mapping. To enable robust training and fair evaluation, we constructed a large-scale synthetic purple fringing dataset (PF-Synth). Extensive experiments in synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance in purple fringing removal. --- ### Aggregating Conformal Prediction Sets via α-Allocation Authors: Congbin Xu, Yue Yu, Haojie Ren, Zhaojun Wang, Changliang Zou Published: 2025-11-15 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.12065v1 Conformal prediction offers a distribution-free framework for constructing prediction sets with finite-sample coverage. Yet, efficiently leveraging multiple conformity scores to reduce prediction set size remains a major open challenge. Instead of selecting a single best score, this work introduces a principled aggregation strategy, COnfidence-Level Allocation (COLA), that optimally allocates confidence levels across multiple conformal prediction sets to minimize empirical set size while maintaining provable coverage. Two variants are further developed, COLA-s and COLA-f, which guarantee finite-sample marginal coverage via sample splitting and full conformalization, respectively. In addition, we develop COLA-l, an individualized allocation strategy that promotes local size efficiency while achieving asymptotic conditional coverage. Extensive experiments on synthetic and real-world datasets demonstrate that COLA achieves considerably smaller prediction sets than state-of-the-art baselines while maintaining valid coverage. --- ### TextBO: Bayesian Optimization in Language Space for Eval-Efficient Self-Improving AI Authors: Enoch Hyunwook Kang, Hema Yoganarasimhan Published: 2025-11-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.12063v3 Large Language Models (LLMs) have enabled self-improving AI systems that iteratively generate, evaluate, and refine their outcomes. Recent studies show that prompt-optimization-based self-improvement can outperform state-of-the-art reinforcement-learning fine-tuning of LLMs, but performance is typically measured by generation efficiency. However, in many applications, the constraint is evaluation efficiency: obtaining reliable feedback is far more costly than generating candidates. To optimize for evaluation efficiency, we extend Upper Confidence Bound-Bayesian Optimization (UCB-BO), a framework known for optimal evaluation-efficiency guarantees, to the language domain. Doing so is challenging for two reasons: (i) gradients needed for UCB-BO are ill-defined in discrete prompt space; and (ii) UCB-style exploration relies on a surrogate model and acquisition function, which only live implicitly in the LLM. We overcome these challenges by proving that combining simple textual gradients (LLM-proposed local edits) with the Best-of-N selection strategy statistically emulates ascent along the gradient of the canonical UCB acquisition function. Based on this result, we propose TextBO, a simple, evaluation-efficient self-improving algorithm that operates purely in language space without explicit surrogates or calibrated uncertainty models. We empirically validate TextBO on automated ad-alignment tasks using a persona-induced preference distribution, demonstrating superior performance per evaluation compared to strong baselines such as Best-of-N and GEPA. We also evaluate TextBO's Best-of-N multi-step textual-gradient mechanism on agentic AI benchmarks by augmenting GEPA with it and show that it significantly outperforms standard GEPA. In sum, TextBO is a simple and principled framework for AI self-improving system design that bridges prompt optimization with classical Bayesian optimization. --- ### MovSemCL: Movement-Semantics Contrastive Learning for Trajectory Similarity (Extension) Authors: Zhichen Lai, Hua Lu, Huan Li, Jialiang Li, Christian S. Jensen Published: 2025-11-15 Categories: cs.CV, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2511.12061v2 Trajectory similarity computation is fundamental functionality that is used for, e.g., clustering, prediction, and anomaly detection. However, existing learning-based methods exhibit three key limitations: (1) insufficient modeling of trajectory semantics and hierarchy, lacking both movement dynamics extraction and multi-scale structural representation; (2) high computational costs due to point-wise encoding; and (3) use of physically implausible augmentations that distort trajectory semantics. To address these issues, we propose MovSemCL, a movement-semantics contrastive learning framework for trajectory similarity computation. MovSemCL first transforms raw GPS trajectories into movement-semantics features and then segments them into patches. Next, MovSemCL employs intra- and inter-patch attentions to encode local as well as global trajectory patterns, enabling efficient hierarchical representation and reducing computational costs. Moreover, MovSemCL includes a curvature-guided augmentation strategy that preserves informative segments (e.g., turns and intersections) and masks redundant ones, generating physically plausible augmented views. Experiments on real-world datasets show that MovSemCL is capable of outperforming state-of-the-art methods, achieving mean ranks close to the ideal value of 1 at similarity search tasks and improvements by up to 20.3% at heuristic approximation, while reducing inference latency by up to 43.4%. --- ### Intelligent Collaborative Optimization for Rubber Tyre Film Production Based on Multi-path Differentiated Clipping Proximal Policy Optimization Authors: Yinghao Ruan, Wei Pang, Shuaihao Liu, Huili Yang, Leyi Han, Xinghui Dong Published: 2025-11-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.12060v2 The advent of smart manufacturing is addressing the limitations of traditional centralized scheduling and inflexible production line configurations in the rubber tyre industry, especially in terms of coping with dynamic production demands. Contemporary tyre manufacturing systems form complex networks of tightly coupled subsystems pronounced nonlinear interactions and emergent dynamics. This complexity renders the effective coordination of multiple subsystems, posing an essential yet formidable task. For high-dimensional, multi-objective optimization problems in this domain, we introduce a deep reinforcement learning algorithm: Multi-path Differentiated Clipping Proximal Policy Optimization (MPD-PPO). This algorithm employs a multi-branch policy architecture with differentiated gradient clipping constraints to ensure stable and efficient high-dimensional policy updates. Validated through experiments on width and thickness control in rubber tyre film production, MPD-PPO demonstrates substantial improvements in both tuning accuracy and operational efficiency. The framework successfully tackles key challenges, including high dimensionality, multi-objective trade-offs, and dynamic adaptation, thus delivering enhanced performance and production stability for real-time industrial deployment in tyre manufacturing. --- ### PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model Decoupling Authors: Sijie Wang, Qiang Wang, Shaohuai Shi Published: 2025-11-15 Categories: cs.CV, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2511.12056v1 Video generation has been advancing rapidly, and diffusion transformer (DiT) based models have demonstrated remark- able capabilities. However, their practical deployment is of- ten hindered by slow inference speeds and high memory con- sumption. In this paper, we propose a novel pipelining frame- work named PipeDiT to accelerate video generation, which is equipped with three main innovations. First, we design a pipelining algorithm (PipeSP) for sequence parallelism (SP) to enable the computation of latent generation and commu- nication among multiple GPUs to be pipelined, thus reduc- ing inference latency. Second, we propose DeDiVAE to de- couple the diffusion module and the variational autoencoder (VAE) module into two GPU groups, whose executions can also be pipelined to reduce memory consumption and infer- ence latency. Third, to better utilize the GPU resources in the VAE group, we propose an attention co-processing (Aco) method to further reduce the overall video generation latency. We integrate our PipeDiT into both OpenSoraPlan and Hun- yuanVideo, two state-of-the-art open-source video generation frameworks, and conduct extensive experiments on two 8- GPU systems. Experimental results show that, under many common resolution and timestep configurations, our PipeDiT achieves 1.06x to 4.02x speedups over OpenSoraPlan and HunyuanVideo. --- ### UniABG: Unified Adversarial View Bridging and Graph Correspondence for Unsupervised Cross-View Geo-Localization Authors: Cuiqun Chen, Qi Chen, Bin Yang, Xingyi Zhang Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12054v1 Cross-view geo-localization (CVGL) matches query images ($\textit{e.g.}$, drone) to geographically corresponding opposite-view imagery ($\textit{e.g.}$, satellite). While supervised methods achieve strong performance, their reliance on extensive pairwise annotations limits scalability. Unsupervised alternatives avoid annotation costs but suffer from noisy pseudo-labels due to intrinsic cross-view domain gaps. To address these limitations, we propose $\textit{UniABG}$, a novel dual-stage unsupervised cross-view geo-localization framework integrating adversarial view bridging with graph-based correspondence calibration. Our approach first employs View-Aware Adversarial Bridging (VAAB) to model view-invariant features and enhance pseudo-label robustness. Subsequently, Heterogeneous Graph Filtering Calibration (HGFC) refines cross-view associations by constructing dual inter-view structure graphs, achieving reliable view correspondence. Extensive experiments demonstrate state-of-the-art unsupervised performance, showing that UniABG improves Satellite $\rightarrow$ Drone AP by +10.63\% on University-1652 and +16.73\% on SUES-200, even surpassing supervised baselines. The source code is available at https://github.com/chenqi142/UniABG --- ### Exploring AI in Steganography and Steganalysis: Trends, Clusters, and Sustainable Development Potential Authors: Aditya Kumar Sahu, Chandan Kumar, Saksham Kumar, Serdar Solak Published: 2025-11-15 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.12052v1 Steganography and steganalysis are strongly related subjects of information security. Over the past decade, many powerful and efficient artificial intelligence (AI) - driven techniques have been designed and presented during research into steganography as well as steganalysis. This study presents a scientometric analysis of AI-driven steganography-based data hiding techniques using a thematic modelling approach. A total of 654 articles within the time span of 2017 to 2023 have been considered. Experimental evaluation of the study reveals that 69% of published articles are from Asian countries. The China is on top (TP:312), followed by India (TP-114). The study mainly identifies seven thematic clusters: steganographic image data hiding, deep image steganalysis, neural watermark robustness, linguistic steganography models, speech steganalysis algorithms, covert communication networks, and video steganography techniques. The proposed study also assesses the scope of AI-steganography under the purview of sustainable development goals (SDGs) to present the interdisciplinary reciprocity between them. It has been observed that only 18 of the 654 articles are aligned with one of the SDGs, which shows that limited studies conducted in alignment with SDG goals. SDG9 which is Industry, Innovation, and Infrastructure is leading among 18 SDGs mapped articles. To the top of our insight, this study is the unique one to present a scientometric study on AI-driven steganography-based data hiding techniques. In the context of descriptive statistics, the study breaks down the underlying causes of observed trends, including the influence of DL developments, trends in East Asia and maturity of foundational methods. The work also stresses upon the critical gaps in societal alignment, particularly the SDGs, ultimately working on unveiling the field's global impact on AI security challenges. --- ### DeiTFake: Deepfake Detection Model using DeiT Multi-Stage Training Authors: Saksham Kumar, Ashish Singh, Srinivasarao Thota, Sunil Kumar Singh, Chandan Kumar Published: 2025-11-15 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2511.12048v1 Deepfakes are major threats to the integrity of digital media. We propose DeiTFake, a DeiT-based transformer and a novel two-stage progressive training strategy with increasing augmentation complexity. The approach applies an initial transfer-learning phase with standard augmentations followed by a fine-tuning phase using advanced affine and deepfake-specific augmentations. DeiT's knowledge distillation model captures subtle manipulation artifacts, increasing robustness of the detection model. Trained on the OpenForensics dataset (190,335 images), DeiTFake achieves 98.71\% accuracy after stage one and 99.22\% accuracy with an AUROC of 0.9997, after stage two, outperforming the latest OpenForensics baselines. We analyze augmentation impact and training schedules, and provide practical benchmarks for facial deepfake detection. --- ### DCMM-Transformer: Degree-Corrected Mixed-Membership Attention for Medical Imaging Authors: Huimin Cheng, Xiaowei Yu, Shushan Wu, Luyang Fang, Chao Cao, Jing Zhang, Tianming Liu, Dajiang Zhu, Wenxuan Zhong, Ping Ma Published: 2025-11-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12047v1 Medical images exhibit latent anatomical groupings, such as organs, tissues, and pathological regions, that standard Vision Transformers (ViTs) fail to exploit. While recent work like SBM-Transformer attempts to incorporate such structures through stochastic binary masking, they suffer from non-differentiability, training instability, and the inability to model complex community structure. We present DCMM-Transformer, a novel ViT architecture for medical image analysis that incorporates a Degree-Corrected Mixed-Membership (DCMM) model as an additive bias in self-attention. Unlike prior approaches that rely on multiplicative masking and binary sampling, our method introduces community structure and degree heterogeneity in a fully differentiable and interpretable manner. Comprehensive experiments across diverse medical imaging datasets, including brain, chest, breast, and ocular modalities, demonstrate the superior performance and generalizability of the proposed approach. Furthermore, the learned group structure and structured attention modulation substantially enhance interpretability by yielding attention maps that are anatomically meaningful and semantically coherent. --- ### BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning Authors: Shanmin Wang, Dongdong Zhao Published: 2025-11-15 Categories: cs.CR, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.12046v2 Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks--most notably backdoor attacks. Existing KD backdoor methods are typically complex and computationally intensive: they employ surrogate student models and simulated distillation to guarantee transferability, and construct triggers similar to universal adversarial perturbations (UAPs), which being not stealthy in magnitude, inherently exhibit strong adversarial behavior. This work questions whether such complexity is necessary and constructs stealthy "weak" triggers--imperceptible perturbations that have negligible adversarial effect. We propose BackWeak, a simple, surrogate-free attack paradigm. BackWeak shows that a powerful backdoor can be implanted by simply fine-tuning a benign teacher with a weak trigger using a very small learning rate. We demonstrate that this delicate fine-tuning is sufficient to embed a backdoor that reliably transfers to diverse student architectures during a victim's standard distillation process, yielding high attack success rates. Extensive empirical evaluations on multiple datasets, model architectures, and KD methods show that BackWeak is efficient, simpler, and often more stealthy than previous elaborate approaches. This work calls on researchers studying KD backdoor attacks to pay particular attention to the trigger's potential adversarial characteristics. --- ### FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification Authors: Cheng-Chang Tsai, Kai-Wen Cheng, Chun-Shien Lu Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12044v1 Federated learning (FL) has shown success in collaboratively training a model among decentralized data resources without directly sharing privacy-sensitive training data. Despite recent advances, non-IID (non-independent and identically distributed) data poses an inevitable challenge that hinders the use of FL. In this work, we address the issue of non-IID histopathological images with feature distribution shifts from an intuitive perspective that has only received limited attention. Specifically, we address this issue from the perspective of data distribution by solely adjusting the data distributions of all clients. Building on the success of diffusion models in fitting data distributions and leveraging stain separation to extract the pivotal features that are closely related to the non-IID properties of histopathological images, we propose a Federated Stain Distribution Alignment (FedSDA) method. FedSDA aligns the stain distribution of each client with a target distribution in an FL framework to mitigate distribution shifts among clients. Furthermore, considering that training diffusion models on raw data in FL has been shown to be susceptible to privacy leakage risks, we circumvent this problem while still effectively achieving alignment. Extensive experimental results show that FedSDA is not only effective in improving baselines that focus on mitigating disparities across clients' model updates but also outperforms baselines that address the non-IID data issues from the perspective of data distribution. We show that FedSDA provides valuable and practical insights for the computational pathology community. --- ### Mesh-based Super-resolution of Multiscale Detonation Flows with Graph Transformers Authors: Shivam Barwey, Pinaki Pal Published: 2025-11-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12041v4 Super-resolution flow reconstruction using state-of-the-art data-driven techniques is valuable for a variety of applications, such as subgrid/subfilter closure modeling, accelerating spatiotemporal forecasting, data compression, and serving as an upscaling tool for sparse experimental measurements. In the present work, a first-of-its-kind graph transformer approach is developed for mesh-based super-resolution (SR-GT) of reacting flows. The novel data-driven modeling paradigm leverages a graph-based flow-field representation compatible with complex geometries and non-uniform/unstructured grids. Further, the transformer backbone captures long-range dependencies between different parts of the low-resolution flow-field, identifies important features, and then generates the super-resolved flow-field that preserves those features at a higher resolution. The performance of SR-GT is demonstrated in the context of spectral-element-discretized meshes for a challenging test problem of 2D detonation propagation within a premixed hydrogen-air mixture exhibiting highly complex multiscale reacting flow behavior. The SR-GT framework utilizes a unique element + neighborhood graph representation for the coarse input, which is then tokenized before being processed by the transformer component to produce the fine output. It is demonstrated that SR-GT provides high super-resolution accuracy for reacting flow-field features and superior performance compared to traditional interpolation-based SR. --- ### SRSplat: Feed-Forward Super-Resolution Gaussian Splatting from Sparse Multi-View Images Authors: Xinyuan Hu, Changyue Shi, Chuxiao Yang, Minghao Chen, Jiajun Ding, Tao Wei, Chen Wei, Zhou Yu, Min Tan Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12040v1 Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details. This limitation stems from the inherent lack of high-frequency information in LR inputs. To address this, we propose \textbf{SRSplat}, a feed-forward framework that reconstructs high-resolution 3D scenes from only a few LR views. Our main insight is to compensate for the deficiency of texture information by jointly leveraging external high-quality reference images and internal texture cues. We first construct a scene-specific reference gallery, generated for each scene using Multimodal Large Language Models (MLLMs) and diffusion models. To integrate this external information, we introduce the \textit{Reference-Guided Feature Enhancement (RGFE)} module, which aligns and fuses features from the LR input images and their reference twin image. Subsequently, we train a decoder to predict the Gaussian primitives using the multi-view fused feature obtained from \textit{RGFE}. To further refine predicted Gaussian primitives, we introduce \textit{Texture-Aware Density Control (TADC)}, which adaptively adjusts Gaussian density based on the internal texture richness of the LR inputs. Extensive experiments demonstrate that our SRSplat outperforms existing methods on various datasets, including RealEstate10K, ACID, and DTU, and exhibits strong cross-dataset and cross-resolution generalization capabilities. --- ### Preference Learning from Physics-Based Feedback: Tuning Language Models to Design BCC/B2 Superalloys Authors: Satanu Ghosh, Collin Holgate, Neal R. Brodnik, Doug Downey, Samantha Daly, Tresa M. Pollock, Samuel Carton Published: 2025-11-15 Categories: cs.CE, cond-mat.mtrl-sci, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.12036v1 We apply preference learning to the task of language model-guided design of novel structural alloys. In contrast to prior work that focuses on generating stable inorganic crystals, our approach targets the synthesizeability of a specific structural class: BCC/B2 superalloys, an underexplored family of materials with potential applications in extreme environments. Using three open-weight models (LLaMA-3.1, Gemma-2, and OLMo-2), we demonstrate that language models can be optimized for multiple design objectives using a single, unified reward signal through Direct Preference Optimization (DPO). Unlike prior approaches that rely on heuristic or human-in-the-loop feedback (costly), our reward signal is derived from thermodynamic phase calculations, offering a scientifically grounded criterion for model tuning. To our knowledge, this is the first demonstration of preference-tuning a language model using physics-grounded feedback for structural alloy design. The resulting framework is general and extensible, providing a path forward for intelligent design-space exploration across a range of physical science domains. --- ### Timeripple: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space Authors: Wenxuan Miao, Yulin Sun, Aiyue Chen, Jing Lin, Yiwu Yao, Yiming Gan, Jieru Zhao, Jingwen Leng, Minyi Guo, Yu Feng Published: 2025-11-15 Categories: cs.AR, cs.CV arXiv: https://arxiv.org/abs/2511.12035v2 The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly based on the video diffusion transformer (vDiT), however, they suffer from substantial inference delay due to self-attention. While prior studies have focused on reducing redundant computations in self-attention, they often overlook the inherent spatio-temporal correlations in video streams and directly leverage sparsity patterns from large language models to reduce attention computations. In this work, we take a principled approach to accelerate self-attention in vDiTs by leveraging the spatio-temporal correlations in the latent space. We show that the attention patterns within vDiT are primarily due to the dominant spatial and temporal correlations at the token channel level. Based on this insight, we propose a lightweight and adaptive reuse strategy that approximates attention computations by reusing partial attention scores of spatially or temporally correlated tokens along individual channels. We demonstrate that our method achieves significantly higher computational savings (85\%) compared to state-of-the-art techniques over 4 vDiTs, while preserving almost identical video quality ($<$0.06\% loss on VBench). --- ### Calibrated Multimodal Representation Learning with Missing Modalities Authors: Xiaohao Liu, Xiaobo Xia, Jiaheng Wei, Shuo Yang, Xiu Su, See-Kiong Ng, Tat-Seng Chua Published: 2025-11-15 Categories: cs.CV, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2511.12034v2 Multimodal representation learning harmonizes distinct modalities by aligning them into a unified latent space. Recent research generalizes traditional cross-modal alignment to produce enhanced multimodal synergy but requires all modalities to be present for a common instance, making it challenging to utilize prevalent datasets with missing modalities. We provide theoretical insights into this issue from an anchor shift perspective. Observed modalities are aligned with a local anchor that deviates from the optimal one when all modalities are present, resulting in an inevitable shift. To address this, we propose CalMRL to calibrate incomplete alignments caused by missing modalities. CalMRL leverages the priors and the inherent connections among modalities to model the imputation for the missing ones at the representation level. To resolve the optimization dilemma, we employ a bi-step learning method with the closed-form solution of the posterior distribution of shared latents. We validate its mitigation of anchor shift and convergence with theoretical guidance. By equipping the calibrated alignment with the existing advanced method, we offer new flexibility to absorb data with missing modalities, which is originally unattainable. Extensive experiments demonstrate the superiority of CalMRL. The code is released at https://github.com/Xiaohao-Liu/CalMRL. --- ### EARL: Entropy-Aware RL Alignment of LLMs for Reliable RTL Code Generation Authors: Jiahe Shi, Zhengqi Gao, Ching-Yun Ko, Duane Boning Published: 2025-11-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.12033v2 Recent advances in large language models (LLMs) have demonstrated significant potential in hardware design automation, particularly in using natural language to synthesize Register-Transfer Level (RTL) code. Despite this progress, a gap remains between model capability and the demands of real-world RTL design, including syntax errors, functional hallucinations, and weak alignment to designer intent. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising approach to bridge this gap, as hardware provides executable and formally checkable signals that can be used to further align model outputs with design intent. However, in long, structured RTL code sequences, not all tokens contribute equally to functional correctness, and naïvely spreading gradients across all tokens dilutes learning signals. A key insight from our entropy analysis in RTL generation is that only a small fraction of tokens (e.g., always, if, assign, posedge) exhibit high uncertainty and largely influence control flow and module structure. To address these challenges, we present EARL, an Entropy-Aware Reinforcement Learning framework for Verilog generation. EARL performs policy optimization using verifiable reward signals and introduces entropy-guided selective updates that gate policy gradients to high-entropy tokens. This approach preserves training stability and concentrates gradient updates on functionally important regions of code. Our experiments on VerilogEval and RTLLM show that EARL improves functional pass rates over prior LLM baselines by up to 14.7%, while reducing unnecessary updates and improving training stability. These results indicate that focusing RL on critical, high-uncertainty tokens enables more reliable and targeted policy improvement for structured RTL code generation. --- ### Improved Masked Image Generation with Knowledge-Augmented Token Representations Authors: Guotao Liang, Baoquan Zhang, Zhiyuan Wen, Zihao Han, Yunming Ye Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12032v1 Masked image generation (MIG) has demonstrated remarkable efficiency and high-fidelity images by enabling parallel token prediction. Existing methods typically rely solely on the model itself to learn semantic dependencies among visual token sequences. However, directly learning such semantic dependencies from data is challenging because the individual tokens lack clear semantic meanings, and these sequences are usually long. To address this limitation, we propose a novel Knowledge-Augmented Masked Image Generation framework, named KA-MIG, which introduces explicit knowledge of token-level semantic dependencies (\emph{i.e.}, extracted from the training data) as priors to learn richer representations for improving performance. In particular, we explore and identify three types of advantageous token knowledge graphs, including two positive and one negative graphs (\emph{i.e.}, the co-occurrence graph, the semantic similarity graph, and the position-token incompatibility graph). Based on three prior knowledge graphs, we design a graph-aware encoder to learn token and position-aware representations. After that, a lightweight fusion mechanism is introduced to integrate these enriched representations into the existing MIG methods. Resorting to such prior knowledge, our method effectively enhances the model's ability to capture semantic dependencies, leading to improved generation quality. Experimental results demonstrate that our method improves upon existing MIG for class-conditional image generation on ImageNet. --- ### Striking the Right Balance between Compute and Copy: Improving LLM Inferencing Under Speculative Decoding Authors: Arun Ramachandran, Ramaswamy Govindarajan, Murali Annavaram, Prakash Raghavendra, Hossein Entezari Zarch, Lei Gao, Chaoyi Jiang Published: 2025-11-15 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2511.12031v1 With the skyrocketing costs of GPUs and their virtual instances in the cloud, there is a significant desire to use CPUs for large language model (LLM) inference. KV cache update, often implemented as allocation, copying, and in-place strided update for each generated token, incurs significant overhead. As the sequence length increases, the allocation and copy overheads dominate the performance. Alternate approaches may allocate large KV tensors upfront to enable in-place updates, but these matrices (with zero-padded rows) cause redundant computations. In this work, we propose a new KV cache allocation mechanism called Balancing Memory and Compute (BMC). BMC allocates, once every r iterations, KV tensors with r redundant rows, allowing in-place update without copy overhead for those iterations, but at the expense of a small amount of redundant computation. Second, we make an interesting observation that the extra rows allocated in the KV tensors and the resulting redundant computation can be repurposed for Speculative Decoding (SD) that improves token generation efficiency. Last, BMC represents a spectrum of design points with different values of r. To identify the best-performing design point(s), we derive a simple analytical model for BMC. The proposed BMC method achieves an average throughput acceleration of up to 3.2x over baseline HuggingFace (without SD). Importantly when we apply BMC with SD, it results in an additional speedup of up to 1.39x, over and above the speedup offered by SD. Further, BMC achieves a throughput acceleration of up to 1.36x and 2.29x over state-of-the-art inference servers vLLM and DeepSpeed, respectively. Although the BMC technique is evaluated extensively across different classes of CPUs (desktop and server class), we also evaluate the scheme with GPUs and demonstrate that it works well for GPUs. --- ### VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation Authors: Jun Zhou, Chi Xu, Kaifeng Tang, Yuting Ge, Tingrui Guo, Li Cheng Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12030v1 Estimating the 3D poses of hands and objects from a single RGB image is a fundamental yet challenging problem, with broad applications in augmented reality and human-computer interaction. Existing methods largely rely on visual cues alone, often producing results that violate physical constraints such as interpenetration or non-contact. Recent efforts to incorporate physics reasoning typically depend on post-optimization or non-differentiable physics engines, which compromise visual consistency and end-to-end trainability. To overcome these limitations, we propose a novel framework that jointly integrates visual and physical cues for hand-object pose estimation. This integration is achieved through two key ideas: 1) joint visual-physical cue learning: The model is trained to extract 2D visual cues and 3D physical cues, thereby enabling more comprehensive representation learning for hand-object interactions; 2) candidate pose aggregation: A novel refinement process that aggregates multiple diffusion-generated candidate poses by leveraging both visual and physical predictions, yielding a final estimate that is visually consistent and physically plausible. Extensive experiments demonstrate that our method significantly outperforms existing state-of-the-art approaches in both pose accuracy and physical plausibility. --- ### GCAgent: Long-Video Understanding via Schematic and Narrative Episodic Memory Authors: Jeong Hun Yeo, Sangyun Chung, Sungjune Park, Dae Hoe Kim, Jinyoung Moon, Yong Man Ro Published: 2025-11-15 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.12027v1 Long-video understanding remains a significant challenge for Multimodal Large Language Models (MLLMs) due to inherent token limitations and the complexity of capturing long-term temporal dependencies. Existing methods often fail to capture the global context and complex event relationships necessary for deep video reasoning. To address this, we introduce GCAgent, a novel Global-Context-Aware Agent framework that achieves comprehensive long-video understanding. Our core innovation is the Schematic and Narrative Episodic Memory. This memory structurally models events and their causal and temporal relations into a concise, organized context, fundamentally resolving the long-term dependency problem. Operating in a multi-stage Perception-Action-Reflection cycle, our GCAgent utilizes a Memory Manager to retrieve relevant episodic context for robust, context-aware inference. Extensive experiments confirm that GCAgent significantly enhances long-video understanding, achieving up to 23.5\% accuracy improvement on the Video-MME Long split over a strong MLLM baseline. Furthermore, our framework establishes state-of-the-art performance among comparable 7B-scale MLLMs, achieving 73.4\% accuracy on the Long split and the highest overall average (71.9\%) on the Video-MME benchmark, validating our agent-based reasoning paradigm and structured memory for cognitively-inspired long-video understanding. --- ### Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark Authors: Rulin Zhou, Wenlong He, An Wang, Jianhang Zhang, Xuanhui Zeng, Xi Zhang, Chaowei Zhu, Haijun Hu, Hongliang Ren Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12026v1 Accurate point tracking in surgical environments remains challenging due to complex visual conditions, including smoke occlusion, specular reflections, and tissue deformation. While existing surgical tracking datasets provide coordinate information, they lack the semantic context necessary to understand tracking failure mechanisms. We introduce VL-SurgPT, the first large-scale multimodal dataset that bridges visual tracking with textual descriptions of point status in surgical scenes. The dataset comprises 908 in vivo video clips, including 754 for tissue tracking (17,171 annotated points across five challenging scenarios) and 154 for instrument tracking (covering seven instrument types with detailed keypoint annotations). We establish comprehensive benchmarks using eight state-of-the-art tracking methods and propose TG-SurgPT, a text-guided tracking approach that leverages semantic descriptions to improve robustness in visually challenging conditions. Experimental results demonstrate that incorporating point status information significantly improves tracking accuracy and reliability, particularly in adverse visual scenarios where conventional vision-only methods struggle. By bridging visual and linguistic modalities, VL-SurgPT enables the development of context-aware tracking systems crucial for advancing computer-assisted surgery applications that can maintain performance even under challenging intraoperative conditions. --- ### Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging Authors: Jose Reinaldo Cunha Santos A V Silva Neto, Hodaka Kawachi, Yasushi Yagi, Tomoya Nakamura Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12024v3 Lensless imaging reconstructs scenes from highly multiplexed measurements, resulting in a severely ill-posed inverse problem. In this work, we identify a fundamental trade-off between measurement consistency, perceptual quality, and inference speed across lensless reconstruction paradigms. Traditional methods favor consistency but produce perceptually degraded results, supervised approaches achieve high-quality reconstructions with fast inference but may violate physical constraints, and diffusion-prior methods achieve high perceptual quality and consistency--particularly when structured constraints such as range-null decomposition are used--but remain slow due to iterative sampling. Motivated by this observation, we propose Null-Space Diffusion Distillation (NSDD), a single-pass reconstruction model that distills structured diffusion-prior inference into an efficient feed-forward network. NSDD learns to produce high-quality reconstructions that preserve measurement consistency while avoiding costly iterative sampling. Experimental results demonstrate that NSDD achieves perceptual quality and consistency competitive with diffusion-prior methods, while providing significantly faster inference and offering a favorable balance across all three objectives. Furthermore, ablation experiments show that distilling the range--null decomposition improves reconstruction quality and robustness over unstructured full-reconstruction distillation, including on unseen real scenes. These results highlight the potential of structure-aware distillation for efficient lensless imaging. Code is available at github.com/JRCSAVSN/NullSpaceDiffusionDistillation. --- ### LIHE: Linguistic Instance-Split Hyperbolic-Euclidean Framework for Generalized Weakly-Supervised Referring Expression Comprehension Authors: Xianglong Shi, Silin Cheng, Sirui Zhao, Yunhan Jiang, Enhong Chen, Yang Liu, Sebastien Ourselin Published: 2025-11-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.12020v1 Existing Weakly-Supervised Referring Expression Comprehension (WREC) methods, while effective, are fundamentally limited by a one-to-one mapping assumption, hindering their ability to handle expressions corresponding to zero or multiple targets in realistic scenarios. To bridge this gap, we introduce the Weakly-Supervised Generalized Referring Expression Comprehension task (WGREC), a more practical paradigm that handles expressions with variable numbers of referents. However, extending WREC to WGREC presents two fundamental challenges: supervisory signal ambiguity, where weak image-level supervision is insufficient for training a model to infer the correct number and identity of referents, and semantic representation collapse, where standard Euclidean similarity forces hierarchically-related concepts into non-discriminative clusters, blurring categorical boundaries. To tackle these challenges, we propose a novel WGREC framework named Linguistic Instance-Split Hyperbolic-Euclidean (LIHE), which operates in two stages. The first stage, Referential Decoupling, predicts the number of target objects and decomposes the complex expression into simpler sub-expressions. The second stage, Referent Grounding, then localizes these sub-expressions using HEMix, our innovative hybrid similarity module that synergistically combines the precise alignment capabilities of Euclidean proximity with the hierarchical modeling strengths of hyperbolic geometry. This hybrid approach effectively prevents semantic collapse while preserving fine-grained distinctions between related concepts. Extensive experiments demonstrate LIHE establishes the first effective weakly supervised WGREC baseline on gRefCOCO and Ref-ZOM, while HEMix achieves consistent improvements on standard REC benchmarks, improving IoU@0.5 by up to 2.5\%. The code is available at https://anonymous.4open.science/r/LIHE. --- ### Enhancing Road Safety Through Multi-Camera Image Segmentation with Post-Encroachment Time Analysis Authors: Shounak Ray Chaudhuri, Arash Jahangiri, Christopher Paolini Published: 2025-11-15 Categories: cs.CV, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2511.12018v2 Traffic safety analysis at signalized intersections is essential for reducing vehicle and pedestrian collisions, yet traditional crash-based studies are limited by data sparsity and reporting latency. This paper presents a multi-camera computer vision framework for real-time safety assessment through Post-Encroachment Time (PET) computation, demonstrated at the intersection of H Street and Broadway in Chula Vista, California. Four synchronized cameras provide continuous visual coverage, with frames processed on NVIDIA Jetson AGX Xavier edge devices using YOLOv11 segmentation for vehicle detection. Detected vehicle polygons are transformed into a unified bird's-eye map via homography, enabling alignment across overlapping camera views. A pixel-level PET algorithm tracks temporal occupancy at each spatial location by measuring the time between successive vehicle passages, enabling fine-grained hazard visualization through dynamic heatmaps with 3.3 sq-cm spatial resolution. Timestamped vehicle trajectories and PET data are stored in an SQL database for longitudinal analysis. Results across multiple time intervals demonstrate the framework's ability to identify high-risk regions with sub-second temporal sensitivity and real-time edge throughput, generating 800 x 800 logarithmic heatmaps at an average of 2.68 FPS. This paper validates decentralized vision-based PET analysis for intelligent transportation systems and presents a scalable methodology for high-resolution, real-time intersection safety evaluation. --- ### MMDCP: A Distribution-free Approach to Outlier Detection and Classification with Coverage Guarantees and SCW-FDR Control Authors: Youwu Lin, Xiaoyu Qian, Jinru Wu, Qi Liu, Pei Wang Published: 2025-11-15 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2511.12016v1 We propose the Modified Mahalanobis Distance Conformal Prediction (MMDCP), a unified framework for multi-class classification and outlier detection under label shift, where the training and test distributions may differ. In such settings, many existing methods construct nonconformity scores based on empirical cumulative or density functions combined with data-splitting strategies. However, these approaches are often computationally expensive due to their heavy reliance on resampling procedures and tend to produce overly conservative prediction sets with unstable coverage, especially in small samples. To address these challenges, MMDCP combines class-specific distance measures with full conformal prediction to construct a score function, thereby producing adaptive prediction sets that effectively capture both inlier and outlier structures. Under mild regularity conditions, we establish convergence rates for the resulting sets and provide the first theoretical characterization of the gap between oracle and empirical conformal $p$-values, which ensures valid coverage and effective control of the class-wise false discovery rate (CW-FDR). We further introduce the Summarized Class-Wise FDR (SCW-FDR), a novel global error metric aggregating false discoveries across classes, and show that it can be effectively controlled within the MMDCP framework. Extensive simulations and two real-data applications support our theoretical findings and demonstrate the advantages of the proposed method. --- ### CURE: Cultural Understanding and Reasoning Evaluation - A Framework for "Thick" Culture Alignment Evaluation in LLMs Authors: Truong Vo, Sanmi Koyejo Published: 2025-11-15 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2511.12014v1 Large language models (LLMs) are increasingly deployed in culturally diverse environments, yet existing evaluations of cultural competence remain limited. Existing methods focus on de-contextualized correctness or forced-choice judgments, overlooking the need for cultural understanding and reasoning required for appropriate responses. To address this gap, we introduce a set of benchmarks that, instead of directly probing abstract norms or isolated statements, present models with realistic situational contexts that require culturally grounded reasoning. In addition to the standard Exact Match metric, we introduce four complementary metrics (Coverage, Specificity, Connotation, and Coherence) to capture different dimensions of model's response quality. Empirical analysis across frontier models reveals that thin evaluation systematically overestimates cultural competence and produces unstable assessments with high variance. In contrast, thick evaluation exposes differences in reasoning depth, reduces variance, and provides more stable, interpretable signals of cultural understanding. --- ### Leveraging Large Language Models for Career Mobility Analysis: A Study of Gender, Race, and Job Change Using U.S. Online Resume Profiles Authors: Palakorn Achananuparp, Ye Xu, Yao Lu, Xavier Jayaraj Siddarth Ashok, Ee-Peng Lim Published: 2025-11-15 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2511.12010v2 We present a large-scale analysis of career mobility of college-educated U.S. workers using online resume profiles to investigate how gender, race, and job change options are associated with upward mobility. This study addresses key research questions of how the job changes affect their upward career mobility, and how the outcomes of upward career mobility differ by gender and race. We address data challenges -- such as missing demographic attributes, missing wage data, and noisy occupation labels -- through various data processing and Artificial Intelligence (AI) methods. In particular, we develop a large language models (LLMs) based occupation classification method known as FewSOC that achieves accuracy significantly higher than the original occupation labels in the resume dataset. Analysis of 228,710 career trajectories reveals that intra-firm occupation change has been found to facilitate upward mobility most strongly, followed by inter-firm occupation change and inter-firm lateral move. Women and Black college graduates experience significantly lower returns from job changes than men and White peers. Multilevel sensitivity analyses confirm that these disparities are robust to cluster-level heterogeneity and reveal additional intersectional patterns. --- ### Adaptive Diagnostic Reasoning Framework for Pathology with Multimodal Large Language Models Authors: Yunqi Hong, Johnson Kao, Liam Edwards, Nein-Tzu Liu, Chung-Yen Huang, Alex Oliveira-Kowaleski, Cho-Jui Hsieh, Neil Y. C. Lin Published: 2025-11-15 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.12008v1 AI tools in pathology have improved screening throughput, standardized quantification, and revealed prognostic patterns that inform treatment. However, adoption remains limited because most systems still lack the human-readable reasoning needed to audit decisions and prevent errors. We present RECAP-PATH, an interpretable framework that establishes a self-learning paradigm, shifting off-the-shelf multimodal large language models from passive pattern recognition to evidence-linked diagnostic reasoning. At its core is a two-phase learning process that autonomously derives diagnostic criteria: diversification expands pathology-style explanations, while optimization refines them for accuracy. This self-learning approach requires only small labeled sets and no white-box access or weight updates to generate cancer diagnoses. Evaluated on breast and prostate datasets, RECAP-PATH produced rationales aligned with expert assessment and delivered substantial gains in diagnostic accuracy over baselines. By uniting visual understanding with reasoning, RECAP-PATH provides clinically trustworthy AI and demonstrates a generalizable path toward evidence-linked interpretation. --- ### Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy Authors: Kai-Wen K. Yang, Andrew Bai, Alexandra Bermudez, Yunqi Hong, Zoe Latham, Iris Sloan, Michael Liu, Vishrut Goyal, Cho-Jui Hsieh, Neil Y. C. Lin Published: 2025-11-15 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.12006v1 Deep learning is transforming microscopy, yet models often fail when applied to images from new instruments or acquisition settings. Conventional adversarial domain adaptation (ADDA) retrains entire networks, often disrupting learned semantic representations. Here, we overturn this paradigm by showing that adapting only the earliest convolutional layers, while freezing deeper layers, yields reliable transfer. Building on this principle, we introduce Subnetwork Image Translation ADDA with automatic depth selection (SIT-ADDA-Auto), a self-configuring framework that integrates shallow-layer adversarial alignment with predictive uncertainty to automatically select adaptation depth without target labels. We demonstrate robustness via multi-metric evaluation, blinded expert assessment, and uncertainty-depth ablations. Across exposure and illumination shifts, cross-instrument transfer, and multiple stains, SIT-ADDA improves reconstruction and downstream segmentation over full-encoder adaptation and non-adversarial baselines, with reduced drift of semantic features. Our results provide a design rule for label-free adaptation in microscopy and a recipe for field settings; the code is publicly available. --- ### LithoSeg: A Coarse-to-Fine Framework for High-Precision Lithography Segmentation Authors: Xinyu He, Botong Zhao, Bingbing Li, Shujing Lyu, Jiwei Shen, Yue Lu Published: 2025-11-15 Categories: cs.CV, cs.NI arXiv: https://arxiv.org/abs/2511.12005v1 Accurate segmentation and measurement of lithography scanning electron microscope (SEM) images are crucial for ensuring precise process control, optimizing device performance, and advancing semiconductor manufacturing yield. Lithography segmentation requires pixel-level delineation of groove contours and consistent performance across diverse pattern geometries and process window. However, existing methods often lack the necessary precision and robustness, limiting their practical applicability. To overcome this challenge, we propose LithoSeg, a coarse-to-fine network tailored for lithography segmentation. In the coarse stage, we introduce a Human-in-the-Loop Bootstrapping scheme for the Segment Anything Model (SAM) to attain robustness with minimal supervision. In the subsequent fine stage, we recast 2D segmentation as 1D regression problem by sampling groove-normal profiles using the coarse mask and performing point-wise refinement with a lightweight MLP. LithoSeg outperforms previous approaches in both segmentation accuracy and metrology precision while requiring less supervision, offering promising prospects for real-world applications. --- ### Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning Authors: Shuochen Liu, Pengfei Luo, Chao Zhang, Yuhao Chen, Haotian Zhang, Qi Liu, Xin Kou, Tong Xu, Enhong Chen Published: 2025-11-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.12003v2 Aiming to identify precise evidence sources from visual documents, visual evidence attribution for visual document retrieval-augmented generation (VD-RAG) ensures reliable and verifiable predictions from vision-language models (VLMs) in multimodal question answering. Most existing methods adopt end-to-end training to facilitate intuitive answer verification. However, they lack fine-grained supervision and progressive traceability throughout the reasoning process. In this paper, we introduce the Chain-of-Evidence (CoE) paradigm for VD-RAG. CoE unifies Chain-of-Thought (CoT) reasoning and visual evidence attribution by grounding reference elements in reasoning steps to specific regions with bounding boxes and page indexes. To enable VLMs to generate such evidence-grounded reasoning, we propose Look As You Think (LAT), a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution. During training, LAT evaluates the attribution consistency of each evidence region and provides rewards only when the CoE trajectory yields correct answers, encouraging process-level self-verification. Experiments on vanilla Qwen2.5-VL-7B-Instruct with Paper- and Wiki-VISA benchmarks show that LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5. Meanwhile, LAT not only outperforms the supervised fine-tuning baseline, which is trained to directly produce answers with attribution, but also exhibits stronger generalization across domains. --- ### Selecting Fine-Tuning Examples by Quizzing VLMs Authors: Tenghao Ji, Eytan Adar Published: 2025-11-15 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.12002v1 A challenge in fine-tuning text-to-image diffusion models for specific topics is to select good examples. Fine-tuning from image sets of varying quality, such as Wikipedia Commons, will often produce poor output. However, training images that \textit{do} exemplify the target concept (e.g., a \textit{female Mountain Bluebird}) help ensure that the generated images are similarly representative (e.g., have the prototypical blue-wings and gray chest). In this work, we propose QZLoRA, a framework to select images for low-rank adaptation (LoRA). The approach leverages QuizRank, a method to automatically rank images by treating them as an `educational intervention' and `quizzing' a VLM. We demonstrate that QZLoRA can produce better aligned, photorealistic images with fewer samples. We also show that these fine-tuned models can produce stylized that are similarly representative (i.e., illustrations). Our results highlight the promise of combining automated visual reasoning with parameter-efficient fine-tuning for topic-adaptive generative modeling. --- ### Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations Authors: Eunkyu Park, Wesley Hanwen Deng, Vasudha Varadarajan, Mingxi Yan, Gunhee Kim, Maarten Sap, Motahhare Eslami Published: 2025-11-15 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2511.12001v3 Explanations are often promoted as tools for transparency, but they can also foster confirmation bias; users may assume reasoning is correct whenever outputs appear acceptable. We study this double-edged role of Chain-of-Thought (CoT) explanations in multimodal moral scenarios by systematically perturbing reasoning chains and manipulating delivery tones. Specifically, we analyze reasoning errors in vision language models (VLMs) and how they impact user trust and the ability to detect errors. Our findings reveal two key effects: (1) users often equate trust with outcome agreement, sustaining reliance even when reasoning is flawed, and (2) the confident tone suppresses error detection while maintaining reliance, showing that delivery styles can override correctness. These results highlight how CoT explanations can simultaneously clarify and mislead, underscoring the need for NLP systems to provide explanations that encourage scrutiny and critical thinking rather than blind trust. All code will be released publicly. ---