# Research Papers — 2025-11 · bundle page 40 of 197 > Full-text markdown of papers #1951–2000 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/40 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/39.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/41.md) ### AI/ML based Joint Source and Channel Coding for HARQ-ACK Payload Authors: Akash Doshi, Pinar Sen, Kirill Ivanov, Wei Yang, June Namgoong, Runxin Wang, Rachel Wang, Taesang Yoo, Jing Jiang, Tingfang Ji Published: 2025-11-25 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.19943v2 Channel coding from 2G to 5G has assumed the inputs bits at the physical layer to be uniformly distributed. However, hybrid automatic repeat request acknowledgement (HARQ-ACK) bits transmitted in the uplink are inherently non-uniformly distributed. For such sources, significant performance gains could be obtained by employing joint source channel coding, aided by deep learning-based techniques. In this paper, we learn a transformer-based encoder using a novel "free-lunch" training algorithm and propose per-codeword power shaping to exploit the source prior at the encoder whilst being robust to small changes in the HARQ-ACK distribution. Furthermore, any HARQ-ACK decoder has to achieve a low negative acknowledgement (NACK) error rate to avoid radio link failures resulting from multiple NACK errors. We develop an extension of the Neyman-Pearson test to a coded bit system with multiple information bits to achieve Unequal Error Protection of NACK over ACK bits at the decoder. Finally, we apply the proposed encoder and decoder designs to a 5G New Radio (NR) compliant uplink setup under a fading channel, describing the optimal receiver design and a low complexity coherent approximation to it. Our results demonstrate 3-6 dB reduction in the average transmit power required to achieve the target error rates compared to the NR baseline, while also achieving a 2-3 dB reduction in the maximum transmit power, thus providing for significant coverage gains and power savings. --- ### Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning Authors: Jingchu Gai, Guanning Zeng, Huaqing Zhang, Aditi Raghunathan Published: 2025-11-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.19942v2 It is widely recognized that reinforcement learning (RL) fine-tuning of large language models often leads to diversity collapse, where outputs lack variety. Prior work has proposed a range of heuristics to counteract this effect, but these methods are ad hoc: they frequently trade off correctness for diversity, their effectiveness varies across tasks, and in some cases they even contradict one another. In this work, we place these observations on a rigorous foundation. We first provide a formal proof of why RL fine-tuning exhibits diversity collapse via a selection and reinforcement bias. Next, we make a key observation that any reward modification to address diversity collapse only needs to be applied on the correct trajectories. Building directly on this analysis, we introduce a principled method -- differential smoothing -- that provably improves both correctness and diversity, outperforming vanilla RL as well as widely used entropy-based heuristics. Our theory precisely characterizes when existing heuristics help and why they fail, while showing that differential smoothing is universally superior. Extensive experiments with models from 1B to 7B parameters, across domains including CountDown and real-world mathematical reasoning, demonstrate consistent gains. Differential smoothing improves both Pass@1 and Pass@k, with up to 6.7% improvements on AIME24 dataset. --- ### Optimize Flip Angle Schedules In MR Fingerprinting Using Reinforcement Learning Authors: Shenjun Zhong, Zhifeng Chen, Zhaolin Chen Published: 2025-11-25 Categories: cs.LG, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2511.19941v1 Magnetic Resonance Fingerprinting (MRF) leverages transient-state signal dynamics generated by the tunable acquisition parameters, making the design of an optimal, robust sequence a complex, high-dimensional sequential decision problem, such as optimizing one of the key parameters, flip angle. Reinforcement learning (RL) offers a promising approach to automate parameter selection, to optimize pulse sequences that maximize the distinguishability of fingerprints across the parameter space. In this work, we introduce an RL framework for optimizing the flip-angle schedule in MRF and demonstrate a learned schedule exhibiting non-periodic patterns that enhances fingerprint separability. Additionally, an interesting observation is that the RL-optimized schedule may enable a reduction in the number of repetition time, potentially accelerate MRF acquisitions. --- ### Adaptivity and Universality: Problem-dependent Universal Regret for Online Convex Optimization Authors: Peng Zhao, Yu-Hu Yan, Hang Yu, Zhi-Hua Zhou Published: 2025-11-25 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2511.19937v1 Universal online learning aims to achieve optimal regret guarantees without requiring prior knowledge of the curvature of online functions. Existing methods have established minimax-optimal regret bounds for universal online learning, where a single algorithm can simultaneously attain $\mathcal{O}(\sqrt{T})$ regret for convex functions, $\mathcal{O}(d \log T)$ for exp-concave functions, and $\mathcal{O}(\log T)$ for strongly convex functions, where $T$ is the number of rounds and $d$ is the dimension of the feasible domain. However, these methods still lack problem-dependent adaptivity. In particular, no universal method provides regret bounds that scale with the gradient variation $V_T$, a key quantity that plays a crucial role in applications such as stochastic optimization and fast-rate convergence in games. In this work, we introduce UniGrad, a novel approach that achieves both universality and adaptivity, with two distinct realizations: UniGrad.Correct and UniGrad.Bregman. Both methods achieve universal regret guarantees that adapt to gradient variation, simultaneously attaining $\mathcal{O}(\log V_T)$ regret for strongly convex functions and $\mathcal{O}(d \log V_T)$ regret for exp-concave functions. For convex functions, the regret bounds differ: UniGrad.Correct achieves an $\mathcal{O}(\sqrt{V_T \log V_T})$ bound while preserving the RVU property that is crucial for fast convergence in online games, whereas UniGrad.Bregman achieves the optimal $\mathcal{O}(\sqrt{V_T})$ regret bound through a novel design. Both methods employ a meta algorithm with $\mathcal{O}(\log T)$ base learners, which naturally requires $\mathcal{O}(\log T)$ gradient queries per round. To enhance computational efficiency, we introduce UniGrad++, which retains the regret while reducing the gradient query to just $1$ per round via surrogate optimization. We further provide various implications. --- ### Image Diffusion Models Exhibit Emergent Temporal Propagation in Videos Authors: Youngseo Kim, Dohyun Kim, Geonhee Han, Paul Hongsuck Seo Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19936v1 Image diffusion models, though originally developed for image generation, implicitly capture rich semantic structures that enable various recognition and localization tasks beyond synthesis. In this work, we investigate their self-attention maps can be reinterpreted as semantic label propagation kernels, providing robust pixel-level correspondences between relevant image regions. Extending this mechanism across frames yields a temporal propagation kernel that enables zero-shot object tracking via segmentation in videos. We further demonstrate the effectiveness of test-time optimization strategies-DDIM inversion, textual inversion, and adaptive head weighting-in adapting diffusion features for robust and consistent label propagation. Building on these findings, we introduce DRIFT, a framework for object tracking in videos leveraging a pretrained image diffusion model with SAM-guided mask refinement, achieving state-of-the-art zero-shot performance on standard video object segmentation benchmarks. --- ### EfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruning Authors: Songlin Zhao, Michael Pitts, Zhuwei Qin Published: 2025-11-25 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2511.19935v3 Deploying domain-specialized large language models on resource-constrained hardware motivates reducing both adaptation cost and the number of retained weights. LoRA lowers adaptation cost but leaves a dense backbone, while separate pruning can discard weights that become important during adaptation. We propose EfficientXpert, a framework that co-adapts low-rank updates and sparse support. Its ForeSight Mask scores weights through a downstream reconstruction surrogate using the evolving LoRA-augmented weights; Partial Brain Surgeon (PBS) realigns the adapter through a closed-form correction. At 40% sparsity, the strongest variant retains 98.55--108.99% of dense-LoRA aggregate performance across the evaluated LLaMA settings. On Qwen3-8B, adaptation adds 17.9--27.0% training time and at most 4.8% peak GPU memory. Our analysis connects the domain- and rank-dependent effects of PBS to its constrained reconstruction objective, providing guidance for selecting adapter recovery capacity. Together, these results demonstrate efficient production of sparse, domain-specialized experts. Code is available at https://github.com/TagoreZhao/Efficient_Domain_Adaptation. --- ### Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications Authors: Vaishali Vinay Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.19933v2 Large language models (LLMs) are being rapidly integrated into decision-support tools, automation workflows, and AI-enabled software systems. However, their behavior in production environments remains poorly understood, and their failure patterns differ fundamentally from those of traditional machine learning models. This paper presents a system-level taxonomy of fifteen hidden failure modes that arise in real-world LLM applications, including multi-step reasoning drift, latent inconsistency, context-boundary degradation, incorrect tool invocation, version drift, and cost-driven performance collapse. Using this taxonomy, we analyze the growing gap in evaluation and monitoring practices: existing benchmarks measure knowledge or reasoning but provide little insight into stability, reproducibility, drift, or workflow integration. We further examine the production challenges associated with deploying LLMs - including observability limitations, cost constraints, and update-induced regressions - and outline high-level design principles for building reliable, maintainable, and cost-aware LLM systems. Finally, we outline high-level design principles for building reliable, maintainable, and cost-aware LLM-based systems. By framing LLM reliability as a system-engineering problem rather than a purely model-centric one, this work provides an analytical foundation for future research on evaluation methodology, AI system robustness, and dependable LLM deployment. --- ### LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training Authors: Ziwei Liu, Qidong Liu, Wanyu Wang, Yejing Wang, Pengyue Jia, Tong Xu, Wei Huang, Chong Chen, Xiangyu Zhao Published: 2025-11-25 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.19931v2 Cross-domain Sequential Recommendation (CDSR) has been proposed to enrich user-item interactions by incorporating information from various domains. Despite current progress, the imbalance issue and transition issue hinder further development of CDSR. The former one presents a phenomenon that the interactions in one domain dominate the entire behavior, leading to difficulty in capturing the domain-specific features in the other domain. The latter points to the difficulty in capturing users' cross-domain preferences within the mixed interaction sequence, resulting in poor next-item prediction performance for specific domains. With world knowledge and powerful reasoning ability, Large Language Models (LLMs) partially alleviate the above issues by performing as a generator and an encoder. However, current LLMs-enhanced CDSR methods are still under exploration, which fail to recognize the irrelevant noise and rough profiling problems. Thus, to make peace with the aforementioned challenges, we proposed an LLMs Enhanced Cross-domain Sequential Recommendation with Dual-phase Training ({LLM-EDT}). To address the imbalance issue while introducing less irrelevant noise, we first propose the transferable item augmenter to adaptively generate possible cross-domain behaviors for users. Then, to alleviate the transition issue, we introduce a dual-phase training strategy to empower the domain-specific thread with a domain-shared background. As for the rough profiling problem, we devise a domain-aware profiling module to summarize the user's preference in each domain and adaptively aggregate them to generate comprehensive user profiles. The experiments on three public datasets validate the effectiveness of our proposed LLM-EDT. To ease reproducibility, we have released the detailed code online at {https://anonymous.4open.science/r/LLM-EDT-583F}. --- ### Designing Reputation Systems for Manufacturing Data Trading Markets: A Multi-Agent Evaluation with Q-Learning and IRL-Estimated Utilities Authors: Kenta Yamamoto, Teruaki Hayashi Published: 2025-11-25 Categories: cs.GT, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2511.19930v1 Recent advances in machine learning and big data analytics have intensified the demand for high-quality cross-domain datasets and accelerated the growth of data trading across organizations. As data become increasingly recognized as an economic asset, data marketplaces have emerged as a key infrastructure for data-driven innovation. However, unlike mature product or service markets, data-trading environments remain nascent and suffer from pronounced information asymmetry. Buyers cannot verify the content or quality before purchasing data, making trust and quality assurance central challenges. To address these issues, this study develops a multi-agent data-market simulator that models participant behavior and evaluates the institutional mechanisms for trust formation. Focusing on the manufacturing sector, where initiatives such as GAIA-X and Catena-X are advancing, the simulator integrates reinforcement learning (RL) for adaptive agent behavior and inverse reinforcement learning (IRL) to estimate utility functions from empirical behavioral data. Using the simulator, we examine the market-level effects of five representative reputation systems-Time-decay, Bayesian-beta, PageRank, PowerTrust, and PeerTrust-and found that PeerTrust achieved the strongest alignment between data price and quality, while preventing monopolistic dominance. Building on these results, we develop a hybrid reputation mechanism that integrates the strengths of existing systems to achieve improved price-quality consistency and overall market stability. This study extends simulation-based data-market analysis by incorporating trust and reputation as endogenous mechanisms and offering methodological and institutional insights into the design of reliable and efficient data ecosystems. --- ### Context-Aware Token Pruning and Discriminative Selective Attention for Transformer Tracking Authors: Janani Kugarajeevan, Thanikasalam Kokul, Amirthalingam Ramanan, Subha Fernando Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19928v1 One-stream Transformer-based trackers have demonstrated remarkable performance by concatenating template and search region tokens, thereby enabling joint attention across all tokens. However, enabling an excessive proportion of background search tokens to attend to the target template tokens weakens the tracker's discriminative capability. Several token pruning methods have been proposed to mitigate background interference; however, they often remove tokens near the target, leading to the loss of essential contextual information and degraded tracking performance. Moreover, the presence of distractors within the search tokens further reduces the tracker's ability to accurately identify the target. To address these limitations, we propose CPDATrack, a novel tracking framework designed to suppress interference from background and distractor tokens while enhancing computational efficiency. First, a learnable module is integrated between two designated encoder layers to estimate the probability of each search token being associated with the target. Based on these estimates, less-informative background tokens are pruned from the search region while preserving the contextual cues surrounding the target. To further suppress background interference, a discriminative selective attention mechanism is employed that fully blocks search-to-template attention in the early layers. In the subsequent encoder layers, high-probability target tokens are selectively extracted from a localized region to attend to the template tokens, thereby reducing the influence of background and distractor tokens. The proposed CPDATrack achieves state-of-the-art performance across multiple benchmarks, particularly on GOT-10k, where it attains an average overlap of 75.1 percent. --- ### Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity Authors: Qiyao Wei, Edward Morrell, Lea Goetz, Mihaela van der Schaar Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.19925v1 Evaluating the open-form textual responses generated by Large Language Models (LLMs) typically requires measuring the semantic similarity of the response to a (human generated) reference. However, there is evidence that current semantic similarity methods may capture syntactic or lexical forms over semantic content. While benchmarks exist for semantic equivalence, they often suffer from high generation costs due to reliance on subjective human judgment, limited availability for domain-specific applications, and unclear definitions of equivalence. This paper introduces a novel method for generating benchmarks to evaluate semantic similarity methods for LLM outputs, specifically addressing these limitations. Our approach leverages knowledge graphs (KGs) to generate pairs of natural-language statements that are semantically similar or dissimilar, with dissimilar pairs categorized into one of four sub-types. We generate benchmark datasets in four different domains (general knowledge, biomedicine, finance, biology), and conduct a comparative study of semantic similarity methods including traditional natural language processing scores and LLM-as-a-judge predictions. We observe that the sub-type of semantic variation, as well as the domain of the benchmark impact the performance of semantic similarity methods, with no method being consistently superior. Our results present important implications for the use of LLM-as-a-judge in detecting the semantic content of text. Code is available at https://github.com/QiyaoWei/semantic-kg and the dataset is available at https://huggingface.co/datasets/QiyaoWei/Semantic-KG. --- ### Distilling Counterfactual Reasoning from Language to Vision: Causal Graph Guided Post-Training for Video Understanding Authors: Yuefei Chen, Jiang Liu, Xiaodong Lin, Ruixiang Tang Published: 2025-11-25 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2511.19923v2 Vision Language Models (VLMs) have recently shown significant advancements in video understanding, especially in feature alignment, event reasoning, and instruction-following tasks. However, their capability for counterfactual reasoning, inferring alternative outcomes under hypothetical conditions, remains underexplored. This capability is essential for robust video understanding, as it requires identifying underlying causal structures and reasoning about unobserved possibilities, rather than merely recognizing observed patterns. To systematically evaluate this capability, we introduce CounterVQA, a video-based benchmark featuring three progressive difficulty levels that assess different aspects of counterfactual reasoning. Through comprehensive evaluation of both state-of-the-art open-source and closed-source models, we uncover a substantial performance gap: while these models achieve reasonable accuracy on simple counterfactual questions, performance degrades significantly on complex multi-hop causal chains. To address these limitations, we develop a post-training method, CFGPT, that enhances a model's visual counterfactual reasoning ability by distilling its counterfactual reasoning capability from the language modality, yielding consistent improvements across all CounterVQA difficulty levels. Dataset and code will be further released. --- ### Intelligent Image Search Algorithms Fusing Visual Large Models Authors: Kehan Wang, Tingqiong Cui, Yang Zhang, Yu Chen, Shifeng Wu, Zhenzhang Li Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19920v1 Fine-grained image retrieval, which aims to find images containing specific object components and assess their detailed states, is critical in fields like security and industrial inspection. However, conventional methods face significant limitations: manual features (e.g., SIFT) lack robustness; deep learning-based detectors (e.g., YOLO) can identify component presence but cannot perform state-specific retrieval or zero-shot search; Visual Large Models (VLMs) offer semantic and zero-shot capabilities but suffer from poor spatial grounding and high computational cost, making them inefficient for direct retrieval. To bridge these gaps, this paper proposes DetVLM, a novel intelligent image search framework that synergistically fuses object detection with VLMs. The framework pioneers a search-enhancement paradigm via a two-stage pipeline: a YOLO detector first conducts efficient, high-recall component-level screening to determine component presence; then, a VLM acts as a recall-enhancement unit, performing secondary verification for components missed by the detector. This architecture directly enables two advanced capabilities: 1) State Search: Guided by task-specific prompts, the VLM refines results by verifying component existence and executing sophisticated state judgments (e.g., "sun visor lowered"), allowing retrieval based on component state. 2) Zero-shot Search: The framework leverages the VLM's inherent zero-shot capability to recognize and retrieve images containing unseen components or attributes (e.g., "driver wearing a mask") without any task-specific training. Experiments on a vehicle component dataset show DetVLM achieves a state-of-the-art overall retrieval accuracy of 94.82\%, significantly outperforming detection-only baselines. It also attains 94.95\% accuracy in zero-shot search for driver mask-wearing and over 90\% average accuracy in state search tasks. --- ### HybriDLA: Hybrid Generation for Document Layout Analysis Authors: Yufan Chen, Omar Moured, Ruiping Liu, Junwei Zheng, Kunyu Peng, Jiaming Zhang, Rainer Stiefelhagen Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19919v1 Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for early-generation documents with a small, predetermined number of regions, this paradigm struggles with contemporary documents, which exhibit diverse element counts and increasingly complex layouts. To address challenges posed by modern documents, we present HybriDLA, a novel generative framework that unifies diffusion and autoregressive decoding within a single layer. The diffusion component iteratively refines bounding-box hypotheses, whereas the autoregressive component injects semantic and contextual awareness, enabling precise region prediction even in highly varied layouts. To further enhance detection quality, we design a multi-scale feature-fusion encoder that captures both fine-grained and high-level visual cues. This architecture elevates performance to 83.5% mean Average Precision (mAP). Extensive experiments on the DocLayNet and M$^6$Doc benchmarks demonstrate that HybriDLA sets a state-of-the-art performance, outperforming previous approaches. All data and models will be made publicly available at https://yufanchen96.github.io/projects/HybriDLA. --- ### Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models Authors: Qin Ren, Yufei Wang, Lanqing Guo, Wen Zhang, Zhiwen Fan, Chenyu You Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19917v3 Diffusion models have become the dominant paradigm in text-to-image generation, and test-time scaling (TTS) improves sample quality by allocating additional computation at inference. Existing TTS methods, however, resample the entire image, while generation quality is often spatially heterogeneous. This leads to unnecessary computation on regions that are already correct, and localized defects remain insufficiently corrected. In this paper, we explore a new direction - Localized TTS - that adaptively resamples defective regions while preserving high-quality regions, thereby substantially reducing the search space. This raises two challenges: accurately localizing defects and maintaining global consistency. We propose LoTTS, the first fully training-free framework for localized TTS. For defect localization, LoTTS contrasts cross- and self-attention signals under quality-aware prompts (e.g., high-quality vs. low-quality) to identify defective regions, and then refines them into coherent masks. For consistency, LoTTS perturbs only defective regions and denoises them locally, ensuring that corrections remain confined while the rest of the image remains undisturbed. Extensive experiments on SD2.1, SDXL, and FLUX demonstrate that LoTTS achieves state-of-the-art performance: it consistently improves both local quality and global fidelity, while reducing GPU cost by 2-4x compared to Best-of-N sampling. These findings establish localized TTS as a promising new direction for scaling diffusion models at inference time. --- ### Coupled Physics-Gated Adaptation: Spatially Decoding Volumetric Photochemical Conversion in Complex 3D-Printed Objects Authors: Maryam Eftekharifar, Churun Zhang, Jialiang Wei, Xudong Cao, Hossein Heidari Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19913v2 We present a framework that pioneers the prediction of photochemical conversion in complex three-dimensionally printed objects, introducing a challenging new computer vision task: predicting dense, non-visual volumetric physical properties from 3D visual data. This approach leverages the largest-ever optically printed 3D specimen dataset, comprising a large family of parametrically designed complex minimal surface structures that have undergone terminal chemical characterisation. Conventional vision models are ill-equipped for this task, as they lack an inductive bias for the coupled, non-linear interactions of optical physics (diffraction, absorption) and material physics (diffusion, convection) that govern the final chemical state. To address this, we propose Coupled Physics-Gated Adaptation (C-PGA), a novel multimodal fusion architecture. Unlike standard concatenation, C-PGA explicitly models physical coupling by using sparse geometrical and process parameters (e.g., surface transport, print layer height) as a Query to dynamically gate and adapt the dense visual features via feature-wise linear modulation (FiLM). This mechanism spatially modulates dual 3D visual streams-extracted by parallel 3D-CNNs processing raw projection stacks and their diffusion-diffraction corrected counterparts allowing the model to recalibrate its visual perception based on the physical context. This approach offers a breakthrough in virtual chemical characterisation, eliminating the need for traditional post-print measurements and enabling precise control over the chemical conversion state. --- ### Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving Authors: Dapeng Zhang, Zhenlong Yuan, Zhangquan Chen, Chih-Ting Liao, Yinda Chen, Fei Shen, Qingguo Zhou, Tat-Seng Chua Published: 2025-11-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.19912v1 Vision-Language-Action (VLA) models have recently shown strong decision-making capabilities in autonomous driving. However, existing VLAs often struggle with achieving efficient inference and generalizing to novel autonomous vehicle configurations and driving scenarios. In this paper, we propose Reasoning-VLA, a general and fast action-generation VLA framework. The proposed model employs a set of learnable action queries, initialized via Gaussian sampling from ground-truth trajectories within the training corpus. These learnable queries interact with reasoning-enhanced vision-language features to generate continuous action trajectories in parallel. To promote robust generalization, we consolidate eight publicly available autonomous driving datasets into a standardized, Chain-of-Thought reasoning-based, and easy-to-use data format for model training. Leveraging both supervised learning and reinforcement learning fine-tuning, extensive empirical evaluations across multiple benchmarks demonstrate that Reasoning-VLA achieves state-of-the-art performance, superior generalization capability, and the excellent inference speed reported to date. --- ### DLADiff: A Dual-Layer Defense Framework against Fine-Tuning and Zero-Shot Customization of Diffusion Models Authors: Jun Jia, Hongyi Miao, Yingjie Zhou, Linhan Cao, Yanwei Jiang, Wangqiu Zhou, Dandan Zhu, Hua Yang, Wei Sun, Xiongkuo Min, Guangtao Zhai Published: 2025-11-25 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2511.19910v1 With the rapid advancement of diffusion models, a variety of fine-tuning methods have been developed, enabling high-fidelity image generation with high similarity to the target content using only 3 to 5 training images. More recently, zero-shot generation methods have emerged, capable of producing highly realistic outputs from a single reference image without altering model weights. However, technological advancements have also introduced significant risks to facial privacy. Malicious actors can exploit diffusion model customization with just a few or even one image of a person to create synthetic identities nearly identical to the original identity. Although research has begun to focus on defending against diffusion model customization, most existing defense methods target fine-tuning approaches and neglect zero-shot generation defenses. To address this issue, this paper proposes Dual-Layer Anti-Diffusion (DLADiff) to defense both fine-tuning methods and zero-shot methods. DLADiff contains a dual-layer protective mechanism. The first layer provides effective protection against unauthorized fine-tuning by leveraging the proposed Dual-Surrogate Models (DSUR) mechanism and Alternating Dynamic Fine-Tuning (ADFT), which integrates adversarial training with the prior knowledge derived from pre-fine-tuned models. The second layer, though simple in design, demonstrates strong effectiveness in preventing image generation through zero-shot methods. Extensive experimental results demonstrate that our method significantly outperforms existing approaches in defending against fine-tuning of diffusion models and achieves unprecedented performance in protecting against zero-shot generation. --- ### Motion Marionette: Rethinking Rigid Motion Transfer via Prior Guidance Authors: Haoxuan Wang, Jiachen Tao, Junyi Wu, Gaowen Liu, Ramana Rao Kompella, Yan Yan Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19909v1 We present Motion Marionette, a zero-shot framework for rigid motion transfer from monocular source videos to single-view target images. Previous works typically employ geometric, generative, or simulation priors to guide the transfer process, but these external priors introduce auxiliary constraints that lead to trade-offs between generalizability and temporal consistency. To address these limitations, we propose guiding the motion transfer process through an internal prior that exclusively captures the spatial-temporal transformations and is shared between the source video and any transferred target video. Specifically, we first lift both the source video and the target image into a unified 3D representation space. Motion trajectories are then extracted from the source video to construct a spatial-temporal (SpaT) prior that is independent of object geometry and semantics, encoding relative spatial variations over time. This prior is further integrated with the target object to synthesize a controllable velocity field, which is subsequently refined using Position-Based Dynamics to mitigate artifacts and enhance visual coherence. The resulting velocity field can be flexibly employed for efficient video production. Empirical results demonstrate that Motion Marionette generalizes across diverse objects, produces temporally consistent videos that align well with the source motion, and supports controllable video generation. --- ### MHB: Multimodal Handshape-aware Boundary Detection for Continuous Sign Language Recognition Authors: Mingyu Zhao, Zhanfu Yang, Yang Zhou, Zhaoyang Xia, Can Jin, Xiaoxiao He, Dimitris N. Metaxas Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19907v2 This paper employs a multimodal approach for continuous sign recognition by first using ML for detecting the start and end frames of signs in videos of American Sign Language (ASL) sentences, and then by recognizing the segmented signs. For improved robustness we use 3D skeletal features extracted from sign language videos to take into account the convergence of sign properties and their dynamics that tend to cluster at sign boundaries. Another focus of this paper is the incorporation of information from 3D handshape for boundary detection. To detect handshapes normally expected at the beginning and end of signs, we pretrain a handshape classifier for detection of 87 linguistically defined canonical handshape categories using a dataset that we created by integrating and normalizing several existing datasets. A multimodal fusion module is then used to unify the pretrained sign video segmentation framework and handshape classification models. Finally, the estimated boundaries are used for sign recognition, where the recognition model is trained on a large database containing both citation-form isolated signs and signs pre-segmented (based on manual annotations) from continuous signing-as such signs often differ a bit in certain respects. We evaluate our method on the ASLLRP corpus and demonstrate significant improvements over previous work. --- ### Zero-Knowledge Proof Based Verifiable Inference of Models Authors: Yunxiao Wang Published: 2025-11-25 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2511.19902v1 Recent advances in artificial intelligence (AI), particularly deep learning, have led to widespread adoption across various applications. Yet, a fundamental challenge persists: how can we verify the correctness of AI model inference when model owners cannot (or will not) reveal their parameters? These parameters represent enormous training costs and valuable intellectual property, making transparent verification difficult. In this paper, we introduce a zero-knowledge framework capable of verifying deep learning inference without exposing model internal parameters. Built on recursively composed zero-knowledge proofs and requiring no trusted setup, our framework supports both linear and nonlinear neural network layers, including matrix multiplication, normalization, softmax, and SiLU. Leveraging the Fiat-Shamir heuristic, we obtain a succinct non-interactive argument of knowledge (zkSNARK) with constant-size proofs. To demonstrate the practicality of our approach, we translate the DeepSeek model into a fully SNARK-verifiable version named ZK-DeepSeek and show experimentally that our framework delivers both efficiency and flexibility in real-world AI verification workloads. --- ### Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning Authors: Jiaqi Liu, Kaiwen Xiong, Peng Xia, Yiyang Zhou, Haonian Ji, Lu Feng, Siwei Han, Mingyu Ding, Huaxiu Yao Published: 2025-11-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.19900v2 Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to overcome this constraint by allowing models to act as their own critics or reward providers. Yet, purely text-based self-evaluation struggles to verify complex visual reasoning steps and often suffers from evaluation hallucinations. To address these challenges, inspired by recent advances in tool-integrated reasoning, we propose Agent0-VL, a self-evolving vision-language agent that achieves continual improvement with tool-integrated reasoning. Agent0-VL incorporates tool usage not only into reasoning but also into self-evaluation and self-repair, enabling the model to introspect, verify, and refine its reasoning through evidence-grounded analysis. It unifies two synergistic roles within a single LVLM: a Solver that performs multi-turn tool-integrated reasoning, and a Verifier that generates structured feedback and fine-grained self-rewards through tool-grounded critique. These roles interact through a Self-Evolving Reasoning Cycle, where tool-based verification and reinforcement learning jointly align the reasoning and evaluation distributions for stable self-improvement. Through this zero-external-reward evolution, Agent0-VL aligns its reasoning and verification behaviors without any human annotation or external reward models, achieving continual self-improvement. Experiments on geometric problem solving and visual scientific analysis show that Agent0-VL achieves an 12.5% improvement over the base model. Our code is available at https://github.com/aiming-lab/Agent0. --- ### VeriSciQA: An Auto-Verified Dataset for Scientific Visual Question Answering Authors: Yuyi Li, Daoyuan Chen, Zhen Wang, Yutong Lu, Yaliang Li Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19899v3 Large Vision-Language Models (LVLMs) show promise for scientific applications, yet open-source models still struggle with Scientific Visual Question Answering (SVQA), namely answering questions about figures from scientific papers. A key bottleneck is the lack of public, large-scale, high-quality SVQA datasets. Although recent work uses LVLMs to synthesize data at scale, we identify systematic errors in their resulting QA pairs, stemming from LVLMs' inherent limitations and information asymmetry between figures and text. To address these challenges, we propose a Cross-Modal verification framework that generates questions and answers purely from figure-citing paragraphs, then verifies them against the figures themselves, leveraging the inherent text-figure alignment in scientific papers to filter out erroneous QA pairs. We instantiate this framework to curate VeriSciQA, a dataset of 20,272 QA pairs spanning 20 scientific domains and 12 figure types. Difficulty assessment reveals a notable accuracy gap between the best open-source model (65%) and the best proprietary model (80.5%), demonstrating room for improvement. Moreover, models fine-tuned on VeriSciQA achieve consistent improvements on SVQA benchmarks, with performance gains that scale with data size, surpassing models trained on existing datasets. Human evaluation further validates the improved quality of VeriSciQA. These results demonstrate that continued data expansion via our scalable framework can further advance SVQA capability in the open-source community. Our dataset is publicly available at https://huggingface.co/datasets/datajuicer/VeriSciQA. --- ### RPM-MCTS: Knowledge-Retrieval as Process Reward Model with Monte Carlo Tree Search for Code Generation Authors: Yuanyuan Lin, Xiangyu Ouyang, Teng Zhang, Kaixin Sui Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.19895v2 Tree search-based methods have made significant progress in enhancing the code generation capabilities of large language models. However, due to the difficulty in effectively evaluating intermediate algorithmic steps and the inability to locate and timely correct erroneous steps, these methods often generate incorrect code and incur increased computational costs. To tackle these problems, we propose RPM-MCTS, an effective method that utilizes Knowledge-Retrieval as Process Reward Model based on Monte Carlo Tree Search to evaluate intermediate algorithmic steps. By utilizing knowledge base retrieval, RPM-MCTS avoids the complex training of process reward models. During the expansion phase, similarity filtering is employed to remove redundant nodes, ensuring diversity in reasoning paths. Furthermore, our method utilizes sandbox execution feedback to locate erroneous algorithmic steps during generation, enabling timely and targeted corrections. Extensive experiments on four public code generation benchmarks demonstrate that RPM-MCTS outperforms current state-of-the-art methods while achieving an approximately 15% reduction in token consumption. Furthermore, full fine-tuning of the base model using the data constructed by RPM-MCTS significantly enhances its code capabilities. --- ### Frailty-Aware Transformer for Recurrent Survival Modeling of Driver Retention in Ride-Hailing Platforms Authors: Shuoyan Xu, Yu Zhang, Eric J. Miller Published: 2025-11-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.19893v1 Ride-hailing platforms are characterized by high-frequency, behavior-driven environments. Although survival analysis has been applied to recurrent events in other domains, its use in modeling ride-hailing driver behavior remains largely unexplored. This study formulates idle behavior as a recurrent survival process using large-scale platform data and proposes a Transformer-based framework that captures long-term temporal dependencies with causal masking and incorporates driver-specific embeddings to model latent heterogeneity. Results on Toronto ride-hailing data demonstrate that the proposed Frailty-Aware Cox Transformer (FACT) achieves the highest time-dependent C-indices and lowest Brier Scores, outperforming classical and deep learning survival models. This approach enables more accurate risk estimation, supports platform retention strategies, and provides policy-relevant insights. --- ### LiMT: A Multi-task Liver Image Benchmark Dataset Authors: Zhe Liu, Kai Han, Siqi Ma, Yan Zhu, Jun Chen, Chongwen Lyu, Xinyi Qiu, Chengxuan Qian, Yuqing Song, Yi Liu, Liyuan Tian, Yang Ji et al. Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19889v1 Computer-aided diagnosis (CAD) technology can assist clinicians in evaluating liver lesions and intervening with treatment in time. Although CAD technology has advanced in recent years, the application scope of existing datasets remains relatively limited, typically supporting only single tasks, which has somewhat constrained the development of CAD technology. To address the above limitation, in this paper, we construct a multi-task liver dataset (LiMT) used for liver and tumor segmentation, multi-label lesion classification, and lesion detection based on arterial phase-enhanced computed tomography (CT), potentially providing an exploratory solution that is able to explore the correlation between tasks and does not need to worry about the heterogeneity between task-specific datasets during training. The dataset includes CT volumes from 150 different cases, comprising four types of liver diseases as well as normal cases. Each volume has been carefully annotated and calibrated by experienced clinicians. This public multi-task dataset may become a valuable resource for the medical imaging research community in the future. In addition, this paper not only provides relevant baseline experimental results but also reviews existing datasets and methods related to liver-related tasks. Our dataset is available at https://drive.google.com/drive/folders/1l9HRK13uaOQTNShf5pwgSz3OTanWjkag?usp=sharing. --- ### Distilling Cross-Modal Knowledge via Feature Disentanglement Authors: Junhong Liu, Yuan Zhang, Tao Huang, Wenchao Xu, Renyu Yang Published: 2025-11-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.19887v1 Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation, where inconsistencies in representation across modalities lead to difficult knowledge transfer. To address this challenge, we propose frequency-decoupled cross-modal knowledge distillation, a method designed to decouple and balance knowledge transfer across modalities by leveraging frequency-domain features. We observed that low-frequency features exhibit high consistency across different modalities, whereas high-frequency features demonstrate extremely low cross-modal similarity. Accordingly, we apply distinct losses to these features: enforcing strong alignment in the low-frequency domain and introducing relaxed alignment for high-frequency features. We also propose a scale consistency loss to address distributional shifts between modalities, and employ a shared classifier to unify feature spaces. Extensive experiments across multiple benchmark datasets show our method substantially outperforms traditional KD and state-of-the-art cross-modal KD approaches. Code is available at https://github.com/Johumliu/FD-CMKD. --- ### Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection Authors: Chi Liu, Tianqing Zhu, Wanlei Zhou, Wei Zhao Published: 2025-11-25 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2511.19886v1 As deep image forgery powered by AI generative models, such as GANs, continues to challenge today's digital world, detecting AI-generated forgeries has become a vital security topic. Generalizability and robustness are two critical concerns of a forgery detector, determining its reliability when facing unknown GANs and noisy samples in an open world. Although many studies focus on improving these two properties, the root causes of these problems have not been fully explored, and it is unclear if there is a connection between them. Moreover, despite recent achievements in addressing these issues from image forensic or anti-forensic aspects, a universal method that can contribute to both sides simultaneously remains practically significant yet unavailable. In this paper, we provide a fundamental explanation of these problems from a frequency perspective. Our analysis reveals that the frequency bias of a DNN forgery detector is a possible cause of generalization and robustness issues. Based on this finding, we propose a two-step frequency alignment method to remove the frequency discrepancy between real and fake images, offering double-sided benefits: it can serve as a strong black-box attack against forgery detectors in the anti-forensic context or, conversely, as a universal defense to improve detector reliability in the forensic context. We also develop corresponding attack and defense implementations and demonstrate their effectiveness, as well as the effect of the frequency alignment method, in various experimental settings involving twelve detectors, eight forgery models, and five metrics. --- ### Complex Instruction Following with Diverse Style Policies in Football Games Authors: Chenglu Sun, Shuo Shen, Haonan Hu, Wei Zhou, Chen Chen Published: 2025-11-25 Categories: cs.MA, cs.LG arXiv: https://arxiv.org/abs/2511.19885v1 Despite advancements in language-controlled reinforcement learning (LC-RL) for basic domains and straightforward commands (e.g., object manipulation and navigation), effectively extending LC-RL to comprehend and execute high-level or abstract instructions in complex, multi-agent environments, such as football games, remains a significant challenge. To address this gap, we introduce Language-Controlled Diverse Style Policies (LCDSP), a novel LC-RL paradigm specifically designed for complex scenarios. LCDSP comprises two key components: a Diverse Style Training (DST) method and a Style Interpreter (SI). The DST method efficiently trains a single policy capable of exhibiting a wide range of diverse behaviors by modulating agent actions through style parameters (SP). The SI is designed to accurately and rapidly translate high-level language instructions into these corresponding SP. Through extensive experiments in a complex 5v5 football environment, we demonstrate that LCDSP effectively comprehends abstract tactical instructions and accurately executes the desired diverse behavioral styles, showcasing its potential for complex, real-world applications. --- ### ChessMamba: Structure-Aware Interleaving of State Spaces for Change Detection in Remote Sensing Images Authors: Lei Ding, Tong Liu, Xuanguang Liu, Xiangyun Liu, Haitao Guo, Jun Lu Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19882v1 Change detection (CD) in multitemporal remote sensing imagery presents significant challenges for fine-grained recognition, owing to heterogeneity and spatiotemporal misalignment. However, existing methodologies based on vision transformers or state-space models typically disrupt local structural consistency during temporal serialization, obscuring discriminative cues under misalignment and hindering reliable change localization. To address this, we introduce ChessMamba, a structure-aware framework leveraging interleaved state-space modeling for robust CD with multi-temporal inputs. ChessMamba integrates a SpatialMamba encoder with a lightweight cross-source interaction module, featuring two key innovations: (i) Chessboard interleaving with snake scanning order, which serializes multi-temporal features into a unified sequence within a single forward pass, thereby shortening interaction paths and enabling direct comparison for accurate change localization; and (ii) Structure-aware fusion via multi-dilated convolutions, selectively capturing center-and-corner neighborhood contexts within each mono-temporal. Comprehensive evaluations on three CD tasks, including binary CD, semantic CD and multimodal building damage assessment, demonstrate that ChessMamba effectively fuses heterogeneous features and achieves substantial accuracy improvements over state-of-the-art methods.The relevant code will be available at: github.com/DingLei14/ChessMamba. --- ### Learning Degenerate Manifolds of Frustrated Magnets with Boltzmann Machines Authors: Ho Jang, Jackson C. Glass, Gia-Wei Chern Published: 2025-11-25 Categories: cond-mat.str-el, cond-mat.stat-mech, cs.LG arXiv: https://arxiv.org/abs/2511.19879v2 We show that Restricted Boltzmann Machines (RBMs) provide a flexible generative framework for modeling spin configurations in disordered yet strongly correlated phases of frustrated magnets. As a benchmark, we first demonstrate that an RBM can learn the zero-temperature ground-state manifold of the one-dimensional ANNNI model at its multiphase point, accurately reproducing its characteristic oscillatory and exponentially decaying correlations. We then apply RBMs to kagome spin ice and show that they successfully learn the local ice rules and short-range correlations of the extensively degenerate ice-I manifold. Correlation functions computed from RBM-generated configurations closely match those from direct Monte Carlo simulations. For the partially ordered ice-II phase -- featuring long-range charge order and broken time-reversal symmetry -- accurate modeling requires RBMs with uniform-sign bias fields, mirroring the underlying symmetry breaking. These results highlight the utility of RBMs as generative models for learning constrained and highly frustrated magnetic states. --- ### MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization Authors: Chengyue Huang, Mellon M. Zhang, Robert Azarcon, Glen Chou, Zsolt Kira Published: 2025-11-25 Categories: cs.CV, cs.AI, cs.CL, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2511.19878v1 Vision-Language-Action (VLA) models inherit strong priors from pretrained Vision-Language Models (VLMs), but naive fine-tuning often disrupts these representations and harms generalization. Existing fixes -- freezing modules or applying uniform regularization -- either overconstrain adaptation or ignore the differing roles of VLA components. We present MAPS (Module-Wise Proximity Scheduling), the first robust fine-tuning framework for VLAs. Through systematic analysis, we uncover an empirical order in which proximity constraints should be relaxed to balance stability and flexibility. MAPS linearly schedules this relaxation, enabling visual encoders to stay close to their pretrained priors while action-oriented language layers adapt more freely. MAPS introduces no additional parameters or data, and can be seamlessly integrated into existing VLAs. Across MiniVLA-VQ, MiniVLA-OFT, OpenVLA-OFT, and challenging benchmarks such as SimplerEnv, CALVIN, LIBERO, as well as real-world evaluations on the Franka Emika Panda platform, MAPS consistently boosts both in-distribution and out-of-distribution performance (up to +30%). Our findings highlight empirically guided proximity to pretrained VLMs as a simple yet powerful principle for preserving broad generalization in VLM-to-VLA transfer. --- ### It Hears, It Sees too: Multi-Modal LLM for Depression Detection By Integrating Visual Understanding into Audio Language Models Authors: Xiangyu Zhao, Yaling Shen, Yiwen Jiang, Zimu Wang, Jiahe Liu, Maxmartwell H Cheng, Guilherme C Oliveira, Robert Desimone, Dominic Dwyer, Zongyuan Ge Published: 2025-11-25 Categories: cs.MM, cs.CV, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2511.19877v2 Depression is one of the most prevalent mental health disorders globally. In recent years, multi-modal data, such as speech, video, and transcripts, has been increasingly used to develop AI-assisted depression assessment systems. Large language models have further advanced this field due to their strong language understanding and generalization capabilities. However, conventional LLMs remain text-centric and cannot process the rich non-verbal cues found in audio and visual modalities, which are critical components in mental health evaluation. While multi-modal LLMs offer a promising direction, few are tailored for psychological applications. In this study, we propose a novel multi-modal LLM framework for depression detection. Our approach augments an audio language model with visual understanding and aligns audio-visual features at the timestamp level. This fine-grained alignment improves modeling of temporal dynamics across modalities while reducing the need for extensive training data and computational resources. Experiments on the DAIC-WoZ dataset demonstrate that our model outperforms both single-modality approaches and previous multi-modal methods. Moreover, the proposed framework can be extended to incorporate additional physiological signals, paving the way for broader clinical applications beyond mental health. --- ### CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection Authors: Qingyu Zhang, Puzhuo Liu, Peng Di, Chenxiong Qian Published: 2025-11-25 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.19875v1 Version control relies on commit messages to convey the rationale for code changes, but these messages are often low quality and, more critically, inconsistent with their diffs-known as message-code inconsistency (MCI). MCIs mislead reviewers, hinder maintenance, contaminate research datasets, and may obscure security patches. Yet, no dedicated benchmark exists to evaluate models for MCI detection. We introduce CODEFUSE-COMMITEVAL, the first benchmark designed for MCI detection using large language models (LLMs). Built on the ApacheCM dataset for diversity and quality, we generate seven types of inconsistent messages through rule-guided mutations of originally consistent commits and apply two-fold validation to verify both positive and negative samples. Using this labeled dataset of message-diff pairs, we evaluate six state-of-the-art open-source LLMs under a vanilla setting and with three augmentation strategies: few-shot prompting, chain-of-thought, and extended context. Results show models detect inconsistent commits more reliably than consistent ones (average Recall 85.95%, Precision 80.28%, Specificity 63.8%); gpt-oss-20B performs best overall but uses over twice the tokens of others. Augmentation effects vary: adjacent context helps larger models but adds noise for smaller ones; few-shot improves accuracy and reduces token use, yet increases universally incorrect predictions; chain-of-thought boosts precision and specificity at the cost of recall and higher token consumption. Type-wise analysis reveals higher detectability for component, file-path, and operation inconsistencies, but lower accuracy and higher token cost for intent-level "purpose" inconsistencies. CODEFUSE-COMMITEVAL provides a rigorous foundation for measuring, comparing, and advancing MCI detection, highlighting the need for richer context and balanced data to capture high-level semantic gaps. --- ### Cross-LLM Generalization of Behavioral Backdoor Detection in AI Agent Supply Chains Authors: Arun Chowdary Sanna Published: 2025-11-25 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.19874v1 As AI agents become integral to enterprise workflows, their reliance on shared tool libraries and pre-trained components creates significant supply chain vulnerabilities. While previous work has demonstrated behavioral backdoor detection within individual LLM architectures, the critical question of cross-LLM generalization remains unexplored, a gap with serious implications for organizations deploying multiple AI systems. We present the first systematic study of cross-LLM behavioral backdoor detection, evaluating generalization across six production LLMs (GPT-5.1, Claude Sonnet 4.5, Grok 4.1, Llama 4 Maverick, GPT-OSS 120B, and DeepSeek Chat V3.1). Through 1,198 execution traces and 36 cross-model experiments, we quantify a critical finding: single-model detectors achieve 92.7% accuracy within their training distribution but only 49.2% across different LLMs, a 43.4 percentage point generalization gap equivalent to random guessing. Our analysis reveals that this gap stems from model-specific behavioral signatures, particularly in temporal features (coefficient of variation > 0.8), while structural features remain stable across architectures. We show that model-aware detection incorporating model identity as an additional feature achieves 90.6% accuracy universally across all evaluated models. We release our multi-LLM trace dataset and detection framework to enable reproducible research. --- ### Simulated Self-Assessment in Large Language Models: A Psychometric Approach to AI Self-Efficacy Authors: Daniel I Jackson, Emma L Jensen, Syed-Amad Hussain, Emre Sezgin Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.19872v3 Large language model (LLM) proficiency in evaluating and quantifying their capacities remains uncertain. We conducted a controlled psychometric measurement study adapting the 10-item General Self-Efficacy Scale (GSES) to evaluate simulated self-assessment across 10 contemporary LLMs. Models completed the GSES under a no-task control condition and after three task-priming conditions: computational reasoning, social reasoning, and summarization. We examined between-model variation, task versus no-task differences, within-model stability, item-order robustness, internal consistency, and qualitative reasoning patterns. LLM-generated GSES responses were highly stable across repeated administrations, with nearly all model-task-item scores remaining identical across three runs. Internal consistency was high across task conditions, with Cronbachs alpha , and item-order effects were minimal, with intraclass correlation coefficients . Despite this stability, simulated self-efficacy differed significantly between models across all task and no-task conditions . Composite LLM GSES scores were lower and more variable than human norms (compared to the literature), and the latent response structure did not replicate human self-efficacy patterns. Qualitative analysis suggested that models differed in how they interpreted GSES items involving effort, coping, agency, and persistence. Some models rejected these constructs as inapplicable to artificial systems, while others translated them into task-oriented capability language. These findings indicate that LLMs can generate internally consistent psychometric self-assessments, but these outputs appear to reflect model-specific and context-sensitive communication behavior rather than human-like self-efficacy or metacognition. Psychometric prompting may help characterize how LLMs express capability, limitation, and agency under different prompting contexts. --- ### Agentic AI-Empowered Conversational Embodied Intelligence Networks in 6G Authors: Mingkai Chen, Zijie Feng, Lei Wang, Yaser Khamayseh Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.19865v1 In the 6G era, semantic collaboration among multiple embodied intelligent devices (MEIDs) becomes crucial for complex task execution. However, existing systems face challenges in multimodal information fusion, adaptive communication, and decision interpretability. To address these limitations, we propose a collaborative Conversational Embodied Intelligence Network (CC-EIN) integrating multimodal feature fusion, adaptive semantic communication, task coordination, and interpretability. PerceptiNet performs cross-modal fusion of image and radar data to generate unified semantic representations. An adaptive semantic communication strategy dynamically adjusts coding schemes and transmission power according to task urgency and channel quality. A semantic-driven collaboration mechanism further supports task decomposition and conflict-free coordination among heterogeneous devices. Finally, the InDec module enhances decision transparency through Grad-CAM visualization. Simulation results in post-earthquake rescue scenarios demonstrate that CC-EIN achieves 95.4% task completion rate and 95% transmission efficiency while maintaining strong semantic consistency and energy efficiency. --- ### MicroSims: A Framework for AI-Generated, Scalable Educational Simulations with Universal Embedding and Adaptive Learning Support Authors: Valerie Lockhart, Dan McCreary, Troy A. Peterson Published: 2025-11-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.19864v1 Educational simulations have long been recognized as powerful tools for enhancing learning outcomes, yet their creation has traditionally required substantial resources and technical expertise. This paper introduces MicroSims a novel framework for creating lightweight, interactive educational simulations that can be rapidly generated using artificial intelligence, universally embedded across digital learning platforms, and easily customized without programming knowledge. MicroSims occupy a unique position at the intersection of three key innovations: (1) standardized design patterns that enable AI-assisted generation, (2) iframe-based architecture that provides universal embedding and sandboxed security, and (3) transparent, modifiable code that supports customization and pedagogical transparency. We present a comprehensive framework encompassing design principles, technical architecture, metadata standards, and development workflows. Drawing on empirical research from physics education studies and meta-analyses across STEM disciplines, we demonstrate that interactive simulations can improve conceptual understanding by up to 30-40\% compared to traditional instruction. MicroSims extend these benefits while addressing persistent barriers of cost, technical complexity, and platform dependence. This work has significant implications for educational equity, and low-cost intelligent interactive textbooks that enabling educators worldwide to create customized, curriculum-aligned simulations on demand. We discuss implementation considerations, present evidence of effectiveness, and outline future directions for AI-powered adaptive learning systems built on the MicroSim foundation. --- ### GigaWorld-0: World Models as Data Engine to Empower Embodied AI Authors: GigaWorld Team, Angen Ye, Boyuan Wang, Chaojun Ni, Guan Huang, Guosheng Zhao, Haoyun Li, Jiagang Zhu, Kerui Li, Mengyuan Xu, Qiuping Deng, Siting Wang et al. Published: 2025-11-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2511.19861v2 World models are emerging as a foundational paradigm for scalable, data-efficient embodied AI. In this work, we present GigaWorld-0, a unified world model framework designed explicitly as a data engine for Vision-Language-Action (VLA) learning. GigaWorld-0 integrates two synergistic components: GigaWorld-0-Video, which leverages large-scale video generation to produce diverse, texture-rich, and temporally coherent embodied sequences under fine-grained control of appearance, camera viewpoint, and action semantics; and GigaWorld-0-3D, which combines 3D generative modeling, 3D Gaussian Splatting reconstruction, physically differentiable system identification, and executable motion planning to ensure geometric consistency and physical realism. Their joint optimization enables the scalable synthesis of embodied interaction data that is visually compelling, spatially coherent, physically plausible, and instruction-aligned. Training at scale is made feasible through our efficient GigaTrain framework, which exploits FP8-precision and sparse attention to drastically reduce memory and compute requirements. We conduct comprehensive evaluations showing that GigaWorld-0 generates high-quality, diverse, and controllable data across multiple dimensions. Critically, VLA model (e.g., GigaBrain-0) trained on GigaWorld-0-generated data achieve strong real-world performance, significantly improving generalization and task success on physical robots without any real-world interaction during training. --- ### A Systematic Analysis of Large Language Models with RAG-enabled Dynamic Prompting for Medical Error Detection and Correction Authors: Farzad Ahmed, Joniel Augustine Jerome, Meliha Yetisgen, Özlem Uzuner Published: 2025-11-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.19858v2 Objective: Clinical documentation contains factual, diagnostic, and management errors that can compromise patient safety. Large language models (LLMs) may help detect and correct such errors, but their behavior under different prompting strategies remains unclear. We evaluate zero-shot prompting, static prompting with random exemplars (SPR), and retrieval-augmented dynamic prompting (RDP) for three subtasks of medical error processing: error flag detection, error sentence detection, and error correction. Methods: Using the MEDEC dataset, we evaluated nine instruction-tuned LLMs (GPT, Claude, Gemini, and OpenAI o-series models). We measured performance using accuracy, recall, false-positive rate (FPR), and an aggregate score of ROUGE-1, BLEURT, and BERTScore for error correction. We also analyzed example outputs to identify failure modes and differences between LLM and clinician reasoning. Results: Zero-shot prompting showed low recall in both detection tasks, often missing abbreviation-heavy or atypical errors. SPR improved recall but increased FPR. Across all nine LLMs, RDP reduced FPR by about 15 percent, improved recall by 5 to 10 percent in error sentence detection, and generated more contextually accurate corrections. Conclusion: Across diverse LLMs, RDP outperforms zero-shot and SPR prompting. Using retrieved exemplars improves detection accuracy, reduces false positives, and enhances the reliability of medical error correction. --- ### Temporal-Visual Semantic Alignment: A Unified Architecture for Transferring Spatial Priors from Vision Models to Zero-Shot Temporal Tasks Authors: Xiangkai Ma, Han Zhang, Wenzhong Li, Sanglu Lu Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19856v1 Large Multimodal Models (LMMs) have achieved remarkable progress in aligning and generating content across text and image modalities. However, the potential of using non-visual, continuous sequential, as a conditioning signal for high-fidelity image generation remains largely unexplored. Furthermore, existing methods that convert series into "pseudo-images" for temporal forecasting fail to establish semantic-level alignment. In this paper, we propose TimeArtist, a temporal-visual conversion framework that pioneers semantic-level alignment between time series fluctuations and visual concepts. It pioneers a "warmup-align" paradigm: first, a dual-autoencoder and shared quantizer are self-supervised trained on large-scale datasets to learn modality-shared representations. Then, the encoders and quantizer are frozen, and a projection is introduced to align temporal and visual samples at the representation level. TimeArtist establishes a versatile cross-modal framework, enabling high-quality, diverse image generation directly from time series, while capturing temporal fluctuation patterns to render images as styles transfer. Extensive experiments show that TimeArtist achieves satisfactory performance in image generation metrics, while also attaining superior results in zero-shot temporal tasks. Our work establishes a new paradigm for cross-modal generation, bridging the gap between temporal dynamics and visual semantics. --- ### STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction Authors: Jiankuo Zhao, Xiangyu Zhu, Zidu Wang, Zhen Lei Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19854v3 Reconstructing high-fidelity and animatable 3D head avatars from monocular videos remains a challenging yet essential task. Existing methods based on 3D Gaussian Splatting typically bind Gaussians to mesh triangles and model deformations solely via Linear Blend Skinning, which results in rigid motion and limited expressiveness. Moreover, they lack specialized strategies to handle frequently occluded regions (e.g., mouth interiors, eyelids). To address these limitations, we propose STAvatar, which consists of two key components: (1) a UV-Adaptive Soft Binding framework that leverages both image-based and geometric priors to learn per-Gaussian feature offsets within the UV space. This UV representation supports dynamic resampling, ensuring full compatibility with Adaptive Density Control (ADC) and enhanced adaptability to shape and textural variations. (2) a Temporal ADC strategy, which first clusters structurally similar frames to facilitate more targeted computation of the densification criterion. It further introduces a novel fused perceptual error as clone criterion to jointly capture geometric and textural discrepancies, encouraging densification in regions requiring finer details. Extensive experiments on four benchmark datasets demonstrate that STAvatar achieves state-of-the-art reconstruction performance, especially in capturing fine-grained details and reconstructing frequently occluded regions. --- ### Profile-LLM: Dynamic Profile Optimization for Realistic Personality Expression in LLMs Authors: Shi-Wei Dai, Yan-Wei Shie, Tsung-Huan Yang, Lun-Wei Ku, Yung-Hui Li Published: 2025-11-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.19852v1 Personalized Large Language Models (LLMs) have been shown to be an effective way to create more engaging and enjoyable user-AI interactions. While previous studies have explored using prompts to elicit specific personality traits in LLMs, they have not optimized these prompts to maximize personality expression. To address this limitation, we propose PersonaPulse: Dynamic Profile Optimization for Realistic Personality Expression in LLMs, a framework that leverages LLMs' inherent knowledge of personality traits to iteratively enhance role-play prompts while integrating a situational response benchmark as a scoring tool, ensuring a more realistic and contextually grounded evaluation to guide the optimization process. Quantitative evaluations demonstrate that the prompts generated by PersonaPulse outperform those of prior work, which were designed based on personality descriptions from psychological studies. Additionally, we explore the relationship between model size and personality modeling through extensive experiments. Finally, we find that, for certain personality traits, the extent of personality evocation can be partially controlled by pausing the optimization process. These findings underscore the importance of prompt optimization in shaping personality expression within LLMs, offering valuable insights for future research on adaptive AI interactions. --- ### Accelerating Wireless Distributed Learning via Hybrid Split and Federated Learning Optimization Authors: Kun Guo, Xuefei Li, Xijun Wang, Howard H. Yang, Wei Feng, Tony Q. S. Quek Published: 2025-11-25 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2511.19851v1 Federated learning (FL) and split learning (SL) are two effective distributed learning paradigms in wireless networks, enabling collaborative model training across mobile devices without sharing raw data. While FL supports low-latency parallel training, it may converge to less accurate model. In contrast, SL achieves higher accuracy through sequential training but suffers from increased delay. To leverage the advantages of both, hybrid split and federated learning (HSFL) allows some devices to operate in FL mode and others in SL mode. This paper aims to accelerate HSFL by addressing three key questions: 1) How does learning mode selection affect overall learning performance? 2) How does it interact with batch size? 3) How can these hyperparameters be jointly optimized alongside communication and computational resources to reduce overall learning delay? We first analyze convergence, revealing the interplay between learning mode and batch size. Next, we formulate a delay minimization problem and propose a two-stage solution: a block coordinate descent method for a relaxed problem to obtain a locally optimal solution, followed by a rounding algorithm to recover integer batch sizes with near-optimal performance. Experimental results demonstrate that our approach significantly accelerates convergence to the target accuracy compared to existing methods. --- ### DOGE: Differentiable Bezier Graph Optimization for Road Network Extraction Authors: Jiahui Sun, Junran Lu, Jinhui Yin, Yishuo Xu, Yuanqi Li, Yanwen Guo Published: 2025-11-25 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2511.19850v1 Automatic extraction of road networks from aerial imagery is a fundamental task, yet prevailing methods rely on polylines that struggle to model curvilinear geometry. We maintain that road geometry is inherently curve-based and introduce the Bézier Graph, a differentiable parametric curve-based representation. The primary obstacle to this representation is to obtain the difficult-to-construct vector ground-truth (GT). We sidestep this bottleneck by reframing the task as a global optimization problem over the Bézier Graph. Our framework, DOGE, operationalizes this paradigm by learning a parametric Bézier Graph directly from segmentation masks, eliminating the need for curve GT. DOGE holistically optimizes the graph by alternating between two complementary modules: DiffAlign continuously optimizes geometry via differentiable rendering, while TopoAdapt uses discrete operators to refine its topology. Our method sets a new state-of-the-art on the large-scale SpaceNet and CityScale benchmarks, presenting a new paradigm for generating high-fidelity vector maps of road networks. We will release our code and related data. --- ### Near-Optimal Reinforcement Learning for Constrained Recurrence Objectives Authors: Dominik Wagner, Leon Witzman, Luke Ong Published: 2025-11-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.19849v2 Recurrence objectives, where a target region must be visited infinitely often, are a fundamental class of specifications for Markov decision processes (MDPs) and form the core of $ω$-regular and linear temporal logic (LTL) objectives. We study constrained recurrence objectives, a natural extension of recurrence objectives with probabilistic constraints capable of modelling safety or fairness requirements. We first study the structure of optimal policies, showing that constrained recurrence requires different policy classes than those sufficient for other constrained MDP formalisms. In particular, we show that every feasible instance admits an optimal mixture of two stochastic stationary policies, as well as an optimal mixture of two deterministic stationary policies over a one-bit augmented MDP. We then study the generative-model reinforcement learning setting and propose an algorithm that first identifies the maximal end-component decomposition of the MDP, then reduces constrained recurrence to a constrained average reward problem for a collapsed MDP. Moreover, we establish a $\tilde{\mathcal{O}}(1/p+B/\varepsilon^2)$ sample complexity guarantee per state-action pair, where $p$ bounds certain non-zero transition probabilities and $B$ bounds transient time. Finally, we prove a nearly matching lower bound, showing that $1/p$ dependence, unlike the average-reward setting, is unavoidable. --- ### Face, Whole-Person, and Object Classification in a Unified Space Via The Interleaved Multi-Domain Identity Curriculum Authors: Thomas M Metz, Matthew Q Hill, Alice J O'Toole Published: 2025-11-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19846v1 Vision foundation models can perform generalized object classification in zero-shot mode, and face/person recognition when they are fine-tuned. However, fine-tuned models suffer from catastrophic forgetting. We create models that perform four tasks (object recognition, face recognition from high- and low-quality images, and person recognition from whole-body images) in a single embedding space -- without incurring substantial catastrophic forgetting. To accomplish this, we introduce two variants of the Interleaved Multi-Domain Identity Curriculum (IMIC): a gradient-coupled, interleaving training schedule that fine-tunes a foundation backbone simultaneously on all four tasks. The IMIC method proved effective with three foundation model bases: DINOv3, CLIP, and EVA-02. Two of these (EVA-02 and CLIP) performed comparably with domain experts on all four tasks concurrently and were more accurate than humans at multi-tasking across face, body, and object datasets. Further, we demonstrate that our approach does not substantially harm out-of-distribution generalization, thus maintaining a key property of foundation models. Analysis of the most accurate model variants (EVA-02 + IMIC A and B) showed linearly separable representations of the four tasks in the unified embedding space, but with substantial sharing of features across tasks. Fewer than 100 PCs calculated from any one task could perform all other tasks with nearly zero performance degradation. --- ### SX-GeoTree: Self-eXplaining Geospatial Regression Tree Incorporating the Spatial Similarity of Feature Attributions Authors: Chaogui Kang, Lijian Luo, Qingfeng Guan, Yu Liu Published: 2025-11-25 Categories: cs.LG, cs.CY, stat.ML arXiv: https://arxiv.org/abs/2511.19845v1 Decision trees remain central for tabular prediction but struggle with (i) capturing spatial dependence and (ii) producing locally stable (robust) explanations. We present SX-GeoTree, a self-explaining geospatial regression tree that integrates three coupled objectives during recursive splitting: impurity reduction (MSE), spatial residual control (global Moran's I), and explanation robustness via modularity maximization on a consensus similarity network formed from (a) geographically weighted regression (GWR) coefficient distances (stimulus-response similarity) and (b) SHAP attribution distances (explanatory similarity). We recast local Lipschitz continuity of feature attributions as a network community preservation problem, enabling scalable enforcement of spatially coherent explanations without per-sample neighborhood searches. Experiments on two exemplar tasks (county-level GDP in Fujian, n=83; point-wise housing prices in Seattle, n=21,613) show SX-GeoTree maintains competitive predictive accuracy (within 0.01 $R^{2}$ of decision trees) while improving residual spatial evenness and doubling attribution consensus (modularity: Fujian 0.19 vs 0.09; Seattle 0.10 vs 0.05). Ablation confirms Moran's I and modularity terms are complementary; removing either degrades both spatial residual structure and explanation stability. The framework demonstrates how spatial similarity - extended beyond geometric proximity through GWR-derived local relationships - can be embedded in interpretable models, advancing trustworthy geospatial machine learning and offering a transferable template for domain-aware explainability. --- ### Cisco Time Series Model Technical Report Authors: Liang Gou, Archit Khare, Praneet Pabolu, Prachi Patel, Joseph Ross, Hercy Shen, Yuhan, Song, Jingze Sun, Kristal Curtis, Vedant Dharnidharka, Abhinav Mathur et al. Published: 2025-11-25 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2511.19841v1 We introduce the Cisco Time Series Model, a univariate zero-shot forecaster. This time series foundation model is the result of a general architectural innovation to a time series model enabling it to accept multiresolution input, applied to a popular decoder-only time series model (TimesFM). The resulting multiresolution decoder-only model is trained on over 300B unique data points, with more than half coming from the observability domain. Quantitative and qualitative evaluations demonstrate that the resulting model achieves superior performance on observability datasets while retaining very similar performance on a standard general-purpose forecasting benchmark (GIFT-Eval), and suggest that the multiresolution structure enables the model to make more accurate predictions on long context input. --- ### GED-Consistent Disentanglement of Aligned and Unaligned Substructures for Graph Similarity Learning Authors: Zhentao Zhan, Xiaoliang Xu, Jingjing Wang, Junmei Wang Published: 2025-11-25 Categories: cs.LG, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2511.19837v1 Graph Similarity Computation (GSC) is a fundamental graph related task where Graph Edit Distance (GED) serves as a prevalent metric. GED is determined by an optimal alignment between a pair of graphs that partitions each into aligned (zero-cost) and unaligned (cost-incurring) substructures. Due to NP-hard nature of exact GED computation, GED approximations based on Graph Neural Network(GNN) have emerged. Existing GNN-based GED approaches typically learn node embeddings for each graph and then aggregate pairwise node similarities to estimate the final similarity. Despite their effectiveness, we identify a mismatch between this prevalent node-centric matching paradigm and the core principles of GED. This discrepancy leads to two critical limitations: (1) a failure to capture the global structural correspondence for optimal alignment, and (2) a misattribution of edit costs driven by spurious node level signals. To address these limitations, we propose GCGSim, a GED-consistent graph similarity learning framework centering on graph-level matching and substructure-level edit costs. Specifically, we make three core technical contributions. Extensive experiments on four benchmark datasets show that GCGSim achieves state-of-the-art performance. Our comprehensive analyses further validate that the framework effectively learns disentangled and semantically meaningful substructure representations. ---