# Research Papers — 2025-11 · bundle page 48 of 197 > Full-text markdown of papers #2351–2400 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/48 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/47.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/49.md) ### MoodBench 1.0: An Evaluation Benchmark for Emotional Companionship Dialogue Systems Authors: Haifeng Jing, Yujie Hou, Junfei Liu, Rui Xie, alan Xu, Jinlong Ma, Qichun Deng Published: 2025-11-24 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.18926v1 With the rapid development of Large Language Models, dialogue systems are shifting from information tools to emotional companions, heralding the era of Emotional Companionship Dialogue Systems (ECDs) that provide personalized emotional support for users. However, the field lacks clear definitions and systematic evaluation standards for ECDs. To address this, we first propose a definition of ECDs with formal descriptions. Then, based on this theory and the design principle of "Ability Layer-Task Layer (three level)-Data Layer-Method Layer", we design and implement the first ECD evaluation benchmark - MoodBench 1.0. Through extensive evaluations of 30 mainstream models, we demonstrate that MoodBench 1.0 has excellent discriminant validity and can effectively quantify the differences in emotional companionship abilities among models. Furthermore, the results reveal current models' shortcomings in deep emotional companionship, guiding future technological optimization and significantly aiding developers in enhancing ECDs' user experience. --- ### LookSharp: Attention Entropy Minimization for Test-Time Adaptation Authors: Yash Mali, Evan Shelhamer Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18925v3 Test-time adaptation (TTA) updates models during inference to reduce error on distribution shifts. While entropy minimization over the output distribution has proven effective as a TTA loss, we study using the intermediate distributions computed by transformers in the attention mechanism. We propose LookSharp, which minimizes the entropy of CLS-to-patch attention in the final layer as a novel TTA objective, encouraging the model to maintain focused attention on shifted data. We demonstrate that attention entropy minimization improves robustness on ImageNet-C. We also show that it is complementary to output entropy minimization and maintains performance on clean data. --- ### LLM-Driven Kernel Evolution: Automating Driver Updates in Linux Authors: Arina Kharlamova, Jiawen Liu, Tianyi Zhang, Xinrui Yang, Humaid Alqasimi, Youcheng Sun, Chun Jason Xue Published: 2025-11-24 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.18924v1 Linux kernel evolution breaks drivers through API/ABI changes, semantic shifts, and security-hardening updates. We introduce DRIVEBENCH, an executable corpus of kernel$\rightarrow$driver co-evolution cases, and AUTODRIVER, a closed-loop, LLM-driven system for automating driver maintenance. The system integrates prompt engineering, multi-agent collaboration, static analysis, and iterative validation to ensure that generated patches are not only syntactically correct but also functionally and semantically consistent with kernel conventions. The corpus spans v5.10-v6.10 with 235 validated cases drawn from 612 candidates. In evaluation across 55 cases, AUTODRIVER achieves 56.4% compilation success; QEMU-based boot verification indicates that compiled patches preserve driver initialization in most instances. By releasing DRIVEBENCH and tooling, we enable reproducible research and a practical route to continuous, safe co-evolution of drivers with the Linux kernel. --- ### One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control Authors: Zhenxing Mi, Yuxin Wang, Dan Xu Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18922v1 We present One4D, a unified framework for 4D generation and reconstruction that produces dynamic 4D content as synchronized RGB frames and pointmaps. By consistently handling varying sparsities of conditioning frames through a Unified Masked Conditioning (UMC) mechanism, One4D can seamlessly transition between 4D generation from a single image, 4D reconstruction from a full video, and mixed generation and reconstruction from sparse frames. Our framework adapts a powerful video generation model for joint RGB and pointmap generation, with carefully designed network architectures. The commonly used diffusion finetuning strategies for depthmap or pointmap reconstruction often fail on joint RGB and pointmap generation, quickly degrading the base video model. To address this challenge, we introduce Decoupled LoRA Control (DLC), which employs two modality-specific LoRA adapters to form decoupled computation branches for RGB frames and pointmaps, connected by lightweight, zero-initialized control links that gradually learn mutual pixel-level consistency. Trained on a mixture of synthetic and real 4D datasets under modest computational budgets, One4D produces high-quality RGB frames and accurate pointmaps across both generation and reconstruction tasks. This work represents a step toward general, high-quality geometry-based 4D world modeling using video diffusion models. Project page: https://mizhenxing.github.io/One4D --- ### BackdoorVLM: A Benchmark for Backdoor Attacks and Defenses on Vision-Language Models Authors: Juncheng Li, Yige Li, Hanxun Huang, Yunhao Chen, Xin Wang, Yixu Wang, Xingjun Ma, Yu-Gang Jiang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18921v2 Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal settings, their impact on multimodal foundation models, particularly vision-language models (VLMs), remains largely underexplored. In this work, we introduce BackdoorVLM, the first comprehensive benchmark for evaluating backdoor attacks and defenses on VLMs across a broad range of settings. It adopts a unified perspective that injects and analyzes backdoors across core vision-language tasks, including image captioning and visual question answering. BackdoorVLM organizes multimodal backdoor threats into 5 representative categories: targeted refusal, malicious injection, jailbreak, concept substitution, and perceptual hijack. Each category captures a distinct pathway through which an adversary can manipulate a model's behavior. We evaluate these threats using 12 representative attack methods spanning text, image, and bimodal triggers, tested on 2 open-source VLMs and 3 multimodal datasets along with 5 representative defense methods. Our analysis reveals that VLMs exhibit strong sensitivity to textual instructions, and in bimodal backdoors the text trigger typically overwhelms the image trigger when forming the backdoor mapping. Notably, backdoors involving the textual modality remain highly potent, with poisoning rates as low as 1\% yielding over 90\% success across most tasks. Moreover, existing defenses lack generalization across trigger types and backdoor scenarios, leading to unreliable protection against diverse triggers across modalities and forms. These findings highlight significant, underexplored vulnerabilities in current VLMs. We hope that BackdoorVLM can serve as a useful benchmark for analyzing and mitigating multimodal backdoor threats. --- ### EventSTU: Event-Guided Efficient Spatio-Temporal Understanding for Video Large Language Models Authors: Wenhao Xu, Xin Dong, Yue Li, Haoyuan Shi, Zhiwei Xiong Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18920v1 Video large language models have demonstrated strong video understanding capabilities but suffer from high inference costs due to the massive number of tokens in long videos. Inspired by event-based vision, we propose an event-guided, training-free framework for efficient spatio-temporal understanding, named EventSTU. In the temporal domain, we design a coarse-to-fine keyframe sampling algorithm that exploits the change-triggered property of event cameras to eliminate redundant frames. In the spatial domain, we design an adaptive token pruning algorithm that leverages the visual saliency of events as a zero-cost prior to guide spatial reduction. From a holistic spatio-temporal perspective, we further integrate question relevance from keyframe sampling to adaptively allocate token pruning budgets. To facilitate evaluation, we construct EventBench, the first event-inclusive, human-annotated multimodal benchmark that covers diverse real-world scenarios. Beyond physical event cameras, EventSTU also supports general video understanding using simulated events. Comprehensive experiments show that EventSTU achieves 3.01x FLOPs reduction and 3.10x prefilling speedup over the strongest baseline while still improving performance. --- ### Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation Authors: Ruiying Liu, Yuanzhi Liang, Haibin Huang, Tianshu Yu, Chi Zhang Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18919v1 Group Relative Policy Optimization (GRPO) has emerged as an effective and lightweight framework for post-training visual generative models. However, its performance is fundamentally limited by the ambiguity of textual visual correspondence: a single prompt may validly describe diverse visual outputs, and a single image or video may support multiple equally correct interpretations. This many to many relationship leads reward models to generate uncertain and weakly discriminative signals, causing GRPO to underutilize reliable feedback and overfit noisy ones. We introduce Bayesian Prior-Guided Optimization (BPGO), a novel extension of GRPO that explicitly models reward uncertainty through a semantic prior anchor. BPGO adaptively modulates optimization trust at two levels: inter-group Bayesian trust allocation emphasizes updates from groups consistent with the prior while down-weighting ambiguous ones, and intra-group prior-anchored renormalization sharpens sample distinctions by expanding confident deviations and compressing uncertain scores. Across both image and video generation tasks, BPGO delivers consistently stronger semantic alignment, enhanced perceptual fidelity, and faster convergence than standard GRPO and recent variants. --- ### How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining Authors: Kairong Luo, Zhenbo Sun, Haodong Wen, Xinyu Shi, Jiarui Cui, Chenyi Dang, Kaifeng Lyu, Wenguang Chen Published: 2025-11-24 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.18903v3 Due to the scarcity of high-quality data, large language models (LLMs) are often trained on mixtures of data with varying quality levels, even after sophisticated data curation. A natural approach to better leverage high-quality data is curriculum-based pretraining, where the model is trained on data sorted in ascending order of quality as determined by a quality metric. However, prior studies have reported limited improvements from such curriculum-based pretraining strategies. This work identifies a critical factor constraining these methods: the incompatibility between the ascending data quality order and the decaying learning rate (LR) schedule. We find that while curriculum-based training substantially outperforms random shuffling when using a constant LR, its advantage diminishes under standard LR decay schedules. Our experiments show this incompatibility can be mitigated by two simple strategies: (1) employing a more moderate LR decay schedule, where the final LR is only moderately smaller than the peak LR, and (2) replacing LR decay with model averaging, i.e., computing a weighted average of the final few checkpoints. By combining these strategies, we improve the average score on a suite of standard benchmarks by 1.64% over random shuffling, without additional data refinement. Validated on 1.5B-parameter models trained over 30B tokens with various data-quality metrics, our findings call for a re-evaluation of curriculum-based LLM pretraining and underscore the potential of co-designing data curricula with optimization methods. --- ### VADE: Variance-Aware Dynamic Sampling via Online Sample-Level Difficulty Estimation for Multimodal RL Authors: Zengjie Hu, Jiantao Qiu, Tianyi Bai, Haojin Yang, Binhang Yuan, Qi Jing, Conghui He, Wentao Zhang Published: 2025-11-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.18902v1 Group-based policy optimization methods like GRPO and GSPO have become standard for training multimodal models, leveraging group-wise rollouts and relative advantage estimation. However, they suffer from a critical \emph{gradient vanishing} problem when all responses within a group receive identical rewards, causing advantage estimates to collapse and training signals to diminish. Existing attempts to mitigate this issue fall into two paradigms: filtering-based and sampling-based methods. Filtering-based methods first generate rollouts broadly and then retroactively filter out uninformative groups, leading to substantial computational overhead. Sampling-based methods proactively select effective samples before rollout but rely on static criteria or prior dataset knowledge, lacking real-time adaptability. To address these issues, we propose \textbf{VADE}, a \textbf{V}ariance-\textbf{A}ware \textbf{D}ynamic sampling framework via online sample-level difficulty \textbf{E}stimation. Our framework integrates three key components: online sample-level difficulty estimation using Beta distributions, a Thompson sampler that maximizes information gain through the estimated correctness probability, and a two-scale prior decay mechanism that maintains robust estimation under policy evolution. This three components design enables VADE to dynamically select the most informative samples, thereby amplifying training signals while eliminating extra rollout costs. Extensive experiments on multimodal reasoning benchmarks show that VADE consistently outperforms strong baselines in both performance and sample efficiency, while achieving a dramatic reduction in computational overhead. More importantly, our framework can serves as a plug-and-play component to be seamlessly integrated into existing group-based RL algorithms. Code and models are available at https://VADE-RL.github.io. --- ### MatMart: Material Reconstruction of 3D Objects via Diffusion Authors: Xiuchao Wu, Pengfei Zhu, Jiangjing Lyu, Xinguo Liu, Jie Guo, Yanwen Guo, Weiwei Xu, Chengfei Lyu Published: 2025-11-24 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2511.18900v1 Applying diffusion models to physically-based material estimation and generation has recently gained prominence. In this paper, we propose \ttt, a novel material reconstruction framework for 3D objects, offering the following advantages. First, \ttt\ adopts a two-stage reconstruction, starting with accurate material prediction from inputs and followed by prior-guided material generation for unobserved views, yielding high-fidelity results. Second, by utilizing progressive inference alongside the proposed view-material cross-attention (VMCA), \ttt\ enables reconstruction from an arbitrary number of input images, demonstrating strong scalability and flexibility. Finally, \ttt\ achieves both material prediction and generation capabilities through end-to-end optimization of a single diffusion model, without relying on additional pre-trained models, thereby exhibiting enhanced stability across various types of objects. Extensive experiments demonstrate that \ttt\ achieves superior performance in material reconstruction compared to existing methods. --- ### Not All Pixels Are Equal: Pixel-wise Meta-Learning for Medical Segmentation with Noisy Labels Authors: Chenyu Mu, Guihai Chen, Xun Yang, Erkun Yang, Cheng Deng Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18894v6 Medical image segmentation is crucial for clinical applications, but it is frequently disrupted by noisy annotations and ambiguous anatomical boundaries, limiting its application in real-world scenarios. Existing methods often directly adapt noisy label learning techniques designed for instance classification, overlooking the pixel-wise heterogeneity in medical segmentation with its spatially and anatomically varying difficulties. Consequently, global assumptions or simple confidence metrics fail to address these local variations, leaving boundary ambiguities unresolved. To address this issue, we propose MetaDCSeg, a robust framework that dynamically learns optimal pixel-wise weights to suppress the influence of noisy labels while preserving reliable annotations. By explicitly modeling boundary uncertainty through a Dynamic Center Distance (DCD) mechanism, our approach utilizes weighted feature distances for foreground, background, and boundary centers, directing the model's attention toward hard-to-segment pixels near ambiguous boundaries. This strategy enables more precise handling of structural boundaries, which are often overlooked by existing methods, and significantly enhances segmentation performance. Extensive experiments across four benchmark datasets with varying noise levels demonstrate that MetaDCSeg outperforms existing state-of-the-art methods. --- ### Reproducibility Study of Large Language Model Bayesian Optimization Authors: Adam Rychert, Gasper Spagnolo, Evgenii Posashkov Published: 2025-11-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18891v1 In this reproducibility study, we revisit the LLAMBO framework of Daxberger et al. (2024), a prompting-based Bayesian optimization (BO) method that uses large language models as discriminative surrogates and acquisition optimizers via text-only interactions. We replicate the core Bayesmark and HPOBench experiments under the original evaluation protocol, but replace GPT-3.5 with the open-weight Llama 3.1 70B model used for all text encoding components. Our results broadly confirm the main claims of LLAMBO. Contextual warm starting via textual problem and hyperparameter descriptions substantially improves early regret behaviour and reduces variance across runs. LLAMBO's discriminative surrogate is weaker than GP or SMAC as a pure single task regressor, yet benefits from cross task semantic priors induced by the language model. Ablations that remove textual context markedly degrade predictive accuracy and calibration, while the LLAMBO candidate sampler consistently generates higher quality and more diverse proposals than TPE or random sampling. Experiments with smaller backbones (Gemma 27B, Llama 3.1 8B) yield unstable or invalid predictions, suggesting insufficient capacity for reliable surrogate behaviour. Overall, our study shows that the LLAMBO architecture is robust to changing the language model backbone and remains effective when instantiated with Llama 3.1 70B. --- ### Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models Authors: Yonggan Fu, Xin Dong, Shizhe Diao, Matthijs Van keirsbilck, Hanrong Ye, Wonmin Byeon, Yashaswi Karnati, Lucas Liebenwein, Hannah Zhang, Nikolaus Binder, Maksim Khadkevich, Alexander Keller et al. Published: 2025-11-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.18890v1 Efficient deployment of small language models (SLMs) is essential for numerous real-world applications with stringent latency constraints. While previous work on SLM design has primarily focused on reducing the number of parameters to achieve parameter-optimal SLMs, parameter efficiency does not necessarily translate into proportional real-device speed-ups. This work aims to identify the key determinants of SLMs' real-device latency and offer generalizable principles and methodologies for SLM design and training when real-device latency is the primary consideration. Specifically, we identify two central architectural factors: depth-width ratios and operator choices. The former is crucial for small-batch-size latency, while the latter affects both latency and large-batch-size throughput. In light of this, we first study latency-optimal depth-width ratios, with the key finding that although deep-thin models generally achieve better accuracy under the same parameter budget, they may not lie on the accuracy-latency trade-off frontier. Next, we explore emerging efficient attention alternatives to evaluate their potential as candidate building operators. Using the identified promising operators, we construct an evolutionary search framework to automatically discover latency-optimal combinations of these operators within hybrid SLMs, thereby advancing the accuracy-latency frontier. In addition to architectural improvements, we further enhance SLM training using a weight normalization technique that enables more effective weight updates and improves final convergence. Combining these methods, we introduce a new family of hybrid SLMs, called Nemotron-Flash, which significantly advances the accuracy-efficiency frontier of state-of-the-art SLMs, e.g., achieving over +5.5% average accuracy, 1.3x/1.9x lower latency, and 18.7x/45.6x higher throughput compared to Qwen3-1.7B/0.6B, respectively. --- ### CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation Authors: Jingqian Zhao, Bingbing Wang, Geng Tu, Yice Zhang, Qianlong Wang, Bin Liang, Jing Li, Ruifeng Xu Published: 2025-11-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.18889v1 Data contamination poses a significant challenge to the fairness of LLM evaluations in natural language processing tasks by inadvertently exposing models to test data during training. Current studies attempt to mitigate this issue by modifying existing datasets or generating new ones from freshly collected information. However, these methods fall short of ensuring contamination-resilient evaluation, as they fail to fully eliminate pre-existing knowledge from models or preserve the semantic complexity of the original datasets. To address these limitations, we propose \textbf{CoreEval}, a \textbf{Co}ntamination-\textbf{re}silient \textbf{Eval}uation strategy for automatically updating data with real-world knowledge. This approach begins by extracting entity relationships from the original data and leveraging the GDELT database to retrieve relevant, up-to-date knowledge. The retrieved knowledge is then recontextualized and integrated with the original data, which is refined and restructured to ensure semantic coherence and enhanced task relevance. Ultimately, a robust data reflection mechanism is employed to iteratively verify and refine labels, ensuring consistency between the updated and original datasets. Extensive experiments on updated datasets validate the robustness of CoreEval, demonstrating its effectiveness in mitigating performance overestimation caused by data contamination. --- ### MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model Authors: Qian Jiang, Qianqian Wang, Xin Jin, Michal Wozniak, Shaowen Yao, Wei Zhou Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18888v1 Remote sensing images are becoming increasingly widespread in military, earth resource exploration. Because of the limitation of a single sensor, we can obtain high spatial resolution grayscale panchromatic (PAN) images and low spatial resolution color multispectral (MS) images. Therefore, an important issue is to obtain a color image with high spatial resolution when there is only a PAN image at the input. The existing methods improve spatial resolution using super-resolution (SR) technology and spectral recovery using colorization technology. However, the SR technique cannot improve the spectral resolution, and the colorization technique cannot improve the spatial resolution. Moreover, the pansharpening method needs two registered inputs and can not achieve SR. As a result, an integrated approach is expected. To solve the above problems, we designed a novel multi-function model (MFmamba) to realize the tasks of SR, spectral recovery, joint SR and spectral recovery through three different inputs. Firstly, MFmamba utilizes UNet++ as the backbone, and a Mamba Upsample Block (MUB) is combined with UNet++. Secondly, a Dual Pool Attention (DPA) is designed to replace the skip connection in UNet++. Finally, a Multi-scale Hybrid Cross Block (MHCB) is proposed for initial feature extraction. Many experiments show that MFmamba is competitive in evaluation metrics and visual results and performs well in the three tasks when only the input PAN image is used. --- ### Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning Authors: Hyeong-Gun Joo, Songnam Hong, Seunghwan Lee, Dong-Joon Shin Published: 2025-11-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18887v1 Federated learning (FL) faces challenges in ensuring both privacy and communication efficiency, particularly in resource-constrained environments such as Internet of Things (IoT) and edge networks. While sign-based methods, such as sign stochastic gradient descent with majority voting (SIGNSGD-MV), offer substantial bandwidth savings, they remain vulnerable to inference attacks due to exposure of gradient signs. Existing secure aggregation techniques are either incompatible with sign-based methods or incur prohibitive overhead. To address these limitations, we propose Hi-SAFE, a lightweight and cryptographically secure aggregation framework for sign-based FL. Our core contribution is the construction of efficient majority vote polynomials for SIGNSGD-MV, derived from Fermat's Little Theorem. This formulation represents the majority vote as a low-degree polynomial over a finite field, enabling secure evaluation that hides intermediate values and reveals only the final result. We further introduce a hierarchical subgrouping strategy that ensures constant multiplicative depth and bounded per-user complexity, independent of the number of users n. --- ### MagicWorld: Towards Long-Horizon Stability for Interactive Video World Exploration Authors: Guangyuan Li, Bo Li, Jinwei Chen, Xiaobin Hu, Lei Zhao, Peng-Tao Jiang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18886v2 Recent interactive video world model methods generate scene evolution conditioned on user instructions. Although they achieve impressive results, two key limitations remain. First, they exhibit motion drift in complex environments with multiple interacting subjects, where dynamic subjects fail to follow realistic motion patterns during scene evolution. Second, they suffer from error accumulation in long-horizon interactions, where autoregressive generation gradually drifts from earlier scene states and causes structural and semantic inconsistencies. In this paper, we propose MagicWorld, an interactive video world model built upon an autoregressive framework. To address motion drift, we incorporate a flow-guided motion preservation constraint that mitigates motion degradation in dynamic subjects, encouraging realistic motion patterns and stable interactions during scene evolution. To mitigate error accumulation in long-horizon interactions, we design two complementary strategies, including a history cache retrieval strategy and an enhanced interactive training strategy. The former reinforces historical scene states by retrieving past generations during interaction, while the latter adopts multi-shot aggregated distillation with dual-reward weighting for interactive training, enhancing long-term stability and reducing error accumulation. In addition, we construct RealWM120K, a real-world dataset with diverse city-walk videos and multimodal annotations to support dynamic perception and long-horizon world modeling. Experimental results demonstrate that MagicWorld improves motion realism and alleviates error accumulation during long-horizon interactions. --- ### Facade Segmentation for Solar Photovoltaic Suitability Authors: Ayca Duran, Christoph Waibel, Bernd Bickel, Iro Armeni, Arno Schlueter Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18882v1 Building integrated photovoltaic (BIPV) facades represent a promising pathway towards urban decarbonization, especially where roof areas are insufficient and ground-mounted arrays are infeasible. Although machine learning-based approaches to support photovoltaic (PV) planning on rooftops are well researched, automated approaches for facades still remain scarce and oversimplified. This paper therefore presents a pipeline that integrates detailed information on the architectural composition of the facade to automatically identify suitable surfaces for PV application and estimate the solar energy potential. The pipeline fine-tunes SegFormer-B5 on the CMP Facades dataset and converts semantic predictions into facade-level PV suitability masks and PV panel layouts considering module sizes and clearances. Applied to a dataset of 373 facades with known dimensions from ten cities, the results show that installable BIPV potential is significantly lower than theoretical potential, thus providing valuable insights for reliable urban energy planning. With the growing availability of facade imagery, the proposed pipeline can be scaled to support BIPV planning in cities worldwide. --- ### Accelerating Reinforcement Learning via Error-Related Human Brain Signals Authors: Suzie Kim, Hye-Bin Shin, Hyo-Jeong Jang Published: 2025-11-24 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2511.18878v1 In this work, we investigate how implicit neural feed back can accelerate reinforcement learning in complex robotic manipulation settings. While prior electroencephalogram (EEG) guided reinforcement learning studies have primarily focused on navigation or low-dimensional locomotion tasks, we aim to understand whether such neural evaluative signals can improve policy learning in high-dimensional manipulation tasks involving obstacles and precise end-effector control. We integrate error related potentials decoded from offline-trained EEG classifiers into reward shaping and systematically evaluate the impact of human-feedback weighting. Experiments on a 7-DoF manipulator in an obstacle-rich reaching environment show that neural feedback accelerates reinforcement learning and, depending on the human-feedback weighting, can yield task success rates that at times exceed those of sparse-reward baselines. Moreover, when applying the best-performing feedback weighting across all sub jects, we observe consistent acceleration of reinforcement learning relative to the sparse-reward setting. Furthermore, leave-one subject-out evaluations confirm that the proposed framework remains robust despite the intrinsic inter-individual variability in EEG decodability. Our findings demonstrate that EEG-based reinforcement learning can scale beyond locomotion tasks and provide a viable pathway for human-aligned manipulation skill acquisition. --- ### Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification Authors: Lilian Say, Christophe Denis, Rafael Pinot Published: 2025-11-24 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.18876v1 The increasing use of machine learning in sensitive applications demands algorithms that simultaneously preserve data privacy and ensure fairness across potentially sensitive sub-populations. While privacy and fairness have each been extensively studied, their joint treatment remains poorly understood. Existing research often frames them as conflicting objectives, with multiple studies suggesting that strong privacy notions such as differential privacy inevitably compromise fairness. In this work, we challenge that perspective by showing that differential privacy can be integrated into a fairness-enhancing pipeline with minimal impact on fairness guarantees. We design a postprocessing algorithm, called DP2DP, that enforces both demographic parity and differential privacy. Our analysis reveals that our algorithm converges towards its demographic parity objective at essentially the same rate (up logarithmic factor) as the best non-private methods from the literature. Experiments on both synthetic and real datasets confirm our theoretical results, showing that the proposed algorithm achieves state-of-the-art accuracy/fairness/privacy trade-offs. --- ### Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference Authors: Wengyi Zhan, Mingbao Lin, Zhihang Lin, Rongrong Ji Published: 2025-11-24 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2511.18875v1 Multimodal large language models (MLLMs) deliver impressive vision-language reasoning but suffer steep inference latency because self-attention scales quadratically with sequence length and thousands of visual tokens contributed by high-resolution images. Naively pruning less-informative visual tokens reduces this burden, yet indiscriminate removal can strip away contextual cues essential for background or fine-grained questions, undermining accuracy. In this paper, we present ParVTS (Parallel Vision Token Scheduling), a training-free scheduling framework that partitions visual tokens into subject and non-subject groups, processes them in parallel to transfer their semantics into question tokens, and discards the non-subject path mid-inference to reduce computation. This scheduling reduces computational complexity, requires no heuristics or additional modules, and is compatible with diverse existing MLLM architectures. Experiments across multiple MLLM backbones show that ParVTS prunes up to 88.9% of visual tokens with minimal performance drop, achieving 1.77x speedup and 70% FLOPs reduction. --- ### GContextFormer: A global context-aware hybrid multi-head attention approach with scaled additive aggregation for multimodal trajectory prediction Authors: Yuzhi Chen, Yuanchang Xie, Lei Zhao, Pan Liu, Yajie Zou, Chen Wang Published: 2025-11-24 Categories: cs.AI, cs.CV, cs.LG, cs.MA, cs.RO, cs.SI arXiv: https://arxiv.org/abs/2511.18874v1 Multimodal trajectory prediction generates multiple plausible future trajectories to address vehicle motion uncertainty from intention ambiguity and execution variability. However, HD map-dependent models suffer from costly data acquisition, delayed updates, and vulnerability to corrupted inputs, causing prediction failures. Map-free approaches lack global context, with pairwise attention over-amplifying straight patterns while suppressing transitional patterns, resulting in motion-intention misalignment. This paper proposes GContextFormer, a plug-and-play encoder-decoder architecture with global context-aware hybrid attention and scaled additive aggregation achieving intention-aligned multimodal prediction without map reliance. The Motion-Aware Encoder builds scene-level intention prior via bounded scaled additive aggregation over mode-embedded trajectory tokens and refines per-mode representations under shared global context, mitigating inter-mode suppression and promoting intention alignment. The Hierarchical Interaction Decoder decomposes social reasoning into dual-pathway cross-attention: a standard pathway ensures uniform geometric coverage over agent-mode pairs while a neighbor-context-enhanced pathway emphasizes salient interactions, with gating module mediating their contributions to maintain coverage-focus balance. Experiments on eight highway-ramp scenarios from TOD-VT dataset show GContextFormer outperforms state-of-the-art baselines. Compared to existing transformer models, GContextFormer achieves greater robustness and concentrated improvements in high-curvature and transition zones via spatial distributions. Interpretability is achieved through motion mode distinctions and neighbor context modulation exposing reasoning attribution. The modular architecture supports extensibility toward cross-domain multimodal reasoning tasks. Source: https://fenghy-chen.github.io/sources/. --- ### Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction Authors: Yiming Wang, Shaofei Wang, Marko Mihajlovic, Siyu Tang Published: 2025-11-24 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2511.18873v1 3D Gaussian Splatting (3DGS) has emerged as a leading approach for high-quality novel view synthesis, with numerous variants extending its applicability to a broad spectrum of 3D and 4D scene reconstruction tasks. Despite its success, the representational capacity of 3DGS remains limited by the use of 3D Gaussian kernels to model local variations. Recent works have proposed to augment 3DGS with additional per-primitive capacity, such as per-splat textures, to enhance its expressiveness. However, these per-splat texture approaches primarily target dense novel view synthesis with a reduced number of Gaussian primitives, and their effectiveness tends to diminish when applied to more general reconstruction scenarios. In this paper, we aim to achieve concrete performance improvement over state-of-the-art 3DGS variants across a wide range of reconstruction tasks, including novel view synthesis, geometry and dynamic reconstruction, under both sparse and dense input settings. To this end, we introduce Neural Texture Splatting (NTS). At the core of our approach is a global neural field (represented as a hybrid of a tri-plane and a neural decoder) that predicts local appearance and geometric fields for each primitive. By leveraging this shared global representation that models local texture fields across primitives, we significantly reduce model size and facilitate efficient global information exchange, demonstrating strong generalization across tasks. Furthermore, our neural modeling of local texture fields introduces expressive view- and time-dependent effects, a critical aspect that existing methods fail to account for. Extensive experiments show that Neural Texture Splatting consistently improves models and achieves state-of-the-art results across multiple benchmarks. --- ### Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement Learning Authors: Jian Lu, Yi Luo Published: 2025-11-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.18871v8 Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention for LLM post-training, yet training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training are co-located on the same devices, and their synchronous execution prevents concurrent inference and training. In this work, we revisit the strategy of separating inference and training deployment, and propose a periodically asynchronous framework that transforms synchronous RL training into an asynchronous producer-consumer pipeline. By synchronising model weights at the beginning of each training iteration and generating all rollouts from the same policy, the proposed framework remains inherently on-policy -- without any modification to standard RL algorithms -- thereby avoiding the off-policy bias introduced by existing asynchronous approaches. We further introduce a unified tri-model architecture and a shared-prompt attention mechanism to support efficient asynchronous execution and reduce redundant computation. Experiments on NPU platforms show approximately 2x throughput improvement from asynchronous execution, with additional gains from system-level optimisations, substantially outperforming mainstream RL frameworks in end-to-end throughput, with speedups of up to 3x on GPU platforms, further confirming cross-architecture generalisability while maintaining comparable accuracy. The proposed framework thus offers a practical, algorithm-agnostic solution for scalable RL post-training without sacrificing on-policy correctness. Code available at: https://github.com/janelu9/EasyLLM --- ### HunyuanVideo 1.5 Technical Report Authors: Bing Wu, Chang Zou, Changlin Li, Duojun Huang, Fang Yang, Hao Tan, Jack Peng, Jianbing Wu, Jiangfeng Xiong, Jie Jiang, Linus, Patrol et al. Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18870v2 We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source video generation models. By releasing the code and model weights, we provide the community with a high-performance foundation that lowers the barrier to video creation and research, making advanced video generation accessible to a broader audience. All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5. --- ### Hear: Hierarchically Enhanced Aesthetic Representations For Multidimensional Music Evaluation Authors: Shuyang Liu, Yuan Jin, Rui Lin, Shizhe Chen, Junyu Dai, Tao Jiang Published: 2025-11-24 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2511.18869v2 Evaluating song aesthetics is challenging due to the multidimensional nature of musical perception and the scarcity of labeled data. We propose HEAR, a robust music aesthetic evaluation framework that combines: (1) a multi-source multi-scale representations module to obtain complementary segment- and track-level features, (2) a hierarchical augmentation strategy to mitigate overfitting, and (3) a hybrid training objective that integrates regression and ranking losses for accurate scoring and reliable top-tier song identification. Experiments demonstrate that HEAR consistently outperforms the baseline across all metrics on both tracks of the ICASSP 2026 SongEval benchmark. The code and trained model weights are available at https://github.com/Eps-Acoustic-Revolution-Lab/EAR_HEAR. --- ### KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits Authors: Dezhi Ran, Shuxiao Xie, Mingfang Ji, Anmin Liu, Mengzhou Wu, Yuan Cao, Yuzhe Guo, Hao Yu, Linyi Li, Yitao Hu, Wei Yang, Tao Xie Published: 2025-11-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.18868v2 High-performance GPU kernels are critical for efficient LLM serving, yet their optimization remains a bottleneck requiring deep system expertise. While code LLMs show promise in generating functionally correct code, kernel optimization is intrinsically a search problem over a vast optimization space. The fundamental mismatch prevents existing LLM agents from efficiently exploring the optimization space for diverse hardware and compute patterns. To bridge the gap, we present KernelBand, a framework that formulates kernel optimization as a Multi-Armed Bandit (MAB) problem, explicitly balancing exploration and exploitation to unlock the potential of code LLMs. To navigate the infinite arm space of optimization strategies applied to candidate kernels, we design two key mechanisms: a hardware-aware pruning strategy via profiling bounds and a trace-driven clustering algorithm that leverages Lipschitz continuity. Theoretically, we prove that KernelBand reduces the regret bound to depend on the compact covering number of runtime clusters, ensuring sample-efficient discovery of high-performance kernels. Extensive experiments on TritonBench-G with three GPU architectures and four code LLMs show that KernelBand consistently and substantially outperforms state-of-the-art methods with over 33% average improvement. --- ### DualGazeNet: A Biologically Inspired Dual-Gaze Query Network for Salient Object Detection Authors: Yu Zhang, Haoan Ping, Yuchen Li, Zhenshan Bing, Fuchun Sun, Alois Knoll Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18865v1 Recent salient object detection (SOD) methods aim to improve performance in four key directions: semantic enhancement, boundary refinement, auxiliary task supervision, and multi-modal fusion. In pursuit of continuous gains, these approaches have evolved toward increasingly sophisticated architectures with multi-stage pipelines, specialized fusion modules, edge-guided learning, and elaborate attention mechanisms. However, this complexity paradoxically introduces feature redundancy and cross-component interference that obscure salient cues, ultimately reaching performance bottlenecks. In contrast, human vision achieves efficient salient object identification without such architectural complexity. This contrast raises a fundamental question: can we design a biologically grounded yet architecturally simple SOD framework that dispenses with most of this engineering complexity, while achieving state-of-the-art accuracy, computational efficiency, and interpretability? In this work, we answer this question affirmatively by introducing DualGazeNet, a biologically inspired pure Transformer framework that models the dual biological principles of robust representation learning and magnocellular-parvocellular dual-pathway processing with cortical attention modulation in the human visual system. Extensive experiments on five RGB SOD benchmarks show that DualGazeNet consistently surpasses 25 state-of-the-art CNN- and Transformer-based methods. On average, DualGazeNet achieves about 60\% higher inference speed and 53.4\% fewer FLOPs than four Transformer-based baselines of similar capacity (VST++, MDSAM, Sam2unet, and BiRefNet). Moreover, DualGazeNet exhibits strong cross-domain generalization, achieving leading or highly competitive performance on camouflaged and underwater SOD benchmarks without relying on additional modalities. --- ### Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models Authors: Yang Xiang, Yixin Ji, Juntao Li, Min Zhang Published: 2025-11-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18864v1 Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex reasoning benchmarks. However, their long chain-of-thought reasoning processes incur significant inference overhead. Pruning has emerged as a promising approach to reducing computational costs. However, existing efforts have primarily focused on large language models (LLMs), while pruning LRMs remains unexplored. In this work, we conduct the first empirical study on pruning LRMs and show that directly applying existing pruning techniques fails to yield satisfactory results. Our findings indicate that using self-generated reasoning data for calibration can substantially improve pruning performance. We further investigate how the difficulty and length of reasoning data affect pruning outcomes. Our analysis reveals that challenging and moderately long self-generated reasoning data serve as ideal calibration data. Based on these insights, we propose a Selective Self-Generated Reasoning (SSGR) data construction strategy to provide effective calibration data for pruning LRMs. Experimental results on the DeepSeek-R1-Distill model series validate that our strategy improves the reasoning ability of pruned LRMs by 10%-13% compared to general pruning methods. --- ### Generating Reading Comprehension Exercises with Large Language Models for Educational Applications Authors: Xingyu Huang, Fei Jiang, Jianli Xiao Published: 2025-11-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.18860v1 With the rapid development of large language models (LLMs), the applications of LLMs have grown substantially. In the education domain, LLMs demonstrate significant potential, particularly in automatic text generation, which enables the creation of intelligent and adaptive learning content. This paper proposes a new LLMs framework, which is named as Reading Comprehension Exercise Generation (RCEG). It can generate high-quality and personalized English reading comprehension exercises automatically. Firstly, RCEG uses fine-tuned LLMs to generate content candidates. Then, it uses a discriminator to select the best candidate. Finally, the quality of the generated content has been improved greatly. To evaluate the performance of RCEG, a dedicated dataset for English reading comprehension is constructed to perform the experiments, and comprehensive evaluation metrics are used to analyze the experimental results. These metrics include content diversity, factual accuracy, linguistic toxicity, and pedagogical alignment. Experimental results show that RCEG significantly improves the relevance and cognitive appropriateness of the generated exercises. --- ### Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning Authors: Bo Jiang, Weijun Zhao, Beibei Wang, Xiao Wang, Jin Tang Published: 2025-11-24 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.18859v1 Recently, fine-tuning large-scale pre-trained GNNs has yielded remarkable attention in adapting pre-trained GNN models for downstream graph learning tasks. One representative fine-tuning method is to exploit adapter (termed AdapterGNN) which aims to 'augment' the pre-trained model by inserting a lightweight module to make the 'augmented' model better adapt to the downstream tasks. However, graph data may contain various types of noise in downstream tasks, such as noisy edges and ambiguous node attributes. Existing AdapterGNNs are often prone to graph noise and exhibit limited generalizability. How to enhance the robustness and generalization ability of GNNs' fine tuning remains an open problem. In this paper, we show that the above problem can be well addressed by integrating uncertainty learning into the GNN adapter. We propose the Uncertainty-aware Adapter (UAdapterGNN) that fortifies pre-trained GNN models against noisy graph data in the fine-tuning process. Specifically, in contrast to regular AdapterGNN, our UAdapterGNN exploits Gaussian probabilistic adapter to augment the pre-trained GNN model. In this way, when the graph contains various noises,our method can automatically absorb the effects of changes in the variances of the Gaussian distribution, thereby significantly enhancing the model's robustness. Also, UAdapterGNN can further improve the generalization ability of the model on the downstream tasks. Extensive experiments on several benchmarks demonstrate the effectiveness, robustness and high generalization ability of the proposed UAdapterGNN method. --- ### Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling Authors: Xiao Cui, Yulei Qin, Xinyue Li, Wengang Zhou, Hongsheng Li, Houqiang Li Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18858v2 Dataset distillation creates a small distilled set that enables efficient training by capturing key information from the full dataset. While existing dataset distillation methods perform well on balanced datasets, they struggle under long-tailed distributions, where imbalanced class frequencies induce biased model representations and corrupt statistical estimates such as Batch Normalization (BN) statistics. In this paper, we rethink long-tailed dataset distillation by revisiting the limitations of trajectory-based methods, and instead adopt the statistical alignment perspective to jointly mitigate model bias and restore fair supervision. To this end, we introduce three dedicated components that enable unbiased recovery of distilled images and soft relabeling: (1) enhancing expert models (an observer model for recovery and a teacher model for relabeling) to enable reliable statistics estimation and soft-label generation; (2) recalibrating BN statistics via a full forward pass with dynamically adjusted momentum to reduce representation skew; (3) initializing synthetic images by incrementally selecting high-confidence and diverse augmentations via a multi-round mechanism that promotes coverage and diversity. Extensive experiments on four long-tailed benchmarks show consistent improvements over state-of-the-art methods across varying degrees of class imbalance. Notably, our approach improves top-1 accuracy by 15.6% on CIFAR-100-LT and 11.8% on Tiny-ImageNet-LT under IPC=10 and IF=10. Codes are available at https://github.com/2018cx/RLDD. --- ### Deep Hybrid Model for Region of Interest Detection in Omnidirectional Videos Authors: Sana Alamgeer, Mylene Farias, Marcelo Carvalho Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18856v3 The main goal of the project is to design a new model that predicts regions of interest in 360$^{\circ}$ videos. The region of interest (ROI) plays an important role in 360$^{\circ}$ video streaming. For example, ROIs are used to predict view-ports, intelligently cut the videos for live streaming, etc so that less bandwidth is used. Detecting view-ports in advance helps reduce the movement of the head while streaming and watching a video via the head-mounted device. Whereas, intelligent cuts of the videos help improve the efficiency of streaming the video to users and enhance the quality of their viewing experience. This report illustrates the secondary task to identify ROIs, in which, we design, train, and test a hybrid saliency model. In this work, we refer to saliency regions to represent the regions of interest. The method includes the processes as follows: preprocessing the video to obtain frames, developing a hybrid saliency model for predicting the region of interest, and finally post-processing the output predictions of the hybrid saliency model to obtain the output region of interest for each frame. Then, we compare the performance of the proposed method with the subjective annotations of the 360RAT dataset. --- ### Time Travel: LLM-Assisted Semantic Behavior Localization with Git Bisect Authors: Yujing Wang, Weize Hong Published: 2025-11-24 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.18854v1 We present a novel framework that integrates Large Language Models (LLMs) into the Git bisect process for semantic fault localization. Traditional bisect assumes deterministic predicates and binary failure states assumptions often violated in modern software development due to flaky tests, nonmonotonic regressions, and semantic divergence from upstream repositories. Our system augments bisect traversal with structured chain of thought reasoning, enabling commit by commit analysis under noisy conditions. We evaluate multiple open source and proprietary LLMs for their suitability and fine tune DeepSeekCoderV2 using QLoRA on a curated dataset of semantically labeled diffs. We adopt a weak supervision workflow to reduce annotation overhead, incorporating human in the loop corrections and self consistency filtering. Experiments across multiple open source projects show a 6.4 point absolute gain in success rate from 74.2 to 80.6 percent, leading to significantly fewer failed traversals and by experiment up to 2x reduction in average bisect time. We conclude with discussions on temporal reasoning, prompt design, and finetuning strategies tailored for commit level behavior analysis. --- ### FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models Authors: Masoomali Fatehkia, Enes Altinisik, Husrev Taha Sencar Published: 2025-11-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18852v2 Content moderation filters are a critical safeguard against alignment failures in language models. Yet most existing filters focus narrowly on general safety and overlook cultural context. In this work, we introduce FanarGuard, a bilingual moderation filter that evaluates both safety and cultural alignment in Arabic and English. We construct a dataset of over 468K prompt and response pairs, drawn from synthetic and public datasets, scored by a panel of LLM judges on harmlessness and cultural awareness, and use it to train two filter variants. To rigorously evaluate cultural alignment, we further develop the first benchmark targeting Arabic cultural contexts, comprising over 1k norm-sensitive prompts with LLM-generated responses annotated by human raters. Results show that FanarGuard achieves stronger agreement with human annotations than inter-annotator reliability, while matching the performance of state-of-the-art filters on safety benchmarks. These findings highlight the importance of integrating cultural awareness into moderation and establish FanarGuard as a practical step toward more context-sensitive safeguards. --- ### Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretization Authors: Yilin Wen, Kechuan Dong, Yusuke Sugano Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18851v1 Online test-time adaptation addresses the train-test domain gap by adapting the model on unlabeled streaming test inputs before making the final prediction. However, online adaptation for 3D human pose estimation suffers from error accumulation when relying on self-supervision with imperfect predictions, leading to degraded performance over time. To mitigate this fundamental challenge, we propose a novel solution that highlights the use of motion discretization. Specifically, we employ unsupervised clustering in the latent motion representation space to derive a set of anchor motions, whose regularity aids in supervising the human pose estimator and enables efficient self-replay. Additionally, we introduce an effective and efficient soft-reset mechanism by reverting the pose estimator to its exponential moving average during continuous adaptation. We examine long-term online adaptation by continuously adapting to out-of-domain streaming test videos of the same individual, which allows for the capture of consistent personal shape and motion traits throughout the streaming observation. By mitigating error accumulation, our solution enables robust exploitation of these personal traits for enhanced accuracy. Experiments demonstrate that our solution outperforms previous online test-time adaptation methods and validate our design choices. --- ### Cognitive Alpha Mining via LLM-Driven Code-Based Evolution Authors: Fengyuan Liu, Yi Huang, Sichun Luo, Yuqi Wang, Yazheng Yang, Xinye Li, Zefa Hu, Junlan Feng, Qi Liu Published: 2025-11-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18850v4 Discovering effective predictive signals, or "alphas," from financial data with high dimensionality and extremely low signal-to-noise ratio remains a difficult open problem. Despite progress in deep learning, genetic programming, and, more recently, large language model (LLM)-based factor generation, existing approaches still explore only a narrow region of the vast alpha search space. Neural models tend to produce opaque and fragile patterns, while symbolic or formula-based methods often yield redundant or economically ungrounded expressions that generalize poorly. Although different in form, these paradigms share a key limitation: none can conduct broad, structured, and human-like exploration that balances logical consistency with creative leaps. To address this gap, we introduce the Cognitive Alpha Mining Framework (CogAlpha), which combines code-level alpha representation with LLM-driven reasoning and evolutionary search. Treating LLMs as adaptive cognitive agents, our framework iteratively refines, mutates, and recombines alpha candidates through multi-stage prompts and financial feedback. This synergistic design enables deeper thinking, richer structural diversity, and economically interpretable alpha discovery, while greatly expanding the effective search space. Experiments on 5 stock datasets from 3 stock markets demonstrate that CogAlpha consistently discovers alphas with superior predictive accuracy, robustness, and generalization over existing methods. Our results highlight the promise of aligning evolutionary optimization with LLM-based reasoning for automated and explainable alpha discovery. --- ### Pre-Filtering Code Suggestions using Developer Behavioral Telemetry to Optimize LLM-Assisted Programming Authors: Mohammad Nour Al Awad, Sergey Ivanov, Olga Tikhonova Published: 2025-11-24 Categories: cs.SE, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.18849v1 Large Language Models (LLMs) are increasingly integrated into code editors to provide AI-powered code suggestions. Yet many of these suggestions are ignored, resulting in wasted computation, increased latency, and unnecessary interruptions. We introduce a lightweight pre-filtering model that predicts the likelihood of suggestion acceptance before invoking the LLM, using only real-time developer telemetry such as typing speed, file navigation, and editing activity. Deployed in a production-grade Visual Studio Code plugin over four months of naturalistic use, our approach nearly doubled acceptance rates (18.4% -> 34.2%) while suppressing 35% of low-value LLM calls. These findings demonstrate that behavioral signals alone can meaningfully improve both user experience and system efficiency in LLM-assisted programming, highlighting the value of timing-aware, privacy-preserving adaptation mechanisms. The filter operates solely on pre-invocation editor telemetry and never inspects code or prompts. --- ### Large Language Models for the Summarization of Czech Documents: From History to the Present Authors: Václav Tran, Jakub Šmíd, Ladislav Lenc, Jean-Pierre Salmon, Pavel Král Published: 2025-11-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.18848v1 Text summarization is the task of automatically condensing longer texts into shorter, coherent summaries while preserving the original meaning and key information. Although this task has been extensively studied in English and other high-resource languages, Czech summarization, particularly in the context of historical documents, remains underexplored. This is largely due to the inherent linguistic complexity of Czech and the lack of high-quality annotated datasets. In this work, we address this gap by leveraging the capabilities of Large Language Models (LLMs), specifically Mistral and mT5, which have demonstrated strong performance across a wide range of natural language processing tasks and multilingual settings. In addition, we also propose a translation-based approach that first translates Czech texts into English, summarizes them using an English-language model, and then translates the summaries back into Czech. Our study makes the following main contributions: We demonstrate that LLMs achieve new state-of-the-art results on the SumeCzech dataset, a benchmark for modern Czech text summarization, showing the effectiveness of multilingual LLMs even for morphologically rich, medium-resource languages like Czech. We introduce a new dataset, Posel od Čerchova, designed for the summarization of historical Czech texts. This dataset is derived from digitized 19th-century publications and annotated for abstractive summarization. We provide initial baselines using modern LLMs to facilitate further research in this underrepresented area. By combining cutting-edge models with both modern and historical Czech datasets, our work lays the foundation for further progress in Czech summarization and contributes valuable resources for future research in Czech historical document processing and low-resource summarization more broadly. --- ### Personalized Federated Segmentation with Shared Feature Aggregation and Boundary-Focused Calibration Authors: Ishmam Tashdeed, Md. Atiqur Rahman, Sabrina Islam, Md. Azam Hossain Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18847v1 Personalized federated learning (PFL) possesses the unique capability of preserving data confidentiality among clients while tackling the data heterogeneity problem of non-independent and identically distributed (Non-IID) data. Its advantages have led to widespread adoption in domains such as medical image segmentation. However, the existing approaches mostly overlook the potential benefits of leveraging shared features across clients, where each client contains segmentation data of different organs. In this work, we introduce a novel personalized federated approach for organ agnostic tumor segmentation (FedOAP), that utilizes cross-attention to model long-range dependencies among the shared features of different clients and a boundary-aware loss to improve segmentation consistency. FedOAP employs a decoupled cross-attention (DCA), which enables each client to retain local queries while attending to globally shared key-value pairs aggregated from all clients, thereby capturing long-range inter-organ feature dependencies. Additionally, we introduce perturbed boundary loss (PBL) which focuses on the inconsistencies of the predicted mask's boundary for each client, forcing the model to localize the margins more precisely. We evaluate FedOAP on diverse tumor segmentation tasks spanning different organs. Extensive experiments demonstrate that FedOAP consistently outperforms existing state-of-the-art federated and personalized segmentation methods. --- ### WaveTuner: Comprehensive Wavelet Subband Tuning for Time Series Forecasting Authors: Yubo Wang, Hui He, Chaoxi Niu, Zhendong Niu Published: 2025-11-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.18846v1 Due to the inherent complexity, temporal patterns in real-world time series often evolve across multiple intertwined scales, including long-term periodicity, short-term fluctuations, and abrupt regime shifts. While existing literature has designed many sophisticated decomposition approaches based on the time or frequency domain to partition trend-seasonality components and high-low frequency components, an alternative line of approaches based on the wavelet domain has been proposed to provide a unified multi-resolution representation with precise time-frequency localization. However, most wavelet-based methods suffer from a persistent bias toward recursively decomposing only low-frequency components, severely underutilizing subtle yet informative high-frequency components that are pivotal for precise time series forecasting. To address this problem, we propose WaveTuner, a Wavelet decomposition framework empowered by full-spectrum subband Tuning for time series forecasting. Concretely, WaveTuner comprises two key modules: (i) Adaptive Wavelet Refinement module, that transforms time series into time-frequency coefficients, utilizes an adaptive router to dynamically assign subband weights, and generates subband-specific embeddings to support refinement; and (ii) Multi-Branch Specialization module, that employs multiple functional branches, each instantiated as a flexible Kolmogorov-Arnold Network (KAN) with a distinct functional order to model a specific spectral subband. Equipped with these modules, WaveTuner comprehensively tunes global trends and local variations within a unified time-frequency framework. Extensive experiments on eight real-world datasets demonstrate WaveTuner achieves state-of-the-art forecasting performance in time series forecasting. --- ### UNeMo: Collaborative Visual-Language Reasoning and Navigation via a Multimodal World Model Authors: Changxin Huang, Lv Tang, Zhaohuan Zhan, Lisha Yu, Runhao Zeng, Zun Liu, Zhengjie Wang, Jianqiang Li Published: 2025-11-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.18845v2 Vision-and-Language Navigation (VLN) requires agents to autonomously navigate complex environments via visual images and natural language instructions--remains highly challenging. Recent research on enhancing language-guided navigation reasoning using pre-trained large language models (LLMs) has shown promising prospects. However, the reasoning of such methods is limited to the linguistic modality, lacking visual reasoning capabilities. Moreover, existing reasoning modules are optimized separately from navigation policies, leading to incompatibility and potential conflicts in optimization objectives.To tackle these challenges, we introduce UNeMo, a novel framework designed for the collaborative optimization of visual state reasoning and navigational decision-making. It introduces a Multimodal World Model (MWM) that takes visual features, language instructions, and navigational actions as inputs to jointly predict subsequent visual states, enabling cross-modal reasoning. Via a Hierarchical Prediction-Feedback (HPN) mechanism, MWM collaborates with navigation policies: the first layer generates actions using current vision-and-language features; MWM then infers post-action visual states to guide the second layer's fine-grained decisions. This forms a dynamic bidirectional promotion mechanism where MWM reasoning optimizes navigation policies, while policy decisions feedback to improve MWM's reasoning accuracy. Experiments on R2R and REVERIE datasets show UNeMo outperforms state-of-the-art methods by 2.1% and 0.7% in navigation accuracy for unseen scenes, validating its effectiveness. --- ### A Reproducible Framework for Neural Topic Modeling in Focus Group Analysis Authors: Heger Arfaoui, Mohammed Iheb Hergli, Beya Benzina, Slimane BenMiled Published: 2025-11-24 Categories: cs.CL, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2511.18843v2 Focus group discussions generate rich qualitative data but their analysis traditionally relies on labor-intensive manual coding that limits scalability and reproducibility. We present a systematic framework for applying BERTopic to focus group transcripts using data from ten focus groups exploring HPV vaccine perceptions in Tunisia (1,075 utterances). We conducted comprehensive hyperparameter exploration across 27 configurations, evaluating each through bootstrap stability analysis, performance metrics, and comparison with LDA baseline. Bootstrap analysis revealed that stability metrics (NMI and ARI) exhibited strong disagreement (r = -0.691) and showed divergent relationships with coherence, demonstrating that stability is multifaceted rather than monolithic. Our multi-criteria selection framework yielded a 7-topic model achieving 18\% higher coherence than optimized LDA (0.573 vs. 0.486) with interpretable topics validated through independent human evaluation (ICC = 0.700, weighted Cohen's kappa = 0.678). These findings demonstrate that transformer-based topic modeling can extract interpretable themes from small focus group transcript corpora when systematically configured and validated, while revealing that quality metrics capture distinct, sometimes conflicting constructs requiring multi-criteria evaluation. We provide complete documentation and code to support reproducibility. --- ### Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds Authors: Mohammad Nour Al Awad, Sergey Ivanov, Olga Tikhonova Published: 2025-11-24 Categories: cs.SE, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.18842v1 Large Language Models (LLMs) have transformed code auto-completion by generating context-aware suggestions. Yet, deciding when to present these suggestions remains underexplored, often leading to interruptions or wasted inference calls. We propose an adaptive timing mechanism that dynamically adjusts the delay before offering a suggestion based on real-time developer feedback. Our suggested method combines a logistic transform of recent acceptance rates with a bounded delay range, anchored by a high-level binary prediction of the developer's cognitive state. In a two-month deployment with professional developers, our system improved suggestion acceptance from 4.9% with no delay to 15.4% with static delays, and to 18.6% with adaptive timing-while reducing blind rejections (rejections without being read) from 8.3% to 0.36%. Together, these improvements increase acceptance and substantially reduce wasted inference calls by 75%, making LLM-based code assistants more efficient and cost-effective in practice. --- ### Federated style aware transformer aggregation of representations Authors: Mincheol Jeon, Euinam Huh Published: 2025-11-24 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2511.18841v1 Personalized Federated Learning (PFL) faces persistent challenges, including domain heterogeneity from diverse client data, data imbalance due to skewed participation, and strict communication constraints. Traditional federated learning often lacks personalization, as a single global model cannot capture client-specific characteristics, leading to biased predictions and poor generalization, especially for clients with highly divergent data distributions. To address these issues, we propose FedSTAR, a style-aware federated learning framework that disentangles client-specific style factors from shared content representations. FedSTAR aggregates class-wise prototypes using a Transformer-based attention mechanism, allowing the server to adaptively weight client contributions while preserving personalization. Furthermore, by exchanging compact prototypes and style vectors instead of full model parameters, FedSTAR significantly reduces communication overhead. Experimental results demonstrate that combining content-style disentanglement with attention-driven prototype aggregation improves personalization and robustness in heterogeneous environments without increasing communication cost. --- ### Addressing Situated Teaching Needs: A Multi-Agent Framework for Automated Slide Adaptation Authors: Binglin Liu, Yucheng Wang, Zheyuan Zhang, Jiyuan Lu, Shen Yang, Daniel Zhang-Li, Huiqin Liu, Jifan Yu Published: 2025-11-24 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2511.18840v1 The adaptation of teaching slides to instructors' situated teaching needs, including pedagogical styles and their students' context, is a critical yet time-consuming task for educators. Through a series of educator interviews, we first identify and systematically categorize the key friction points that impede this adaptation process. Grounded in these findings, we introduce a novel multi-agent framework designed to automate slide adaptation based on high-level instructor specifications. An evaluation involving 16 modification requests across 8 real-world courses validates our approach. The framework's output consistently achieved high scores in intent alignment, content coherence and factual accuracy, and performed on par with baseline methods regarding visual clarity, while also demonstrating appropriate timeliness and a high operational agreement with human experts, achieving an F1 score of 0.89. This work heralds a new paradigm where AI agents handle the logistical burdens of instructional design, liberating educators to focus on the creative and strategic aspects of teaching. --- ### Enhancing Multi-Label Thoracic Disease Diagnosis with Deep Ensemble-Based Uncertainty Quantification Authors: Yasiru Laksara, Uthayasanker Thayasivam Published: 2025-11-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.18839v1 The utility of deep learning models, such as CheXNet, in high stakes clinical settings is fundamentally constrained by their purely deterministic nature, failing to provide reliable measures of predictive confidence. This project addresses this critical gap by integrating robust Uncertainty Quantification (UQ) into a high performance diagnostic platform for 14 common thoracic diseases on the NIH ChestX-ray14 dataset. Initial architectural development failed to stabilize performance and calibration using Monte Carlo Dropout (MCD), yielding an unacceptable Expected Calibration Error (ECE) of 0.7588. This technical failure necessitated a rigorous architectural pivot to a high diversity, 9-member Deep Ensemble (DE). This resulting DE successfully stabilized performance and delivered superior reliability, achieving a State-of-the-Art (SOTA) average Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.8559 and an average F1 Score of 0.3857. Crucially, the DE demonstrated superior calibration (Mean ECE of 0.0728 and Negative Log-Likelihood (NLL) of 0.1916) and enabled the reliable decomposition of total uncertainty into its Aleatoric (irreducible data noise) and Epistemic (reducible model knowledge) components, with a mean Epistemic Uncertainty (EU) of 0.0240. These results establish the Deep Ensemble as a trustworthy and explainable platform, transforming the model from a probabilistic tool into a reliable clinical decision support system. --- ### FVAR: Visual Autoregressive Modeling via Next Focus Prediction Authors: Xiaofan Li, Chenming Wu, Yanpeng Sun, Jiaming Zhou, Delin Qu, Yansong Qu, Weihao Bo, Haibao Yu, Dingkang Liang Published: 2025-11-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.18838v1 Visual autoregressive models achieve remarkable generation quality through next-scale predictions across multi-scale token pyramids. However, the conventional method uses uniform scale downsampling to build these pyramids, leading to aliasing artifacts that compromise fine details and introduce unwanted jaggies and moiré patterns. To tackle this issue, we present \textbf{FVAR}, which reframes the paradigm from \emph{next-scale prediction} to \emph{next-focus prediction}, mimicking the natural process of camera focusing from blur to clarity. Our approach introduces three key innovations: \textbf{1) Next-Focus Prediction Paradigm} that transforms multi-scale autoregression by progressively reducing blur rather than simply downsampling; \textbf{2) Progressive Refocusing Pyramid Construction} that uses physics-consistent defocus kernels to build clean, alias-free multi-scale representations; and \textbf{3) High-Frequency Residual Learning} that employs a specialized residual teacher network to effectively incorporate alias information during training while maintaining deployment simplicity. Specifically, we construct optical low-pass views using defocus point spread function (PSF) kernels with decreasing radius, creating smooth blur-to-clarity transitions that eliminate aliasing at its source. To further enhance detail generation, we introduce a High-Frequency Residual Teacher that learns from both clean structure and alias residuals, distilling this knowledge to a vanilla VAR deployment network for seamless inference. Extensive experiments on ImageNet demonstrate that FVAR substantially reduces aliasing artifacts, improves fine detail preservation, and enhances text readability, achieving superior performance with perfect compatibility to existing VAR frameworks. --- ### Auto-ML Graph Neural Network Hypermodels for Outcome Prediction in Event-Sequence Data Authors: Fang Wang, Lance Kosca, Adrienne Kosca, Marko Gacesa, Ernesto Damiani Published: 2025-11-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.18835v1 This paper introduces HGNN(O), an AutoML GNN hypermodel framework for outcome prediction on event-sequence data. Building on our earlier work on graph convolutional network hypermodels, HGNN(O) extends four architectures-One Level, Two Level, Two Level Pseudo Embedding, and Two Level Embedding-across six canonical GNN operators. A self-tuning mechanism based on Bayesian optimization with pruning and early stopping enables efficient adaptation over architectures and hyperparameters without manual configuration. Empirical evaluation on both balanced and imbalanced event logs shows that HGNN(O) achieves accuracy exceeding 0.98 on the Traffic Fines dataset and weighted F1 scores up to 0.86 on the Patients dataset without explicit imbalance handling. These results demonstrate that the proposed AutoML-GNN approach provides a robust and generalizable benchmark for outcome prediction in complex event-sequence data. --- ### FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories Authors: Lei Ke, Hubery Yin, Gongye Liu, Zhengyao Lv, Jingcai Guo, Chen Li, Wenhan Luo, Yujiu Yang, Jing Lyu Published: 2025-11-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.18834v1 With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, ReFlow has been somehow overlooked although it has theoretical consistency with flow matching. This is primarily due to its suboptimal performance in practical scenarios compared to consistency distillation and score distillation. In this work, we investigate this issue within the ReFlow framework and propose FlowSteer, a method unlocks the potential of ReFlow-based distillation by guiding the student along teacher's authentic generation trajectories. We first identify that Piecewised ReFlow's performance is hampered by a critical distribution mismatch during the training and propose Online Trajectory Alignment(OTA) to resolve it. Then, we introduce a adversarial distillation objective applied directly on the ODE trajectory, improving the student's adherence to the teacher's generation trajectory. Furthermore, we find and fix a previously undiscovered flaw in the widely-used FlowMatchEulerDiscreteScheduler that largely degrades few-step inference quality. Our experiment result on SD3 demonstrates our method's efficacy. ---