# Research Papers — 2025-11 · bundle page 87 of 197 > Full-text markdown of papers #4301–4350 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/87 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/86.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/88.md) ### Enhancing Regional Airbnb Trend Forecasting Using LLM-Based Embeddings of Accessibility and Human Mobility Authors: Hongju Lee, Youngjun Park, Jisun An, Dongman Lee Published: 2025-11-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.14248v1 The expansion of short-term rental platforms, such as Airbnb, has significantly disrupted local housing markets, often leading to increased rental prices and housing affordability issues. Accurately forecasting regional Airbnb market trends can thus offer critical insights for policymakers and urban planners aiming to mitigate these impacts. This study proposes a novel time-series forecasting framework to predict three key Airbnb indicators -- Revenue, Reservation Days, and Number of Reservations -- at the regional level. Using a sliding-window approach, the model forecasts trends 1 to 3 months ahead. Unlike prior studies that focus on individual listings at fixed time points, our approach constructs regional representations by integrating listing features with external contextual factors such as urban accessibility and human mobility. We convert structured tabular data into prompt-based inputs for a Large Language Model (LLM), producing comprehensive regional embeddings. These embeddings are then fed into advanced time-series models (RNN, LSTM, Transformer) to better capture complex spatio-temporal dynamics. Experiments on Seoul's Airbnb dataset show that our method reduces both average RMSE and MAE by approximately 48% compared to conventional baselines, including traditional statistical and machine learning models. Our framework not only improves forecasting accuracy but also offers practical insights for detecting oversupplied regions and supporting data-driven urban policy decisions. --- ### V2VLoc: Robust GNSS-Free Collaborative Perception via LiDAR Localization Authors: Wenkai Lin, Qiming Xia, Wen Li, Xun Huang, Chenglu Wen Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14247v1 Multi-agents rely on accurate poses to share and align observations, enabling a collaborative perception of the environment. However, traditional GNSS-based localization often fails in GNSS-denied environments, making consistent feature alignment difficult in collaboration. To tackle this challenge, we propose a robust GNSS-free collaborative perception framework based on LiDAR localization. Specifically, we propose a lightweight Pose Generator with Confidence (PGC) to estimate compact pose and confidence representations. To alleviate the effects of localization errors, we further develop the Pose-Aware Spatio-Temporal Alignment Transformer (PASTAT), which performs confidence-aware spatial alignment while capturing essential temporal context. Additionally, we present a new simulation dataset, V2VLoc, which can be adapted for both LiDAR localization and collaborative detection tasks. V2VLoc comprises three subsets: Town1Loc, Town4Loc, and V2VDet. Town1Loc and Town4Loc offer multi-traversal sequences for training in localization tasks, whereas V2VDet is specifically intended for the collaborative detection task. Extensive experiments conducted on the V2VLoc dataset demonstrate that our approach achieves state-of-the-art performance under GNSS-denied conditions. We further conduct extended experiments on the real-world V2V4Real dataset to validate the effectiveness and generalizability of PASTAT. --- ### MuCPT: Music-related Natural Language Model Continued Pretraining Authors: Kai Tian, Yirong Mao, Wendong Bi, Hanjie Wang, Que Wenhui Published: 2025-11-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.14245v1 Large language models perform strongly on general tasks but remain constrained in specialized settings such as music, particularly in the music-entertainment domain, where corpus scale, purity, and the match between data and training objectives are critical. We address this by constructing a large, music-related natural language corpus (40B tokens) that combines open source and in-house data, and by implementing a domain-first data pipeline: a lightweight classifier filters and weights in-domain text, followed by multi-stage cleaning, de-duplication, and privacy-preserving masking. We further integrate multi-source music text with associated metadata to form a broader, better-structured foundation of domain knowledge. On the training side, we introduce reference-model (RM)-based token-level soft scoring for quality control: a unified loss-ratio criterion is used both for data selection and for dynamic down-weighting during optimization, reducing noise gradients and amplifying task-aligned signals, thereby enabling more effective music-domain continued pretraining and alignment. To assess factuality, we design the MusicSimpleQA benchmark, which adopts short, single-answer prompts with automated agreement scoring. Beyond the benchmark design, we conduct systematic comparisons along the axes of data composition. Overall, this work advances both the right corpus and the right objective, offering a scalable data-training framework and a reusable evaluation tool for building domain LLMs in the music field. --- ### Enhancing Generalization of Depth Estimation Foundation Model via Weakly-Supervised Adaptation with Regularization Authors: Yan Huang, Yongyi Su, Xin Lin, Le Zhang, Xun Xu Published: 2025-11-18 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.14238v1 The emergence of foundation models has substantially advanced zero-shot generalization in monocular depth estimation (MDE), as exemplified by the Depth Anything series. However, given access to some data from downstream tasks, a natural question arises: can the performance of these models be further improved? To this end, we propose WeSTAR, a parameter-efficient framework that performs Weakly supervised Self-Training Adaptation with Regularization, designed to enhance the robustness of MDE foundation models in unseen and diverse domains. We first adopt a dense self-training objective as the primary source of structural self-supervision. To further improve robustness, we introduce semantically-aware hierarchical normalization, which exploits instance-level segmentation maps to perform more stable and multi-scale structural normalization. Beyond dense supervision, we introduce a cost-efficient weak supervision in the form of pairwise ordinal depth annotations to further guide the adaptation process, which enforces informative ordinal constraints to mitigate local topological errors. Finally, a weight regularization loss is employed to anchor the LoRA updates, ensuring training stability and preserving the model's generalizable knowledge. Extensive experiments on both realistic and corrupted out-of-distribution datasets under diverse and challenging scenarios demonstrate that WeSTAR consistently improves generalization and achieves state-of-the-art performance across a wide range of benchmarks. --- ### Breaking the Passive Learning Trap: An Active Perception Strategy for Human Motion Prediction Authors: Juncheng Hu, Zijian Zhang, Zeyu Wang, Guoyu Wang, Yingji Li, Kedi Lyu Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14237v1 Forecasting 3D human motion is an important embodiment of fine-grained understanding and cognition of human behavior by artificial agents. Current approaches excessively rely on implicit network modeling of spatiotemporal relationships and motion characteristics, falling into the passive learning trap that results in redundant and monotonous 3D coordinate information acquisition while lacking actively guided explicit learning mechanisms. To overcome these issues, we propose an Active Perceptual Strategy (APS) for human motion prediction, leveraging quotient space representations to explicitly encode motion properties while introducing auxiliary learning objectives to strengthen spatio-temporal modeling. Specifically, we first design a data perception module that projects poses into the quotient space, decoupling motion geometry from coordinate redundancy. By jointly encoding tangent vectors and Grassmann projections, this module simultaneously achieves geometric dimension reduction, semantic decoupling, and dynamic constraint enforcement for effective motion pose characterization. Furthermore, we introduce a network perception module that actively learns spatio-temporal dependencies through restorative learning. This module deliberately masks specific joints or injects noise to construct auxiliary supervision signals. A dedicated auxiliary learning network is designed to actively adapt and learn from perturbed information. Notably, APS is model agnostic and can be integrated with different prediction models to enhance active perceptual. The experimental results demonstrate that our method achieves the new state-of-the-art, outperforming existing methods by large margins: 16.3% on H3.6M, 13.9% on CMU Mocap, and 10.1% on 3DPW. --- ### ArbESC+: Arabic Enhanced Edit Selection System Combination for Grammatical Error Correction Resolving conflict and improving system combination in Arabic GEC Authors: Ahlam Alrehili, Areej Alhothali Published: 2025-11-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.14230v1 Grammatical Error Correction (GEC) is an important aspect of natural language processing. Arabic has a complicated morphological and syntactic structure, posing a greater challenge than other languages. Even though modern neural models have improved greatly in recent years, the majority of previous attempts used individual models without taking into account the potential benefits of combining different systems. In this paper, we present one of the first multi-system approaches for correcting grammatical errors in Arabic, the Arab Enhanced Edit Selection System Complication (ArbESC+). Several models are used to collect correction proposals, which are represented as numerical features in the framework. A classifier determines and implements the appropriate corrections based on these features. In order to improve output quality, the framework uses support techniques to filter overlapping corrections and estimate decision reliability. A combination of AraT5, ByT5, mT5, AraBART, AraBART+Morph+GEC, and Text editing systems gave better results than a single model alone, with F0.5 at 82.63% on QALB-14 test data, 84.64% on QALB-15 L1 data, and 65.55% on QALB-15 L2 data. As one of the most significant contributions of this work, it's the first Arab attempt to integrate linguistic error correction. Improving existing models provides a practical step towards developing advanced tools that will benefit users and researchers of Arabic text processing. --- ### EBind: a practical approach to space binding Authors: Jim Broadbent, Felix Cohen, Frederik Hvilshøj, Eric Landau, Eren Sasoglu Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.14229v1 We simplify space binding by focusing on two core components, a single encoder per modality and high-quality data; enabling training state-of-the-art models on a single GPU in a few hours as opposed to multiple days. We present EBind, an Easy, data-centric, and parameter-efficient method to Bind the embedding spaces of multiple contrastive models. We demonstrate that a simple 1.8B-parameter image-text-video-audio-3D model can outperform models 4 to 17x the size. The key to achieving this is a carefully curated dataset of three complementary data sources: i) 6.7M fully-automated multimodal quintuples sourced via SOTA retrieval models, ii) 1M diverse, semi-automated triples annotated by humans as negative, partial, or positive matches, and iii) 3.4M pre-existing captioned data items. We use 13 different evaluations to demonstrate the value of each data source. Due to limitations with existing benchmarks, we further introduce the first high-quality, consensus-annotated zero-shot classification benchmark between audio and PCs. In contrast to related work, we will open-source our code, model weights, and datasets. --- ### DevPiolt: Operation Recommendation for IoT Devices at Xiaomi Home Authors: Yuxiang Wang, Siwen Wang, Haowei Han, Ao Wang, Boya Liu, Yong Zhao, Chengbo Wu, Bin Zhu, Bin Qin, Xiaokai Zhou, Xiao Yan, Jiawei Jiang et al. Published: 2025-11-18 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.14227v1 Operation recommendation for IoT devices refers to generating personalized device operations for users based on their context, such as historical operations, environment information, and device status. This task is crucial for enhancing user satisfaction and corporate profits. Existing recommendation models struggle with complex operation logic, diverse user preferences, and sensitive to suboptimal suggestions, limiting their applicability to IoT device operations. To address these issues, we propose DevPiolt, a LLM-based recommendation model for IoT device operations. Specifically, we first equip the LLM with fundamental domain knowledge of IoT operations via continual pre-training and multi-task fine-tuning. Then, we employ direct preference optimization to align the fine-tuned LLM with specific user preferences. Finally, we design a confidence-based exposure control mechanism to avoid negative user experiences from low-quality recommendations. Extensive experiments show that DevPiolt significantly outperforms baselines on all datasets, with an average improvement of 69.5% across all metrics. DevPiolt has been practically deployed in Xiaomi Home app for one quarter, providing daily operation recommendations to 255,000 users. Online experiment results indicate a 21.6% increase in unique visitor device coverage and a 29.1% increase in page view acceptance rates. --- ### StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model Authors: Yifan Yang, Zhi Cen, Sida Peng, Xiangwei Chen, Yifu Deng, Xinyu Zhu, Fan Jia, Xiaowei Zhou, Hujun Bao Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14223v3 This paper focuses on the task of speech-driven 3D facial animation, which aims to generate realistic and synchronized facial motions driven by speech inputs. Recent methods have employed audio-conditioned diffusion models for 3D facial animation, achieving impressive results in generating expressive and natural animations. However, these methods process the whole audio sequences in a single pass, which poses two major challenges: they tend to perform poorly when handling audio sequences that exceed the training horizon and will suffer from significant latency when processing long audio inputs. To address these limitations, we propose a novel autoregressive diffusion model that processes input audio in a streaming manner. This design ensures flexibility with varying audio lengths and achieves low latency independent of audio duration. Specifically, we select a limited number of past frames as historical motion context and combine them with the audio input to create a dynamic condition. This condition guides the diffusion process to iteratively generate facial motion frames, enabling real-time synthesis with high-quality results. Additionally, we implemented a real-time interactive demo, highlighting the effectiveness and efficiency of our approach. We will release the code at https://zju3dv.github.io/StreamingTalker/. --- ### LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation Authors: Hao Jiang, Guoquan Wang, Donglin Zhou, Sheng Yu, Yang Zeng, Wencong Zeng, Kun Gai, Guorui Zhou Published: 2025-11-18 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.14221v1 Recent advances in Large Language Models (LLMs) have enhanced text-based recommendation by enriching traditional ID-based methods with semantic generalization capabilities. Text-based methods typically encode item textual information via prompt design and generate discrete semantic IDs through item tokenization. However, in domain-specific tasks such as local-life services, simply injecting location information into prompts fails to capture fine-grained spatial characteristics and real-world distance awareness among items. To address this, we propose LGSID, an LLM-Aligned Geographic Item Tokenization Framework for Local-life Recommendation. This framework consists of two key components: (1) RL-based Geographic LLM Alignment, and (2) Hierarchical Geographic Item Tokenization. In the RL-based alignment module, we initially train a list-wise reward model to capture real-world spatial relationships among items. We then introduce a novel G-DPO algorithm that uses pre-trained reward model to inject generalized spatial knowledge and collaborative signals into LLMs while preserving their semantic understanding. Furthermore, we propose a hierarchical geographic item tokenization strategy, where primary tokens are derived from discrete spatial and content attributes, and residual tokens are refined using the aligned LLM's geographic representation vectors. Extensive experiments on real-world Kuaishou industry datasets show that LGSID consistently outperforms state-of-the-art discriminative and generative recommendation models. Ablation studies, visualizations, and case studies further validate its effectiveness. --- ### Twice Sequential Monte Carlo for Tree Search Authors: Yaniv Oren, Joery A. de Vries, Pascal R. van der Vaart, Matthijs T. J. Spaan, Wendelin Böhmer Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14220v3 Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alternative to the Monte Carlo Tree Search (MCTS) algorithm which drove these breakthroughs. SMC is easier to parallelize and more suitable to GPU acceleration. However, it also suffers from large variance and path degeneracy which prevent it from scaling well with increased search depth, i.e., increased sequential compute. To address these problems, we introduce Twice Sequential Monte Carlo Tree Search (TSMCTS). Across discrete and continuous environments TSMCTS outperforms the SMC baseline as well as a popular modern version of MCTS as a policy improvement operator, scales favorably with sequential compute, reduces estimator variance and mitigates the effects of path degeneracy while retaining the properties that make SMC natural to parallelize. --- ### Listen Like a Teacher: Mitigating Whisper Hallucinations using Adaptive Layer Attention and Knowledge Distillation Authors: Kumud Tripathi, Aditya Srinivas Menon, Aman Gaurav, Raj Prakash Gohil, Pankaj Wasnik Published: 2025-11-18 Categories: cs.AI, cs.SD arXiv: https://arxiv.org/abs/2511.14219v1 The Whisper model, an open-source automatic speech recognition system, is widely adopted for its strong performance across multilingual and zero-shot settings. However, it frequently suffers from hallucination errors, especially under noisy acoustic conditions. Previous works to reduce hallucinations in Whisper-style ASR systems have primarily focused on audio preprocessing or post-processing of transcriptions to filter out erroneous content. However, modifications to the Whisper model itself remain largely unexplored to mitigate hallucinations directly. To address this challenge, we present a two-stage architecture that first enhances encoder robustness through Adaptive Layer Attention (ALA) and further suppresses hallucinations using a multi-objective knowledge distillation (KD) framework. In the first stage, ALA groups encoder layers into semantically coherent blocks via inter-layer correlation analysis. A learnable multi-head attention module then fuses these block representations, enabling the model to jointly exploit low- and high-level features for more robust encoding. In the second stage, our KD framework trains the student model on noisy audio to align its semantic and attention distributions with a teacher model processing clean inputs. Our experiments on noisy speech benchmarks show notable reductions in hallucinations and word error rates, while preserving performance on clean speech. Together, ALA and KD offer a principled strategy to improve Whisper's reliability under real-world noisy conditions. --- ### Resolving sources of uncertainty in AI weather forecasting Authors: Wenbo Hu, Xinlei Xiong, Shuxun Zhou, Kaifeng Bi, Lingxi Xie, Jun Zhu, Richang Hong, Qi Tian Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14218v2 Weather forecast uncertainty arises from imperfect analyses and forecast models, but ensemble spread alone does not reveal how distinct sources relate to downstream targets. We introduce Pangu-Bayes, a probabilistic forecasting hierarchy that treats atmospheric-state and learned-model uncertainty as distinct stochastic variables, crossing flow-dependent perturbations of the evolving state with Bayesian parameter samples. This construction yields model-defined source-resolved variance components and matched pathway evaluation. Across 90 held-out 2023 tropical cyclones, Pangu-Bayes reduces track, pressure and wind errors by 54.2%, 17.2% and 24.9%, respectively, while improving rapid-intensification detection. Among 88 cyclones supporting pathway comparison, atmospheric-state variability is more consistently associated with improved track prediction, whereas learned-model variability is more often associated with improved intensity prediction. During Mawar and Khanun, state perturbations sample alternative steering-flow evolutions associated with recurvature, whereas parameter sampling broadens intensity evolution. Pangu-Bayes thus connects model-defined uncertainty resolution to target-dependent value and dynamical interpretation while retaining competitive global probabilistic skill. --- ### Do Large Language Models (LLMs) Understand Chronology? Authors: Pattaraphon Kenny Wongchamcharoen, Paul Glasserman Published: 2025-11-18 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.14214v2 Large language models (LLMs) are increasingly used in finance and economics, where prompt-based attempts against look-ahead bias implicitly assume that models understand chronology. We test this fundamental question with a series of chronological ordering tasks with increasing complexities over facts the model already knows from pre-training. Our tasks cover (1) chronological ordering, (2) conditional sorting (filter, then order), and (3) anachronism detection. We evaluate GPT-4.1, Claude-3.7 Sonnet, with and without Extended Thinking (ET), and GPT-5 across multiple reasoning-effort settings. Across models, Exact match rate drops sharply as sequences lengthen even while rank correlations stay high as LLMs largely preserve local order but struggle to maintain a single globally consistent timeline. In conditional sorting, most failures stem from the filtering step rather than the ordering step, but GPT-5 and Claude-3.7 Sonnet with Extended Thinking outshine normal models significantly. Lastly, anachronism detection is found to be the easiest task for the LLMs but performance still declines with increasingly overlapping timelines or entities. Overall, our main contribution is showing that allocating explicit reasoning budget helps with chronological ordering with GPT-5 at medium/high reasoning effort achieving flawless ordering at all lengths and perfect conditional sorting (both self-filtered and given-subset), whereas low/minimal effort degrades with longer lists, mirroring earlier models. Our findings delineate limits of current LLMs on chronological tasks, providing insights into task complexity, and demonstrate scenarios in which reasoning helps. These patterns are important for the real-time application of LLMs in finance. We release all code and evaluation templates to support full reproducibility. --- ### Measurement-Constrained Sampling for Text-Prompted Blind Face Restoration Authors: Wenjie Li, Yulun Zhang, Guangwei Gao, Heng Guo, Zhanyu Ma Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14213v1 Blind face restoration (BFR) may correspond to multiple plausible high-quality (HQ) reconstructions under extremely low-quality (LQ) inputs. However, existing methods typically produce deterministic results, struggling to capture this one-to-many nature. In this paper, we propose a Measurement-Constrained Sampling (MCS) approach that enables diverse LQ face reconstructions conditioned on different textual prompts. Specifically, we formulate BFR as a measurement-constrained generative task by constructing an inverse problem through controlled degradations of coarse restorations, which allows posterior-guided sampling within text-to-image diffusion. Measurement constraints include both Forward Measurement, which ensures results align with input structures, and Reverse Measurement, which produces projection spaces, ensuring that the solution can align with various prompts. Experiments show that our MCS can generate prompt-aligned results and outperforms existing BFR methods. Codes will be released after acceptance. --- ### Orion: A Unified Visual Agent for Multimodal Perception, Advanced Visual Reasoning and Execution Authors: N Dinesh Reddy, Dylan Snyder, Lona Kiragu, Mirajul Mohin, Shahrear Bin Amin, Sudeep Pillai Published: 2025-11-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.14210v2 We introduce Orion, a visual agent that integrates vision-based reasoning with tool-augmented execution to achieve powerful, precise, multi-step visual intelligence across images, video, and documents. Unlike traditional vision-language models that generate descriptive outputs, Orion orchestrates a suite of specialized computer vision tools, including object detection, keypoint localization, panoptic segmentation, Optical Character Recognition (OCR), and geometric analysis, to execute complex multi-step visual workflows. The system achieves competitive performance across MMMU, MMBench, DocVQA, and MMLongBench while extending monolithic VLM capabilities to production-grade visual intelligence. Through its agentic, tool-augmented approach, Orion enables autonomous visual reasoning that bridges neural perception with symbolic execution, marking the transition from passive visual understanding to active, tool-driven visual intelligence. Try Orion for free at: https://chat.vlm.run Learn more at: https://www.vlm.run/orion --- ### InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion Prior Authors: Weimin Bai, Suzhe Xu, Yiwei Ren, Jinhua Hao, Ming Sun, Wenzheng Chen, He Sun Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14208v3 Video inverse problems are fundamental to streaming, telepresence, and AR/VR, where high perceptual quality must coexist with tight latency constraints. Diffusion-based priors currently deliver state-of-the-art reconstructions, but existing approaches either adapt image diffusion models with ad hoc temporal regularizers - leading to temporal artifacts - or rely on native video diffusion models whose iterative posterior sampling is far too slow for real-time use. We introduce InstantViR, an amortized inference framework for ultra-fast video reconstruction powered by a pre-trained video diffusion prior. We distill a powerful bidirectional video diffusion model (teacher) into a causal autoregressive student that maps a degraded video directly to its restored version in a single forward pass, inheriting the teacher's strong temporal modeling while completely removing iterative test-time optimization. The distillation is prior-driven: it only requires the teacher diffusion model and known degradation operators, and does not rely on externally paired clean/noisy video data. To further boost throughput, we replace the video-diffusion backbone VAE with a high-efficiency LeanVAE via an innovative teacher-space regularized distillation scheme, enabling low-latency latent-space processing. Across streaming random inpainting, Gaussian deblurring and super-resolution, InstantViR matches or surpasses the reconstruction quality of diffusion-based baselines while running at over 35 FPS on NVIDIA A100 GPUs, achieving up to 100 times speedups over iterative video diffusion solvers. These results show that diffusion-based video reconstruction is compatible with real-time, interactive, editable, streaming scenarios, turning high-quality video restoration into a practical component of modern vision systems. --- ### Causal Discovery on Higher-Order Interactions Authors: Alessio Zanga, Marco Scutari, Fabio Stella Published: 2025-11-18 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.14206v1 Causal discovery combines data with knowledge provided by experts to learn the DAG representing the causal relationships between a given set of variables. When data are scarce, bagging is used to measure our confidence in an average DAG obtained by aggregating bootstrapped DAGs. However, the aggregation step has received little attention from the specialized literature: the average DAG is constructed using only the confidence in the individual edges of the bootstrapped DAGs, thus disregarding complex higher-order edge structures. In this paper, we introduce a novel theoretical framework based on higher-order structures and describe a new DAG aggregation algorithm. We perform a simulation study, discussing the advantages and limitations of the proposed approach. Our proposal is both computationally efficient and effective, outperforming state-of-the-art solutions, especially in low sample size regimes and under high dimensionality settings. --- ### Multi-Scale Correlation-Aware Transformer for Maritime Vessel Re-Identification Authors: Yunhe Liu Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14203v1 Maritime vessel re-identification (Re-ID) plays a crucial role in advancing maritime monitoring and intelligent situational awareness systems. However, some existing vessel Re-ID methods are directly adapted from pedestrian-focused algorithms, making them ill-suited for mitigating the unique problems present in vessel images, particularly the greater intra-identity variations and more severe missing of local parts, which lead to the emergence of outlier samples within the same identity. To address these challenges, we propose the Multi-scale Correlation-aware Transformer Network (MCFormer), which explicitly models multi-scale correlations across the entire input set to suppress the adverse effects of outlier samples with intra-identity variations or local missing, incorporating two novel modules, the Global Correlation Module (GCM), and the Local Correlation Module (LCM). Specifically, GCM constructs a global similarity affinity matrix across all input images to model global correlations through feature aggregation based on inter-image consistency, rather than solely learning features from individual images as in most existing approaches. Simultaneously, LCM mines and aligns local features of positive samples with contextual similarity to extract local correlations by maintaining a dynamic memory bank, effectively compensating for missing or occluded regions in individual images. To further enhance feature robustness, MCFormer integrates global and local features that have been respectively correlated across multiple scales, effectively capturing latent relationships among image features. Experiments on three benchmarks demonstrate that MCFormer achieves state-of-the-art performance. --- ### HFL-FlowLLM: Large Language Models for Network Traffic Flow Classification in Heterogeneous Federated Learning Authors: Jiazhuo Tian, Yachao Yuan Published: 2025-11-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.14199v1 In modern communication networks driven by 5G and the Internet of Things (IoT), effective network traffic flow classification is crucial for Quality of Service (QoS) management and security. Traditional centralized machine learning struggles with the distributed data and privacy concerns in these heterogeneous environments, while existing federated learning approaches suffer from high costs and poor generalization. To address these challenges, we propose HFL-FlowLLM, which to our knowledge is the first framework to apply large language models to network traffic flow classification in heterogeneous federated learning. Compared to state-of-the-art heterogeneous federated learning methods for network traffic flow classification, the proposed approach improves the average F1 score by approximately 13%, demonstrating compelling performance and strong robustness. When compared to existing large language models federated learning frameworks, as the number of clients participating in each training round increases, the proposed method achieves up to a 5% improvement in average F1 score while reducing the training costs by about 87%. These findings prove the potential and practical value of HFL-FlowLLM in modern communication networks security. --- ### DiverseClaire: Simulating Students to Improve Introductory Programming Course Materials for All CS1 Learners Authors: Wendy Wong, Yuchao Jiang, Yuekang Li Published: 2025-11-18 Categories: cs.CY, cs.AI, cs.HC, cs.PL arXiv: https://arxiv.org/abs/2511.14198v1 Although CS programs are booming, introductory courses like CS1 still adopt a one-size-fits-all formats that can exacerbate cognitive load and discourage learners with autism, ADHD, dyslexia and other neurological conditions. These call for compassionate pedagogies and Universal Design For Learning (UDL) to create learning environments and materials where cognitive diversity is welcomed. To address this, we introduce DiverseClaire a pilot study, which simulates students including neurodiverse profiles using LLMs and diverse personas. By leveraging Bloom's Taxonomy and UDL, DiverseClaire compared UDL-transformed lecture slides with traditional formats. To evaluate DiverseClaire controlled experiments, we used the evaluation metric the average score. The findings revealed that the simulated neurodiverse students struggled with learning due to lecture slides that were in inaccessible formats. These results highlight the need to provide course materials in multiple formats for diverse learner preferences. Data from our pilot study will be made available to assist future CS1 instructors. --- ### Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision Authors: Zitang Sun, Masakazu Yoshimura, Junji Otsuka, Atsushi Irie, Takeshi Ohashi Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14197v2 High-quality data has become a primary driver of progress under scale laws, with curated datasets often outperforming much larger unfiltered ones at lower cost. Online data curation extends this idea by dynamically selecting training samples based on the model's evolving state. While effective in classification and multimodal learning, existing online sampling strategies rarely extend to object detection because of its structural complexity and domain gaps. We introduce DetGain, an online data curation method specifically for object detection that estimates the marginal perturbation of each image to dataset-level Average Precision (AP) based on its prediction quality. By modeling global score distributions, DetGain efficiently estimates the global AP change and computes teacher-student contribution gaps to select informative samples at each iteration. The method is architecture-agnostic and minimally intrusive, enabling straightforward integration into diverse object detection architectures. Experiments on the COCO dataset with multiple representative detectors show consistent improvements in accuracy. DetGain also demonstrates strong robustness under low-quality data and can be effectively combined with knowledge distillation techniques to further enhance performance, highlighting its potential as a general and complementary strategy for data-efficient object detection. --- ### MindCross: Fast New Subject Adaptation with Limited Data for Cross-subject Video Reconstruction from Brain Signals Authors: Xuan-Hao Liu, Yan-Kai Liu, Tianyi Zhou, Bao-Liang Lu, Wei-Long Zheng Published: 2025-11-18 Categories: cs.MM, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2511.14196v1 Reconstructing video from brain signals is an important brain decoding task. Existing brain decoding frameworks are primarily built on a subject-dependent paradigm, which requires large amounts of brain data for each subject. However, the expensive cost of collecting brain-video data causes severe data scarcity. Although some cross-subject methods being introduced, they often overfocus with subject-invariant information while neglecting subject-specific information, resulting in slow fine-tune-based adaptation strategy. To achieve fast and data-efficient new subject adaptation, we propose MindCross, a novel cross-subject framework. MindCross's N specific encoders and one shared encoder are designed to extract subject-specific and subject-invariant information, respectively. Additionally, a Top-K collaboration module is adopted to enhance new subject decoding with the knowledge learned from previous subjects' encoders. Extensive experiments on fMRI/EEG-to-video benchmarks demonstrate MindCross's efficacy and efficiency of cross-subject decoding and new subject adaptation using only one model. --- ### N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator Authors: Zheyu Lin, Jirui Yang, Yukui Qiu, Hengqi Guo, Yubing Bao, Yao Guan Published: 2025-11-18 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2511.14195v2 Evaluating the safety robustness of LLMs is critical for their deployment. However, mainstream Red Teaming methods rely on online generation and black-box output analysis. These approaches are not only costly but also suffer from feedback latency, making them unsuitable for agile diagnostics after training a new model. To address this, we propose N-GLARE (A Non-Generative, Latent Representation-Efficient LLM Safety Evaluator). N-GLARE operates entirely on the model's latent representations, bypassing the need for full text generation. It characterizes hidden layer dynamics by analyzing the APT (Angular-Probabilistic Trajectory) of latent representations and introducing the JSS (Jensen-Shannon Separability) metric. Experiments on over 40 models and 20 red teaming strategies demonstrate that the JSS metric exhibits high consistency with the safety rankings derived from Red Teaming. N-GLARE reproduces the discriminative trends of large-scale red-teaming tests at less than 1\% of the token cost and the runtime cost, providing an efficient output-free evaluation proxy for real-time diagnostics. --- ### Hierarchical Semantic Learning for Multi-Class Aorta Segmentation Authors: Pengcheng Shi Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14187v1 The aorta, the body's largest artery, is prone to pathologies such as dissection, aneurysm, and atherosclerosis, which often require timely intervention. Minimally invasive repairs involving branch vessels necessitate detailed 3D anatomical analysis. Existing methods often overlook hierarchical anatomical relationships while struggling with severe class imbalance inherent in vascular structures. We address these challenges with a curriculum learning strategy that leverages a novel fractal softmax for hierarchical semantic learning. Inspired by human cognition, our approach progressively learns anatomical constraints by decomposing complex structures from simple to complex components. The curriculum learning framework naturally addresses class imbalance by first establishing robust feature representations for dominant classes before tackling rare but anatomically critical structures, significantly accelerating model convergence in multi-class scenarios. Our two-stage inference strategy achieves up to fivefold acceleration, enhancing clinical practicality. On the validation set at epoch 50, our hierarchical semantic loss improves the Dice score of nnU-Net ResEnc M by 11.65%. The proposed model demonstrates a 5.6% higher Dice score than baselines on the test set. Experimental results show significant improvements in segmentation accuracy and efficiency, making the framework suitable for real-time clinical applications. The implementation code for this challenge entry is publicly available at: https://github.com/PengchengShi1220/AortaSeg24. The code for fractal softmax will be available at https://github.com/PengchengShi1220/fractal-softmax. --- ### Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation Authors: Zhaoyu Liu, Kan Jiang, Murong Ma, Zhe Hou, Yun Lin, Jin Song Dong Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14186v1 Precise event spotting (PES) aims to recognize fine-grained events at exact moments and has become a key component of sports analytics. This task is particularly challenging due to rapid succession, motion blur, and subtle visual differences. Consequently, most existing methods rely on domain-specific, end-to-end training with large labeled datasets and often struggle in few-shot conditions due to their dependence on pixel- or pose-based inputs alone. However, obtaining large labeled datasets is practically hard. We propose a Unified Multi-Entity Graph Network (UMEG-Net) for few-shot PES. UMEG-Net integrates human skeletons and sport-specific object keypoints into a unified graph and features an efficient spatio-temporal extraction module based on advanced GCN and multi-scale temporal shift. To further enhance performance, we employ multimodal distillation to transfer knowledge from keypoint-based graphs to visual representations. Our approach achieves robust performance with limited labeled data and significantly outperforms baseline models in few-shot settings, providing a scalable and effective solution for few-shot PES. Code is publicly available at https://github.com/LZYAndy/UMEG-Net. --- ### PAVE: An End-to-End Dataset for Production Autonomous Vehicle Evaluation Authors: Xiangyu Li, Chen Wang, Yumao Liu, Dengbo He, Jiahao Zhang, Ke Ma Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14185v2 Most existing autonomous-driving datasets (e.g., KITTI, nuScenes, and the Waymo Perception Dataset), collected by human-driving mode or unidentified driving mode, can only serve as early training for the perception and prediction of autonomous vehicles (AVs). To evaluate the real behavioral safety of AVs controlled in the black box, we present the first end-to-end benchmark dataset collected entirely by autonomous-driving mode in the real world. This dataset contains over 100 hours of naturalistic data from multiple production autonomous-driving vehicle models in the market. We segment the original data into 32,727 key frames, each consisting of four synchronized camera images and high-precision GNSS/IMU data (0.8 cm localization accuracy). For each key frame, 20 Hz vehicle trajectories spanning the past 6 s and future 5 s are provided, along with detailed 2D annotations of surrounding vehicles, pedestrians, traffic lights, and traffic signs. These key frames have rich scenario-level attributes, including driver intent, area type (covering highways, urban roads, and residential areas), lighting (day, night, or dusk), weather (clear or rain), road surface (paved or unpaved), traffic and vulnerable road users (VRU) density, traffic lights, and traffic signs (warning, prohibition, and indication). To evaluate the safety of AVs, we employ an end-to-end motion planning model that predicts vehicle trajectories with an Average Displacement Error (ADE) of 1.4 m on autonomous-driving frames. The dataset continues to expand by over 10 hours of new data weekly, thereby providing a sustainable foundation for research on AV driving behavior analysis and safety evaluation. The PAVE dataset is publicly available at https://hkustgz-my.sharepoint.com/:f:/g/personal/kema_hkust-gz_edu_cn/IgDXyoHKfdGnSZ3JbbidjduMAXxs-Z3NXzm005A_Ix9tr0Q?e=9HReCu. --- ### GloTok: Global Perspective Tokenizer for Image Reconstruction and Generation Authors: Xuan Zhao, Zhongyu Zhang, Yuge Huang, Yuxi Mi, Guodong Mu, Shouhong Ding, Jun Wang, Rizen Guo, Shuigeng Zhou Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14184v3 Existing state-of-the-art image tokenization methods leverage diverse semantic features from pre-trained vision models for additional supervision, to expand the distribution of latent representations and thereby improve the quality of image reconstruction and generation. These methods employ a locally supervised approach for semantic supervision, which limits the uniformity of semantic distribution. However, VA-VAE proves that a more uniform feature distribution yields better generation performance. In this work, we introduce a Global Perspective Tokenizer (GloTok), which utilizes global relational information to model a more uniform semantic distribution of tokenized features. Specifically, a codebook-wise histogram relation learning method is proposed to transfer the semantics, which are modeled by pre-trained models on the entire dataset, to the semantic codebook. Then, we design a residual learning module that recovers the fine-grained details to minimize the reconstruction error caused by quantization. Through the above design, GloTok delivers more uniformly distributed semantic latent representations, which facilitates the training of autoregressive (AR) models for generating high-quality images without requiring direct access to pre-trained models during the training process. Experiments on the standard ImageNet-1k benchmark clearly show that our proposed method achieves state-of-the-art reconstruction performance and generation quality. --- ### UniSER: A Foundation Model for Unified Soft Effects Removal Authors: Jingdong Zhang, Lingzhi Zhang, Qing Liu, Mang Tik Chiu, Connelly Barnes, Yizhou Wang, Haoran You, Xiaoyang Liu, Yuqian Zhou, Zhe Lin, Eli Shechtman, Sohrab Amirghodsi et al. Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14183v3 Digital images are often degraded by soft effects such as lens flare, haze, shadows, and reflections, which reduce aesthetics even though the underlying pixels remain partially visible. The prevailing works address these degradations in isolation, developing highly specialized, specialist models that lack scalability and fail to exploit the shared underlying essences of these restoration problems. Meanwhile, although recent large-scale generalist models (e.g., GPT-4o, Flux Kontext, Nano Banana) offer powerful text-driven editing capabilities, they heavily rely on detailed prompts and often fail to achieve robust removal on such fine-grained tasks while preserving the scene's identity. Leveraging the common essence of soft effects, i.e., semi-transparent occlusions, we introduce a foundational versatile model UniSER, capable of addressing diverse degradations caused by soft effects within a single framework. Our methodology centers on curating a massive 3.8M-pair dataset to ensure robustness and generalization, which includes novel, physically-plausible data to fill critical gaps in public benchmarks, and a tailored training pipeline that fine-tunes a Diffusion Transformer to learn robust restoration priors from this diverse data, integrating fine-grained mask and strength controls. This synergistic approach allows UniSER to significantly outperform both specialist and generalist models, achieving robust, high-fidelity restoration in the wild. --- ### Harnessing Deep LLM Participation for Robust Entity Linking Authors: Jiajun Hou, Chenyu Zhang, Rui Meng Published: 2025-11-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.14181v1 Entity Linking (EL), the task of mapping textual entity mentions to their corresponding entries in knowledge bases, constitutes a fundamental component of natural language understanding. Recent advancements in Large Language Models (LLMs) have demonstrated remarkable potential for enhancing EL performance. Prior research has leveraged LLMs to improve entity disambiguation and input representation, yielding significant gains in accuracy and robustness. However, these approaches typically apply LLMs to isolated stages of the EL task, failing to fully integrate their capabilities throughout the entire process. In this work, we introduce DeepEL, a comprehensive framework that incorporates LLMs into every stage of the entity linking task. Furthermore, we identify that disambiguating entities in isolation is insufficient for optimal performance. To address this limitation, we propose a novel self-validation mechanism that utilizes global contextual information, enabling LLMs to rectify their own predictions and better recognize cohesive relationships among entities within the same sentence. Extensive empirical evaluation across ten benchmark datasets demonstrates that DeepEL substantially outperforms existing state-of-the-art methods, achieving an average improvement of 2.6\% in overall F1 score and a remarkable 4% gain on out-of-domain datasets. These results underscore the efficacy of deep LLM integration in advancing the state-of-the-art in entity linking. --- ### DoGCLR: Dominance-Game Contrastive Learning Network for Skeleton-Based Action Recognition Authors: Yanshan Li, Ke Ma, Miaomiao Wei, Linhui Dai Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14179v2 Existing self-supervised contrastive learning methods for skeleton-based action recognition often process all skeleton regions uniformly, and adopt a first-in-first-out (FIFO) queue to store negative samples, which leads to motion information loss and non-optimal negative sample selection. To address these challenges, this paper proposes Dominance-Game Contrastive Learning network for skeleton-based action Recognition (DoGCLR), a self-supervised framework based on game theory. DoGCLR models the construction of positive and negative samples as a dynamic Dominance Game, where both sample types interact to reach an equilibrium that balances semantic preservation and discriminative strength. Specifically, a spatio-temporal dual weight localization mechanism identifies key motion regions and guides region-wise augmentations to enhance motion diversity while maintaining semantics. In parallel, an entropy-driven dominance strategy manages the memory bank by retaining high entropy (hard) negatives and replacing low-entropy (weak) ones, ensuring consistent exposure to informative contrastive signals. Extensive experiments are conducted on NTU RGB+D and PKU-MMD datasets. On NTU RGB+D 60 X-Sub/X-View, DoGCLR achieves 81.1%/89.4% accuracy, and on NTU RGB+D 120 X-Sub/X-Set, DoGCLR achieves 71.2%/75.5% accuracy, surpassing state-of-the-art methods by 0.1%, 2.7%, 1.1%, and 2.3%, respectively. On PKU-MMD Part I/Part II, DoGCLR performs comparably to the state-of-the-art methods and achieves a 1.9% higher accuracy on Part II, highlighting its strong robustness on more challenging scenarios. --- ### Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion Authors: Zhuo Li, Junjia Liu, Zhipeng Dong, Tao Teng, Quentin Rouxel, Darwin Caldwell, Fei Chen Published: 2025-11-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2511.14178v2 Vision-Language-Action (VLA) models have demonstrated significant potential in real-world robotic manipulation. However, pre-trained VLA policies still suffer from substantial performance degradation during downstream deployment. Although fine-tuning can mitigate this issue, its reliance on costly demonstration collection and intensive computation makes it impractical in real-world settings. In this work, we introduce VLA-Pilot, a plug-and-play inference-time policy steering method for zero-shot deployment of pre-trained VLA without any additional fine-tuning or data collection. We evaluate VLA-Pilot on six real-world downstream manipulation tasks across two distinct robotic embodiments, encompassing both in-distribution and out-of-distribution scenarios. Experimental results demonstrate that VLA-Pilot substantially boosts the success rates of off-the-shelf pre-trained VLA policies, enabling robust zero-shot generalization to diverse tasks and embodiments. Experimental videos and code are available at: https://rip4kobe.github.io/vla-pilot/. --- ### SymLoc: Symbolic Localization of Hallucination across HaluEval and TruthfulQA Authors: Naveen Lamba, Sanju Tiwari, Manas Gaur Published: 2025-11-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.14172v1 LLMs still struggle with hallucination, especially when confronted with symbolic triggers like modifiers, negation, numbers, exceptions, and named entities. Yet, we lack a clear understanding of where these symbolic hallucinations originate, making it crucial to systematically handle such triggers and localize the emergence of hallucination inside the model. While prior work explored localization using statistical techniques like LSC and activation variance analysis, these methods treat all tokens equally and overlook the role symbolic linguistic knowledge plays in triggering hallucinations. So far, no approach has investigated how symbolic elements specifically drive hallucination failures across model layers, nor has symbolic linguistic knowledge been used as the foundation for a localization framework. We propose the first symbolic localization framework that leverages symbolic linguistic and semantic knowledge to meaningfully trace the development of hallucinations across all model layers. By focusing on how models process symbolic triggers, we analyze five models using HaluEval and TruthfulQA. Our symbolic knowledge approach reveals that attention variance for these linguistic elements explodes to critical instability in early layers (2-4), with negation triggering catastrophic variance levels, demonstrating that symbolic semantic processing breaks down from the very beginning. Through the lens of symbolic linguistic knowledge, despite larger model sizes, hallucination rates remain consistently high (78.3%-83.7% across Gemma variants), with steep attention drops for symbolic semantic triggers throughout deeper layers. Our findings demonstrate that hallucination is fundamentally a symbolic linguistic processing failure, not a general generation problem, revealing that symbolic semantic knowledge provides the key to understanding and localizing hallucination mechanisms in LLMs. --- ### AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs Authors: Xinliang Zhang, Lei Zhu, Hangzhou He, Shuang Zeng, Ourui Fu, Jiakui Hu, Zhengjian Yao, Yanye Lu Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14169v2 Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural paradigm. However, patch-level tokenization leads to a quadratic growth in image tokens, burdening MLLMs' understanding and reasoning with enormous computation and memory. Additionally, the traditional patch-wise scanning tokenization workflow misaligns with the human vision cognition system, further leading to hallucination and computational redundancy. To address this issue, we propose an object-level token merging strategy for Adaptive Token compression, revealing the consistency with human vision system. The experiments are conducted on multiple comprehensive benchmarks, which show that our approach averagely, utilizes only 10% tokens while achieving almost 96% of the vanilla model's performance. More extensive experimental results in comparison with relevant works demonstrate the superiority of our method in balancing compression ratio and performance. Our code will be available. --- ### Certified Signed Graph Unlearning Authors: Junpeng Zhao, Lin Li, Kaixi Hu, Kaize Shi, Jingling Yuan Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.14168v1 Signed graphs model complex relationships through positive and negative edges, with widespread real-world applications. Given the sensitive nature of such data, selective removal mechanisms have become essential for privacy protection. While graph unlearning enables the removal of specific data influences from Graph Neural Networks (GNNs), existing methods are designed for conventional GNNs and overlook the unique heterogeneous properties of signed graphs. When applied to Signed Graph Neural Networks (SGNNs), these methods lose critical sign information, degrading both model utility and unlearning effectiveness. To address these challenges, we propose Certified Signed Graph Unlearning (CSGU), which provides provable privacy guarantees while preserving the sociological principles underlying SGNNs. CSGU employs a three-stage method: (1) efficiently identifying minimal influenced neighborhoods via triangular structures, (2) applying sociological theories to quantify node importance for optimal privacy budget allocation, and (3) performing importance-weighted parameter updates to achieve certified modifications with minimal utility degradation. Extensive experiments demonstrate that CSGU outperforms existing methods, achieving superior performance in both utility preservation and unlearning effectiveness on SGNNs. --- ### Selective Weak-to-Strong Generalization Authors: Hao Lang, Fei Huang, Yongbin Li Published: 2025-11-18 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.14166v1 Future superhuman models will surpass the ability of humans and humans will only be able to \textit{weakly} supervise superhuman models. To alleviate the issue of lacking high-quality data for model alignment, some works on weak-to-strong generalization (W2SG) finetune a strong pretrained model with a weak supervisor so that it can generalize beyond weak supervision. However, the invariable use of weak supervision in existing methods exposes issues in robustness, with a proportion of weak labels proving harmful to models. In this paper, we propose a selective W2SG framework to avoid using weak supervision when unnecessary. We train a binary classifier P(IK) to identify questions that a strong model can answer and use its self-generated labels for alignment. We further refine weak labels with a graph smoothing method. Extensive experiments on three benchmarks show that our method consistently outperforms competitive baselines. Further analyses show that P(IK) can generalize across tasks and difficulties, which indicates selective W2SG can help superalignment. --- ### RoboTidy : A 3D Gaussian Splatting Household Tidying Benchmark for Embodied Navigation and Action Authors: Xiaoquan Sun, Ruijian Zhang, Kang Pang, Bingchen Miao, Yuxiang Tan, Zhen Yang, Ming Li, Jiayu Chen Published: 2025-11-18 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.14161v2 Household tidying is an important application area, yet current benchmarks neither model user preferences nor support mobility, and they generalize poorly, making it hard to comprehensively assess integrated language-to-action capabilities. To address this, we propose RoboTidy, a unified benchmark for language-guided household tidying that supports Vision-Language-Action (VLA) and Vision-Language-Navigation (VLN) training and evaluation. RoboTidy provides 500 photorealistic 3D Gaussian Splatting (3DGS) household scenes (covering 500 objects and containers) with collisions, formulates tidying as an "Action (Object, Container)" list, and supplies 6.4k high-quality manipulation demonstration trajectories and 1.5k naviagtion trajectories to support both few-shot and large-scale training. We also deploy RoboTidy in the real world for object tidying, establishing an end-to-end benchmark for household tidying. RoboTidy offers a scalable platform and bridges a key gap in embodied AI by enabling holistic and realistic evaluation of language-guided robots. --- ### MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs Authors: Huiyi Chen, Jiawei Peng, Dehai Min, Changchang Sun, Kaijie Chen, Yan Yan, Xu Yang, Lu Cheng Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14159v4 Evaluating the robustness of Large Vision-Language Models (LVLMs) is essential for their continued development and responsible deployment in real-world applications. However, existing robustness benchmarks typically focus on hallucination or misleading textual inputs, while largely overlooking the equally critical challenge posed by misleading visual inputs in assessing visual understanding. To fill this important gap, we introduce MVI-Bench, the first comprehensive benchmark specially designed for evaluating how Misleading Visual Inputs undermine the robustness of LVLMs. Grounded in fundamental visual primitives, the design of MVI-Bench centers on three hierarchical levels of misleading visual inputs: Visual Concept, Visual Attribute, and Visual Relationship. Using this taxonomy, we curate six representative categories and compile 1,248 expertly annotated VQA instances. To facilitate fine-grained robustness evaluation, we further introduce MVI-Sensitivity, a novel metric that characterizes LVLM robustness at a granular level. Empirical results across 18 state-of-the-art LVLMs uncover pronounced vulnerabilities to misleading visual inputs, and our in-depth analyses on MVI-Bench provide actionable insights that can guide the development of more reliable and robust LVLMs. The benchmark and codebase can be accessed at https://github.com/chenyil6/MVI-Bench. --- ### Learning Representation and Synergy Invariances: A Povable Framework for Generalized Multimodal Face Anti-Spoofing Authors: Xun Lin, Shuai Wang, Yi Yu, Zitong Yu, Jiale Zhou, Yizhong Liu, Xiaochun Cao, Alex Kot, Yefeng Zheng Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14157v1 Multimodal Face Anti-Spoofing (FAS) methods, which integrate multiple visual modalities, often suffer even more severe performance degradation than unimodal FAS when deployed in unseen domains. This is mainly due to two overlooked risks that affect cross-domain multimodal generalization. The first is the modal representation invariant risk, i.e., whether representations remain generalizable under domain shift. We theoretically show that the inherent class asymmetry in FAS (diverse spoofs vs. compact reals) enlarges the upper bound of generalization error, and this effect is further amplified in multimodal settings. The second is the modal synergy invariant risk, where models overfit to domain-specific inter-modal correlations. Such spurious synergy cannot generalize to unseen attacks in target domains, leading to performance drops. To solve these issues, we propose a provable framework, namely Multimodal Representation and Synergy Invariance Learning (RiSe). For representation risk, RiSe introduces Asymmetric Invariant Risk Minimization (AsyIRM), which learns an invariant spherical decision boundary in radial space to fit asymmetric distributions, while preserving domain cues in angular space. For synergy risk, RiSe employs Multimodal Synergy Disentanglement (MMSD), a self-supervised task enhancing intrinsic, generalizable modal features via cross-sample mixing and disentanglement. Theoretical analysis and experiments verify RiSe, which achieves state-of-the-art cross-domain performance. --- ### A Comprehensive Study of Implicit and Explicit Biases in Large Language Models Authors: Fatima Kazi, Alex Young, Yash Inani, Setareh Rafatirad Published: 2025-11-18 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2511.14153v1 Large Language Models (LLMs) inherit explicit and implicit biases from their training datasets. Identifying and mitigating biases in LLMs is crucial to ensure fair outputs, as they can perpetuate harmful stereotypes and misinformation. This study highlights the need to address biases in LLMs amid growing generative AI. We studied bias-specific benchmarks such as StereoSet and CrowSPairs to evaluate the existence of various biases in multiple generative models such as BERT and GPT 3.5. We proposed an automated Bias-Identification Framework to recognize various social biases in LLMs such as gender, race, profession, and religion. We adopted a two-pronged approach to detect explicit and implicit biases in text data. Results indicated fine-tuned models struggle with gender biases but excelled at identifying and avoiding racial biases. Our findings illustrated that despite having some success, LLMs often over-relied on keywords. To illuminate the capability of the analyzed LLMs in detecting implicit biases, we employed Bag-of-Words analysis and unveiled indications of implicit stereotyping within the vocabulary. To bolster the model performance, we applied an enhancement strategy involving fine-tuning models using prompting techniques and data augmentation of the bias benchmarks. The fine-tuned models exhibited promising adaptability during cross-dataset testing and significantly enhanced performance on implicit bias benchmarks, with performance gains of up to 20%. --- ### Wave-Former: Through-Occlusion 3D Reconstruction via Wireless Shape Completion Authors: Laura Dodds, Maisy Lam, Waleed Akbar, Yibo Cheng, Fadel Adib Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14152v2 We present Wave-Former, a novel method capable of high-accuracy 3D shape reconstruction for completely occluded, diverse, everyday objects. This capability can open new applications spanning robotics, augmented reality, and logistics. Our approach leverages millimeter-wave (mmWave) wireless signals, which can penetrate common occlusions and reflect off hidden objects. In contrast to past mmWave reconstruction methods, which suffer from limited coverage and high noise, Wave-Former introduces a physics-aware shape completion model capable of inferring full 3D geometry. At the heart of Wave-Former's design is a novel three-stage pipeline which bridges raw wireless signals with recent advancements in vision-based shape completion by incorporating physical properties of mmWave signals. The pipeline proposes candidate geometric surfaces, employs a transformer-based shape completion model designed specifically for mmWave signals, and finally performs entropy-guided surface selection. This enables Wave-Former to be trained using entirely synthetic point-clouds, while demonstrating impressive generalization to real-world data. In head-to-head comparisons with state-of-the-art baselines, Wave-Former raises recall from 54% to 72% while maintaining a high precision of 85%. --- ### iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion Authors: Hao Wang, Linqing Zhao, Xiuwei Xu, Jiwen Lu, Haibin Yan Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14149v1 Recent trends in SLAM and visual navigation have embraced 3D Gaussians as the preferred scene representation, highlighting the importance of estimating camera poses from a single image using a pre-built Gaussian model. However, existing approaches typically rely on an iterative \textit{render-compare-refine} loop, where candidate views are first rendered using NeRF or Gaussian Splatting, then compared against the target image, and finally, discrepancies are used to update the pose. This multi-round process incurs significant computational overhead, hindering real-time performance in robotics. In this paper, we propose iGaussian, a two-stage feed-forward framework that achieves real-time camera pose estimation through direct 3D Gaussian inversion. Our method first regresses a coarse 6DoF pose using a Gaussian Scene Prior-based Pose Regression Network with spatial uniform sampling and guided attention mechanisms, then refines it through feature matching and multi-model fusion. The key contribution lies in our cross-correlation module that aligns image embeddings with 3D Gaussian attributes without differentiable rendering, coupled with a Weighted Multiview Predictor that fuses features from Multiple strategically sampled viewpoints. Experimental results on the NeRF Synthetic, Mip-NeRF 360, and T\&T+DB datasets demonstrate a significant performance improvement over previous methods, reducing median rotation errors to 0.2° while achieving 2.87 FPS tracking on mobile robots, which is an impressive 10 times speedup compared to optimization-based approaches. Code: https://github.com/pythongod-exe/iGaussian --- ### AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models Authors: Yuhua Jiang, Shuang Cheng, Yan Ding, Feifei Gao, Biqing Qi Published: 2025-11-18 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.14148v2 Vision-language-action (VLA) models have recently emerged as a powerful paradigm for building generalist robots. However, traditional VLA models that generate actions through flow matching (FM) typically rely on rigid and uniform time schedules, i.e., synchronous FM (SFM). Without action context awareness and asynchronous self-correction, SFM becomes unstable in long-horizon tasks, where a single action error can cascade into failure. In this work, we propose asynchronous flow matching VLA (AsyncVLA), a novel framework that introduces temporal flexibility in asynchronous FM (AFM) and enables self-correction in action generation. AsyncVLA breaks from the vanilla SFM in VLA models by generating the action tokens in a non-uniform time schedule with action context awareness. Besides, our method introduces the confidence rater to extract confidence of the initially generated actions, enabling the model to selectively refine inaccurate action tokens before execution. Moreover, we propose a unified training procedure for SFM and AFM that endows a single model with both modes, improving KV-cache utilization. Extensive experiments on robotic manipulation benchmarks demonstrate that AsyncVLA is data-efficient and exhibits self-correction ability. AsyncVLA outperforms existing methods across both simulation and real-world evaluations. Our code is available at https://github.com/YuhuaJiang2002/AsyncVLA. --- ### Imaging with super-resolution in changing random media Authors: Alexander Christie, Matan Leibovich, Miguel Moscoso, Alexei Novikov, George Papanicolaou, Chrysoula Tsogka Published: 2025-11-18 Categories: physics.optics, cs.LG arXiv: https://arxiv.org/abs/2511.14147v2 We develop an imaging algorithm that exploits strong scattering to achieve super-resolution in changing random media. The method processes large and diverse array datasets using sparse dictionary learning, clustering, and multidimensional scaling. Starting from random initializations, the algorithm reliably extracts the unknown medium properties necessary for accurate imaging using back-propagation, $\ell_2$ or $\ell_1$ methods. Remarkably, scattering enhances resolution beyond homogeneous medium limits. When abundant data are available, the algorithm allows the realization of super-resolution in imaging. --- ### SCOPE: Spectral Concentration by Distributionally Robust Joint Covariance-Precision Estimation Authors: Renjie Chen, Viet Anh Nguyen, Huifu Xu Published: 2025-11-18 Categories: stat.ML, cs.LG, math.OC arXiv: https://arxiv.org/abs/2511.14146v1 We propose a distributionally robust formulation for simultaneously estimating the covariance matrix and the precision matrix of a random vector.The proposed model minimizes the worst-case weighted sum of the Frobenius loss of the covariance estimator and Stein's loss of the precision matrix estimator against all distributions from an ambiguity set centered at the nominal distribution. The radius of the ambiguity set is measured via convex spectral divergence. We demonstrate that the proposed distributionally robust estimation model can be reduced to a convex optimization problem, thereby yielding quasi-analytical estimators. The joint estimators are shown to be nonlinear shrinkage estimators. The eigenvalues of the estimators are shrunk nonlinearly towards a positive scalar, where the scalar is determined by the weight coefficient of the loss terms. By tuning the coefficient carefully, the shrinkage corrects the spectral bias of the empirical covariance/precision matrix estimator. By this property, we call the proposed joint estimator the Spectral concentrated COvariance and Precision matrix Estimator (SCOPE). We demonstrate that the shrinkage effect improves the condition number of the estimator. We provide a parameter-tuning scheme that adjusts the shrinkage target and intensity that is asymptotically optimal. Numerical experiments on synthetic and real data show that our shrinkage estimators perform competitively against state-of-the-art estimators in practical applications. --- ### Applying Relation Extraction and Graph Matching to Answering Multiple Choice Questions Authors: Naoki Shimoda, Akihiro Yamamoto Published: 2025-11-18 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2511.14144v1 In this research, we combine Transformer-based relation extraction with matching of knowledge graphs (KGs) and apply them to answering multiple-choice questions (MCQs) while maintaining the traceability of the output process. KGs are structured representations of factual knowledge consisting of entities and relations. Due to the high construction cost, they had been regarded as static databases with validated links. However, the recent development of Transformer-based relation extraction (RE) methods has enabled us to generate KGs dynamically by giving them natural language texts, and thereby opened the possibility for representing the meaning of the input sentences with the created KGs. Using this effect, we propose a method that answers MCQs in the "fill-in-the-blank" format, taking care of the point that RE methods generate KGs that represent false information if provided with factually incorrect texts. We measure the truthfulness of each question sentence by (i) converting the sentence into a relational graph using an RE method and (ii) verifying it against factually correct KGs under the closed-world assumption. The experimental results demonstrate that our method correctly answers up to around 70% of the questions, while providing traceability of the procedure. We also highlight that the question category has a vast influence on the accuracy. --- ### SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM Authors: An Yu, Weiheng Lu, Jian Li, Zhenfei Zhang, Yunhang Shen, Felix X. -F. Ye, Ming-Ching Chang Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.14143v2 Video Moment Retrieval is a task in video understanding that aims to localize a specific temporal segment in an untrimmed video based on a natural language query. Despite recent progress in moment retrieval from videos using both traditional techniques and Multimodal Large Language Models (MLLM), most existing methods still rely on coarse temporal understanding and a single visual modality, limiting performance on complex videos. To address this, we introduce \textit{S}hot-aware \textit{M}ultimodal \textit{A}udio-enhanced \textit{R}etrieval of \textit{T}emporal \textit{S}egments (SMART), an MLLM-based framework that integrates audio cues and leverages shot-level temporal structure. SMART enriches multimodal representations by combining audio and visual features while applying \textbf{Shot-aware Token Compression}, which selectively retains high-information tokens within each shot to reduce redundancy and preserve fine-grained temporal details. We also refine prompt design to better utilize audio-visual cues. Evaluations on Charades-STA and QVHighlights show that SMART achieves significant improvements over state-of-the-art methods, including a 1.61\% increase in R1@0.5 and 2.59\% gain in R1@0.7 on Charades-STA. --- ### From Graphs to Hypergraphs: Enhancing Aspect-Based Sentiment Analysis via Multi-Level Relational Modeling Authors: Omkar Mahesh Kashyap, Padegal Amit, Madhav Kashyap, Ashwini M Joshi, Shylaja SS Published: 2025-11-18 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.14142v1 Aspect-Based Sentiment Analysis (ABSA) predicts sentiment polarity for specific aspect terms, a task made difficult by conflicting sentiments across aspects and the sparse context of short texts. Prior graph-based approaches model only pairwise dependencies, forcing them to construct multiple graphs for different relational views. These introduce redundancy, parameter overhead, and error propagation during fusion, limiting robustness in short-text, low-resource settings. We present HyperABSA, a dynamic hypergraph framework that induces aspect-opinion structures through sample-specific hierarchical clustering. To construct these hyperedges, we introduce a novel acceleration-fallback cutoff for hierarchical clustering, which adaptively determines the level of granularity. Experiments on three benchmarks (Lap14, Rest14, MAMS) show consistent improvements over strong graph baselines, with substantial gains when paired with RoBERTa backbones. These results position dynamic hypergraph construction as an efficient, powerful alternative for ABSA, with potential extensions to other short-text NLP tasks. --- ### Unifying Convolution and Attention via Convolutional Nearest Neighbors Authors: Mingi Kang, Jeová Farias Sales Rocha Neto Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14137v3 Convolutional Neural Networks and Vision Transformers are the two dominant architectural families in computer vision, defined by spatially local convolution and global self-attention respectively. Despite their apparent differences, we show that both operations are special cases of a single $k$-nearest neighbor aggregation framework: convolution selects neighbors by spatial proximity while attention selects by feature similarity, placing them at two ends of a shared operational spectrum. We introduce Convolutional Nearest Neighbors (ConvNN), a unified framework that exactly recovers standard and depthwise convolution, self-attention, and sparse attention variants including KVT-attention as special cases, and exposes the design space of neighbor-selection strategies between them through configurable similarity functions, positional encodings, and aggregation kernels. We validate ConvNN on ImageNet-1K classification across two complementary architectures: a hybrid branching layer in ResNet-50 that combines local and global feature learning, improving top-1 accuracy by 3.0% over the ResNet-50 baseline, and ConvNN-attention in ViT-Base that achieves 81.64% top-1 accuracy, surpassing standard multi-head self-attention by 0.7%. Together, these results demonstrate that ConvNN provides a principled foundation for designing operations that bridge convolutional and attention-based computation. --- ### Beyond Accuracy: A Multi-Dimensional Framework for Evaluating Enterprise Agentic AI Systems Authors: Sushant Mehta Published: 2025-11-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.14136v1 Current agentic AI benchmarks predominantly evaluate task completion accuracy, while overlooking critical enterprise requirements such as cost-efficiency, reliability, and operational stability. Through systematic analysis of 12 main benchmarks and empirical evaluation of state-of-the-art agents, we identify three fundamental limitations: (1) absence of cost-controlled evaluation leading to 50x cost variations for similar precision, (2) inadequate reliability assessment where agent performance drops from 60\% (single run) to 25\% (8-run consistency), and (3) missing multidimensional metrics for security, latency, and policy compliance. We propose \textbf{CLEAR} (Cost, Latency, Efficacy, Assurance, Reliability), a holistic evaluation framework specifically designed for enterprise deployment. Evaluation of six leading agents on 300 enterprise tasks demonstrates that optimizing for accuracy alone yields agents 4.4-10.8x more expensive than cost-aware alternatives with comparable performance. Expert evaluation (N=15) confirms that CLEAR better predicts production success (correlation $ρ=0.83$) compared to accuracy-only evaluation ($ρ=0.41$). ---