# Research Papers — 2025-11 · bundle page 3 of 197 > Full-text markdown of papers #101–150 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/3 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/2.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/4.md) ### Dr.Mi-Bench: A Modular-integrated Benchmark for Scientific Deep Research Agent Authors: Zhihan Guo, Feiyang Xu, Yifan Li, Muzhi Li, Shuai Zou, Jiele Wu, Han Shi, Haoli Bai, Ho-fung Leung, Irwin King Published: 2025-11-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.00986v1 The explosive growth in academic literature necessitates automated deep research (DR) agents, yet their evaluation remains a significant challenge. First, existing benchmarks often focus narrowly on retrieval while neglecting high-level planning and reasoning. Second, existing benchmarks favor general domains over the scientific domains that are the core application for DR agents. To address these gaps, we introduce Dr.Mi-Bench, a Modular-integrated benchmark for scientific DR agents. Grounded in academic literature, our benchmark uses a human-annotated dataset of 200 instances across 10 scientific domains, including both research and review papers. Besides, we also propose a Modular-integrated Evaluation Paradigm for DR Agents (Dr.Mi-Eval), a novel modular-integrated evaluation paradigm, which leverages the rich structure of academic papers to assess the core competencies of planning, retrieval, and reasoning through two complementary modes: an end-to-end evaluation for DR agents and an isolated evaluation for foundational LLMs as potential backbones. Experimental results reveal a fragmented performance landscape: agents exhibit specialized strengths but share critical weaknesses, most notably in performing the multi-source retrieval required for review-style tasks and performing consistently across diverse scientific fields. Moreover, improving high-level planning capability is the crucial factor for unlocking the reasoning potential of foundational LLMs as backbones. By exposing these actionable failure modes, Dr.Mi-Bench provides a diagnostic tool to guide the development of more reliable academic research assistants. --- ### An Approach to Variable Clustering: K-means in Transposed Data and its Relationship with Principal Component Analysis Authors: Victor Saquicela, Kenneth Palacio-Baus, Mario Chifla Published: 2025-11-30 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.00979v1 Principal Component Analysis (PCA) and K-means constitute fundamental techniques in multivariate analysis. Although they are frequently applied independently or sequentially to cluster observations, the relationship between them, especially when K-means is used to cluster variables rather than observations, has been scarcely explored. This study seeks to address this gap by proposing an innovative method that analyzes the relationship between clusters of variables obtained by applying K-means on transposed data and the principal components of PCA. Our approach involves applying PCA to the original data and K-means to the transposed data set, where the original variables are converted into observations. The contribution of each variable cluster to each principal component is then quantified using measures based on variable loadings. This process provides a tool to explore and understand the clustering of variables and how such clusters contribute to the principal dimensions of variation identified by PCA. --- ### Subgroup Validity in Machine Learning for Echocardiogram Data Authors: Cynthia Feeney, Shane Williams, Benjamin S. Wessler, Michael C. Hughes Published: 2025-11-30 Categories: cs.LG, stat.OT arXiv: https://arxiv.org/abs/2512.00976v1 Echocardiogram datasets enable training deep learning models to automate interpretation of cardiac ultrasound, thereby expanding access to accurate readings of diagnostically-useful images. However, the gender, sex, race, and ethnicity of the patients in these datasets are underreported and subgroup-specific predictive performance is unevaluated. These reporting deficiencies raise concerns about subgroup validity that must be studied and addressed before model deployment. In this paper, we show that current open echocardiogram datasets are unable to assuage subgroup validity concerns. We improve sociodemographic reporting for two datasets: TMED-2 and MIMIC-IV-ECHO. Analysis of six open datasets reveals no consideration of gender-diverse patients and insufficient patient counts for many racial and ethnic groups. We further perform an exploratory subgroup analysis of two published aortic stenosis detection models on TMED-2. We find insufficient evidence for subgroup validity for sex, racial, and ethnic subgroups. Our findings highlight that more data for underrepresented subgroups, improved demographic reporting, and subgroup-focused analyses are needed to prove subgroup validity in future work. --- ### MM-ACT: Learn from Multimodal Parallel Generation to Act Authors: Haotian Liang, Xinyi Chen, Bin Wang, Mingkang Chen, Yitian Liu, Yuhao Zhang, Zanxin Chen, Tianshuo Yang, Yilun Chen, Jiangmiao Pang, Dong Liu, Xiaokang Yang et al. Published: 2025-11-30 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2512.00975v2 A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA) model that integrates text, image, and action in shared token space and performs generation across all three modalities. MM-ACT adopts a re-mask parallel decoding strategy for text and image generation, and employs a one-step parallel decoding strategy for action generation to improve efficiency. We introduce Context-Shared Multimodal Learning, a unified training paradigm that supervises generation in all three modalities from a shared context, enhancing action generation through cross-modal learning. Experiments were conducted on the LIBERO simulation and Franka real-robot setups as well as RoboTwin2.0 to assess in-domain and out-of-domain performances respectively. Our approach achieves a success rate of 96.3% on LIBERO, 72.0% across three tasks of real Franka, and 52.38% across eight bimanual tasks of RoboTwin2.0 with an additional gain of 9.25% from cross-modal learning. We release our codes, models and data at https://github.com/HHYHRHY/MM-ACT. --- ### MM-ACT: Learn from Multimodal Parallel Generation to Act Authors: Haotian Liang, Xinyi Chen, Bin Wang, Mingkang Chen, Yitian Liu, Yuhao Zhang, Zanxin Chen, Tianshuo Yang, Yilun Chen, Jiangmiao Pang, Dong Liu, Xiaokang Yang et al. Published: 2025-11-30 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2512.00975v1 A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA) model that integrates text, image, and action in shared token space and performs generation across all three modalities. MM-ACT adopts a re-mask parallel decoding strategy for text and image generation, and employs a one-step parallel decoding strategy for action generation to improve efficiency. We introduce Context-Shared Multimodal Learning, a unified training paradigm that supervises generation in all three modalities from a shared context, enhancing action generation through cross-modal learning. Experiments were conducted on the LIBERO simulation and Franka real-robot setups as well as RoboTwin2.0 to assess in-domain and out-of-domain performances respectively. Our approach achieves a success rate of 96.3% on LIBERO, 72.0% across three tasks of real Franka, and 52.38% across eight bimanual tasks of RoboTwin2.0 with an additional gain of 9.25% from cross-modal learning. We release our codes, models and data at https://github.com/HHYHRHY/MM-ACT. --- ### Integrating a Causal Foundation Model into a Prescriptive Maintenance Framework for Optimising Production-Line OEE Authors: Felix Saretzky, Lucas Andersen, Thomas Engel, Fazel Ansari Published: 2025-11-30 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2512.00969v2 The transition to prescriptive maintenance (PsM) in manufacturing is critically constrained by a dependence on predictive models. Such purely predictive models tend to capture statistical associations in the data without identifying the underlying causal drivers of failure, which can lead to costly misdiagnoses and ineffective measures. This fundamental limitation results in a key challenge: while we can predict that a failure may occur, we lack a systematic method to understand why a failure occurs. This paper proposes a model based on causal machine learning to bridge this gap. Our objective is to move beyond diagnosis to active prescription by simulating and evaluating potential fixes to optimise KPIs such as Overall Equipment Effectiveness (OEE). For this purpose, a pre-trained causal foundation model is used as a ``what-if'' simulator to estimate the effects of potential fixes. By estimating the causal effect of each intervention on system-level KPIs, specific actions can be recommended for the production line. This can help identify plausible root causes and quantify their operational impact. The model is evaluated using semi-synthetic manufacturing data and compared with non-causal and causal baseline machine learning models. This paper provides a technical basis for a human-centred approach, allowing engineers to test potential solutions in a causal environment to make more effective operational decisions and reduce costly downtimes. --- ### Integrating Causal Foundation Model in Prescriptive Maintenance Framework for Optimizing Production Line OEE Authors: Felix Saretzky, Lucas Andersen, Thomas Engel, Fazel Ansari Published: 2025-11-30 Categories: cs.AI, eess.SY arXiv: https://arxiv.org/abs/2512.00969v1 The transition to prescriptive maintenance in manufacturing is critically constrained by a dependence on predictive models. These models tend to rely on spurious correlations rather than identifying the true causal drivers of failures, often leading to costly misdiagnoses and ineffective interventions. This fundamental limitation results in a key-challenge: while we can predict that a failure may occur, we lack a systematic method to understand why a failure occurs, thereby providing the basis for identifying the most effective intervention. This paper proposes a model based on causal machine learning to bridge this gap. Our objective is to move beyond diagnosis to active prescription by simulating and evaluating potential fixes toward optimizing KPIs such as Overall Equipment Effectiveness (OEE). For this purpose a pre-trained causal foundation model is used as a "what-if" model to estimate the effects of potential fixes. By measuring the causal effect of each intervention on system-level KPIs, it provides a data-driven ranking of actions to recommend at the production line. This process not only identifies root causes but also quantifies their operational impact. The model is evaluated using semi-synthetic manufacturing data and compared with a baseline machine learning model. This paper sets the technical basis for a robust prescriptive maintenance framework, allowing engineers to test potential solutions in a causal environment to make more effective operational decisions and reduce costly downtimes. --- ### Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search Authors: Ziyang Zeng, Heming Jing, Jindong Chen, Xiangli Li, Hongyu Liu, Yixuan He, Zhengyu Li, Yige Sun, Zheyong Xie, Yuqing Yang, Shaosheng Cao, Jun Fan et al. Published: 2025-11-30 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.00968v2 Ranking relevance is a fundamental task in search engines, aiming to identify the items most relevant to a given user query. Traditional relevance models typically produce scalar scores or directly predict relevance labels, limiting both interpretability and the modeling of complex relevance signals. Inspired by recent advances in Chain-of-Thought (CoT) reasoning for complex tasks, we investigate whether explicit reasoning can enhance both interpretability and performance in relevance modeling. However, existing reasoning-based Generative Relevance Models (GRMs) primarily rely on supervised fine-tuning on large amounts of human-annotated or synthetic CoT data, which often leads to limited generalization. Moreover, domain-agnostic, free-form reasoning tends to be overly generic and insufficiently grounded, limiting its potential to handle the diverse and ambiguous cases prevalent in open-domain search. In this work, we formulate relevance modeling in Xiaohongshu search as a reasoning task and introduce a Reinforcement Learning (RL)-based training framework to enhance the grounded reasoning capabilities of GRMs. Specifically, we incorporate practical business-specific relevance criteria into the multi-step reasoning prompt design and propose Stepwise Advantage Masking (SAM), a lightweight process-supervision strategy which facilitates effective learning of these criteria through improved credit assignment. To enable industrial deployment, we further distill the large-scale RL-tuned model to a lightweight version suitable for real-world search systems. Extensive offline evaluations and online A/B tests demonstrate that our approach consistently delivers significant improvements across key relevance and business metrics, validating its effectiveness, robustness, and practicality for large-scale industrial search systems. --- ### Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search Authors: Ziyang Zeng, Heming Jing, Jindong Chen, Xiangli Li, Hongyu Liu, Yixuan He, Zhengyu Li, Yige Sun, Zheyong Xie, Yuqing Yang, Shaosheng Cao, Jun Fan et al. Published: 2025-11-30 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2512.00968v1 Ranking relevance is a fundamental task in search engines, aiming to identify the items most relevant to a given user query. Traditional relevance models typically produce scalar scores or directly predict relevance labels, limiting both interpretability and the modeling of complex relevance signals. Inspired by recent advances in Chain-of-Thought (CoT) reasoning for complex tasks, we investigate whether explicit reasoning can enhance both interpretability and performance in relevance modeling. However, existing reasoning-based Generative Relevance Models (GRMs) primarily rely on supervised fine-tuning on large amounts of human-annotated or synthetic CoT data, which often leads to limited generalization. Moreover, domain-agnostic, free-form reasoning tends to be overly generic and insufficiently grounded, limiting its potential to handle the diverse and ambiguous cases prevalent in open-domain search. In this work, we formulate relevance modeling in Xiaohongshu search as a reasoning task and introduce a Reinforcement Learning (RL)-based training framework to enhance the grounded reasoning capabilities of GRMs. Specifically, we incorporate practical business-specific relevance criteria into the multi-step reasoning prompt design and propose Stepwise Advantage Masking (SAM), a lightweight process-supervision strategy which facilitates effective learning of these criteria through improved credit assignment. To enable industrial deployment, we further distill the large-scale RL-tuned model to a lightweight version suitable for real-world search systems. Extensive experiments on industrial datasets, along with online A/B tests, demonstrate the effectiveness of our approach. --- ### Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis Authors: Mintong Kang, Chong Xiang, Sanjay Kariyappa, Chaowei Xiao, Bo Li, Edward Suh Published: 2025-11-30 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2512.00966v1 Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In this paper, we present IntentGuard, a general defense framework based on instruction-following intent analysis. The key insight of IntentGuard is that the decisive factor in IPIAs is not the presence of malicious text, but whether the LLM intends to follow instructions from untrusted data. Building on this insight, IntentGuard leverages an instruction-following intent analyzer (IIA) to identify which parts of the input prompt the model recognizes as actionable instructions, and then flag or neutralize any overlaps with untrusted data segments. To instantiate the framework, we develop an IIA that uses three "thinking intervention" strategies to elicit a structured list of intended instructions from reasoning-enabled LLMs. These techniques include start-of-thinking prefilling, end-of-thinking refinement, and adversarial in-context demonstration. We evaluate IntentGuard on two agentic benchmarks (AgentDojo and Mind2Web) using two reasoning-enabled LLMs (Qwen-3-32B and gpt-oss-20B). Results demonstrate that IntentGuard achieves (1) no utility degradation in all but one setting and (2) strong robustness against adaptive prompt injection attacks (e.g., reducing attack success rates from 100% to 8.5% in a Mind2Web scenario). --- ### Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning Authors: Qi Wang, Mian Wu, Yuyang Zhang, Mingqi Yuan, Wenyao Zhang, Haoxiang You, Yunbo Wang, Xin Jin, Xiaokang Yang, Wenjun Zeng Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00961v2 Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not generalize well across different tasks. To address this limitation, we leverage the rich world knowledge contained in pretrained video diffusion models to provide goal-driven reward signals for RL agents without ad-hoc design of reward. Our key idea is to exploit off-the-shelf video diffusion models pretrained on large-scale video datasets as informative reward functions in terms of video-level and frame-level goals. For video-level rewards, we first finetune a pretrained video diffusion model on domain-specific datasets and then employ its video encoder to evaluate the alignment between the latent representations of agent's trajectories and the generated goal videos. To enable more fine-grained goal-achievement, we derive a frame-level goal by identifying the most relevant frame from the generated video using CLIP, which serves as the goal state. We then employ a learned forward-backward representation that represents the probability of visiting the goal state from a given state-action pair as frame-level reward, promoting more coherent and goal-driven trajectories. Experiments on Meta-World and Distracting Control Suite demonstrate the effectiveness of our approach. --- ### Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning Authors: Qi Wang, Mian Wu, Yuyang Zhang, Mingqi Yuan, Wenyao Zhang, Haoxiang You, Yunbo Wang, Xin Jin, Xiaokang Yang, Wenjun Zeng Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00961v1 Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not generalize well across different tasks. To address this limitation, we leverage the rich world knowledge contained in pretrained video diffusion models to provide goal-driven reward signals for RL agents without ad-hoc design of reward. Our key idea is to exploit off-the-shelf video diffusion models pretrained on large-scale video datasets as informative reward functions in terms of video-level and frame-level goals. For video-level rewards, we first finetune a pretrained video diffusion model on domain-specific datasets and then employ its video encoder to evaluate the alignment between the latent representations of agent's trajectories and the generated goal videos. To enable more fine-grained goal-achievement, we derive a frame-level goal by identifying the most relevant frame from the generated video using CLIP, which serves as the goal state. We then employ a learned forward-backward representation that represents the probability of visiting the goal state from a given state-action pair as frame-level reward, promoting more coherent and goal-driven trajectories. Experiments on various Meta-World tasks demonstrate the effectiveness of our approach. --- ### Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction Authors: Boran Wen, Ye Lu, Sirui Wang, Keyan Wan, Jiahong Zhou, Junxuan Liang, Xinpeng Liu, Bang Xiao, Ruiyang Liu, Yong-Lu Li Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00960v3 Generalized robots must learn from diverse, large-scale human-object interactions (HOI) to operate robustly in the real world. Monocular internet videos offer a nearly limitless and readily available source of data, capturing an unparalleled diversity of human activities, objects, and environments. However, accurately and scalably extracting 4D interaction data from these in-the-wild videos remains a significant and unsolved challenge. To overcome the annotation bottleneck, we introduce an efficient sparse contact annotation paradigm. To scale this process, we develop InterPoint, a multi-modal predictor that drives a human-in-the-loop data engine. Building upon these efficiently acquired annotations, we introduce 4DHOISolver, a novel optimization framework that constrains the ill-posed 4D HOI reconstruction problem, maintaining high spatio-temporal coherence and physical plausibility. Leveraging this framework, we introduce Open4DHOI, a new large-scale 4D HOI dataset featuring a diverse catalog of 135 object types and 133 actions. Furthermore, we demonstrate the effectiveness of our reconstructions by enabling an RL-based agent to imitate the recovered motions. Data and code will be publicly available at https://github.com/wenboran2002/open4dhoi_code. --- ### Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction Authors: Boran Wen, Ye Lu, Keyan Wan, Sirui Wang, Jiahong Zhou, Junxuan Liang, Xinpeng Liu, Bang Xiao, Dingbang Huang, Ruiyang Liu, Yong-Lu Li Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00960v1 Generalized robots must learn from diverse, large-scale human-object interactions (HOI) to operate robustly in the real world. Monocular internet videos offer a nearly limitless and readily available source of data, capturing an unparalleled diversity of human activities, objects, and environments. However, accurately and scalably extracting 4D interaction data from these in-the-wild videos remains a significant and unsolved challenge. Thus, in this work, we introduce 4DHOISolver, a novel and efficient optimization framework that constrains the ill-posed 4D HOI reconstruction problem by leveraging sparse, human-in-the-loop contact point annotations, while maintaining high spatio-temporal coherence and physical plausibility. Leveraging this framework, we introduce Open4DHOI, a new large-scale 4D HOI dataset featuring a diverse catalog of 144 object types and 103 actions. Furthermore, we demonstrate the effectiveness of our reconstructions by enabling an RL-based agent to imitate the recovered motions. However, a comprehensive benchmark of existing 3D foundation models indicates that automatically predicting precise human-object contact correspondences remains an unsolved problem, underscoring the immediate necessity of our human-in-the-loop strategy while posing an open challenge to the community. Data and code will be publicly available at https://wenboran2002.github.io/open4dhoi/ --- ### WUSH: Near-Optimal Adaptive Transforms for LLM Quantization Authors: Jiale Chen, Vage Egiazarian, Roberto L. Castro, Torsten Hoefler, Dan Alistarh Published: 2025-11-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2512.00956v3 Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization errors. Prior transform-based mitigations (e.g., Hadamard rotations) are fixed and data-agnostic, and their optimality for quantization has remained unclear. We derive closed-form optimal linear blockwise transforms for joint weight-activation quantization under standard RTN AbsMax-scaled block quantizers, covering both integer and floating-point formats. The resulting construction, WUSH, combines a Hadamard backbone with a data-dependent second-moment component to form a non-orthogonal transform that is provably near-optimal for FP and INT quantizers under mild assumptions while admitting an efficient fused GPU implementation. Empirically, WUSH improves W4A4 accuracy over the strongest Hadamard-based baselines (e.g., on Llama-3.1-8B-Instruct in MXFP4, it gains +2.8 average points with RTN and +0.7 with GPTQ) while delivering up to 5.8$\times$ per-layer throughput over BF16 via FP4 MatMul. Source code is available at https://github.com/IST-DASLab/WUSH. --- ### WUSH: Near-Optimal Adaptive Transforms for LLM Quantization Authors: Jiale Chen, Vage Egiazarian, Torsten Hoefler, Dan Alistarh Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00956v1 Quantization to low bitwidth is a standard approach for deploying large language models, however, a few extreme weights and activations stretch the dynamic range and reduce the effective resolution of the quantizer. A common mitigation approach is to apply some fixed orthogonal transforms, such as Hadamard matrices, before quantization, which typically reduces the dynamic range. Yet, these transforms ignore the statistics of the data, and their optimality is currently not understood. In this work, we derive, for the first time, closed-form optimal linear blockwise transforms for joint weight-activation quantization using standard data-free quantizers for common numerical formats. Specifically, we provide derivations of the optimal adaptive (data-aware) transforms for round-to-nearest (RTN), AbsMax-scaled block quantizers for both integer and floating-point formats. The resulting construction, which we call WUSH, combines a Hadamard backbone with a data-dependent component based on second-order moments, yielding a non-orthogonal transform that is provably optimal under mild assumptions and remains structured for efficient implementation. Preliminary experimental results show that our approach consistently improves upon the Hadamard transform for common formats. --- ### Adaptive Evidential Learning for Temporal-Semantic Robustness in Moment Retrieval Authors: Haojian Huang, Kaijing Ma, Jin Chen, Haodong Chen, Zhou Wu, Xianghao Zang, Han Fang, Chao Ban, Hao Sun, Mulin Chen, Zhongjiang He Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00953v1 In the domain of moment retrieval, accurately identifying temporal segments within videos based on natural language queries remains challenging. Traditional methods often employ pre-trained models that struggle with fine-grained information and deterministic reasoning, leading to difficulties in aligning with complex or ambiguous moments. To overcome these limitations, we explore Deep Evidential Regression (DER) to construct a vanilla Evidential baseline. However, this approach encounters two major issues: the inability to effectively handle modality imbalance and the structural differences in DER's heuristic uncertainty regularizer, which adversely affect uncertainty estimation. This misalignment results in high uncertainty being incorrectly associated with accurate samples rather than challenging ones. Our observations indicate that existing methods lack the adaptability required for complex video scenarios. In response, we propose Debiased Evidential Learning for Moment Retrieval (DEMR), a novel framework that incorporates a Reflective Flipped Fusion (RFF) block for cross-modal alignment and a query reconstruction task to enhance text sensitivity, thereby reducing bias in uncertainty estimation. Additionally, we introduce a Geom-regularizer to refine uncertainty predictions, enabling adaptive alignment with difficult moments and improving retrieval accuracy. Extensive testing on standard datasets and debiased datasets ActivityNet-CD and Charades-CD demonstrates significant enhancements in effectiveness, robustness, and interpretability, positioning our approach as a promising solution for temporal-semantic robustness in moment retrieval. The code is publicly available at https://github.com/KaijingOfficial/DEMR. --- ### Multi-Modal AI for Remote Patient Monitoring in Cancer Care Authors: Yansong Liu, Ronnie Stafford, Pramit Khetrapal, Huriye Kocadag, Graça Carvalho, Patricia de Winter, Maryam Imran, Amelia Snook, Adamos Hadjivasiliou, D. Vijay Anand, Weining Lin, John Kelly et al. Published: 2025-11-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00949v2 For patients undergoing systemic cancer therapy, the time between clinic visits is full of uncertainties and risks of unmonitored side effects. To bridge this gap in care, we developed and prospectively trialed a multi-modal AI framework for remote patient monitoring (RPM). This system integrates multi-modal data from the HALO-X platform, such as demographics, wearable sensors, daily surveys, and clinical events. Our observational trial is one of the largest of its kind and has collected over 2.1 million data points (6,080 patient-days) of monitoring from 84 patients. We developed and adapted a multi-modal AI model to handle the asynchronous and incomplete nature of real-world RPM data, forecasting a continuous risk of future adverse events. The model achieved an accuracy of 83.9% (AUROC=0.70). Notably, the model identified previous treatments, wellness check-ins, and daily maximum heart rate as key predictive features. A case study demonstrated the model's ability to provide early warnings by outputting escalating risk profiles prior to the event. This work establishes the feasibility of multi-modal AI RPM for cancer care and offers a path toward more proactive patient support.(Accepted at Europe NeurIPS 2025 Multimodal Representation Learning for Healthcare Workshop. Best Paper Poster Award.) --- ### Multi-Modal AI for Remote Patient Monitoring in Cancer Care Authors: Yansong Liu, Ronnie Stafford, Pramit Khetrapal, Huriye Kocadag, Graça Carvalho, Patricia de Winter, Maryam Imran, Amelia Snook, Adamos Hadjivasiliou, D. Vijay Anand, Weining Lin, John Kelly et al. Published: 2025-11-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00949v1 For patients undergoing systemic cancer therapy, the time between clinic visits is full of uncertainties and risks of unmonitored side effects. To bridge this gap in care, we developed and prospectively trialed a multi-modal AI framework for remote patient monitoring (RPM). This system integrates multi-modal data from the HALO-X platform, such as demographics, wearable sensors, daily surveys, and clinical events. Our observational trial is one of the largest of its kind and has collected over 2.1 million data points (6,080 patient-days) of monitoring from 84 patients. We developed and adapted a multi-modal AI model to handle the asynchronous and incomplete nature of real-world RPM data, forecasting a continuous risk of future adverse events. The model achieved an accuracy of 83.9% (AUROC=0.70). Notably, the model identified previous treatments, wellness check-ins, and daily maximum heart rate as key predictive features. A case study demonstrated the model's ability to provide early warnings by outputting escalating risk profiles prior to the event. This work establishes the feasibility of multi-modal AI RPM for cancer care and offers a path toward more proactive patient support.(Accepted at Europe NeurIPS 2025 Multimodal Representation Learning for Healthcare Workshop) --- ### Table as a Modality for Large Language Models Authors: Liyao Li, Chao Ye, Wentao Ye, Yifei Sun, Zhe Jiang, Haobo Wang, Jiaming Tian, Yiming Zhang, Ningtao Wang, Xing Fu, Gang Chen, Junbo Zhao Published: 2025-11-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.00947v2 To migrate the remarkable successes of Large Language Models (LLMs), the community has made numerous efforts to generalize them to the table reasoning tasks for the widely deployed tabular data. Despite that, in this work, by showing a probing experiment on our proposed StructQA benchmark, we postulate that even the most advanced LLMs (such as GPTs) may still fall short of coping with tabular data. More specifically, the current scheme often simply relies on serializing the tabular data, together with the meta information, then inputting them through the LLMs. We argue that the loss of structural information is the root of this shortcoming. In this work, we further propose TAMO, which bears an ideology to treat the tables as an independent modality integrated with the text tokens. The resulting model in TAMO is a multimodal framework consisting of a hypergraph neural network as the global table encoder seamlessly integrated with the mainstream LLM. Empirical results on various benchmarking datasets, including HiTab, WikiTQ, WikiSQL, FeTaQA, and StructQA, have demonstrated significant improvements on generalization with an average relative gain of 42.65%. --- ### Table as a Modality for Large Language Models Authors: Liyao Li, Chao Ye, Wentao Ye, Yifei Sun, Zhe Jiang, Haobo Wang, Jiaming Tian, Yiming Zhang, Ningtao Wang, Xing Fu, Gang Chen, Junbo Zhao Published: 2025-11-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.00947v1 To migrate the remarkable successes of Large Language Models (LLMs), the community has made numerous efforts to generalize them to the table reasoning tasks for the widely deployed tabular data. Despite that, in this work, by showing a probing experiment on our proposed StructQA benchmark, we postulate that even the most advanced LLMs (such as GPTs) may still fall short of coping with tabular data. More specifically, the current scheme often simply relies on serializing the tabular data, together with the meta information, then inputting them through the LLMs. We argue that the loss of structural information is the root of this shortcoming. In this work, we further propose TAMO, which bears an ideology to treat the tables as an independent modality integrated with the text tokens. The resulting model in TAMO is a multimodal framework consisting of a hypergraph neural network as the global table encoder seamlessly integrated with the mainstream LLM. Empirical results on various benchmarking datasets, including HiTab, WikiTQ, WikiSQL, FeTaQA, and StructQA, have demonstrated significant improvements on generalization with an average relative gain of 42.65%. --- ### Fine-tuning of lightweight large language models for sentiment classification on heterogeneous financial textual data Authors: Alvaro Paredes Amorin, Andre Python, Christoph Weisser Published: 2025-11-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.00946v1 Large language models (LLMs) play an increasingly important role in financial markets analysis by capturing signals from complex and heterogeneous textual data sources, such as tweets, news articles, reports, and microblogs. However, their performance is dependent on large computational resources and proprietary datasets, which are costly, restricted, and therefore inaccessible to many researchers and practitioners. To reflect realistic situations we investigate the ability of lightweight open-source LLMs -- smaller and publicly available models designed to operate with limited computational resources -- to generalize sentiment understanding from financial datasets of varying sizes, sources, formats, and languages. We compare the benchmark finance natural language processing (NLP) model, FinBERT, and three open-source lightweight LLMs, DeepSeek-LLM 7B, Llama3 8B Instruct, and Qwen3 8B on five publicly available datasets: FinancialPhraseBank, Financial Question Answering, Gold News Sentiment, Twitter Sentiment and Chinese Finance Sentiment. We find that LLMs, specially Qwen3 8B and Llama3 8B, perform best in most scenarios, even from using only 5% of the available training data. These results hold in zero-shot and few-shot learning scenarios. Our findings indicate that lightweight, open-source large language models (LLMs) constitute a cost-effective option, as they can achieve competitive performance on heterogeneous textual data even when trained on only a limited subset of the extensive annotated corpora that are typically deemed necessary. --- ### Binary-Gaussian: Compact and Progressive Representation for 3D Gaussian Segmentation Authors: An Yang, Chenyu Liu, Jun Du, Jianqing Gao, Jia Pan, Jinshui Hu, Baocai Yin, Bing Yin, Cong Liu Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00944v1 3D Gaussian Splatting (3D-GS) has emerged as an efficient 3D representation and a promising foundation for semantic tasks like segmentation. However, existing 3D-GS-based segmentation methods typically rely on high-dimensional category features, which introduce substantial memory overhead. Moreover, fine-grained segmentation remains challenging due to label space congestion and the lack of stable multi-granularity control mechanisms. To address these limitations, we propose a coarse-to-fine binary encoding scheme for per-Gaussian category representation, which compresses each feature into a single integer via the binary-to-decimal mapping, drastically reducing memory usage. We further design a progressive training strategy that decomposes panoptic segmentation into a series of independent sub-tasks, reducing inter-class conflicts and thereby enhancing fine-grained segmentation capability. Additionally, we fine-tune opacity during segmentation training to address the incompatibility between photometric rendering and semantic segmentation, which often leads to foreground-background confusion. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art segmentation performance while significantly reducing memory consumption and accelerating inference. --- ### Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks Authors: Susmit Agrawal, Krishn Vishwas Kher, Saksham Mittal, Swarnim Maheshwari, Vineeth N. Balasubramanian Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00940v1 Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowledge of once-learned environments sans catastrophic forgetting, a phenomenon neuroscientists hypothesize, is due to a singular neural circuitry dynamically overlayed by neuromodulatory agents such as dopamine and acetylcholine. In parallel, deep learning research addresses analogous challenges via domain generalization (DG) and continual learning (CL), yet these methods remain siloed, despite the brains ability to perform them seamlessly. In particular, prior work has not explored architectures involving associative memories (AMs), which are an integral part of biological systems, to jointly address these tasks. We propose Memory-Integrated Reconfigurable Adapters (MIRA), a unified framework that integrates Hopfield-style associative memory modules atop a shared backbone. Associative memory keys are learned post-hoc to index and retrieve an affine combination of stored adapter updates for any given task or domain on a per-sample basis. By varying only the task-specific objectives, we demonstrate that MIRA seamlessly accommodates domain shifts and sequential task exposures under one roof. Empirical evaluations on standard benchmarks confirm that our AM-augmented architecture significantly enhances adaptability and retention: in DG, MIRA achieves SoTA out-of-distribution accuracy, and in incremental learning settings, it outperforms architectures explicitly designed to handle catastrophic forgetting using generic CL algorithms. By unifying adapter-based modulation with biologically inspired associative memory, MIRA delivers rapid task switching and enduring knowledge retention in a single extensible architecture, charting a path toward more versatile and memory-augmented AI systems. --- ### Constant-Time Planning for Chaining Collision-free Motion to Manipulation Behaviors Authors: Nayesha Gandotra, Itamar Mishani, Lai Yuan, Oren Salzman, Maxim Likhachev Published: 2025-11-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.00939v3 Recent progress in contact-rich robotic manipulation has been striking, yet most deployed systems remain confined to simple, scripted routines. One of the barriers is the lack of motion planning algorithms that can provide verifiable guarantees for safety, efficiency and reliability. Constant-Time Motion Planning (CTMP) is a recent step toward such guarantees for collision-free motion in a priori known environments:: a preprocessing phase enables queries to be answered within a fixed, user-specified time budget (e.g., 10 milliseconds). However, CTMP certifies only reachability---a binary predicate---and ignores the manipulation behavior that completes the task, which is increasingly stochastic (e.g., a learned skill) and whose success no single offline rollout can establish, let alone certify. We introduce the Behavioral Constant-Time Motion Planner (B-CTMP), which extends CTMP to two-step manipulation tasks in semi-structured environments: a collision-free motion to a behavior initiation state, followed by execution of a behavior such as grasping or insertion. B-CTMP departs from prior CTMP in two ways: neighborhoods are constructed in object-pose space rather than robot configuration space, and coverage is established by statistical certification rather than a reachability check. A plan is cached only if repeated rollouts lower-bound its success rate above a user-specified threshold, and we prove these bounds hold simultaneously across the entire cache at a prescribed confidence level. For deterministic behaviors a single rollout suffices, recovering the binary check of prior CTMP as a special case. We evaluate B-CTMP on three manipulation tasks---shelf picking, plug insertion, and wheel replacement---in simulation and on real robots. B-CTMP's certified plans succeed consistently where baselines fail during behavior execution, and it rejects infeasible object poses in constant time. --- ### Constant-Time Motion Planning with Manipulation Behaviors Authors: Nayesha Gandotra, Itamar Mishani, Maxim Likhachev Published: 2025-11-30 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2512.00939v1 Recent progress in contact-rich robotic manipulation has been striking, yet most deployed systems remain confined to simple, scripted routines. One of the key barriers is the lack of motion planning algorithms that can provide verifiable guarantees for safety, efficiency and reliability. To address this, a family of algorithms called Constant-Time Motion Planning (CTMP) was introduced, which leverages a preprocessing phase to enable collision-free motion queries in a fixed, user-specified time budget (e.g., 10 milliseconds). However, existing CTMP methods do not explicitly incorporate the manipulation behaviors essential for object handling. To bridge this gap, we introduce the \textit{Behavioral Constant-Time Motion Planner} (B-CTMP), an algorithm that extends CTMP to solve a broad class of two-step manipulation tasks: (1) a collision-free motion to a behavior initiation state, followed by (2) execution of a manipulation behavior (such as grasping or insertion) to reach the goal. By precomputing compact data structures, B-CTMP guarantees constant-time query in mere milliseconds while ensuring completeness and successful task execution over a specified set of states. We evaluate B-CTMP on two canonical manipulation tasks in simulation, shelf picking and plug insertion,and demonstrate its effectiveness on a real robot. Our results show that B-CTMP unifies collision-free planning and object manipulation within a single constant-time framework, providing provable guarantees of speed and success for manipulation in semi-structured environments. --- ### DeformAr: Rethinking NER Evaluation through Component Analysis and Visual Analytics Authors: Ahmed Mustafa Younes Published: 2025-11-30 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.00938v1 Transformer models have significantly advanced Natural Language Processing (NLP), demonstrating strong performance in English. However, their effectiveness in Arabic, particularly for Named Entity Recognition (NER), remains limited, even with larger pre-trained models. This performance gap stems from multiple factors, including tokenisation, dataset quality, and annotation inconsistencies. Existing studies often analyze these issues in isolation, failing to capture their joint effect on system behaviour and performance. We introduce DeformAr (Debugging and Evaluation Framework for Transformer-based NER Systems), a novel framework designed to investigate and explain the performance discrepancy between Arabic and English NER systems. DeformAr integrates a data extraction library and an interactive dashboard, supporting two modes of evaluation: cross-component analysis and behavioural analysis. The framework divides each language into dataset and model components to examine their interactions. The analysis proceeds in two stages. First, cross-component analysis provides systematic diagnostic measures across data and model subcomponents, addressing the "what," "how," and "why" behind observed discrepancies. The second stage applies behavioural analysis by combining interpretability techniques with token-level metrics, interactive visualisations, and representation space analysis. These stages enable a component-aware diagnostic process that detects model behaviours and explains them by linking them to underlying representational patterns and data factors. DeformAr is the first Arabic-specific, component-based interpretability tool, offering a crucial resource for advancing model analysis in under-resourced languages. --- ### SceneProp: Combining Neural Network and Markov Random Field for Scene-Graph Grounding Authors: Keita Otani, Tatsuya Harada Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00936v1 Grounding complex, compositional visual queries with multiple objects and relationships is a fundamental challenge for vision-language models. While standard phrase grounding methods excel at localizing single objects, they lack the structural inductive bias to parse intricate relational descriptions, often failing as queries become more descriptive. To address this structural deficit, we focus on scene-graph grounding, a powerful but less-explored formulation where the query is an explicit graph of objects and their relationships. However, existing methods for this task also struggle, paradoxically showing decreased performance as the query graph grows -- failing to leverage the very information that should make grounding easier. We introduce SceneProp, a novel method that resolves this issue by reformulating scene-graph grounding as a Maximum a Posteriori (MAP) inference problem in a Markov Random Field (MRF). By performing global inference over the entire query graph, SceneProp finds the optimal assignment of image regions to nodes that jointly satisfies all constraints. This is achieved within an end-to-end framework via a differentiable implementation of the Belief Propagation algorithm. Experiments on four benchmarks show that our dedicated focus on the scene-graph grounding formulation allows SceneProp to significantly outperform prior work. Critically, its accuracy consistently improves with the size and complexity of the query graph, demonstrating for the first time that more relational context can, and should, lead to better grounding. Codes are available at https://github.com/keitaotani/SceneProp. --- ### Mitigating Hallucinations in Zero-Shot Scientific Summarisation: A Pilot Study Authors: Imane Jaaouine, Ross D. King Published: 2025-11-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2512.00931v1 Large language models (LLMs) produce context inconsistency hallucinations, which are LLM generated outputs that are misaligned with the user prompt. This research project investigates whether prompt engineering (PE) methods can mitigate context inconsistency hallucinations in zero-shot LLM summarisation of scientific texts, where zero-shot indicates that the LLM relies purely on its pre-training data. Across eight yeast biotechnology research paper abstracts, six instruction-tuned LLMs were prompted with seven methods: a baseline prompt, two levels of increasing instruction complexity (PE-1 and PE-2), two levels of context repetition (CR-K1 and CR-K2), and two levels of random addition (RA-K1 and RA-K2). Context repetition involved the identification and repetition of K key sentences from the abstract, whereas random addition involved the repetition of K randomly selected sentences from the abstract, where K is 1 or 2. A total of 336 LLM-generated summaries were evaluated using six metrics: ROUGE-1, ROUGE-2, ROUGE-L, BERTScore, METEOR, and cosine similarity, which were used to compute the lexical and semantic alignment between the summaries and the abstracts. Four hypotheses on the effects of prompt methods on summary alignment with the reference text were tested. Statistical analysis on 3744 collected datapoints was performed using bias-corrected and accelerated (BCa) bootstrap confidence intervals and Wilcoxon signed-rank tests with Bonferroni-Holm correction. The results demonstrated that CR and RA significantly improve the lexical alignment of LLM-generated summaries with the abstracts. These findings indicate that prompt engineering has the potential to impact hallucinations in zero-shot scientific summarisation tasks. --- ### Thompson Sampling for Multi-Objective Linear Contextual Bandit Authors: Somangchan Park, Heesang Ann, Min-hwan Oh Published: 2025-11-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.00930v1 We study the multi-objective linear contextual bandit problem, where multiple possible conflicting objectives must be optimized simultaneously. We propose \texttt{MOL-TS}, the \textit{first} Thompson Sampling algorithm with Pareto regret guarantees for this problem. Unlike standard approaches that compute an empirical Pareto front each round, \texttt{MOL-TS} samples parameters across objectives and efficiently selects an arm from a novel \emph{effective Pareto front}, which accounts for repeated selections over time. Our analysis shows that \texttt{MOL-TS} achieves a worst-case Pareto regret bound of $\widetilde{O}(d^{3/2}\sqrt{T})$, where $d$ is the dimension of the feature vectors, $T$ is the total number of rounds, matching the best known order for randomized linear bandit algorithms for single objective. Empirical results confirm the benefits of our proposed approach, demonstrating improved regret minimization and strong multi-objective performance. --- ### LAHNet: Local Attentive Hashing Network for Point Cloud Registration Authors: Wentao Qu, Xiaoshui Huang, Liang Xiao Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00927v2 Most existing learning-based point cloud descriptors for point cloud registration focus on perceiving local information of point clouds to generate distinctive features. However, a reasonable and broader receptive field is essential for enhancing feature distinctiveness. In this paper, we propose a Local Attentive Hashing Network for point cloud registration, called LAHNet, which introduces a local attention mechanism with the inductive bias of locality of convolution-like operators into point cloud descriptors. Specifically, a Group Transformer is designed to capture reasonable long-range context between points. This employs a linear neighborhood search strategy, Locality-Sensitive Hashing, enabling uniformly partitioning point clouds into non-overlapping windows. Meanwhile, an efficient cross-window strategy is adopted to further expand the reasonable feature receptive field. Furthermore, building on this effective windowing strategy, we propose an Interaction Transformer to enhance the feature interactions of the overlap regions within point cloud pairs. This computes an overlap matrix to match overlap regions between point cloud pairs by representing each window as a global signal. Extensive results demonstrate that LAHNet can learn robust and distinctive features, achieving significant registration results on real-world indoor and outdoor benchmarks. --- ### LAHNet: Local Attentive Hashing Network for Point Cloud Registration Authors: Wentao Qu, Xiaoshui Huang, Liang Xiao Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00927v1 Most existing learning-based point cloud descriptors for point cloud registration focus on perceiving local information of point clouds to generate distinctive features. However, a reasonable and broader receptive field is essential for enhancing feature distinctiveness. In this paper, we propose a Local Attentive Hashing Network for point cloud registration, called LAHNet, which introduces a local attention mechanism with the inductive bias of locality of convolution-like operators into point cloud descriptors. Specifically, a Group Transformer is designed to capture reasonable long-range context between points. This employs a linear neighborhood search strategy, Locality-Sensitive Hashing, enabling uniformly partitioning point clouds into non-overlapping windows. Meanwhile, an efficient cross-window strategy is adopted to further expand the reasonable feature receptive field. Furthermore, building on this effective windowing strategy, we propose an Interaction Transformer to enhance the feature interactions of the overlap regions within point cloud pairs. This computes an overlap matrix to match overlap regions between point cloud pairs by representing each window as a global signal. Extensive results demonstrate that LAHNet can learn robust and distinctive features, achieving significant registration results on real-world indoor and outdoor benchmarks. --- ### D-CTNet: A Dual-Branch Channel-Temporal Forecasting Network with Frequency-Domain Correction Authors: Shaoxun Wang, Xingjun Zhang, Kun Xia, Qianyang Li, Jiawei Cao, Zhendong Tan Published: 2025-11-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2512.00925v1 Accurate Multivariate Time Series (MTS) forecasting is crucial for collaborative design of complex systems, Digital Twin building, and maintenance ahead of time. However, the collaborative industrial environment presents new challenges for MTS forecasting models: models should decouple complex inter-variable dependencies while addressing non-stationary distribution shift brought by environmental changes. To address these challenges and improve collaborative sensing reliability, we propose a Patch-Based Dual-Branch Channel-Temporal Forecasting Network (D-CTNet). Particularly, with a parallel dual-branch design incorporating linear temporal modeling layer and channel attention mechanism, our method explicitly decouples and jointly learns intra-channel temporal evolution patterns and dynamic multivariate correlations. Furthermore, a global patch attention fusion module goes beyond the local window scope to model long range dependencies. Most importantly, aiming at non-stationarity, a Frequency-Domain Stationarity Correction mechanism adaptively suppresses distribution shift impacts from environment change by spectrum alignment. Evaluations on seven benchmark datasets show that our model achieves better forecasting accuracy and robustness compared with state-of-the-art methods. Our work shows great promise as a new forecasting engine for industrial collaborative systems. --- ### Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios Authors: Jianxiang Zang, Yongda Wei, Ruxue Bai, Shiyu Jiang, Nijia Mo, Binhong Li, Qiang Sun, Hui Liu Published: 2025-11-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.00920v5 Reliable reward models (RMs) are critical for ensuring the safe alignment of large language models (LLMs). However, current RM evaluation methods focus solely on preference perception accuracies in given specific scenarios, obscuring the critical vulnerabilities of RMs in real-world scenarios. We identify the true challenge lies in assessing a novel dimension: Suitability, defined as conditional reliability under specific real-world perturbations. To this end, we introduce Reward Auditor, a hypothesis-testing framework specifically designed for RM suitability inference. Rather than answering "How accurate is the RM's preference perception for given samples?", it employs scientific auditing to answer: "Can we infer RMs exhibit systematic vulnerabilities in specific real-world scenarios?". Under real-world perturbed scenarios, Reward Auditor quantifies statistical significance and effect size by auditing distribution degradation of RM preference perception confidence. This enables inference of both the certainty and severity of RM vulnerabilities across diverse real-world scenarios. This lays a solid foundation for building next-generation LLM alignment systems that are verifiably safe, more robust, and trustworthy. --- ### Reward Auditor: Inference on Reward Modeling Suitability in Real-World Perturbed Scenarios Authors: Jianxiang Zang, Yongda Wei, Ruxue Bai, Shiyu Jiang, Nijia Mo, Binhong Li, Qiang Sun, Hui Liu Published: 2025-11-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2512.00920v1 Reliable reward models (RMs) are critical for ensuring the safe alignment of large language models (LLMs). However, current evaluation methods focus solely on preference perception accuracies in given specific scenarios, obscuring the critical vulnerabilities of RMs in real-world scenarios. We identify the true challenge lies in assessing a novel dimension: Suitability, defined as conditional reliability under specific real-world perturbations. To this end, we introduce Reward Auditor, a hypothesis-testing framework specifically designed for RM suitability inference. Rather than answering "How accurate is the RM's preference perception for given samples?", it employs scientific auditing to answer: "Can we infer RMs exhibit systematic vulnerabilities in specific real-world scenarios?". Under real-world perturbed scenarios, Reward Auditor quantifies statistical significance and effect size by auditing distribution degradation of RM preference perception confidence. This enables inference of both the certainty and severity of RM vulnerabilities across diverse real-world scenarios. This lays a solid foundation for building next-generation LLM alignment systems that are verifiably safe, more robust, and trustworthy. --- ### Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression Authors: Dimitri Meunier, Jakub Wornbard, Vladimir R. Kostic, Antoine Moulin, Alek Fröhlich, Karim Lounici, Massimiliano Pontil, Arthur Gretton Published: 2025-11-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.00919v2 We address the problem of causal effect estimation in the presence of hidden confounders using nonparametric instrumental variable (IV) regression. An established approach is to use estimators based on learned spectral features, that is, features spanning the top singular subspaces of the operator linking treatments to instruments. While powerful, such features are agnostic to the outcome variable. Consequently, the method can fail when the true causal function is poorly represented by these dominant singular functions. To mitigate, we introduce Augmented Spectral Feature Learning, a framework that makes the feature learning process outcome-aware. Our method learns features by minimizing a novel contrastive loss derived from an augmented operator that incorporates information from the outcome. By learning these task-specific features, our approach remains effective even under spectral misalignment. We provide a theoretical analysis of this framework and validate our approach on challenging benchmarks. --- ### Outcome-Aware Spectral Feature Learning for Instrumental Variable Regression Authors: Dimitri Meunier, Jakub Wornbard, Vladimir R. Kostic, Antoine Moulin, Alek Fröhlich, Karim Lounici, Massimiliano Pontil, Arthur Gretton Published: 2025-11-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2512.00919v1 We address the problem of causal effect estimation in the presence of hidden confounders using nonparametric instrumental variable (IV) regression. An established approach is to use estimators based on learned spectral features, that is, features spanning the top singular subspaces of the operator linking treatments to instruments. While powerful, such features are agnostic to the outcome variable. Consequently, the method can fail when the true causal function is poorly represented by these dominant singular functions. To mitigate, we introduce Augmented Spectral Feature Learning, a framework that makes the feature learning process outcome-aware. Our method learns features by minimizing a novel contrastive loss derived from an augmented operator that incorporates information from the outcome. By learning these task-specific features, our approach remains effective even under spectral misalignment. We provide a theoretical analysis of this framework and validate our approach on challenging benchmarks. --- ### Sparse Neuron Ablation Triggers Catastrophic Collapse of the Language Core in Large Vision-Language Models Authors: Cen Lu, Yung-Chen Tang, Andrea Cavallaro Published: 2025-11-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.00918v2 Large Vision-Language Models (LVLMs) have shown impressive multimodal understanding capabilities, yet the structures that sustain their functionality remain poorly understood from a mechanistic interpretability standpoint. We propose Consistently Activated Neurons (CAN), a progressive neuron ablation method to identify critical neurons whose removal triggers catastrophic collapse, and use it to investigate structural vulnerabilities in representative 7B LVLMs. Experiments reveal that catastrophic collapse can be triggered by ablating as few as four neurons in \texttt{LLaVA-1.5-7b-hf} and a few thousand in \texttt{InstructBLIP-vicuna-7b}, both representing a small fraction of model parameters. Notably, critical neurons are predominantly localized in the language model, particularly in its down-projection layer, rather than in the vision components. We also observe a consistent two-stage collapse pattern: initial expressive degradation followed by sudden, complete collapse. These findings reveal that LVLM functionality depends on a sparse subset of neurons concentrated in the language backbone, offering mechanistic insights into how their functionality is structured and where these models are most vulnerable. --- ### Minimal neuron ablation triggers catastrophic collapse in the language core of Large Vision-Language Models Authors: Cen Lu, Yung-Chen Tang, Andrea Cavallaro Published: 2025-11-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.00918v1 Large Vision-Language Models (LVLMs) have shown impressive multimodal understanding capabilities, yet their robustness is poorly understood. In this paper, we investigate the structural vulnerabilities of LVLMs to identify any critical neurons whose removal triggers catastrophic collapse. In this context, we propose CAN, a method to detect Consistently Activated Neurons and to locate critical neurons by progressive masking. Experiments on LLaVA-1.5-7b-hf and InstructBLIP-Vicuna-7b reveal that masking only a tiny portion of the language model's feed-forward networks (just as few as four neurons in extreme cases) suffices to trigger catastrophic collapse. Notably, critical neurons are predominantly localized in the language model rather than in the vision components, and the down-projection layer is a particularly vulnerable structure. We also observe a consistent two-stage collapse pattern: initial expressive degradation followed by sudden, complete collapse. Our findings provide important insights for safety research in LVLMs. --- ### An Imbalance-Robust Evaluation Framework for Extreme Risk Forecasts Authors: Sotirios D. Nikolopoulos Published: 2025-11-30 Categories: stat.ME, q-fin.RM, stat.ML arXiv: https://arxiv.org/abs/2512.00916v1 Evaluating rare-event forecasts is challenging because standard metrics collapse as event prevalence declines. Measures such as F1-score, AUPRC, MCC, and accuracy induce degenerate thresholds -- converging to zero or one -- and their values become dominated by class imbalance rather than tail discrimination. We develop a family of rare-event-stable (RES) metrics whose optimal thresholds remain strictly interior as the event probability approaches zero, ensuring coherent decision rules under extreme rarity. Simulations spanning event probabilities from 0.01 down to one in a million show that RES metrics maintain stable thresholds, consistent model rankings, and near-complete prevalence invariance, whereas traditional metrics exhibit statistically significant threshold drift and structural collapse. A credit-default application confirms these results: RES metrics yield interpretable probability-of-default cutoffs (4-9%) and remain robust under subsampling, while classical metrics fail operationally. The RES framework provides a principled, prevalence-invariant basis for evaluating extreme-risk forecasts. --- ### Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments Authors: Junwoo Chang, Minwoo Park, Joohwan Seo, Roberto Horowitz, Jongmin Lee, Jongeun Choi Published: 2025-11-30 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2512.00915v2 Group symmetries provide a powerful inductive bias for reinforcement learning (RL), enabling efficient generalization across symmetric states and actions via group-invariant Markov Decision Processes (MDPs). However, real-world environments almost never realize fully group-invariant MDPs; dynamics, actuation limits, and reward design usually break symmetries, often only locally. Under group-invariant Bellman backups for such cases, local symmetry-breaking introduces errors that propagate across the entire state-action space, resulting in global value estimation errors. To address this, we introduce Partially group-Invariant MDP (PI-MDP), which selectively applies group-invariant or standard Bellman backups depending on where symmetry holds. This framework mitigates error propagation from locally broken symmetries while maintaining the benefits of equivariance, thereby enhancing sample efficiency and generalizability. Building on this framework, we present practical RL algorithms -- Partially Equivariant (PE)-DQN for discrete control and PE-SAC for continuous control -- that combine the benefits of equivariance with robustness to symmetry-breaking. Experiments across Grid-World, locomotion, and manipulation benchmarks demonstrate that PE-DQN and PE-SAC significantly outperform baselines, highlighting the importance of selective symmetry exploitation for robust and sample-efficient RL. Project page: https://pranaboy72.github.io/perl_page/ --- ### Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments Authors: Junwoo Chang, Minwoo Park, Joohwan Seo, Roberto Horowitz, Jongmin Lee, Jongeun Choi Published: 2025-11-30 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2512.00915v1 Group symmetries provide a powerful inductive bias for reinforcement learning (RL), enabling efficient generalization across symmetric states and actions via group-invariant Markov Decision Processes (MDPs). However, real-world environments almost never realize fully group-invariant MDPs; dynamics, actuation limits, and reward design usually break symmetries, often only locally. Under group-invariant Bellman backups for such cases, local symmetry-breaking introduces errors that propagate across the entire state-action space, resulting in global value estimation errors. To address this, we introduce Partially group-Invariant MDP (PI-MDP), which selectively applies group-invariant or standard Bellman backups depending on where symmetry holds. This framework mitigates error propagation from locally broken symmetries while maintaining the benefits of equivariance, thereby enhancing sample efficiency and generalizability. Building on this framework, we present practical RL algorithms -- Partially Equivariant (PE)-DQN for discrete control and PE-SAC for continuous control -- that combine the benefits of equivariance with robustness to symmetry-breaking. Experiments across Grid-World, locomotion, and manipulation benchmarks demonstrate that PE-DQN and PE-SAC significantly outperform baselines, highlighting the importance of selective symmetry exploitation for robust and sample-efficient RL. --- ### ForamDeepSlice: A High-Accuracy Deep Learning Framework for Foraminifera Species Classification from 2D Micro-CT Slices Authors: Abdelghafour Halimi, Ali Alibrahim, Didier Barradas-Bautista, Ronell Sicat, Abdulkader M. Afifi Published: 2025-11-30 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.00912v2 This study presents a comprehensive deep learning pipeline for the automated classification of foraminifera species using 2D micro-CT slices derived from 3D scans. We curated a scientifically rigorous dataset of 97 micro-CT scanned specimens spanning 27 species, from which we selected 12 representative species with sufficient specimen counts (at least four 3D models each) for robust classification. To ensure methodological integrity and prevent data leakage, we employed specimen-level data splitting, resulting in 109,617 high-quality 2D slices (44,103 for training, 14,046 for validation, and 51,468 for testing). We evaluated seven state-of-the-art 2D convolutional neural network (CNN) architectures using transfer learning. Our final ensemble model, ForamDeepSlice (FDS), combining ConvNeXt-Large and EfficientNetV2-Small, achieved a test accuracy of 95.64%, with a top-3 accuracy of 99.6% and an area under the ROC curve (AUC) of 0.998 across all species. To facilitate practical deployment, we developed an interactive advanced dashboard that supports real-time slice classification and 3D slice matching using advanced similarity metrics, including SSIM, NCC, and the Dice coefficient. This work establishes new benchmarks for AI-assisted micropaleontological identification and provides a fully reproducible framework for foraminifera classification research, bridging the gap between deep learning and applied geosciences. --- ### ForamDeepSlice: A High-Accuracy Deep Learning Framework for Foraminifera Species Classification from 2D Micro-CT Slices Authors: Abdelghafour Halimi, Ali Alibrahim, Didier Barradas-Bautista, Ronell Sicat, Abdulkader M. Afifi Published: 2025-11-30 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2512.00912v1 This study presents a comprehensive deep learning pipeline for the automated classification of 12 foraminifera species using 2D micro-CT slices derived from 3D scans. We curated a scientifically rigorous dataset comprising 97 micro-CT scanned specimens across 27 species, selecting 12 species with sufficient representation for robust machine learning. To ensure methodological integrity and prevent data leakage, we employed specimen-level data splitting, resulting in 109,617 high-quality 2D slices (44,103 for training, 14,046 for validation, and 51,468 for testing). We evaluated seven state-of-the-art 2D convolutional neural network (CNN) architectures using transfer learning. Our final ensemble model, combining ConvNeXt-Large and EfficientNetV2-Small, achieved a test accuracy of 95.64%, with a top-3 accuracy of 99.6% and an area under the ROC curve (AUC) of 0.998 across all species. To facilitate practical deployment, we developed an interactive advanced dashboard that supports real-time slice classification and 3D slice matching using advanced similarity metrics, including SSIM, NCC, and the Dice coefficient. This work establishes new benchmarks for AI-assisted micropaleontological identification and provides a fully reproducible framework for foraminifera classification research, bridging the gap between deep learning and applied geosciences. --- ### Learning Projection-Aware 360-Degree Image Rectification via Dual-Projection Fusion Authors: Yuhao Shan, Qianyi Yuan, Jingguo Liu, Shigang Li, Jianfeng Li, Tong Chen Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00911v2 Panoramic cameras provide a 360° field of view and are widely used in panoramic vision, immersive visual computing, and robotic perception. However, changes in camera orientation can produce non-upright panoramas, introducing geometric variations that can complicate downstream visual analysis. Existing vision-based rectification methods usually operate within a single projection domain, limiting their ability to jointly exploit local geometric structures and global contextual information. To address this, we formulate 360° image rectification as a projection-aware representation learning problem and propose a dual-projection framework for upright panoramic rectification. A convolutional neural network branch captures local geometric structures from equirectangular projection (ERP) inputs, while a vision transformer branch models global contextual cues from cubemap projections. Cross-projection feature transformation and multi-level feature fusion enable effective interaction between these complementary representations. The learned representation supports collaborative inclination estimation and upright panorama generation, with the two tasks providing complementary geometric and appearance supervision. Experiments on SUN360 and M3D show consistent improvements over existing methods, achieving accuracies within a 1° error threshold of 65.9% and 85.2% and Fréchet Inception Distance scores of 5.87 and 3.26, respectively. Ablation studies verify the contributions of dual-projection representation, cross-projection feature transformation and fusion, and collaborative multi-task learning. The proposed framework provides a projection-aware visual computing approach for panoramic rectification. Code, pretrained models, and training/testing scripts are available at https://github.com/YuhaoShine/DualProjectionFusion. --- ### Dual-Projection Fusion for Accurate Upright Panorama Generation in Robotic Vision Authors: Yuhao Shan, Qianyi Yuan, Jingguo Liu, Shigang Li, Jianfeng Li, Tong Chen Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00911v1 Panoramic cameras, capable of capturing a 360-degree field of view, are crucial in robotic vision, particularly in environments with sparse features. However, non-upright panoramas due to unstable robot postures hinder downstream tasks. Traditional IMU-based correction methods suffer from drift and external disturbances, while vision-based approaches offer a promising alternative. This study presents a dual-stream angle-aware generation network that jointly estimates camera inclination angles and reconstructs upright panoramic images. The network comprises a CNN branch that extracts local geometric structures from equirectangular projections and a ViT branch that captures global contextual cues from cubemap projections. These are integrated through a dual-projection adaptive fusion module that aligns spatial features across both domains. To further enhance performance, we introduce a high-frequency enhancement block, circular padding, and channel attention mechanisms to preserve 360° continuity and improve geometric sensitivity. Experiments on the SUN360 and M3D datasets demonstrate that our method outperforms existing approaches in both inclination estimation and upright panorama generation. Ablation studies further validate the contribution of each module and highlight the synergy between the two tasks. The code and related datasets can be found at: https://github.com/YuhaoShine/DualProjectionFusion. --- ### TalkingPose: Efficient Face and Gesture Animation with Feedback-guided Diffusion Model Authors: Alireza Javanmardi, Pragati Jaiswal, Tewodros Amberbir Habtegebrial, Christen Millerdurai, Shaoxiang Wang, Alain Pagani, Didier Stricker Published: 2025-11-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2512.00909v1 Recent advancements in diffusion models have significantly improved the realism and generalizability of character-driven animation, enabling the synthesis of high-quality motion from just a single RGB image and a set of driving poses. Nevertheless, generating temporally coherent long-form content remains challenging. Existing approaches are constrained by computational and memory limitations, as they are typically trained on short video segments, thus performing effectively only over limited frame lengths and hindering their potential for extended coherent generation. To address these constraints, we propose TalkingPose, a novel diffusion-based framework specifically designed for producing long-form, temporally consistent human upper-body animations. TalkingPose leverages driving frames to precisely capture expressive facial and hand movements, transferring these seamlessly to a target actor through a stable diffusion backbone. To ensure continuous motion and enhance temporal coherence, we introduce a feedback-driven mechanism built upon image-based diffusion models. Notably, this mechanism does not incur additional computational costs or require secondary training stages, enabling the generation of animations with unlimited duration. Additionally, we introduce a comprehensive, large-scale dataset to serve as a new benchmark for human upper-body animation. --- ### Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs Authors: Xinzhu Chen, Xuesheng Li, Zhongxiang Sun, Weijie Yu Published: 2025-11-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2512.00908v1 Reinforcement Learning with Verifiable Rewards (RLVR) has become a central approach for improving the reasoning ability of large language models. Recent work studies RLVR through token entropy, arguing that high-entropy tokens drive exploration and should receive stronger updates. However, they overlook the fact that most of a reasoning trajectory consists of low-entropy segments that encode stable and reusable structural patterns. Through qualitative and quantitative analyses, we find that the overlap of low-entropy segments across correct responses strongly correlates with model accuracy, while overlaps involving incorrect responses exhibit stable but unproductive patterns. Motivated by these findings, we propose LESS, a correctness-aware reinforcement framework that performs fine-grained advantage modulation over low-entropy segments. LESS amplifies segments unique to correct responses, suppresses those unique to incorrect ones, and neutralizes segments shared by both, while preserving high-entropy exploration in the underlying RL algorithm. Instantiated on top of the popular GRPO, LESS consistently improves accuracy over strong RL baselines across three backbones and six math benchmarks, achieves stronger robustness of the performance floor. --- ### Hierarchical Semantic Alignment for Image Clustering Authors: Xingyu Zhu, Beier Zhu, Yunfan Li, Junfeng Fang, Shuo Wang, Kesen Zhao, Hanwang Zhang Published: 2025-11-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2512.00904v1 Image clustering is a classic problem in computer vision, which categorizes images into different groups. Recent studies utilize nouns as external semantic knowledge to improve clustering performance. However, these methods often overlook the inherent ambiguity of nouns, which can distort semantic representations and degrade clustering quality. To address this issue, we propose a hierarChical semAntic alignmEnt method for image clustering, dubbed CAE, which improves clustering performance in a training-free manner. In our approach, we incorporate two complementary types of textual semantics: caption-level descriptions, which convey fine-grained attributes of image content, and noun-level concepts, which represent high-level object categories. We first select relevant nouns from WordNet and descriptions from caption datasets to construct a semantic space aligned with image features. Then, we align image features with selected nouns and captions via optimal transport to obtain a more discriminative semantic space. Finally, we combine the enhanced semantic and image features to perform clustering. Extensive experiments across 8 datasets demonstrate the effectiveness of our method, notably surpassing the state-of-the-art training-free approach with a 4.2% improvement in accuracy and a 2.9% improvement in adjusted rand index (ARI) on the ImageNet-1K dataset. --- ### SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead Authors: Chaojun Ni, Cheng Chen, Xiaofeng Wang, Zheng Zhu, Wenzhao Zheng, Boyuan Wang, Tianrun Chen, Guosheng Zhao, Haoyun Li, Zhehao Dong, Qiang Zhang, Yun Ye et al. Published: 2025-11-30 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2512.00903v1 Vision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To mitigate this issue, using a lightweight VLM has been explored, but it compromises spatiotemporal reasoning. Although some methods suggest that incorporating additional 3D inputs can help, they usually rely on large VLMs to fuse 3D and 2D inputs and still lack temporal understanding. Therefore, we propose SwiftVLA, an architecture that enhances a compact model with 4D understanding while preserving design efficiency. Specifically, our approach features a pretrained 4D visual geometry transformer with a temporal cache that extracts 4D features from 2D images. Then, to enhance the VLM's ability to exploit both 2D images and 4D features, we introduce Fusion Tokens, a set of learnable tokens trained with a future prediction objective to generate unified representations for action generation. Finally, we introduce a mask-and-reconstruct strategy that masks 4D inputs to the VLM and trains the VLA to reconstruct them, enabling the VLM to learn effective 4D representations and allowing the 4D branch to be dropped at inference with minimal performance loss. Experiments in real and simulated environments show that SwiftVLA outperforms lightweight baselines and rivals VLAs up to 7 times larger, achieving comparable performance on edge devices while being 18 times faster and reducing memory footprint by 12 times. ---