# Research Papers — 2026-02 · bundle page 38 of 210 > Full-text markdown of papers #1851–1900 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/38 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/37.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/39.md) ### TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer Authors: Jiawei Wang, Chuang Yang, Jiawei Yong, Xiaohang Xu, Hongjun Wang, Noboru Koshizuka, Shintaro Fukushima, Ryosuke Shibasaki, Renhe Jiang Published: 2026-02-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.20643v1 Mobility trajectories are essential for understanding urban dynamics and enhancing urban planning, yet access to such data is frequently hindered by privacy concerns. This research introduces a transformative framework for generating large-scale urban mobility trajectories, employing a novel application of a transformer-based model pre-trained and fine-tuned through a two-phase process. Initially, trajectory generation is conceptualized as an offline reinforcement learning (RL) problem, with a significant reduction in vocabulary space achieved during tokenization. The integration of Inverse Reinforcement Learning (IRL) allows for the capture of trajectory-wise reward signals, leveraging historical data to infer individual mobility preferences. Subsequently, the pre-trained model is fine-tuned using the constructed reward model, effectively addressing the challenges inherent in traditional RL-based autoregressive methods, such as long-term credit assignment and handling of sparse reward environments. Comprehensive evaluations on multiple datasets illustrate that our framework markedly surpasses existing models in terms of reliability and diversity. Our findings not only advance the field of urban mobility modeling but also provide a robust methodology for simulating urban data, with significant implications for traffic management and urban development planning. The implementation is publicly available at https://github.com/Wangjw6/TrajGPT_R. --- ### Scalable multitask Gaussian processes for complex mechanical systems with functional covariates Authors: Razak Christophe Sabi Gninkou, Andrés F. López-Lopera, Franck Massa, Rodolphe Le Riche Published: 2026-02-24 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2602.20640v2 Functional covariates arise in many scientific and engineering applications when model inputs take the form of time-dependent or spatially distributed profiles, such as varying boundary conditions or changing material behaviours. In addition, new practices in digital simulation require predictions accompanied by confidence intervals. Models based on Gaussian processes (GPs) provide principled uncertainty quantification. However, GPs capable of jointly handling functional covariates and multiple correlated functional tasks remain largely under-explored. In this work, we extend the framework of GPs with functional covariates to multitask problems by introducing a fully separable kernel structure that captures dependencies across tasks and functional inputs. By taking advantage of the Kronecker structure of the covariance matrix, the model is made scalable. The proposed model is validated on a synthetic benchmark and applied to a realistic structure, a riveted assembly with functional descriptions of the material behaviour and response forces. The proposed functional multitask GP significantly improves over single task GPs. For the riveted assembly, it requires less than 100 samples to produce an accurate mean and confidence interval prediction. Despite its larger number of parameters, the multitask GP is computationally easier to learn than its single task pendant. --- ### Grounding LLMs in Scientific Discovery via Embodied Actions Authors: Bo Zhang, Jinfeng Zhou, Yuxuan Chen, Jianing Yin, Minlie Huang, Hongning Wang Published: 2026-02-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.20639v1 Large Language Models (LLMs) have shown significant potential in scientific discovery but struggle to bridge the gap between theoretical reasoning and verifiable physical simulation. Existing solutions operate in a passive "execute-then-response" loop and thus lacks runtime perception, obscuring agents to transient anomalies (e.g., numerical instability or diverging oscillations). To address this limitation, we propose EmbodiedAct, a framework that transforms established scientific software into active embodied agents by grounding LLMs in embodied actions with a tight perception-execution loop. We instantiate EmbodiedAct within MATLAB and evaluate it on complex engineering design and scientific modeling tasks. Extensive experiments show that EmbodiedAct significantly outperforms existing baselines, achieving SOTA performance by ensuring satisfactory reliability and stability in long-horizon simulations and enhanced accuracy in scientific modeling. --- ### Identifying two piecewise linear additive value functions from anonymous preference information Authors: Vincent Auriau, Khaled Belahcene, Emmanuel Malherbe, Vincent Mousseau, Marc Pirlot Published: 2026-02-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.20638v1 Eliciting a preference model involves asking a person, named decision-maker, a series of questions. We assume that these preferences can be represented by an additive value function. In this work, we query simultaneously two decision-makers in the aim to elicit their respective value functions. For each query we receive two answers, without noise, but without knowing which answer corresponds to which decision-maker.We propose an elicitation procedure that identifies the two preference models when the marginal value functions are piecewise linear with known breaking points. --- ### SurgAtt-Tracker: Online Surgical Attention Tracking via Temporal Proposal Reranking and Motion-Aware Refinement Authors: Rulin Zhou, Guankun Wang, An Wang, Yujie Ma, Lixin Ouyang, Bolin Cui, Junyan Li, Chaowei Zhu, Mingyang Li, Ming Chen, Xiaopin Zhong, Peng Lu et al. Published: 2026-02-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.20636v1 Accurate and stable field-of-view (FoV) guidance is critical for safe and efficient minimally invasive surgery, yet existing approaches often conflate visual attention estimation with downstream camera control or rely on direct object-centric assumptions. In this work, we formulate surgical attention tracking as a spatio-temporal learning problem and model surgeon focus as a dense attention heatmap, enabling continuous and interpretable frame-wise FoV guidance. We propose SurgAtt-Tracker, a holistic framework that robustly tracks surgical attention by exploiting temporal coherence through proposal-level reranking and motion-aware refinement, rather than direct regression. To support systematic training and evaluation, we introduce SurgAtt-1.16M, a large-scale benchmark with a clinically grounded annotation protocol that enables comprehensive heatmap-based attention analysis across procedures and institutions. Extensive experiments on multiple surgical datasets demonstrate that SurgAtt-Tracker consistently achieves state-of-the-art performance and strong robustness under occlusion, multi-instrument interference, and cross-domain settings. Beyond attention tracking, our approach provides a frame-wise FoV guidance signal that can directly support downstream robotic FoV planning and automatic camera control. --- ### Enhancing Hate Speech Detection on Social Media: A Comparative Analysis of Machine Learning Models and Text Transformation Approaches Authors: Saurabh Mishra, Shivani Thakur, Radhika Mamidi Published: 2026-02-24 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.20634v1 The proliferation of hate speech on social media platforms has necessitated the development of effective detection and moderation tools. This study evaluates the efficacy of various machine learning models in identifying hate speech and offensive language and investigates the potential of text transformation techniques to neutralize such content. We compare traditional models like CNNs and LSTMs with advanced neural network models such as BERT and its derivatives, alongside exploring hybrid models that combine different architectural features. Our results indicate that while advanced models like BERT show superior accuracy due to their deep contextual understanding, hybrid models exhibit improved capabilities in certain scenarios. Furthermore, we introduce innovative text transformation approaches that convert negative expressions into neutral ones, thereby potentially mitigating the impact of harmful content. The implications of these findings are discussed, highlighting the strengths and limitations of current technologies and proposing future directions for more robust hate speech detection systems. --- ### Boosting Instance Awareness via Cross-View Correlation with 4D Radar and Camera for 3D Object Detection Authors: Xiaokai Bai, Lianqing Zheng, Si-Yuan Cao, Xiaohan Zhang, Zhe Wu, Beinan Yu, Fang Wang, Jie Bai, Hui-Liang Shen Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20632v1 4D millimeter-wave radar has emerged as a promising sensing modality for autonomous driving due to its robustness and affordability. However, its sparse and weak geometric cues make reliable instance activation difficult, limiting the effectiveness of existing radar-camera fusion paradigms. BEV-level fusion offers global scene understanding but suffers from weak instance focus, while perspective-level fusion captures instance details but lacks holistic context. To address these limitations, we propose SIFormer, a scene-instance aware transformer for 3D object detection using 4D radar and camera. SIFormer first suppresses background noise during view transformation through segmentation- and depth-guided localization. It then introduces a cross-view activation mechanism that injects 2D instance cues into BEV space, enabling reliable instance awareness under weak radar geometry. Finally, a transformer-based fusion module aggregates complementary image semantics and radar geometry for robust perception. As a result, with the aim of enhancing instance awareness, SIFormer bridges the gap between the two paradigms, combining their complementary strengths to address inherent sparse nature of radar and improve detection accuracy. Experiments demonstrate that SIFormer achieves state-of-the-art performance on View-of-Delft, TJ4DRadSet and NuScenes datasets. Source code is available at github.com/shawnnnkb/SIFormer. --- ### From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection Authors: Yepeng Liu, Hao Li, Liwen Yang, Fangzhen Li, Xudi Ge, Yuliang Gu, kuang Gao, Bing Wang, Guang Chen, Hangjun Ye, Yongchao Xu Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20630v4 Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM. Most existing learning-based methods are trained on image pairs, a paradigm that fails to explicitly optimize for the long-term trackability of keypoints across sequences under challenging viewpoint and illumination changes. In this paper, we reframe keypoint detection as a sequential decision-making problem. We introduce TraqPoint, a novel, end-to-end Reinforcement Learning (RL) framework designed to optimize the \textbf{Tra}ck-\textbf{q}uality (Traq) of keypoints directly on image sequences. Our core innovation is a track-aware reward mechanism that jointly encourages the consistency and distinctiveness of keypoints across multiple views, guided by a policy gradient method. Extensive evaluations on sparse matching benchmarks, including relative pose estimation and 3D reconstruction, demonstrate that TraqPoint significantly outperforms some state-of-the-art (SOTA) keypoint detection and description methods.The code will be available at https://github.com/xiaomi-research/traqpoint. --- ### QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs Authors: Santiago Gonzalez, Alireza Amiri Bavandpour, Peter Ye, Edward Zhang, Ruslans Aleksejevs, Todor Antić, Polina Baron, Sujeet Bhalerao, Shubhrajit Bhattacharya, Zachary Burton, John Byrne, Hyungjun Choi et al. Published: 2026-02-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.20629v3 As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation. We demonstrate that standard "LLM-as-a-Judge" protocols suffer from a systematic Alignment Gap when applied to upper-undergraduate to early graduate level mathematics. To quantify this, we introduce QEDBench, the first large-scale dual-rubric alignment benchmark to systematically measure alignment with human experts on university-level math proofs by contrasting course-specific rubrics against expert common knowledge criteria. By deploying a dual-evaluation matrix (7 judges x 5 solvers) against 1,000+ hours of human evaluation, we reveal that certain frontier evaluators like Claude Opus 4.5, DeepSeek-V3, Qwen 2.5 Max, and Llama 4 Maverick exhibit significant positive bias (up to +0.18, +0.20, +0.30, +0.36 mean score inflation, respectively). Furthermore, we uncover a critical reasoning gap in the discrete domain: while Gemini 3.0 Pro achieves state-of-the-art performance (0.91 average human evaluation score), other reasoning models like GPT-5 Pro and Claude Sonnet 4.5 see their performance significantly degrade in discrete domains. Specifically, their average human evaluation scores drop to 0.72 and 0.63 in Discrete Math, and to 0.74 and 0.50 in Graph Theory. In addition to these research results, we also release QEDBench as a public benchmark for evaluating and improving AI judges. Our benchmark is publicly published at https://github.com/qqliu/Yale-QEDBench. --- ### When can we trust untrusted monitoring? A safety case sketch across collusion strategies Authors: Nelson Gardner-Challis, Jonathan Bostock, Georgiy Kozhevnikov, Morgan Sinclaire, Joan Velja, Alessandro Abate, Charlie Griffin Published: 2026-02-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.20628v2 AIs are increasingly being deployed with greater autonomy and capabilities, which increases the risk that a misaligned AI may be able to cause catastrophic harm. Untrusted monitoring -- using one untrusted model to oversee another -- is one approach to reducing risk. Justifying the safety of an untrusted monitoring deployment is challenging because developers cannot safely deploy a misaligned model to test their protocol directly. In this paper, we develop upon existing methods for rigorously demonstrating safety based on pre-deployment testing. We relax assumptions that previous AI control research made about the collusion strategies a misaligned AI might use to subvert untrusted monitoring. We develop a taxonomy covering passive self-recognition, causal collusion (hiding pre-shared signals), acausal collusion (hiding signals via Schelling points), and combined strategies. We create a safety case sketch to clearly present our argument, explicitly state our assumptions, and highlight unsolved challenges. We identify conditions under which passive self-recognition could be a more effective collusion strategy than those studied previously. Our work builds towards more robust evaluations of untrusted monitoring. --- ### When can we trust untrusted monitoring? A safety case sketch across collusion strategies Authors: Nelson Gardner-Challis, Jonathan Bostock, Georgiy Kozhevnikov, Morgan Sinclaire, Joan Velja, Alessandro Abate, Charlie Griffin Published: 2026-02-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.20628v1 AIs are increasingly being deployed with greater autonomy and capabilities, which increases the risk that a misaligned AI may be able to cause catastrophic harm. Untrusted monitoring -- using one untrusted model to oversee another -- is one approach to reducing risk. Justifying the safety of an untrusted monitoring deployment is challenging because developers cannot safely deploy a misaligned model to test their protocol directly. In this paper, we develop upon existing methods for rigorously demonstrating safety based on pre-deployment testing. We relax assumptions that previous AI control research made about the collusion strategies a misaligned AI might use to subvert untrusted monitoring. We develop a taxonomy covering passive self-recognition, causal collusion (hiding pre-shared signals), acausal collusion (hiding signals via Schelling points), and combined strategies. We create a safety case sketch to clearly present our argument, explicitly state our assumptions, and highlight unsolved challenges. We identify conditions under which passive self-recognition could be a more effective collusion strategy than those studied previously. Our work builds towards more robust evaluations of untrusted monitoring. --- ### Object-Scene-Camera Decomposition and Recomposition for Data-Efficient Monocular 3D Object Detection Authors: Zhaonian Kuang, Rui Ding, Meng Yang, Xinhu Zheng, Gang Hua Published: 2026-02-24 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.20627v1 Monocular 3D object detection (M3OD) is intrinsically ill-posed, hence training a high-performance deep learning based M3OD model requires a humongous amount of labeled data with complicated visual variation from diverse scenes, variety of objects and camera poses.However, we observe that, due to strong human bias, the three independent entities, i.e., object, scene, and camera pose, are always tightly entangled when an image is captured to construct training data. More specifically, specific 3D objects are always captured in particular scenes with fixed camera poses, and hence lacks necessary diversity. Such tight entanglement induces the challenging issues of insufficient utilization and overfitting to uniform training data. To mitigate this, we propose an online object-scene-camera decomposition and recomposition data manipulation scheme to more efficiently exploit the training data. We first fully decompose training images into textured 3D object point models and background scenes in an efficient computation and storage manner. We then continuously recompose new training images in each epoch by inserting the 3D objects into the freespace of the background scenes, and rendering them with perturbed camera poses from textured 3D point representation. In this way, the refreshed training data in all epochs can cover the full spectrum of independent object, scene, and camera pose combinations. This scheme can serve as a plug-and-play component to boost M3OD models, working flexibly with both fully and sparsely supervised settings. In the sparsely-supervised setting, objects closest to the ego-camera for all instances are sparsely annotated. We then can flexibly increase the annotated objects to control annotation cost. For validation, our method is widely applied to five representative M3OD models and evaluated on both the KITTI and the more complicated Waymo datasets. --- ### Physics-based phenomenological characterization of cross-modal bias in multimodal models Authors: Hyeongmo Kim, Sohyun Kang, Yerin Choi, Seungyeon Ji, Junhyuk Woo, Hyunsuk Chung, Soyeon Caren Han, Kyungreem Han Published: 2026-02-24 Categories: cs.AI, cond-mat.stat-mech arXiv: https://arxiv.org/abs/2602.20624v1 The term 'algorithmic fairness' is used to evaluate whether AI models operate fairly in both comparative (where fairness is understood as formal equality, such as "treat like cases as like") and non-comparative (where unfairness arises from the model's inaccuracy, arbitrariness, or inscrutability) contexts. Recent advances in multimodal large language models (MLLMs) are breaking new ground in multimodal understanding, reasoning, and generation; however, we argue that inconspicuous distortions arising from complex multimodal interaction dynamics can lead to systematic bias. The purpose of this position paper is twofold: first, it is intended to acquaint AI researchers with phenomenological explainable approaches that rely on the physical entities that the machine experiences during training/inference, as opposed to the traditional cognitivist symbolic account or metaphysical approaches; second, it is to state that this phenomenological doctrine will be practically useful for tackling algorithmic fairness issues in MLLMs. We develop a surrogate physics-based model that describes transformer dynamics (i.e., semantic network structure and self-/cross-attention) to analyze the dynamics of cross-modal bias in MLLM, which are not fully captured by conventional embedding- or representation-level analyses. We support this position through multi-input diagnostic experiments: 1) perturbation-based analyses of emotion classification using Qwen2.5-Omni and Gemma 3n, and 2) dynamical analysis of Lorenz chaotic time-series prediction through the physical surrogate. Across two architecturally distinct MLLMs, we show that multimodal inputs can reinforce modality dominance rather than mitigate it, as revealed by structured error-attractor patterns under systematic label perturbation, complemented by dynamical analysis. --- ### RecoverMark: Robust Watermarking for Localization and Recovery of Manipulated Faces Authors: Haonan An, Xiaohui Ye, Guang Hua, Yihang Tao, Hangcheng Cao, Xiangyu Yu, Yuguang Fang Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20618v1 The proliferation of AI-generated content has facilitated sophisticated face manipulation, severely undermining visual integrity and posing unprecedented challenges to intellectual property. In response, a common proactive defense leverages fragile watermarks to detect, localize, or even recover manipulated regions. However, these methods always assume an adversary unaware of the embedded watermark, overlooking their inherent vulnerability to watermark removal attacks. Furthermore, this fragility is exacerbated in the commonly used dual-watermark strategy that adds a robust watermark for image ownership verification, where mutual interference and limited embedding capacity reduce the fragile watermark's effectiveness. To address the gap, we propose RecoverMark, a watermarking framework that achieves robust manipulation localization, content recovery, and ownership verification simultaneously. Our key insight is twofold. First, we exploit a critical real-world constraint: an adversary must preserve the background's semantic consistency to avoid visual detection, even if they apply global, imperceptible watermark removal attacks. Second, using the image's own content (face, in this paper) as the watermark enhances extraction robustness. Based on these insights, RecoverMark treats the protected face content itself as the watermark and embeds it into the surrounding background. By designing a robust two-stage training paradigm with carefully crafted distortion layers that simulate comprehensive potential attacks and a progressive training strategy, RecoverMark achieves a robust watermark embedding in no fragile manner for image manipulation localization, recovery, and image IP protection simultaneously. Extensive experiments demonstrate the proposed RecoverMark's robustness against both seen and unseen attacks and its generalizability to in-distribution and out-of-distribution data. --- ### Knowing the Unknown: Interpretable Open-World Object Detection via Concept Decomposition Model Authors: Xueqiang Lv, Shizhou Zhang, Yinghui Xing, Di Xu, Peng Wang, Yanning Zhang Published: 2026-02-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.20616v1 Open-world object detection (OWOD) requires incrementally detecting known categories while reliably identifying unknown objects. Existing methods primarily focus on improving unknown recall, yet overlook interpretability, often leading to known-unknown confusion and reduced prediction reliability. This paper aims to make the entire OWOD framework interpretable, enabling the detector to truly "knowing the unknown". To this end, we propose a concept-driven InterPretable OWOD framework(IPOW) by introducing a Concept Decomposition Model (CDM) for OWOD, which explicitly decomposes the coupled RoI features in Faster R-CNN into discriminative, shared, and background concepts. Discriminative concepts identify the most discriminative features to enlarge the distances between known categories, while shared and background concepts, due to their strong generalization ability, can be readily transferred to detect unknown categories. Leveraging the interpretable framework, we identify that known-unknown confusion arises when unknown objects fall into the discriminative space of known classes. To address this, we propose Concept-Guided Rectification (CGR) to further resolve such confusion. Extensive experiments show that IPOW significantly improves unknown recall while mitigating confusion, and provides concept-level interpretability for both known and unknown predictions. --- ### Amortized Bayesian inference for actigraph time sheet data from mobile devices Authors: Daniel Zhou, Sudipto Banerjee Published: 2026-02-24 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2602.20611v1 Mobile data technologies use ``actigraphs'' to furnish information on health variables as a function of a subject's movement. The advent of wearable devices and related technologies has propelled the creation of health databases consisting of human movement data to conduct research on mobility patterns and health outcomes. Statistical methods for analyzing high-resolution actigraph data depend on the specific inferential context, but the advent of Artificial Intelligence (AI) frameworks require that the methods be congruent to transfer learning and amortization. This article devises amortized Bayesian inference for actigraph time sheets. We pursue a Bayesian approach to ensure full propagation of uncertainty and its quantification using a hierarchical dynamic linear model. We build our analysis around actigraph data from the Physical Activity through Sustainable Transport Approaches in Los Angeles (PASTA-LA) study conducted by the Fielding School of Public Health in the University of California, Los Angeles. Apart from achieving probabilistic imputation of actigraph time sheets, we are also able to statistically learn about the time-varying impact of explanatory variables on the magnitude of acceleration (MAG) for a cohort of subjects. --- ### SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference Authors: Cuong Chi Le, Minh V. T Pham, Tung Vu Duy, Cuong Duc Van, Huy N. Phan, Hoang N. Phan, Tien N. Nguyen Published: 2026-02-24 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2602.20610v3 Specifications are vital for ensuring program correctness, yet writing them manually remains challenging and time-intensive. Recent large language model (LLM)-based methods have shown successes in generating specifications such as postconditions, but existing single-pass prompting often yields inaccurate results. In this paper, we present SpecMind, a novel framework for postcondition generation that treats LLMs as interactive and exploratory reasoners rather than one-shot generators. SpecMind employs feedback-driven multi-turn prompting approaches, enabling the model to iteratively refine candidate postconditions by incorporating implicit and explicit correctness feedback, while autonomously deciding when to stop. This process fosters deeper code comprehension and improves alignment with true program behavior via exploratory attempts. Our empirical evaluation shows that SpecMind significantly outperforms state-of-the-art approaches in both accuracy and completeness of generated postconditions. --- ### VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos Authors: Aihua Mao, Kaihang Huang, Yong-Jin Liu, Chee Seng Chan, Ying He Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20608v1 3D object affordance grounding aims to identify regions on 3D objects that support human-object interaction (HOI), a capability essential to embodied visual reasoning. However, most existing approaches rely on static visual or textual cues, neglecting that affordances are inherently defined by dynamic actions. As a result, they often struggle to localize the true contact regions involved in real interactions. We take a different perspective. Humans learn how to use objects by observing and imitating actions, not just by examining shapes. Motivated by this intuition, we introduce video-guided 3D affordance grounding, which leverages dynamic interaction sequences to provide functional supervision. To achieve this, we propose VAGNet, a framework that aligns video-derived interaction cues with 3D structure to resolve ambiguities that static cues cannot address. To support this new setting, we introduce PVAD, the first HOI video-3D pairing affordance dataset, providing functional supervision unavailable in prior works. Extensive experiments on PVAD show that VAGNet achieves state-of-the-art performance, significantly outperforming static-based baselines. The code and dataset will be open publicly. --- ### Interaction-aware Representation Modeling with Co-occurrence Consistency for Egocentric Hand-Object Parsing Authors: Yuejiao Su, Yi Wang, Lei Yao, Yawen Cui, Lap-Pui Chau Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20597v1 A fine-grained understanding of egocentric human-environment interactions is crucial for developing next-generation embodied agents. One fundamental challenge in this area involves accurately parsing hands and active objects. While transformer-based architectures have demonstrated considerable potential for such tasks, several key limitations remain unaddressed: 1) existing query initialization mechanisms rely primarily on semantic cues or learnable parameters, demonstrating limited adaptability to changing active objects across varying input scenes; 2) previous transformer-based methods utilize pixel-level semantic features to iteratively refine queries during mask generation, which may introduce interaction-irrelevant content into the final embeddings; and 3) prevailing models are susceptible to "interaction illusion", producing physically inconsistent predictions. To address these issues, we propose an end-to-end Interaction-aware Transformer (InterFormer), which integrates three key components, i.e., a Dynamic Query Generator (DQG), a Dual-context Feature Selector (DFS), and the Conditional Co-occurrence (CoCo) loss. The DQG explicitly grounds query initialization in the spatial dynamics of hand-object contact, enabling targeted generation of interaction-aware queries for hands and various active objects. The DFS fuses coarse interactive cues with semantic features, thereby suppressing interaction-irrelevant noise and emphasizing the learning of interactive relationships. The CoCo loss incorporates hand-object relationship constraints to enhance physical consistency in prediction. Our model achieves state-of-the-art performance on both the EgoHOS and the challenging out-of-distribution mini-HOI4D datasets, demonstrating its effectiveness and strong generalization ability. Code and models are publicly available at https://github.com/yuggiehk/InterFormer. --- ### OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services Authors: Longxiang Wang, Xiang Zheng, Xuhao Zhang, Yao Zhang, Ye Wu, Cong Wang Published: 2026-02-24 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.20595v1 Multi-tenant LLM serving frameworks widely adopt shared Key-Value caches to enhance efficiency. However, this creates side-channel vulnerabilities enabling prompt leakage attacks. Prior studies identified these attack surfaces yet focused on expanding attack vectors rather than optimizing attack performance, reporting impractically high attack costs that underestimate the true privacy risk. We propose OptiLeak, a reinforcement learning-enhanced framework that maximizes prompt reconstruction efficiency through two-stage fine-tuning. Our key insight is that domain-specific ``hard tokens'' -- terms difficult to predict yet carrying sensitive information -- can be automatically identified via likelihood ranking and used to construct preference pairs for Direct Preference Optimization, eliminating manual annotation. This enables effective preference alignment while avoiding the overfitting issues of extended supervised fine-tuning. Evaluated on three benchmarks spanning medical and financial domains, OptiLeak achieves up to $12.48\times$ reduction in average requests per token compared to baseline approaches, with consistent improvements across model scales from 3B to 14B parameters. Our findings demonstrate that cache-based prompt leakage poses a more severe threat than previously reported, underscoring the need for robust cache isolation in production deployments. --- ### Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning Authors: Yige Liu, Yiwei Lou, Che Wang, Yongzhi Cao, Hanpin Wang Published: 2026-02-24 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2602.20593v1 As a distributed collaborative machine learning paradigm, vertical federated learning (VFL) allows multiple passive parties with distinct features and one active party with labels to collaboratively train a model. Although it is known for the privacy-preserving capabilities, VFL still faces significant privacy and security threats from backdoor attacks. Existing backdoor attacks typically involve an attacker implanting a trigger into the model during the training phase and executing the attack by adding the trigger to the samples during the inference phase. However, in this paper, we find that triggers are not essential for backdoor attacks in VFL. In light of this, we disclose a new backdoor attack pathway in VFL by introducing a feature-based triggerless backdoor attack. This attack operates under a more stringent security assumption, where the attacker is honest-but-curious rather than malicious during the training phase. It comprises three modules: label inference for the targeted backdoor attack, poison generation with amplification and perturbation mechanisms, and backdoor execution to implement the attack. Extensive experiments on five benchmark datasets demonstrate that our attack outperforms three baseline backdoor attacks by 2 to 50 times while minimally impacting the main task. Even in VFL scenarios with 32 passive parties and only one set of auxiliary data, our attack maintains high performance. Moreover, when confronted with distinct defense strategies, our attack remains largely unaffected and exhibits strong robustness. We hope that the disclosure of this triggerless backdoor attack pathway will encourage the community to revisit security threats in VFL scenarios and inspire researchers to develop more robust and practical defense strategies. --- ### Characterizing Online and Private Learnability under Distributional Constraints via Generalized Smoothness Authors: Moïse Blanchard, Abhishek Shetty, Alexander Rakhlin Published: 2026-02-24 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.20585v1 Understanding minimal assumptions that enable learning and generalization is perhaps the central question of learning theory. Several celebrated results in statistical learning theory, such as the VC theorem and Littlestone's characterization of online learnability, establish conditions on the hypothesis class that allow for learning under independent data and adversarial data, respectively. Building upon recent work bridging these extremes, we study sequential decision making under distributional adversaries that can adaptively choose data-generating distributions from a fixed family $U$ and ask when such problems are learnable with sample complexity that behaves like the favorable independent case. We provide a near complete characterization of families $U$ that admit learnability in terms of a notion known as generalized smoothness i.e. a distribution family admits VC-dimension-dependent regret bounds for every finite-VC hypothesis class if and only if it is generalized smooth. Further, we give universal algorithms that achieve low regret under any generalized smooth adversary without explicit knowledge of $U$. Finally, when $U$ is known, we provide refined bounds in terms of a combinatorial parameter, the fragmentation number, that captures how many disjoint regions can carry nontrivial mass under $U$. These results provide a nearly complete understanding of learnability under distributional adversaries. In addition, building upon the surprising connection between online learning and differential privacy, we show that the generalized smoothness also characterizes private learnability under distributional constraints. --- ### Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Change Authors: Beverley Gorry, Tobias Fischer, Michael Milford, Alejandro Fontan Published: 2026-02-24 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.20584v1 Long-term environmental monitoring requires the ability to reconstruct and align 3D models across repeated site visits separated by months or years. However, existing Structure-from-Motion (SfM) pipelines implicitly assume near-simultaneous image capture and limited appearance change, and therefore fail when applied to long-term monitoring scenarios such as coral reef surveys, where substantial visual and structural change is common. In this paper, we show that the primary limitation of current approaches lies in their reliance on post-hoc alignment of independently reconstructed sessions, which is insufficient under large temporal appearance change. We address this limitation by enforcing cross-session correspondences directly within a joint SfM reconstruction. Our approach combines complementary handcrafted and learned visual features to robustly establish correspondences across large temporal gaps, enabling the reconstruction of a single coherent 3D model from imagery captured years apart, where standard independent and joint SfM pipelines break down. We evaluate our method on long-term coral reef datasets exhibiting significant real-world change, and demonstrate consistent joint reconstruction across sessions in cases where existing methods fail to produce coherent reconstructions. To ensure scalability to large datasets, we further restrict expensive learned feature matching to a small set of likely cross-session image pairs identified via visual place recognition, which reduces computational cost and improves alignment robustness. --- ### PropFly: Learning to Propagate via On-the-Fly Supervision from Pre-trained Video Diffusion Models Authors: Wonyong Seo, Jaeho Moon, Jaehyup Lee, Soo Ye Kim, Munchurl Kim Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20583v1 Propagation-based video editing enables precise user control by propagating a single edited frame into following frames while maintaining the original context such as motion and structures. However, training such models requires large-scale, paired (source and edited) video datasets, which are costly and complex to acquire. Hence, we propose the PropFly, a training pipeline for Propagation-based video editing, relying on on-the-Fly supervision from pre-trained video diffusion models (VDMs) instead of requiring off-the-shelf or precomputed paired video editing datasets. Specifically, our PropFly leverages one-step clean latent estimations from intermediate noised latents with varying Classifier-Free Guidance (CFG) scales to synthesize diverse pairs of 'source' (low-CFG) and 'edited' (high-CFG) latents on-the-fly. The source latent serves as structural information of the video, while the edited latent provides the target transformation for learning propagation. Our pipeline enables an additional adapter attached to the pre-trained VDM to learn to propagate edits via Guidance-Modulated Flow Matching (GMFM) loss, which guides the model to replicate the target transformation. Our on-the-fly supervision ensures the model to learn temporally consistent and dynamic transformations. Extensive experiments demonstrate that our PropFly significantly outperforms the state-of-the-art methods on various video editing tasks, producing high-quality editing results. --- ### Personal Information Parroting in Language Models Authors: Nishant Subramani, Kshitish Ghate, Mona Diab Published: 2026-02-24 Categories: cs.CL, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.20580v1 Modern language models (LM) are trained on large scrapes of the Web, containing millions of personal information (PI) instances, many of which LMs memorize, increasing privacy risks. In this work, we develop the regexes and rules (R&R) detector suite to detect email addresses, phone numbers, and IP addresses, which outperforms the best regex-based PI detectors. On a manually curated set of 483 instances of PI, we measure memorization: finding that 13.6% are parroted verbatim by the Pythia-6.9b model, i.e., when the model is prompted with the tokens that precede the PI in the original document, greedy decoding generates the entire PI span exactly. We expand this analysis to study models of varying sizes (160M-6.9B) and pretraining time steps (70k-143k iterations) in the Pythia model suite and find that both model size and amount of pretraining are positively correlated with memorization. Even the smallest model, Pythia-160m, parrots 2.7% of the instances exactly. Consequently, we strongly recommend that pretraining datasets be aggressively filtered and anonymized to minimize PI parroting. --- ### Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets Authors: Yiyang Lu, Haresh Jadav, Mohammad Pedramfar, Ranveer Singh, Vaneet Aggarwal Published: 2026-02-24 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2602.20578v2 We study online maximization of non-monotone Diminishing-Return(DR)-submodular functions over down-closed convex sets, a regime where existing projection-free online methods suffer from suboptimal regret and limited feedback guarantees. Our main contribution is a new structural result showing that this class is $1/e$-linearizable under carefully designed exponential reparametrization, scaling parameter, and surrogate potential, enabling a reduction to online linear optimization. As a result, we obtain $O(T^{1/2})$ static regret with a single gradient query per round and unlock adaptive and dynamic regret guarantees, together with improved rates under semi-bandit, bandit, and zeroth-order feedback. Across all feedback models, our bounds strictly improve the state of the art. --- ### Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusion Authors: Jiaru Zhang, Manav Gagvani, Can Cui, Juntong Peng, Ruqi Zhang, Ziran Wang Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20577v1 Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged as promising candidates for end-to-end autonomous driving. However, these models typically face challenges in inference latency, action precision, and explainability. Existing autoregressive approaches struggle with slow token-by-token generation, while prior diffusion-based planners often rely on verbose, general-purpose language tokens that lack explicit geometric structure. In this work, we propose Masked Vision-Language-Action Diffusion for Autonomous Driving (MVLAD-AD), a novel framework designed to bridge the gap between efficient planning and semantic explainability via a masked vision-language-action diffusion model. Unlike methods that force actions into the language space, we introduce a discrete action tokenization strategy that constructs a compact codebook of kinematically feasible waypoints from real-world driving distributions. Moreover, we propose geometry-aware embedding learning to ensure that embeddings in the latent space approximate physical geometric metrics. Finally, an action-priority decoding strategy is introduced to prioritize trajectory generation. Extensive experiments on nuScenes and derived benchmarks demonstrate that MVLAD-AD achieves superior efficiency and outperforms state-of-the-art autoregressive and diffusion baselines in planning precision, while providing high-fidelity and explainable reasoning. --- ### An interactive enhanced driving dataset for autonomous driving Authors: Haojie Feng, Xinrui Zhang, Mengjie Tian, Peizhi Zhang, Zhuoren Li, Junpeng Huang, Xiurong Wang, Junfan Zhu, Jianzhou Wang, Dongxiao Yin, Lu Xiong Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20575v2 Driving interaction data are important for training and evaluating autonomous drivingVision-Language-Action (VLA) models, but existing datasets contain limited denseinteraction samples and weak alignment between trajectories, visual inputs, and languageannotations. This work presents the Interactive Enhanced Driving Dataset (IEDD), alarge-scale interaction-oriented dataset constructed from five naturalistic trajectory datasets:Lyft Level 5, Waymo, nuPlan, INTERACTION, and SIND. IEDD contains 7.31 millionego-centric interaction segments, including 6.66 million multi agents cases, covering head-on,car-following, merging, and crossing interactions. Each segment is associated withtrajectory-derived interaction metrics describing interaction intensity and efficiency. Based onthese annotations, IEDD-VQA further provides trajectory-reconstructed BEV videos,structured interaction semantics, and multi-turn question-answer pairs. The dataset cansupport interaction mining, long-tail scenario analysis, VLA instruction tuning, andhierarchical evaluation of perception, behavior description, physical quantification, andcounterfactual reasoning. --- ### GATES: Self-Distillation under Privileged Context with Consensus Gating Authors: Alex Stein, Furong Huang, Tom Goldstein Published: 2026-02-24 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2602.20574v1 We study self-distillation in settings where supervision is unreliable: there are no ground truth labels, verifiable rewards, or external graders to evaluate answers. We focus on document-grounded question answering with asymmetric context, where a single model serves as both tutor (with access to a relevant source document during training) and student (answering from the question alone at test time). Rather than assuming tutor correctness, we derive supervision online from tutor consensus by sampling multiple document-grounded reasoning traces and using agreement to gate learning. Conditioned on this reliability signal, we distill knowledge through full tutor reasoning trajectories (not just final answers), providing a dense and stable learning signal. Empirically, this consensus-gated trajectory distillation substantially improves transfer to the document-free student. Held-out in-domain accuracy under asymmetric evaluation improves from 46.0\% to 62.0\%, and average (maj@8) accuracy on public document-free math benchmarks improves from 20.2\% to 35.4\%. --- ### MolGraphBench: A Benchmark of GNN Architectures for Molecular Regression Tasks Authors: Rajan, Ishaan Gupta Published: 2026-02-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.20573v3 Molecules are often represented as SMILES strings, which can be readily converted to hand-crafted descriptors or fingerprints (FP) for molecular property prediction. Research has demonstrated that SMILES can be converted to molecular graphs $G = (V, E)$, with atoms as nodes $(V)$ and bonds as edges $(E)$. These molecular graphs can subsequently be used to train graph neural networks (GNN) models. Despite the recent surge in application of GNN (existing and novel architectures) for molecular property prediction, a rigorous benchmark is still lacking. We propose MolGraphBench, a comprehensive benchmark of four commonly used GNN models for molecular property prediction. Benchmarking results demonstrate graph convolutional network (GCN) and graph isomorphism networks (GIN) as the optimal GNN architectures for molecular graph regression tasks, based on absolute performance, training efficiency, transfer learning and prediction quality. The study also indicates the non-complementary nature of molecular fingerprints in the fusion (GNN-FP) framework. Furthermore, our GNN models achieved performance superior or comparable performance to current state-of-the-art GNN baselines across three datasets (GCN with RMSE of $0.518$ on B3DB, GIN-FP with RMSE of $1.022$ on FreeSolv and GIN with MAE of $63.783$ on RT datasets). Findings from this study indicate that type of GNN-layer, should be treated as a tunable hyperparameter rather than a fixed design choice to achieve superior performance. --- ### CausalReasoningBenchmark: A Real-World Benchmark for Disentangled Evaluation of Causal Identification and Estimation Authors: Ayush Sawarni, Jiyuan Tan, Vasilis Syrgkanis Published: 2026-02-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.20571v3 Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effect (ATE). This approach conflates two distinct steps in causal analysis: identification, formulating a valid research design under stated assumptions, and estimation, implementing that design numerically on finite data. We introduce CausalReasoningBenchmark, a benchmark of 174 queries across 139 real-world datasets, curated from 73 peer-reviewed research papers and three widely used causal-inference textbooks. For each query, a system must produce (i) a structured identification specification that names the strategy, the treatment, outcome, and control variables, and all design-specific elements, and (ii) a point estimate with a standard error. By scoring these two components separately, our benchmark enables granular diagnosis: it distinguishes failures in causal reasoning from errors in numerical execution. Baseline results with a state-of-the-art LLM show that, while the model correctly identifies the high-level strategy in 81% of cases, full identification-specification correctness drops to only 38%, revealing that the bottleneck lies in the nuanced details of research design rather than in computation. CausalReasoningBenchmark is publicly available on Hugging Face and is designed to foster the development of more robust automated causal-inference systems. --- ### CausalReasoningBenchmark: A Real-World Benchmark for Disentangled Evaluation of Causal Identification and Estimation Authors: Ayush Sawarni, Jiyuan Tan, Vasilis Syrgkanis Published: 2026-02-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.20571v2 Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effect (ATE). This approach conflates two distinct steps in causal analysis: identification - formulating a valid research design under stated assumptions - and estimation - implementing that design numerically on finite data. We introduce CausalReasoningBenchmark, a benchmark of 173 queries across 132 real-world datasets, curated from 79 peer-reviewed research papers and three widely-used causal-inference textbooks. For each query a system must produce (i) a structured identification specification that names the strategy, the treatment, outcome, and control variables, and all design-specific elements, and (ii) a point estimate with a standard error. By scoring these two components separately, our benchmark enables granular diagnosis: it distinguishes failures in causal reasoning from errors in numerical execution. Baseline results with a state of the art LLM show that, while the model correctly identifies the high-level strategy in 79% of cases, full identification-specification correctness drops to only 34%, revealing that the bottleneck lies in the nuanced details of research design rather than in computation. CausalReasoningBenchmark is publicly available on Hugging Face and is designed to foster the development of more robust automated causal-inference systems. --- ### AIForge-Doc: A Benchmark for Detecting AI-Forged Tampering in Financial and Form Documents Authors: Jiaqi Wu, Yuchen Zhou, Muduo Xu, Zisheng Liang, Simiao Ren, Jiayu Xue, Meige Yang, Siying Chen, Jingheng Huan Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20569v1 We present AIForge-Doc, the first dedicated benchmark targeting exclusively diffusion-model-based inpainting in financial and form documents with pixel-level annotation. Existing document forgery datasets rely on traditional digital editing tools (e.g., Adobe Photoshop, GIMP), creating a critical gap: state-of-the-art detectors are blind to the rapidly growing threat of AI-forged document fraud. AIForge-Doc addresses this gap by systematically forging numeric fields in real-world receipt and form images using two AI inpainting APIs -- Gemini 2.5 Flash Image and Ideogram v2 Edit -- yielding 4,061 forged images from four public document datasets (CORD, WildReceipt, SROIE, XFUND) across nine languages, annotated with pixel-precise tampered-region masks in DocTamper-compatible format. We benchmark three representative detectors -- TruFor, DocTamper, and a zero-shot GPT-4o judge -- and find that all existing methods degrade substantially: TruFor achieves AUC=0.751 (zero-shot, out-of-distribution) vs. AUC=0.96 on NIST16; DocTamper achieves AUC=0.563 vs. AUC=0.98 in-distribution, with pixel-level IoU=0.020; GPT-4o achieves only 0.509 -- essentially at chance -- confirming that AI-forged values are indistinguishable to automated detectors and VLMs. These results demonstrate that AIForge-Doc represents a qualitatively new and unsolved challenge for document forensics. --- ### Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs Authors: Yifei Liang, Yan Sun, Xiaochun Cao, Li Shen Published: 2026-02-24 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2602.20567v1 Push-Sum-based decentralized learning enables optimization over directed communication networks, where information exchange may be asymmetric. While convergence properties of such methods are well understood, their finite-iteration stability and generalization behavior remain unclear due to structural bias induced by column-stochastic mixing and asymmetric error propagation. In this work, we develop a unified uniform-stability framework for the Stochastic Gradient Push (SGP) algorithm that captures the effect of directed topology. A key technical ingredient is an imbalance-aware consistency bound for Push-Sum, which controls consensus deviation through two quantities: the stationary distribution imbalance parameter $δ$ and the spectral gap $(1-λ)$ governing mixing speed. This decomposition enables us to disentangle statistical effects from topology-induced bias. We establish finite-iteration stability and optimization guarantees for both convex objectives and non-convex objectives satisfying the Polyak--Łojasiewicz condition. For convex problems, SGP attains excess generalization error of order $\tilde{\mathcal{O}}\!\left(\frac{1}{\sqrt{mn}}+\fracγ{δ(1-λ)}+γ\right)$ under step-size schedules, and we characterize the corresponding optimal early stopping time that minimizes this bound. For PŁ objectives, we obtain convex-like optimization and generalization rates with dominant dependence proportional to $κ\!\left(1+\frac{1}{δ(1-λ)}\right)$, revealing a multiplicative coupling between problem conditioning and directed communication topology. Our analysis clarifies when Push-Sum correction is necessary compared with standard decentralized SGD and quantifies how imbalance and mixing jointly shape the best attainable learning performance. --- ### BFA++: Hierarchical Best-Feature-Aware Token Prune for Multi-View Vision Language Action Model Authors: Haosheng Li, Weixin Mao, Zihan Lan, Hongwei Xiong, Hongan Wang, Chenyang Si, Ziwei Liu, Xiaoming Deng, Hua Chen Published: 2026-02-24 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.20566v1 Vision-Language-Action (VLA) models have achieved significant breakthroughs by leveraging Large Vision Language Models (VLMs) to jointly interpret instructions and visual inputs. However, the substantial increase in visual tokens, particularly from multi-view inputs, poses serious challenges to real-time robotic manipulation. Existing acceleration techniques for VLMs, such as token pruning, often result in degraded performance when directly applied to VLA models, as they overlook the relationships between different views and fail to account for the dynamic and task-specific characteristics of robotic operation. To address this, we propose BFA++, a dynamic token pruning framework designed specifically for VLA models. BFA++ introduces a hierarchical pruning strategy guided by two-level importance predictors: an intra-view predictor highlights task-relevant regions within each image to suppress spatial noise, while an inter-view predictor identifies critical camera views throughout different manipulation phases to reduce cross-view redundancy. This design enables efficient token selection while preserving essential visual cues, resulting in improved computational efficiency and higher manipulation success rates. Evaluations on the RoboTwin benchmark and real-world robotic tasks demonstrate that BFA++ consistently outperforms existing methods. BFA++ improves the success rate by about 10% on both the π0 and RDT models, achieving speedup of 1.8X and 1.5X, respectively. Our results highlight that context-sensitive and task-aware token pruning serves as a more effective strategy than full visual processing, enabling faster inference and improved manipulation accuracy in real-world robotic systems. --- ### From Logs to Language: Learning Optimal Verbalization for LLM-Based Recommendation at Industry Scale Authors: Yucheng Shi, Ying Li, Yu Wang, Yesu Feng, Arjun Rao, Rein Houthooft, Shradha Sehgal, Jin Wang, Hao Zhen, Ninghao Liu, Linas Baltrunas Published: 2026-02-24 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2602.20558v2 Large language models (LLMs) are promising backbones for generative recommender systems, yet a key challenge remains underexplored: verbalization, i.e., converting structured user interaction logs into effective natural language inputs. Existing methods rely on rigid templates that simply concatenate fields, yielding suboptimal representations for recommendation. We propose a data-centric framework that learns verbalization for LLM-based recommendation. Using reinforcement learning, a verbalization agent transforms raw interaction histories into optimized textual contexts, with recommendation accuracy as the training signal. This agent learns to filter noise, incorporate relevant metadata, and reorganize information to improve downstream predictions. Experiments on a large-scale industrial streaming dataset from Netflix show that learned verbalization delivers up to 93% relative improvement in discovery item recommendation accuracy over template-based baselines. Further analysis reveals emergent strategies such as user interest summarization, noise removal, and syntax normalization, offering insights into effective context construction for LLM-based recommender systems. --- ### GENSR: Symbolic Regression Based in Equation Generative Space Authors: Qian Li, Yuxiao Hu, Juncheng Liu, Yuntian Chen Published: 2026-02-24 Categories: cs.LG, cs.SC arXiv: https://arxiv.org/abs/2602.20557v1 Symbolic Regression (SR) tries to reveal the hidden equations behind observed data. However, most methods search within a discrete equation space, where the structural modifications of equations rarely align with their numerical behavior, leaving fitting error feedback too noisy to guide exploration. To address this challenge, we propose GenSR, a generative latent space-based SR framework following the `map construction -> coarse localization -> fine search'' paradigm. Specifically, GenSR first pretrains a dual-branch Conditional Variational Autoencoder (CVAE) to reparameterize symbolic equations into a generative latent space with symbolic continuity and local numerical smoothness. This space can be regarded as a well-structured `map'' of the equation space, providing directional signals for search. At inference, the CVAE coarsely localizes the input data to promising regions in the latent space. Then, a modified CMA-ES refines the candidate region, leveraging smooth latent gradients. From a Bayesian perspective, GenSR reframes the SR task as maximizing the conditional distribution $p(\mathrm{Equ.} \mid \mathrm{Num.})$, with CVAE training achieving this objective through the Evidence Lower Bound (ELBO). This new perspective provides a theoretical guarantee for the effectiveness of GenSR. Extensive experiments show that GenSR jointly optimizes predictive accuracy, expression simplicity, and computational efficiency, while remaining robust under noise. --- ### WildGHand: Learning Anti-Perturbation Gaussian Hand Avatars from Monocular In-the-Wild Videos Authors: Hanhui Li, Xuan Huang, Wanquan Liu, Yuhao Cheng, Long Chen, Yiqiang Yan, Xiaodan Liang, Chenqiang Gao Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20556v1 Despite recent progress in 3D hand reconstruction from monocular videos, most existing methods rely on data captured in well-controlled environments and therefore degrade in real-world settings with severe perturbations, such as hand-object interactions, extreme poses, illumination changes, and motion blur. To tackle these issues, we introduce WildGHand, an optimization-based framework that enables self-adaptive 3D Gaussian splatting on in-the-wild videos and produces high-fidelity hand avatars. WildGHand incorporates two key components: (i) a dynamic perturbation disentanglement module that explicitly represents perturbations as time-varying biases on 3D Gaussian attributes during optimization, and (ii) a perturbation-aware optimization strategy that generates per-frame anisotropic weighted masks to guide optimization. Together, these components allow the framework to identify and suppress perturbations across both spatial and temporal dimensions. We further curate a dataset of monocular hand videos captured under diverse perturbations to benchmark in-the-wild hand avatar reconstruction. Extensive experiments on this dataset and two public datasets demonstrate that WildGHand achieves state-of-the-art performance and substantially improves over its base model across multiple metrics (e.g., up to a $15.8\%$ relative gain in PSNR and a $23.1\%$ relative reduction in LPIPS). Our implementation and dataset are available at https://github.com/XuanHuang0/WildGHand. --- ### Standard Transformers Achieve the Minimax Rate in Nonparametric Regression with $C^{s,λ}$ Targets Authors: Yanming Lai, Defeng Sun Published: 2026-02-24 Categories: stat.ML, cs.IT, cs.LG arXiv: https://arxiv.org/abs/2602.20555v2 The tremendous success of Transformer models in fields such as large language models and computer vision necessitates a rigorous theoretical investigation. To the best of our knowledge, this paper is the first work proving that standard Transformers can approximate Hölder functions $ C^{s,λ}\left((0,1)^{d\times n}\right) $$ (s\in\mathbb{N}_{\geq0},0<λ\leq1) $ under the $L^t$ distance ($t \in (1, \infty)$) with arbitrary precision. Building upon this approximation result, we demonstrate that standard Transformers achieve the minimax optimal rate in nonparametric regression for Hölder target functions. It is worth mentioning that, by introducing two metrics: the size tuple and the dimension vector, we provide a fine-grained characterization of Transformer structures, which facilitates future research on the generalization and optimization errors of Transformers with different structures. As intermediate results, we also derive the upper bounds for the Lipschitz constant of standard Transformers and their memorization capacity, which may be of independent interest. These findings provide theoretical justification for the powerful capabilities of Transformer models. --- ### CAD-Prompted SAM3: Geometry-Conditioned Instance Segmentation for Industrial Objects Authors: Zhenran Tang, Rohan Nagabhirava, Changliu Liu Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20551v3 Verbal-prompted segmentation is inherently limited by the expressiveness of natural language and struggles with uncommon, instance-specific, or difficult-to-describe objects: scenarios frequently encountered in manufacturing and 3D printing environments. While image exemplars provide an alternative, they primarily encode appearance cues such as color and texture, which are often unrelated to a part's geometric identity. In industrial settings, a single component may be produced in different materials, finishes, or colors, making appearance-based prompting unreliable. In contrast, such objects are typically defined by precise CAD models that capture their canonical geometry. We propose a CAD-prompted segmentation framework built on SAM3 that uses canonical multi-view renderings of a CAD model as prompt input. The rendered views provide geometry-based conditioning independent of surface appearance. The model is trained using synthetic data generated from mesh renderings in simulation under diverse viewpoints and scene contexts. Our approach enables single-stage, CAD-prompted mask prediction, extending promptable segmentation to objects that cannot be robustly described by language or appearance alone. --- ### The Finite Primitive Basis Theorem for Computational Imaging: Formal Foundations of the OperatorGraph Representation Authors: Chengshuai Yang Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20550v1 Computational imaging forward models, from coded aperture spectral cameras to MRI scanners, are traditionally implemented as monolithic, modality-specific codes. We prove that every forward model in a broad, precisely defined operator class Cimg (encompassing clinical, scientific, and industrial imaging modalities, both linear and nonlinear) admits an epsilon-approximate representation as a typed directed acyclic graph (DAG) whose nodes are drawn from a library of exactly 11 canonical primitives: Propagate, Modulate, Project, Encode, Convolve, Accumulate, Detect, Sample, Disperse, Scatter, and Transform. We call this the Finite Primitive Basis Theorem. The proof is constructive: we provide an algorithm that, given any H in Cimg, produces a DAG G with relative operator error at most epsilon and graph complexity within prescribed bounds. We further prove that the library is minimal: removing any single primitive causes at least one modality to lose its epsilon-approximate representation. A systematic analysis of nonlinearities in imaging physics shows they fall into two structural categories: pointwise scalar functions (handled by Transform) and self-consistent iterations (unrolled into existing linear primitives). Empirical validation on 31 linear modalities confirms eimg below 0.01 with at most 5 nodes and depth 5, and we provide constructive DAG decompositions for 9 additional nonlinear modalities. These results establish mathematical foundations for the Physics World Model (PWM) framework. --- ### Sample-efficient evidence estimation of score based priors for model selection Authors: Frederic Wang, Katherine L. Bouman Published: 2026-02-24 Categories: cs.LG, cs.CV, stat.ME arXiv: https://arxiv.org/abs/2602.20549v2 The choice of prior is central to solving ill-posed imaging inverse problems, making it essential to select one consistent with the measurements $y$ to avoid severe bias. In Bayesian inverse problems, this could be achieved by evaluating the model evidence $p(y \mid M)$ under different models $M$ that specify the prior and then selecting the one with the highest value. Diffusion models are the state-of-the-art approach to solving inverse problems with a data-driven prior; however, directly computing the model evidence with respect to a diffusion prior is intractable. Furthermore, most existing model evidence estimators require either many pointwise evaluations of the unnormalized prior density or an accurate clean prior score. We propose DiME, an estimator of the model evidence of a diffusion prior by integrating over the time-marginals of posterior sampling methods. Our method leverages the large amount of intermediate samples naturally obtained during the reverse diffusion sampling process to obtain an accurate estimation of the model evidence using only a handful of posterior samples (e.g., 20). We also demonstrate how to implement our estimator in tandem with recent diffusion posterior sampling methods. Empirically, our estimator matches the model evidence when it can be computed analytically, and it is able to both select the correct diffusion model prior and diagnose prior misfit under different highly ill-conditioned, non-linear inverse problems, including a real-world black hole imaging problem. --- ### Robust Spiking Neural Networks Against Adversarial Attacks Authors: Shuai Wang, Malu Zhang, Yulin Jiang, Dehao Zhang, Ammar Belatreche, Yu Liang, Yimeng Shan, Zijian Zhou, Yang Yang, Haizhou Li Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20548v1 Spiking Neural Networks (SNNs) represent a promising paradigm for energy-efficient neuromorphic computing due to their bio-plausible and spike-driven characteristics. However, the robustness of SNNs in complex adversarial environments remains significantly constrained. In this study, we theoretically demonstrate that those threshold-neighboring spiking neurons are the key factors limiting the robustness of directly trained SNNs. We find that these neurons set the upper limits for the maximum potential strength of adversarial attacks and are prone to state-flipping under minor disturbances. To address this challenge, we propose a Threshold Guarding Optimization (TGO) method, which comprises two key aspects. First, we incorporate additional constraints into the loss function to move neurons' membrane potentials away from their thresholds. It increases SNNs' gradient sparsity, thereby reducing the theoretical upper bound of adversarial attacks. Second, we introduce noisy spiking neurons to transition the neuronal firing mechanism from deterministic to probabilistic, decreasing their state-flipping probability due to minor disturbances. Extensive experiments conducted in standard adversarial scenarios prove that our method significantly enhances the robustness of directly trained SNNs. These findings pave the way for advancing more reliable and secure neuromorphic computing in real-world applications. --- ### What Drives Students' Use of AI Chatbots? Technology Acceptance in Conversational AI Authors: Griffin Pitts, Sanaz Motamedi Published: 2026-02-24 Categories: cs.HC, cs.AI, cs.CY, cs.ET arXiv: https://arxiv.org/abs/2602.20547v1 Conversational AI tools have been rapidly adopted by students and are becoming part of their learning routines. To understand what drives this adoption, we draw on the Technology Acceptance Model (TAM) and examine how perceived usefulness and perceived ease of use relate to students' behavioral intention to use conversational AI that generates responses for learning tasks. We extend TAM by incorporating trust, perceived enjoyment, and subjective norms as additional factors that capture social and affective influences and uncertainty around AI outputs. Using partial least squares structural equation modeling, we find perceived usefulness remains the strongest predictor of students' intention to use conversational AI. However, perceived ease of use does not exert a significant direct effect on behavioral intention once other factors are considered, operating instead indirectly through perceived usefulness. Trust and subjective norms significantly influence perceptions of usefulness, while perceived enjoyment exerts both a direct and indirect effect on usage intentions. These findings suggest that adoption decisions for conversational AI systems are influenced less by effort-related considerations and more by confidence in system outputs, affective engagement, and social context. Future research is needed to further examine how these acceptance relationships generalize across different conversational systems and usage contexts. --- ### Beyond Human Performance: A Vision-Language Multi-Agent Approach for Quality Control in Pharmaceutical Manufacturing Authors: Subhra Jyoti Mandal, Lara Rachidi, Puneet Jain, Matthieu Duvinage, Sander W. Timmer Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20543v1 Colony-forming unit (CFU) detection is critical in pharmaceutical manufacturing, serving as a key component of Environmental Monitoring programs and ensuring compliance with stringent quality standards. Manual counting is labor-intensive and error-prone, while deep learning (DL) approaches, though accurate, remain vulnerable to sample quality variations and artifacts. Building on our earlier CNN-based framework (Beznik et al., 2020), we evaluated YOLOv5, YOLOv7, and YOLOv8 for CFU detection; however, these achieved only 97.08 percent accuracy, insufficient for pharmaceutical-grade requirements. A custom Detectron2 model trained on GSK's dataset of over 50,000 Petri dish images achieved 99 percent detection rate with 2 percent false positives and 0.6 percent false negatives. Despite high validation accuracy, Detectron2 performance degrades on outlier cases including contaminated plates, plastic artifacts, or poor optical clarity. To address this, we developed a multi-agent framework combining DL with vision-language models (VLMs). The VLM agent first classifies plates as valid or invalid. For valid samples, both DL and VLM agents independently estimate colony counts. When predictions align within 5 percent, results are automatically recorded in Postgres and SAP; otherwise, samples are routed for expert review. Expert feedback enables continuous retraining and self-improvement. Initial DL-based automation reduced human verification by 50 percent across vaccine manufacturing sites. With VLM integration, this increased to 85 percent, delivering significant operational savings. The proposed system provides a scalable, auditable, and regulation-ready solution for microbiological quality control, advancing automation in biopharmaceutical production. --- ### Maximin Share Guarantees via Limited Cost-Sensitive Sharing Authors: Hana Salavcova, Martin Černý, Arpita Biswas Published: 2026-02-24 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2602.20541v3 We study the problem of fairly allocating indivisible goods when limited sharing is allowed, that is, each good may be allocated to up to $k$ agents, while incurring a cost for sharing. While classic maximin share (MMS) allocations may not exist in many instances, we demonstrate that allowing controlled sharing can restore fairness guarantees that are otherwise unattainable in certain scenarios. (1) Our first contribution shows that exact maximin share (MMS) allocations are guaranteed to exist whenever goods are allowed to be cost-sensitively shared among at least half of the agents and the number of agents is even; for odd numbers of agents, we obtain a slightly weaker MMS guarantee. (2) We further design a Shared Bag-Filling Algorithm that guarantees a $(1 - C)(k - 1)$-approximate MMS allocation, where $C$ is the maximum cost of sharing a good. Notably, when $(1 - C)(k - 1) \geq 1$, our algorithm recovers an exact MMS allocation. (3) We additionally introduce the Sharing Maximin Share (SMMS) fairness notion, a natural extension of MMS to the $k$-sharing setting. (4) We show that SMMS allocations always exist under identical utilities and for instances with two agents. (5) We construct a counterexample to show the impossibility of the universal existence of an SMMS allocation. (6) Finally, we establish a connection between SMMS and constrained MMS (CMMS), yielding approximation guarantees for SMMS via existing CMMS results. These contributions provide deep theoretical insights for the problem of fair resource allocation when a limited sharing of resources are allowed in multi-agent environments. --- ### Progressive Per-Branch Depth Optimization for DEFOM-Stereo and SAM3 Joint Analysis in UAV Forestry Applications Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green Published: 2026-02-24 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.20539v1 Accurate per-branch 3D reconstruction is a prerequisite for autonomous UAV-based tree pruning; however, dense disparity maps from modern stereo matchers often remain too noisy for individual branch analysis in complex forest canopies. This paper introduces a progressive pipeline integrating DEFOM-Stereo foundation-model disparity estimation, SAM3 instance segmentation, and multi-stage depth optimization to deliver robust per-branch point clouds. Starting from a naive baseline, we systematically identify and resolve three error families through successive refinements. Mask boundary contamination is first addressed through morphological erosion and subsequently refined via a skeleton-preserving variant to safeguard thin-branch topology. Segmentation inaccuracy is then mitigated using LAB-space Mahalanobis color validation coupled with cross-branch overlap arbitration. Finally, depth noise - the most persistent error source - is initially reduced by outlier removal and median filtering, before being superseded by a robust five-stage scheme comprising MAD global detection, spatial density consensus, local MAD filtering, RGB-guided filtering, and adaptive bilateral filtering. Evaluated on 1920x1080 stereo imagery of Radiata pine (Pinus radiata) acquired with a ZED Mini camera (63 mm baseline) from a UAV in Canterbury, New Zealand, the proposed pipeline reduces the average per-branch depth standard deviation by 82% while retaining edge fidelity. The result is geometrically coherent 3D point clouds suitable for autonomous pruning tool positioning. All code and processed data are publicly released to facilitate further UAV forestry research. --- ### PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning Authors: Xinyong Cai, Changbin Sun, Yong Wang, Hongyu Yang, Yuankai Wu Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20537v3 Spatiotemporal predictive learning (STPL) aims to forecast future frames from past observations and is essential across a wide range of applications. Compared with recurrent or hybrid architectures, pure convolutional models offer superior efficiency and full parallelism, yet their fixed receptive fields limit their ability to adaptively capture spatially varying motion patterns. Inspired by biological center-surround organization and frequency-selective signal processing, we propose PFGNet, a fully convolutional framework that dynamically modulates receptive fields through pixel-wise frequency-guided gating. The core Peripheral Frequency Gating (PFG) block extracts localized spectral cues and adaptively fuses multi-scale large-kernel peripheral responses with learnable center suppression, effectively forming spatially adaptive band-pass filters. To maintain efficiency, all large kernels are decomposed into separable 1D convolutions ($1 \times k$ followed by $k \times 1$), reducing per-channel computational cost from $O(k^2)$ to $O(2k)$. PFGNet enables structure-aware spatiotemporal modeling without recurrence or attention. Experiments on Moving MNIST, TaxiBJ, Human3.6M, and KTH show that PFGNet delivers SOTA or near-SOTA forecasting performance with substantially fewer parameters and FLOPs. Our code is available at https://github.com/fhjdqaq/PFGNet. --- ### Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Training Authors: Zhengyao Gu, Jonathan Light, Raul Astudillo, Ziyu Ye, Langzhou He, Henry Peng Zou, Wei Cheng, Santiago Paternain, Philip S. Yu, Yisong Yue Published: 2026-02-24 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.20532v1 Post-training large foundation models with reinforcement learning typically relies on massive and heterogeneous datasets, making effective curriculum learning both critical and challenging. In this work, we propose ACTOR-CURATOR, a scalable and fully automated curriculum learning framework for reinforcement learning post-training of large language models (LLMs). ACTOR-CURATOR learns a neural curator that dynamically selects training problems from large problem banks by directly optimizing for expected policy performance improvement. We formulate problem selection as a non-stationary stochastic bandit problem, derive a principled loss function based on online stochastic mirror descent, and establish regret guarantees under partial feedback. Empirically, ACTOR-CURATOR consistently outperforms uniform sampling and strong curriculum baselines across a wide range of challenging reasoning benchmarks, demonstrating improved training stability and efficiency. Notably, it achieves relative gains of 28.6% on AIME2024 and 30.5% on ARC-1D over the strongest baseline and up to 80% speedup. These results suggest that ACTOR-CURATOR is a powerful and practical approach for scalable LLM post-training. --- ### A Lightweight Vision-Language Fusion Framework for Predicting App Ratings from User Interfaces and Metadata Authors: Azrin Sultana, Firoz Ahmed Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.20531v1 App ratings are among the most significant indicators of the quality, usability, and overall user satisfaction of mobile applications. However, existing app rating prediction models are largely limited to textual data or user interface (UI) features, overlooking the importance of jointly leveraging UI and semantic information. To address these limitations, this study proposes a lightweight vision--language framework that integrates both mobile UI and semantic information for app rating prediction. The framework combines MobileNetV3 to extract visual features from UI layouts and DistilBERT to extract textual features. These multimodal features are fused through a gated fusion module with Swish activations, followed by a multilayer perceptron (MLP) regression head. The proposed model is evaluated using mean absolute error (MAE), root mean square error (RMSE), mean squared error (MSE), coefficient of determination (R2), and Pearson correlation. After training for 20 epochs, the model achieves an MAE of 0.1060, an RMSE of 0.1433, an MSE of 0.0205, an R2 of 0.8529, and a Pearson correlation of 0.9251. Extensive ablation studies further demonstrate the effectiveness of different combinations of visual and textual encoders. Overall, the proposed lightweight framework provides valuable insights for developers and end users, supports sustainable app development, and enables efficient deployment on edge devices. ---