# Research Papers — 2026-02 · bundle page 4 of 210

> Full-text markdown of papers #151–200 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/4
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/3.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/5.md)

### MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs

Authors: Yilian Liu, Xiaojun Jia, Guoshun Nan, Jiuyang Lyu, Zhican Chen, Tao Guan, Shuyuan Luo, Zhongyi Zhai, Yang Liu
Published: 2026-02-28
Categories: cs.CV, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2603.00565v1

Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content and undermine their secure deployment. Previous studies have shown that introducing additional inference steps, which disrupt security attention, can make MLLMs more susceptible to being misled into generating malicious content. However, these methods rely on single-image masking or isolated visual cues, which only modestly extend reasoning paths and thus achieve limited effectiveness, particularly against strongly aligned commercial closed-source models. To address this problem, in this paper, we propose Multi-Image Dispersion and Semantic Reconstruction (MIDAS), a multimodal jailbreak framework that decomposes harmful semantics into risk-bearing subunits, disperses them across multiple visual clues, and leverages cross-image reasoning to gradually reconstruct the malicious intent, thereby bypassing existing safety mechanisms. The proposed MIDAS enforces longer and more structured multi-image chained reasoning, substantially increases the model's reliance on visual cues while delaying the exposure of malicious semantics and significantly reducing the model's security attention, thereby improving the performance of jailbreak against advanced MLLMs. Extensive experiments across different datasets and MLLMs demonstrate that the proposed MIDAS outperforms state-of-the-art jailbreak attacks for MLLMs and achieves an average attack success rate of 81.46% across 4 closed-source MLLMs. Our code is available at this (link)(https://github.com/Winnie-Lian/MIDAS).

---

### Whisper-MLA: Reducing GPU Memory Consumption of ASR Models based on MHA2MLA Conversion

Authors: Sen Zhang, Jianguo Wei, Wenhuan Lu, Xianghu Yue, Wei Li, Qiang Li, Pengcheng Zhao, Ming Cai, Luo Si
Published: 2026-02-28
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2603.00563v1

The Transformer-based Whisper model has achieved state-of-the-art performance in Automatic Speech Recognition (ASR). However, its Multi-Head Attention (MHA) mechanism results in significant GPU memory consumption due to the linearly growing Key-Value (KV) cache usage, which is problematic for many applications especially with long-form audio. To address this, we introduce Whisper-MLA, a novel architecture that incorporates Multi-Head Latent Attention (MLA) into the Whisper model. Specifically, we adapt MLA for Whisper's absolute positional embeddings and systematically investigate its application across encoder self-attention, decoder self-attention, and cross-attention modules. Empirical results indicate that applying MLA exclusively to decoder self-attention yields the desired balance between performance and memory efficiency. Our proposed approach allows conversion of a pretrained Whisper model to Whisper-MLA with minimal fine-tuning. Extensive experiments on the LibriSpeech benchmark validate the effectiveness of this conversion, demonstrating that Whisper-MLA reduces the KV cache size by up to 87.5% while maintaining competitive accuracy.

---

### Geometry OR Tracker: Universal Geometric Operating Room Tracking

Authors: Yihua Shao, Kang Chen, Feng Xue, Siyu Chen, Long Bai, Hongyuan Yu, Hao Tang, Jinlin Wu, Nassir Navab
Published: 2026-02-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00560v1

In operating rooms (OR), world-scale multi-view 3D tracking supports downstream applications such as surgeon behavior recognition, where physically meaningful quantities such as distances and motion statistics must be measured in meters. However, real clinical deployments rarely satisfy the geometric prerequisites for stable multi-view fusion and tracking: camera calibration and RGB-D registration are always unreliable, leading to cross-view geometric inconsistency that produces "ghosting" during fusion and degrades 3D trajectories in a shared OR coordinate frame. To address this, we introduce Geometry OR Tracker, a two-stage pipeline that first rectifies imprecise calibration into a scaleconsistent and geometrically consistent camera setup with a single global scale via a Multi-view Metric Geometry Rectification module, and then performs Occlusion-Robust 3D Point Tracking directly in the unified OR world frame. On the MM-OR benchmark, improved geometric consistency translates into tracking gains: our rectification front-end reduces cross-view depth disagreement by more than 30$\times$ compared to raw calibration. Ablation studies further demonstrate the relationship between calibration quality and tracking accuracy, showing that improved geometric consistency yields stronger world-frame tracking.

---

### EMPA: Evaluating Persona-Aligned Empathy as a Process

Authors: Shiya Zhang, Yuhan Zhan, Ruixi Su, Ruihan Sun, Ziyi Song, Zhaohan Chen, Xiaofan Zhang
Published: 2026-02-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.00552v2

Evaluating persona-aligned empathy in LLM-based dialogue agents remains challenging. User states are latent, feedback is sparse and difficult to verify in situ, and seemingly supportive turns can still accumulate into trajectories that drift from persona-specific needs. We introduce EMPA, a process-oriented framework that evaluates persona-aligned support as sustained intervention rather than isolated replies. EMPA distills real interactions into controllable, psychologically grounded scenarios, couples them with an open-ended multi-agent sandbox that exposes strategic adaptation and failure modes, and scores trajectories in a latent psychological space by directional alignment, cumulative impact, and stability. The resulting signals and metrics support reproducible comparison and optimization of long-horizon empathic behavior, and they extend to other agent settings shaped by latent dynamics and weak, hard-to-verify feedback.

---

### GCL-Sampler: Discovering Kernel Similarity for Sampled GPU Simulation via Graph Contrastive Learning

Authors: Jiaqi Wang, Jingwei Sun, Jiyu Luo, Han Li, Guangzhong Sun
Published: 2026-02-28
Categories: cs.PF, cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2603.00551v1

GPU architectural simulation is orders of magnitude slower than native execution, necessitating workload sampling for practical speedups. Existing methods rely on hand-crafted features with limited expressiveness, yielding either aggressive sampling with high errors or conservative sampling with constrained speedups. To address these issues, we propose GCL-Sampler, a sampling framework that leverages Relational Graph Convolutional Networks with contrastive learning to automatically discover high-dimensional kernel similarities from trace graphs. By encoding instruction sequences and data dependencies into graph embeddings, GCL-Sampler captures rich structural and semantic properties of program execution, enabling both high fidelity and substantial speedup. Evaluations on extensive benchmarks show that GCL-Sampler achieves 258.94x average speedup against full workload with 0.37% error, outperforming state-of-the-art methods, PKA (129.23x, 20.90%), Sieve (94.90x, 4.10%) and STEM+ROOT (56.57x, 0.38%).

---

### Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning

Authors: Yu Wang, Shengjie Zhao
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00550v1

Weakly supervised video anomaly detection (WS-VAD) involves identifying the temporal intervals that contain anomalous events in untrimmed videos, where only video-level annotations are provided as supervisory signals. However, a key limitation persists in WS-VAD, as dense frame-level annotations are absent, which often leaves existing methods struggling to learn anomaly semantics effectively. To address this issue, we propose a novel framework named LAS-VAD, short for Learning Anomaly Semantics for WS-VAD, which integrates anomaly-connected component mechanism and intention awareness mechanism. The former is designed to assign video frames into distinct semantic groups within a video, and frame segments within the same group are deemed to share identical semantic information. The latter leverages an intention-aware strategy to distinguish between similar normal and abnormal behaviors (e.g., taking items and stealing). To further model the semantic information of anomalies, as anomaly occurrence is accompanied by distinct characteristic attributes (i.e., explosions are characterized by flames and thick smoke), we additionally incorporate anomaly attribute information to guide accurate detection. Extensive experiments on two benchmark datasets, XD-Violence and UCF-Crime, demonstrate that our LAS-VAD outperforms current state-of-the-art methods with remarkable gains.

---

### Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation

Authors: Zeyu Chen, Huanjin Yao, Ziwang Zhao, Min Yang
Published: 2026-02-28
Categories: cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.00546v2

Using Multimodal Large Language Models (MLLMs) as judges to achieve precise and consistent evaluations has gradually become an emerging paradigm across various domains. Evaluating the capability and reliability of MLLM-as-a-judge systems is therefore essential for ensuring trustworthy assessment. Existing judge benchmarks categorize samples by task types but fail to capture the fundamental judgment capabilities required for reliable evaluation. In this work, we introduce M-JudgeBench, a ten-dimensional capability-oriented benchmark designed to comprehensively assess the judgment abilities of MLLMs. Our benchmark decomposes evaluation into pairwise Chain-of-Thought (CoT) comparison, length bias avoidance, and process error detection tasks, jointly covering ten fine-grained subtasks. This design enables diagnosis of model reliability across reasoning styles, response lengths, and cross-model variations. Systematic evaluation uncovers the systematic weaknesses in existing MLLM-as-a-judge systems. To address this issue, we further propose Judge-MCTS, a data construction framework generating pairwise reasoning trajectories with various correctness and length. Using Judge-MCTS, we construct an MCTS-augmented dataset and train M-Judger, a series of strong judge models. Extensive experiments demonstrate the superiority of M-Judger on existing judge benchmarks as well as M-JudgeBench. Overall, our work establishes a more principled foundation for evaluating MLLM-as-a-judge through M-JudgeBench and Judge-MCTS framework, paving the way for future research on judge model evaluation and capability-driven judge training.

---

### Multiple Inputs and Mixwd data for Alzheimer's Disease Classification Based on 3D Vision Transformer

Authors: Juan A. Castro-Silva, Maria N. Moreno Garcia, Diego H. Peluffo-Ordoñez
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00545v1

The current methods for diagnosing Alzheimer Disease using Magnetic Resonance Imaging (MRI) have significant limitations. Many previous studies used 2D Transformers to analyze individual brain slices independently, potentially losing critical 3D contextual information. Region of interest-based models often focus on only a few brain regions despite Alzheimer's affecting multiple areas. Additionally, most classification models rely on a single test, whereas diagnosing Alzheimer's requires a multifaceted approach integrating diverse data sources for a more accurate assessment. This study introduces a novel methodology called the Multiple Inputs and Mixed Data 3D Vision Transformer (MIMD-3DVT). This method processes consecutive slices together to capture the feature dimensions and spatial information, fuses multiple 3D ROI imaging data inputs, and integrates mixed data from demographic factors, cognitive assessments, and brain imaging. The proposed methodology was experimentally evaluated using a combined dataset that included the Alzheimer's Disease Neuroimaging Initiative (ADNI), the Australian Imaging, Biomarker, and Lifestyle Flagship Study of Ageing (AIBL), and the Open Access Series of Imaging Studies (OASIS). Our MIMD-3DVT, utilizing single or multiple ROIs, achieved an accuracy of 97.14%, outperforming the state-of-the-art methods in distinguishing between Normal Cognition and Alzheimer's Disease.

---

### Cross-Scale Pansharpening via ScaleFormer and the PanScale Benchmark

Authors: Ke Cao, Xuanhua He, Xueheng Li, Lingting Zhu, Yingying Wang, Ao Ma, Zhanjie Zhang, Man Zhou, Chengjun Xie, Jie Zhang
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00543v2

Pansharpening aims to generate high-resolution multi-spectral images by fusing the spatial detail of panchromatic images with the spectral richness of low-resolution MS data. However, most existing methods are evaluated under limited, low-resolution settings, limiting their generalization to real-world, high-resolution scenarios. To bridge this gap, we systematically investigate the data, algorithmic, and computational challenges of cross-scale pansharpening. We first introduce PanScale, the first large-scale, cross-scale pansharpening dataset, accompanied by PanScale-Bench, a comprehensive benchmark for evaluating generalization across varying resolutions and scales. To realize scale generalization, we propose ScaleFormer, a novel architecture designed for multi-scale pansharpening. ScaleFormer reframes generalization across image resolutions as generalization across sequence lengths: it tokenizes images into patch sequences of the same resolution but variable length proportional to image scale. A Scale-Aware Patchify module enables training for such variations from fixed-size crops. ScaleFormer then decouples intra-patch spatial feature learning from inter-patch sequential dependency modeling, incorporating Rotary Positional Encoding to enhance extrapolation to unseen scales. Extensive experiments show that our approach outperforms SOTA methods in fusion quality and cross-scale generalization. The datasets and source code are available at https://github.com/caoke-963/ScaleFormer.

---

### Adaptive Dynamic Dehazing via Instruction-Driven and Task-Feedback Closed-Loop Optimization for Diverse Downstream Task Adaptation

Authors: Yafei Zhang, Shuaitian Song, Huafeng Li, Shujuan Wang, Yu Liu
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00542v3

In real-world vision systems,haze removal is required not only to enhance image visibility but also to meet the specific needs of diverse downstream tasks.To address this challenge,we propose a novel adaptive dynamic dehazing framework that incorporates a closed-loop optimization mechanism.It enables feedback-driven refinement based on downstream task performance and user instruction-guided adjustment during inference,allowing the model to satisfy the specific requirements of multiple downstream tasks without retraining.Technically,our framework integrates two complementary and innovative mechanisms: (1)a task feedback loop that dynamically modulates dehazing outputs based on performance across multiple downstream tasks,and (2) a text instruction interface that allows users to specify high-level task preferences.This dual-guidance strategy enables the model to adapt its dehazing behavior after training,tailoring outputs in real time to the evolving needs of multiple tasks.Extensive experiments across various vision tasks demonstrate the strong effectiveness,robustness,and generalizability of our approach.These results establish a new paradigm for interactive,task-adaptive dehazing that actively collaborates with downstream applications.

---

### Spectral Condition for $μ$P under Width-Depth Scaling

Authors: Chenyu Zheng, Rongzhen Wang, Xinyu Zhang, Chongxuan Li
Published: 2026-02-28
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.00541v2

Generative foundation models are increasingly scaled in both width and depth, posing significant challenges for stable feature learning and reliable hyperparameter (HP) transfer across model sizes. While maximal update parameterization ($μ$P) has provided a principled solution to both problems for width scaling, existing extensions to the joint width-depth scaling regime remain fragmented, architecture- and optimizer-specific, and often rely on technically involved theories. In this work, we develop a simple and unified spectral framework for $μ$P under joint width-depth scaling. For deep residual networks whose residual blocks contain $k$ transformations, the framework specifies how the norms of weights and their per-step updates should scale with width and depth. It reveals a fundamental transition from $k=1$ to $k\geq 2$, unifying previously disparate $μ$P formulations and identifying the $k\geq 2$ case as more appropriate for practical architectures with multi-transformation branches such as Transformers. Building on this framework, we derive a general recipe for implementing $μ$P across a broad class of optimizers by mapping spectral constraints to concrete HP parameterizations, recovering existing results and extending them to additional optimizers. Finally, experiments on GPT-2 style language models show that the $μ$P formulation derived from the $k\geq 2$ case achieves stable feature learning and robust HP transfer under width-depth scaling, whereas standard parameterization and $μ$P in the $k=1$ case often fail to do so. These results support the practical effectiveness of the proposed spectral framework.

---

### LOGIGEN: Logic-Driven Generation of Verifiable Agentic Tasks

Authors: Yucheng Zeng, Weipeng Lu, Linyun Liu, Shupeng Li, Zitian Qu, Chenghao Zhu, Shaofei Li, Zhengdong Tan, Mengyue Liu, Haotian Zhao, Zhe Zhou, Jianmin Wu
Published: 2026-02-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.00540v1

The evolution of Large Language Models (LLMs) from static instruction-followers to autonomous agents necessitates operating within complex, stateful environments to achieve precise state-transition objectives. However, this paradigm is bottlenecked by data scarcity, as existing tool-centric reverse-synthesis pipelines fail to capture the rigorous logic of real-world applications. We introduce \textbf{LOGIGEN}, a logic-driven framework that synthesizes verifiable training data based on three core pillars: \textbf{Hard-Compiled Policy Grounding}, \textbf{Logic-Driven Forward Synthesis}, and \textbf{Deterministic State Verification}. Specifically, a Triple-Agent Orchestration is employed: the \textbf{Architect} compiles natural-language policy into database constraints to enforce hard rules; the \textbf{Set Designer} initializes boundary-adjacent states to trigger critical policy conflicts; and the \textbf{Explorer} searches this environment to discover causal solution paths. This framework yields a dataset of 20,000 complex tasks across 8 domains, where validity is strictly guaranteed by checking exact state equivalence. Furthermore, we propose a verification-based training protocol where Supervised Fine-Tuning (SFT) on verifiable trajectories establishes compliance with hard-compiled policy, while Reinforcement Learning (RL) guided by dense state-rewards refines long-horizon goal achievement. On $τ^2$-Bench, LOGIGEN-32B(RL) achieves a \textbf{79.5\% success rate}, substantially outperforming the base model (40.7\%). These results demonstrate that logic-driven synthesis combined with verification-based training effectively constructs the causally valid trajectories needed for next-generation agents.

---

### Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement

Authors: Haolin Jin, Huaming Chen
Published: 2026-02-28
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2603.00539v1

Large language models (LLMs) have become essential tools in software development, widely used for requirements engineering, code generation and review tasks. Software engineers often rely on LLMs to verify if code implementation satisfy task requirements, thereby ensuring code robustness and accuracy. However, it remains unclear whether LLMs can reliably determine code against the given task descriptions, which is usually in a form of natural language specifications. In this paper, we uncover a systematic failure of LLMs in matching code to natural language requirements. Specifically, with widely adopted benchmarks and unified prompts design, we demonstrate that LLMs frequently misclassify correct code implementation as non-compliant or defective. Surprisingly, we find that more detailed prompt design, particularly with those requiring explanations and proposed corrections, leads to higher misjudgment rates, highlighting critical reliability issues for LLM-based code assistants. We further analyze the mechanisms driving these failures and evaluate the reliability of rationale-required judgments. Building on these findings, we propose a Fix-guided Verification Filter that treats the model proposed fix as executable counterfactual evidence, and validates the original and revised implementations using benchmark tests and spec-constrained augmented tests. Our results expose previously under-explored limitations in LLM-based code review capabilities, and provide practical guidance for integrating LLM-based reviewers with safeguards in automated review and development pipelines.

---

### Mathematical Foundations of Poisoning Attacks on Linear Regression over Cumulative Distribution Functions

Authors: Atsuki Sato, Martin Aumüller, Yusuke Matsui
Published: 2026-02-28
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2603.00537v1

Learned indexes are a class of index data structures that enable fast search by approximating the cumulative distribution function (CDF) using machine learning models (Kraska et al., SIGMOD'18). However, recent studies have shown that learned indexes are vulnerable to poisoning attacks, where injecting a small number of poison keys into the training data can significantly degrade model accuracy and reduce index performance (Kornaropoulos et al., SIGMOD'22). In this work, we provide a rigorous theoretical analysis of poisoning attacks targeting linear regression models over CDFs, one of the most basic regression models and a core component in many learned indexes. Our main contributions are as follows: (i) We present a theoretical proof characterizing the optimal single-point poisoning attack and show that the existing method yields the optimal attack. (ii) We show that in multi-point attacks, the existing greedy approach is not always optimal, and we rigorously derive the key properties that an optimal attack should satisfy. (iii) We propose a method to compute an upper bound of the multi-point poisoning attack's impact and empirically demonstrate that the loss under the greedy approach is often close to this bound. Our study deepens the theoretical understanding of attack strategies against linear regression models on CDFs and provides a foundation for the theoretical evaluation of attacks and defenses on learned indexes.

---

### RAFM: Retrieval-Augmented Flow Matching for Unpaired CBCT-to-CT Translation

Authors: Xianhao Zhou, Jianghao Wu, Lanfeng Zhong, Ku Zhao, Jinlong He, Shaoting Zhang, Guotai Wang
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00535v1

Cone-beam CT (CBCT) is routinely acquired in radiotherapy but suffers from severe artifacts and unreliable Hounsfield Unit (HU) values, limiting its direct use for dose calculation. Synthetic CT (sCT) generation from CBCT is therefore an important task, yet paired CBCT--CT data are often unavailable or unreliable due to temporal gaps, anatomical variation, and registration errors. In this work, we introduce rectified flow (RF) into unpaired CBCT-to-CT translation in medical imaging. Although RF is theoretically compatible with unpaired learning through distribution-level coupling and deterministic transport, its practical effectiveness under small medical datasets and limited batch sizes remains underexplored. Direct application with random or batch-local pseudo pairing can produce unstable supervision due to semantically mismatched endpoint samples. To address this challenge, we propose Retrieval-Augmented Flow Matching (RAFM), which adapts RF to the medical setting by constructing retrieval-guided pseudo pairs using a frozen DINOv3 encoder and a global CT memory bank. This strategy improves empirical coupling quality and stabilizes unpaired flow-based training. Experiments on SynthRAD2023 under a strict subject-level true-unpaired protocol show that RAFM outperforms existing methods across FID, MAE, SSIM, PSNR, and SegScore. The code is available at https://github.com/HiLab-git/RAFM.git.

---

### DenoiseFlow: Uncertainty-Aware Denoising for Reliable LLM Agentic Workflows

Authors: Yandong Yan, Junwei Peng, Shijie Li, Chenxi Li, Yifei Shang, Can Deng, Ruiting Dai, Yongqiang Zhao, Jiaqi Zhu, Yu Huang
Published: 2026-02-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.00532v1

Autonomous agents are increasingly entrusted with complex, long-horizon tasks, ranging from mathematical reasoning to software generation. While agentic workflows facilitate these tasks by decomposing them into multi-step reasoning chains, reliability degrades significantly as the sequence lengthens. Specifically, minor interpretation errors in natural-language instructions tend to compound silently across steps. We term this failure mode accumulated semantic ambiguity. Existing approaches to mitigate this often lack runtime adaptivity, relying instead on static exploration budgets, reactive error recovery, or single-path execution that ignores uncertainty entirely. We formalize the multi-step reasoning process as a Noisy MDP and propose DenoiseFlow, a closed-loop framework that performs progressive denoising through three coordinated stages: (1)Sensing estimates per-step semantic uncertainty; (2)Regulating adaptively allocates computation by routing between fast single-path execution and parallel exploration based on estimated risk; and (3)Correcting performs targeted recovery via influence-based root-cause localization. Online self-calibration continuously aligns decision boundaries with verifier feedback, requiring no ground-truth labels. Experiments on six benchmarks spanning mathematical reasoning, code generation, and multi-hop QA show that DenoiseFlow achieves the highest accuracy on every benchmark (83.3% average, +1.3% over the strongest baseline) while reducing cost by 40--56% through adaptive branching. Detailed ablation studies further confirm framework-level's robustness and generality. Code is available at https://anonymous.4open.science/r/DenoiseFlow-21D3/.

---

### Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching

Authors: Denis Blessing, Lorenz Richter, Julius Berner, Egor Malitskiy, Gerhard Neumann
Published: 2026-02-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.00530v1

Sampling from unnormalized densities using diffusion models has emerged as a powerful paradigm. However, while recent approaches that use least-squares `matching' objectives have improved scalability, they often necessitate significant trade-offs, such as restricting prior distributions or relying on unstable optimization schemes. By generalizing these methods as special forms of fixed-point iterations rooted in Nelson's relation, we develop a new method that addresses these limitations, called Bridge Matching Sampler (BMS). Our approach enables learning a stochastic transport map between arbitrary prior and target distributions with a single, scalable, and stable objective. Furthermore, we introduce a damped variant of this iteration that incorporates a regularization term to mitigate mode collapse and further stabilize training. Empirically, we demonstrate that our method enables sampling at unprecedented scales while preserving mode diversity, achieving state-of-the-art results on complex synthetic densities and high-dimensional molecular benchmarks.

---

### CaptionFool: Universal Image Captioning Model Attacks

Authors: Swapnil Parekh
Published: 2026-02-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00529v1

Image captioning models are encoder-decoder architectures trained on large-scale image-text datasets, making them susceptible to adversarial attacks. We present CaptionFool, a novel universal (input-agnostic) adversarial attack against state-of-the-art transformer-based captioning models. By modifying only 7 out of 577 image patches (approximately 1.2% of the image), our attack achieves 94-96% success rate in generating arbitrary target captions, including offensive content. We further demonstrate that CaptionFool can generate "slang" terms specifically designed to evade existing content moderation filters. Our findings expose critical vulnerabilities in deployed vision-language models and underscore the urgent need for robust defenses against such attacks. Warning: This paper contains model outputs which are offensive in nature.

---

### TP-Spikformer: Token Pruned Spiking Transformer

Authors: Wenjie Wei, Xiaolong Zhou, Malu Zhang, Ammar Belatreche, Qian Sun, Yimeng Shan, Dehao Zhang, Zijian Zhou, Zeyu Ma, Yang Yang, Haizhou Li
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00527v1

Spiking neural networks (SNNs) offer an energy-efficient alternative to traditional neural networks due to their event-driven computing paradigm. However, recent advancements in spiking transformers have focused on improving accuracy with large-scale architectures, which require significant computational resources and limit deployment on resource-constrained devices. In this paper, we propose a simple yet effective token pruning method for spiking transformers, termed TP-Spikformer, that reduces storage and computational overhead while maintaining competitive performance. Specifically, we first introduce a heuristic spatiotemporal information-retaining criterion that comprehensively evaluates tokens' importance, assigning higher scores to informative tokens for retention and lower scores to uninformative ones for pruning. Based on this criterion, we propose an information-retaining token pruning framework that employs a block-level early stopping strategy for uninformative tokens, instead of removing them outright. This also helps preserve more information during token pruning. We demonstrate the effectiveness, efficiency and scalability of TP-Spikformer through extensive experiments across diverse architectures, including Spikformer, QKFormer and Spike-driven Transformer V1 and V3, and a range of tasks such as image classification, object detection, semantic segmentation and event-based object tracking. Particularly, TP-Spikformer performs well in a training-free manner. These results reveal its potential as an efficient and practical solution for deploying SNNs in real-world applications with limited computational resources.

---

### Mesh-Pro: Asynchronous Advantage-guided Ranking Preference Optimization for Artist-style Quadrilateral Mesh Generation

Authors: Zhen Zhou, Jian Liu, Biwen Lei, Jing Xu, Haohan Weng, Yiling Zhu, Zhuo Chen, Junfeng Fan, Yunkai Ma, Dazhao Du, Song Guo, Fengshui Jing et al.
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00526v1

Reinforcement learning (RL) has demonstrated remarkable success in text and image generation, yet its potential in 3D generation remains largely unexplored. Existing attempts typically rely on offline direct preference optimization (DPO) method, which suffers from low training efficiency and limited generalization. In this work, we aim to enhance both the training efficiency and generation quality of RL in 3D mesh generation. Specifically, (1) we design the first asynchronous online RL framework tailored for 3D mesh generation post-training efficiency improvement, which is 3.75$\times$ faster than synchronous RL. (2) We propose Advantage-guided Ranking Preference Optimization (ARPO), a novel RL algorithm that achieves a better trade-off between training efficiency and generalization than current RL algorithms designed for 3D mesh generation, such as DPO and group relative policy optimization (GRPO). (3) Based on asynchronous ARPO, we propose Mesh-Pro, which additionally introduces a novel diagonal-aware mixed triangular-quadrilateral tokenization for mesh representation and a ray-based reward for geometric integrity. Mesh-Pro achieves state-of-the-art performance on artistic and dense meshes.

---

### CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles

Authors: Swapnil Parekh
Published: 2026-02-28
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.00523v2

Every mechanistic circuit carries an invisible asterisk: it reflects not just the model's computation, but the analyst's choice of pruning threshold. Change that choice and the circuit changes, yet current practice treats a single pruned subgraph as ground truth with no way to distinguish robust structure from threshold artifacts. We introduce CIRCUS, which reframes circuit discovery as a problem of uncertainty over explanations. CIRCUS prunes one attribution graph under B configurations, assigns each edge an empirical inclusion frequency s(e) in (0,1) measuring how robustly it survives across the configuration family, and extracts a consensus circuit of edges present in every view. This yields a principled core/contingent/noise decomposition (analogous to posterior model-inclusion indicators in Bayesian variable selection) that separates robust structure from threshold-sensitive artifacts, with negligible overhead. On Gemma-2-2B and Llama-3.2-1B, consensus circuits are 40x smaller than the union of all configurations while retaining comparable influence-flow explanatory power, consistently outperform influence-ranked and random baselines, and are confirmed causally relevant by activation patching.

---

### Phys-Diff: A Physics-Inspired Latent Diffusion Model for Tropical Cyclone Forecasting

Authors: Lei Liu, Xiaoning Yu, Kang Chen, Jiahui Huang, Tengyuan Liu, Hongwei Zhao, Bin Li
Published: 2026-02-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.00521v1

Tropical cyclone (TC) forecasting is critical for disaster warning and emergency response. Deep learning methods address computational challenges but often neglect physical relationships between TC attributes, resulting in predictions lacking physical consistency. To address this, we propose Phys-Diff, a physics-inspired latent diffusion model that disentangles latent features into task-specific components (trajectory, pressure, wind speed) and employs cross-task attention to introduce prior physics-inspired inductive biases, thereby embedding physically consistent dependencies among TC attributes. Phys-Diff integrates multimodal data including historical cyclone attributes, ERA5 reanalysis data, and FengWu forecast fields via a Transformer encoder-decoder architecture, further enhancing forecasting performance. Experiments demonstrate state-of-the-art performance on global and regional datasets.

---

### Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness

Authors: Yuyang Chen, Linqian Zeng, Yijin ZHou, Hengjie Li, Jidong Zhai
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00519v1

Diffusion models have achieved remarkable success in generative AI, yet their computational efficiency remains a significant challenge, particularly for Diffusion Transformers (DiTs) requiring intensive full-attention computation. While existing acceleration approaches focus on content-agnostic uniform optimization strategies, we observe that different regions in generated content exhibit heterogeneous convergence patterns during the denoising process. We present Jano, a training-free framework that leverages this insight for efficient region-aware generation. Jano introduces an early-stage complexity recognition algorithm that accurately identifies regional convergence requirements within initial denoising steps, coupled with an adaptive token scheduling runtime that optimizes computational resource allocation. Through comprehensive evaluation on state-of-the-art models, Jano achieves substantial acceleration (average 2.0 times speedup, up to 2.4 times) while preserving generation quality. Our work challenges conventional uniform processing assumptions and provides a practical solution for accelerating large-scale content generation. The source code of our implementation is available at https://github.com/chen-yy20/Jano.

---

### Vision-TTT: Efficient and Expressive Visual Representation Learning with Test-Time Training

Authors: Quan Kong, Yanru Xiao, Yuhao Shen, Cong Wang
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00518v2

Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision learners, their applications are plagued by the quadratic complexity of the self-attention mechanism. To address the challenge, we introduce a new linear-time sequence modeling method Test-Time Training (TTT) into vision and propose Vision-TTT, which treats visual sequences as datasets and compresses the visual token sequences in a novel self-supervised learning manner. By incorporating the dual-dataset strategy and Conv2d-based dataset preprocessing, Vision-TTT effectively extends vanilla TTT to model 2D visual correlations with global receptive fields. Extensive experiments show that \texttt{Vittt-T/S/B} achieve $77.7\%,81.8\%,82.7\%$ Top-1 accuracy on ImageNet classification and also greatly outperform their counterparts on downstream tasks. At $1280\times1280$ resolution, \texttt{Vittt-T} reduces FLOPs by $79.4\%$ and runs $4.72\times$ faster with $88.9\%$ less memory than DeiT-T. These results demonstrate the expressiveness and efficiency of Vision-TTT as a strong candidate for the next-generation generic visual backbone.

---

### FastBUS: A Fast Bayesian Framework for Unified Weakly-Supervised Learning

Authors: Ziquan Wang, Haobo Wang, Ke Chen, Lei Feng, Gang Chen
Published: 2026-02-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.00517v1

Machine Learning often involves various imprecise labels, leading to diverse weakly supervised settings. While recent methods aim for universal handling, they usually suffer from complex manual pre-work, ignore the relationships between associated labels, or are unable to batch process due to computational design flaws, resulting in long running times. To address these limitations, we propose a novel general framework that efficiently infers latent true label distributions across various weak supervisions. Our key idea is to express the label brute-force search process as a probabilistic transition of label variables, compressing diverse weakly supervised DFS tree structures into a shared Bayesian network. From this, we derived a latent probability calculation algorithm based on generalized belief propagation and proposed two joint acceleration strategies: 1) introducing a low-rank assumption to approximate the transition matrix, reducing time complexity; 2) designing an end-to-end state evolution module to learn batch-scale transition matrices, facilitating multi-category batch processing. In addition, the equivalence of our method with the EM algorithm in most scenarios is further demonstrated. Extensive experiments show that our method achieves SOTA results under most weakly supervised settings, and achieves up to hundreds of times faster acceleration in running time compared to other general methods.

---

### MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence

Authors: Xingyilang Yin, Chengzhengxu Li, Jiahao Chang, Chi-Man Pun, Xiaodong Cun
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00515v1

Humans are born with vision-based 4D spatial-temporal intelligence, which enables us to perceive and reason about the evolution of 3D space over time from purely visual inputs. Despite its importance, this capability remains a significant bottleneck for current multimodal large language models (MLLMs). To tackle this challenge, we introduce MLLM-4D, a comprehensive framework designed to bridge the gaps in training data curation and model post-training for spatiotemporal understanding and reasoning. On the data front, we develop a cost-efficient data curation pipeline that repurposes existing stereo video datasets into high-quality 4D spatiotemporal instructional data. This results in the MLLM4D-2M and MLLM4D-R1-30k datasets for Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT), alongside MLLM4D-Bench for comprehensive evaluation. Regarding model training, our post-training strategy establishes a foundational 4D understanding via SFT and further catalyzes 4D reasoning capabilities by employing Group Relative Policy Optimization (GRPO) with specialized Spatiotemporal Chain of Thought (ST-CoT) prompting and Spatiotemporal reward functions (ST-reward) without involving the modification of architecture. Extensive experiments demonstrate that MLLM-4D achieves state-of-the-art spatial-temporal understanding and reasoning capabilities from purely 2D RGB inputs. Project page: https://github.com/GVCLab/MLLM-4D.

---

### Wavelet-based Frame Selection by Detecting Semantic Boundary for Long Video Understanding

Authors: Wang Chen, Yuhui Zeng, Yongdong Luo, Tianyu Xie, Luojun Lin, Jiayi Ji, Yan Zhang, Xiawu Zheng
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00512v2

Frame selection is crucial due to high frame redundancy and limited context windows when applying Large Vision-Language Models (LVLMs) to long videos. Current methods typically select frames with high relevance to a given query, resulting in a disjointed set of frames that disregard the narrative structure of video. In this paper, we introduce Wavelet-based Frame Selection by Detecting Semantic Boundary (WFS-SB), a training-free framework that presents a new perspective: effective video understanding hinges not only on high relevance but, more importantly, on capturing semantic shifts - pivotal moments of narrative change that are essential to comprehending the holistic storyline of video. However, direct detection of abrupt changes in the query-frame similarity signal is often unreliable due to high-frequency noise arising from model uncertainty and transient visual variations. To address this, we leverage the wavelet transform, which provides an ideal solution through its multi-resolution analysis in both time and frequency domains. By applying this transform, we decompose the noisy signal into multiple scales and extract a clean semantic change signal from the coarsest scale. We identify the local extrema of this signal as semantic boundaries, which segment the video into coherent clips. Building on this, WFS-SB comprises a two-stage strategy: first, adaptively allocating a frame budget to each clip based on a composite importance score; and second, within each clip, employing the Maximal Marginal Relevance approach to select a diverse yet relevant set of frames. Extensive experiments show that WFS-SB significantly boosts LVLM performance, e.g., improving accuracy by 5.5% on VideoMME, 9.5% on MLVU, and 6.2% on LongVideoBench, consistently outperforming state-of-the-art methods. Our code is available at https://github.com/MAC-AutoML/WFS-SB.

---

### Multimodal Adaptive Retrieval Augmented Generation through Internal Representation Learning

Authors: Ruoshuang Du, Xin Sun, Qiang Liu, Bowen Song, Zhongqi Chen, Weiqiang Wang, Liang Wang
Published: 2026-02-28
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2603.00511v1

Visual Question Answering systems face reliability issues due to hallucinations, where models generate answers misaligned with visual input or factual knowledge. While Retrieval Augmented Generation frameworks mitigate this issue by incorporating external knowledge, static retrieval often introduces irrelevant or conflicting content, particularly in visual RAG settings where visually similar but semantically incorrect evidence may be retrieved. To address this, we propose Multimodal Adaptive RAG (MMA-RAG), which dynamically assesses the confidence in the internal knowledge of the model to decide whether to incorporate the retrieved external information into the generation process. Central to MMA-RAG is a decision classifier trained through a layer-wise analysis, which leverages joint internal visual and textual representations to guide the use of reverse image retrieval. Experiments demonstrated that the model achieves a significant improvement in response performance in three VQA datasets. Meanwhile, ablation studies highlighted the importance of internal representations in adaptive retrieval decisions. In general, the experimental results demonstrated that MMA-RAG effectively balances external knowledge utilization and inference robustness in diverse multimodal scenarios.

---

### What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models

Authors: Yingqi Fan, Junlong Tong, Anhao Zhao, Xiaoyu Shen
Published: 2026-02-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00510v1

Multimodal large language models (MLLMs) project visual tokens into the embedding space of language models, yet the internal structuring and processing of visual semantics remain poorly understood. In this work, we introduce a two-fold analytical framework featuring a novel probing tool, $\textbf{EmbedLens}$, to conduct a fine-grained analysis. We uncover a pronounced semantic sparsity at the input level: visual tokens consistently partition into sink, dead, and alive categories. Remarkably, only the alive tokens, comprising $\approx60\%$ of the total input, carry image-specific meaning. Furthermore, using a targeted patch-compression benchmark, we demonstrate that these alive tokens already encode rich, fine-grained cues (e.g., objects, colors, and OCR) prior to entering the LLM. Internal visual computations (such as visual attention and feed-forward networks) are redundant for most standard tasks. For the small subset of highly vision-centric tasks that actually benefit from internal processing, we reveal that alive tokens naturally align with intermediate LLM layers rather than the initial embedding space, indicating that shallow-layer processing is unnecessary and that direct mid-layer injection is both sufficient. Ultimately, our findings provide a unified mechanistic view of visual token processing, paving the way for more efficient and interpretable MLLM architectures through selective token pruning, minimized visual computation, and mid-layer injection. The code is released at: https://github.com/EIT-NLP/EmbedLens.

---

### Hierarchical Classification for Improved Histopathology Image Analysis

Authors: Keunho Byeon, Jinsol Song, Seong Min Hong, Yosep Chong, Jin Tae Kwak
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00504v1

Whole-slide image analysis is essential for diagnostic tasks in pathology, yet existing deep learning methods primarily rely on flat classification, ignoring hierarchical relationships among class labels. In this study, we propose HiClass, a hierarchical classification framework for improved histopathology image analysis, that enhances both coarse-grained and fine-grained WSI classification. Built based upon a multiple instance learning approach, HiClass extends it by introducing bidirectional feature integration that facilitates information exchange between coarse-grained and fine-grained feature representations, effectively learning hierarchical features. Moreover, we introduce tailored loss functions, including hierarchical consistency loss, intra- and inter-class distance loss, and group-wise cross-entropy loss, to further optimize hierarchical learning. We assess the performance of HiClass on a gastric biopsy dataset with 4 coarse-grained and 14 fine-grained classes, achieving superior classification performance for both coarse-grained classification and fine-grained classification. These results demonstrate the effectiveness of HiClass in improving WSI classification by capturing coarse-grained and fine-grained histopathological characteristics.

---

### M$^2$: Dual-Memory Augmentation for Long-Horizon Web Agents via Trajectory Summarization and Insight Retrieval

Authors: Dawei Yan, Haokui Zhang, Guangda Huzhang, Yang Li, Yibo Wang, Qing-Guo Chen, Zhao Xu, Weihua Luo, Ying Li, Wei Dong, Chunhua Shen
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00503v1

Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on extensive data collection and model training, yet still struggle with high computational costs and insufficient reasoning capabilities when facing complex, long-horizon scenarios. To address this, we propose M$^2$, a training-free, memory-augmented framework designed to optimize context efficiency and decision-making robustness. Our approach incorporates a dual-tier memory mechanism that synergizes Dynamic Trajectory Summarization (Internal Memory) to compress verbose interaction history into concise state updates, and Insight Retrieval Augmentation (External Memory) to guide the agent with actionable guidelines retrieved from an offline insight bank. Extensive evaluations across WebVoyager and OnlineMind2Web demonstrate that M$^2$ consistently surpasses baselines, yielding up to a 19.6% success rate increase and 58.7% token reduction for Qwen3-VL-32B, while proprietary models like Claude achieve accuracy gains up to 12.5% alongside significantly lower computational overhead.

---

### Trinity: A Scenario-Aware Recommendation Framework for Large-Scale Cold-Start Users

Authors: Wenhao Zheng, Wang Lu, Fangshuang Tang, Yiyang Lu, Jun Yang, Pengcheng Xiong, Yulan Yan
Published: 2026-02-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.00502v1

Early-stage users in a new scenario intensify cold-start challenges, yet prior works often address only parts of the problem through model architecture. Launching a new user experience to replace an established product involves sparse behavioral signals, low-engagement cohorts, and unstable model performance. We argue that effective recommendations require the synergistic integration of feature engineering, model architecture, and stable model updating. We propose Trinity, a framework embodying this principle. Trinity extracts valuable information from existing scenarios while ensuring predictive effectiveness and accuracy in the new scenario. In this paper, we showcase Trinity applied to a billion-user Microsoft product transition. Both offline and online experiments demonstrate that our framework achieves substantial improvements in addressing the combined challenge of new users in new scenarios.

---

### WirelessAgent++: Automated Agentic Workflow Design and Benchmarking for Wireless Networks

Authors: Jingwen Tong, Zijian Li, Fang Liu, Wei Guo, Jun Zhang
Published: 2026-02-28
Categories: cs.NI, cs.AI, eess.SP
arXiv: https://arxiv.org/abs/2603.00501v1

The integration of large language models (LLMs) into wireless networks has sparked growing interest in building autonomous AI agents for wireless tasks. However, existing approaches rely heavily on manually crafted prompts and static agentic workflows, a process that is labor-intensive, unscalable, and often suboptimal. In this paper, we propose WirelessAgent++, a framework that automates the design of agentic workflows for various wireless tasks. By treating each workflow as an executable code composed of modular operators, WirelessAgent++ casts agent design as a program search problem and solves it with a domain-adapted Monte Carlo Tree Search (MCTS) algorithm. Moreover, we establish WirelessBench, a standardized multi-dimensional benchmark suite comprising Wireless Communication Homework (WCHW), Network Slicing (WCNS), and Mobile Service Assurance (WCMSA), covering knowledge reasoning, code-augmented tool use, and multi-step decision-making. Experiments demonstrate that \wap{} autonomously discovers superior workflows, achieving test scores of $78.37\%$ (WCHW), $90.95\%$ (WCNS), and $97.07\%$ (WCMSA), with a total search cost below $\$ 5$ per task. Notably, our approach outperforms state-of-the-art prompting baselines by up to $31\%$ and general-purpose workflow optimizers by $11.1\%$, validating its effectiveness in generating robust, self-evolving wireless agents. The code is available at https://github.com/jwentong/WirelessAgent-R2.

---

### Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence

Authors: Quoc Minh Nguyen, Trung Le, Jing Wu, Anh Tuan Bui, Mehrtash Harandi
Published: 2026-02-28
Categories: cs.LG
arXiv: https://arxiv.org/abs/2603.00498v1

Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as harmful fine-tuning attacks. In this work, we show that by regularizing the gradient contribution of harmful samples encountered during fine-tuning, we can effectively mitigate the impact of harmful fine-tuning attacks. To this end, we introduce Antibody, a defense strategy that first ensures robust safety alignment for the model before fine-tuning, and then applies a safety-preservation learning algorithm during fine-tuning. Specifically, in the alignment stage before fine-tuning, we propose optimizing the model to be in a flat loss region with respect to harmful samples, which makes the safety alignment more resilient to subsequent harmful fine-tuning. Then, in the fine-tuning stage, we design a fine-tuning algorithm that applies a weighting scheme to all samples in each training batch to inhibit the model from learning from harmful samples while encouraging learning from benign samples. Experimental results demonstrate that Antibody successfully mitigates harmful fine-tuning attacks while boosting fine-tuning performance on the user-submitted dataset.

---

### A Polynomial-Time Axiomatic Alternative to SHAP for Feature Attribution

Authors: Kazuhiro Hiraki, Shinichi Ishihara, Takumi Kongo, Junnosuke Shino
Published: 2026-02-28
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.00496v1

In this paper, we provide a theoretically grounded and computationally efficient alternative to SHAP. To this end, we study feature attribution through the lens of cooperative game theory by formulating a class of XAI--TU games. Building on this formulation, we investigate equal-surplus-type and proportional-allocation-type attribution rules and propose a low-cost attribution rule, ESENSC_rev2, constructed by combining two polynomial-time closed-form rules while ensuring the null-player property in the XAI--TU domain. Extensive experiments on tabular prediction tasks demonstrate that ESENSC_rev2 closely approximates exact SHAP while substantially improving scalability as the number of features increases. These empirical results indicate that equal-surplus-type attribution rules can achieve favorable trade-offs between computational cost and approximation accuracy in high-dimensional explainability settings. To provide theoretical foundations for these findings, we establish an axiomatic characterization showing that ESENSC_rev2 is uniquely determined by efficiency, the null-player axiom, a restricted differential marginality principle, an intermediate inessential-game property, and axioms that reduce computational requirements. Our results suggest that axiomatically justified and computationally efficient attribution rules can serve as practical and theoretically principled substitutes for SHAP-based approximations in modern explainability pipelines.

---

### AI Runtime Infrastructure

Authors: Christopher Cruz
Published: 2026-02-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.00495v2

We introduce AI Runtime Infrastructure, a distinct execution-time layer that operates above the model and below the application, actively observing, reasoning over, and intervening in agent behavior to optimize task success, latency, token efficiency, reliability, and safety while the agent is running. Unlike model-level optimizations or passive logging systems, runtime infrastructure treats execution itself as an optimization surface, enabling adaptive memory management, failure detection, recovery, and policy enforcement over long-horizon agent workflows.

---

### COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation

Authors: Yuchen Che, Jingtu Wu, Hao Zheng, Asako Kanezaki
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00493v1

Estimating the 6DoF pose of a novel object with a single reference view is challenging due to occlusions, view-point changes, and outliers. A core difficulty lies in finding robust cross-view correspondences, as existing methods often rely on discrete one-to-one matching that is non-differentiable and tends to collapse onto sparse key-points. We propose Confidence-aware Optimal Geometric Correspondence (COG), an unsupervised framework that formulates correspondence estimation as a confidence-aware optimal transport problem. COG produces balanced soft correspondences by predicting point-wise confidences and injecting them as optimal transport marginals, suppressing non-overlapping regions. Semantic priors from vision foundation models further regularize the correspondences, leading to stable pose estimation. This design integrates confidence into the correspondence finding and pose estimation pipeline, enabling unsupervised learning. Experiments show unsupervised COG achieves comparable performance to supervised methods, and supervised COG outperforms them.

---

### ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models

Authors: Riccardo de Lutio, Tobias Fischer, Yen-Yu Chang, Yuxuan Zhang, Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Katarina Tothova, Zan Gojcic, Haithem Turki
Published: 2026-02-28
Categories: cs.CV, cs.AI, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2603.00492v2

Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-observed areas. Methods that leverage generative priors to correct artifacts in these areas hold promise but currently suffer from two shortcomings. The first is scalability, as existing methods use image diffusion models or bidirectional video models that are limited in the number of views they can generate in a single pass (and thus require a costly iterative distillation process for consistency). The second is quality itself, as generators used in prior work tend to produce outputs that are inconsistent with existing scene content and fail entirely in completely unobserved regions. To solve these, we propose a two-stage pipeline that leverages two key insights. First, we train a powerful bidirectional generative model with a novel opacity mixing strategy that encourages consistency with existing observations while retaining the model's ability to extrapolate novel content in unseen areas. Second, we distill it into a causal auto-regressive model that generates hundreds of frames in a single pass. This model can directly produce novel views or serve as pseudo-supervision to improve the underlying 3D representation in a simple and highly efficient manner. We evaluate our method extensively and demonstrate that it can generate plausible reconstructions in scenarios where existing approaches fail completely. When measured on commonly benchmarked datasets, we outperform all existing baselines by a wide margin, exceeding prior state-of-the-art methods by 1-3 dB PSNR.

---

### Heaviside Low-Rank Support Matrix Machine

Authors: Xianchao Xiu, Shenghao Sun, Xinrong Li, Jiyuan Tao
Published: 2026-02-28
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2603.00491v1

Support matrix machine (SMM) is an emerging classification framework that directly handles matrix-structured observations, thereby avoiding the spatial correlations destroyed by vectorization. However, most existing SMM variants rely on convex or nonconvex surrogate loss functions, which may lead to high sensitivity to noise. To address this issue, we propose a novel Heaviside low-rank SMM model called HL-SMM, which leverages the Heaviside loss instead of the common hinge or ramp losses for robustness. Moreover, the low-rank constraint is adopted to accurately characterize the inherent global structure. In theory, we analyze the Karush-Kuhn-Tucker (KKT) points and rigorously prove the sufficient and necessary conditions. In algorithms, we develop an effective proximal alternating minimization (PAM) scheme, where all subproblems have closed-form solutions. Extensive experiments on benchmark datasets validate that the proposed HL-SMM achieves superior classification accuracy and robustness compared to state-of-the-art methods.

---

### LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks

Authors: Hengjian Gao, Kaiwei Zhang, Shibo Wang, Mingjie Chen, Qihang Cao, Xianfeng Wang, Yucheng Zhu, Xiongkuo Min, Wei Sun, Dandan Zhu, Guangtao Zhai
Published: 2026-02-28
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.00490v1

The rapid progress of Multimodal Large Language Models (MLLMs) marks a significant step toward artificial general intelligence, offering great potential for augmenting human capabilities. However, their ability to provide effective assistance in dynamic, real-world environments remains largely underexplored. Existing video benchmarks predominantly assess passive understanding through retrospective analysis or isolated perception tasks, failing to capture the interactive and adaptive nature of real-time user assistance. To bridge this gap, we introduce LifeEval, a multimodal benchmark designed to evaluate real-time, task-oriented human-AI collaboration in daily life from an egocentric perspective. LifeEval emphasizes three key aspects: task-oriented holistic evaluation, egocentric real-time perception from continuous first-person streams, and human-assistant collaborative interaction through natural dialogues. Constructed via a rigorous annotation pipeline, the benchmark comprises 4,075 high-quality question-answer pairs across 6 core capability dimensions. Extensive evaluations of 26 state-of-the-art MLLMs on LifeEval reveal substantial challenges in achieving timely, effective and adaptive interaction, highlighting essential directions for advancing human-centered interactive intelligence.

---

### Dynamic Spatio-Temporal Graph Neural Network for Early Detection of Pornography Addiction in Adolescents Based on Electroencephalogram Signals

Authors: Achmad Ardani Prasha, Clavino Ourizqi Rachmadi, Sabrina Laila Mutiara, Hilman Syachr Ramadhan, Chareyl Reinalyta Borneo, Saruni Dwiasnati
Published: 2026-02-28
Categories: cs.LG, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2603.00488v1

Adolescent pornography addiction requires early detection based on objective neurobiological biomarkers because self-report is prone to subjective bias due to social stigma. Conventional machine learning has not been able to model dynamic functional connectivity of the brain that fluctuates temporally during addictive stimulus exposure. This study proposes a state-of-the-art Dynamic Spatio-Temporal Graph Neural Network (DST-GNN) that integrates Phase Lag Index (PLI)-based Graph Attention Network (GAT) for spatial modeling and Bidirectional Gated Recurrent Unit (BiGRU) for temporal dynamics. The dataset consists of 14 adolescents (7 addicted, 7 healthy) with 19-channel EEG across 9 experimental conditions. Leave-One-Subject-Out Cross Validation (LOSO-CV) evaluation shows F1-Score of 71.00%$\pm$12.10% and recall of 85.71%, a 104% improvement compared to baseline. Ablation study confirms temporal contribution of 21% and PLI graph construction of 57%. Frontal-central regions (Fz, Cz, C3, C4) are identified as dominant biomarkers with Beta contribution of 58.9% and Hjorth of 31.2%, while Cz-T7 connectivity is consistent as a trait-level biomarker for objective screening.

---

### Random Wins All: Rethinking Grouping Strategies for Vision Tokens

Authors: Qihang Fan, Yuang Ai, Huaibo Huang, Ran He
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00486v1

Since Transformers are introduced into vision architectures, their quadratic complexity has always been a significant issue that many research efforts aim to address. A representative approach involves grouping tokens, performing self-attention calculations within each group, or pooling the tokens within each group into a single token. To this end, various carefully designed grouping strategies have been proposed to enhance the performance of Vision Transformers. Here, we pose the following questions: \textbf{Are these carefully designed grouping methods truly necessary? Is there a simpler and more unified token grouping method that can replace these diverse methods?} Therefore, we propose the random grouping strategy, which involves a simple and fast random grouping strategy for vision tokens. We validate this approach on multiple baselines, and experiments show that random grouping almost outperforms all other grouping methods. When transferred to downstream tasks, such as object detection, random grouping demonstrates even more pronounced advantages. In response to this phenomenon, we conduct a detailed analysis of the advantages of random grouping from multiple perspectives and identify several crucial elements for the design of grouping strategies: positional information, head feature diversity, global receptive field, and fixed grouping pattern. We demonstrate that as long as these four conditions are met, vision tokens require only an extremely simple grouping strategy to efficiently and effectively handle various visual tasks. We also validate the effectiveness of our proposed random method across multiple modalities, including visual tasks, point cloud processing, and vision-language models. Code will be available at https://github.com/qhfan/random.

---

### RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment

Authors: Liyao Jiang, Ruichen Chen, Chao Gao, Di Niu
Published: 2026-02-28
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.00483v1

Recent text-to-image (T2I) diffusion models achieve remarkable realism, yet faithful prompt-image alignment remains challenging, particularly for complex prompts with multiple objects, relations, and fine-grained attributes. Existing training-free inference-time scaling methods rely on fixed iteration budgets that cannot adapt to prompt difficulty, while reflection-tuned models require carefully curated reflection datasets and extensive joint fine-tuning of diffusion and vision-language models, often overfitting to reflection paths data and lacking transferability across models. We introduce RAISE (Requirement-Adaptive Self-Improving Evolution), a training-free, requirement-driven evolutionary framework for adaptive T2I generation. RAISE formulates image generation as a requirement-driven adaptive scaling process, evolving a population of candidates at inference time through a diverse set of refinement actions-including prompt rewriting, noise resampling, and instructional editing. Each generation is verified against a structured checklist of requirements, enabling the system to dynamically identify unsatisfied items and allocate further computation only where needed. This achieves adaptive test-time scaling that aligns computational effort with semantic query complexity. On GenEval and DrawBench, RAISE attains state-of-the-art alignment (0.94 overall GenEval) while incurring fewer generated samples (reduced by 30-40%) and VLM calls (reduced by 80%) than prior scaling and reflection-tuned baselines, demonstrating efficient, generalizable, and model-agnostic multi-round self-improvement. Code is available at https://github.com/LiyaoJiang1998/RAISE.

---

### TokenCom: Vision-Language Model for Multimodal and Multitask Token Communications

Authors: Feibo Jiang, Siwei Tu, Li Dong, Xiaolong Li, Kezhi Wang, Cunhua Pan, Zhu Han, Jiangzhou Wang
Published: 2026-02-28
Categories: cs.CV, cs.IT
arXiv: https://arxiv.org/abs/2603.00482v1

Visual-Language Models (VLMs), with their strong capabilities in image and text understanding, offer a solid foundation for intelligent communications. However, their effectiveness is constrained by limited token granularity, overlong visual token sequences, and inadequate cross-modal alignment. To overcome these challenges, we propose TaiChi, a novel VLM framework designed for token communications. TaiChi adopts a dual-visual tokenizer architecture that processes both high- and low-resolution images to collaboratively capture pixel-level details and global conceptual features. A Bilateral Attention Network (BAN) is introduced to intelligently fuse multi-scale visual tokens, thereby enhancing visual understanding and producing compact visual tokens. In addition, a Kolmogorov Arnold Network (KAN)-based modality projector with learnable activation functions is employed to achieve precise nonlinear alignment from visual features to the text semantic space, thus minimizing information loss. Finally, TaiChi is integrated into a multimodal and multitask token communication system equipped with a joint VLM-channel coding scheme. Experimental results validate the superior performance of TaiChi, as well as the feasibility and effectiveness of the TaiChi-driven token communication system.

---

### Analyzing Physical Adversarial Example Threats to Machine Learning in Election Systems

Authors: Khaleque Md Aashiq Kamal, Surya Eada, Aayushi Verma, Subek Acharya, Adrian Yemin, Benjamin Fuller, Kaleel Mahmood
Published: 2026-02-28
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.00481v1

Developments in the machine learning voting domain have shown both promising results and risks. Trained models perform well on ballot classification tasks (> 99% accuracy) but are at risk from adversarial example attacks that cause misclassifications. In this paper, we analyze an attacker who seeks to deploy adversarial examples against machine learning ballot classifiers to compromise a U.S. election. We first derive a probabilistic framework for determining the number of adversarial example ballots that must be printed to flip an election, in terms of the probability of each candidate winning and the total number of ballots cast. Second, it is an open question as to which type of adversarial example is most effective when physically printed in the voting domain. We analyze six different types of adversarial example attacks: l_infinity-APGD, l2-APGD, l1-APGD, l0 PGD, l0 + l_infinity PGD, and l0 + sigma-map PGD. Our experiments include physical realizations of 144,000 adversarial examples through printing and scanning with four different machine learning models. We empirically demonstrate an analysis gap between the physical and digital domains, wherein attacks most effective in the digital domain (l2 and l_infinity) differ from those most effective in the physical domain (l1 and l2, depending on the model). By unifying a probabilistic election framework with digital and physical adversarial example evaluations, we move beyond prior close race analyses to explicitly quantify when and how adversarial ballot manipulation could alter outcomes.

---

### U-VLM: Hierarchical Vision Language Modeling for Report Generation

Authors: Pengcheng Shi, Minghui Zhang, Kehan Song, Jiaqi Liu, Yun Gu, Xinglin Zhang
Published: 2026-02-28
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00479v1

Automated radiology report generation is key for reducing radiologist workload and improving diagnostic consistency, yet generating accurate reports for 3D medical imaging remains challenging. Existing vision-language models face two limitations: they do not leverage segmentation-pretrained encoders, and they inject visual features only at the input layer of language models, losing multi-scale information. We propose U-VLM, which enables hierarchical vision-language modeling in both training and architecture: (1) progressive training from segmentation to classification to report generation, and (2) multi-layer visual injection that routes U-Net encoder features to corresponding language model layers. Each training stage can leverage different datasets without unified annotations. U-VLM achieves state-of-the-art performance on CT-RATE (F1: 0.414 vs 0.258, BLEU-mean: 0.349 vs 0.305) and AbdomenAtlas 3.0 (F1: 0.624 vs 0.518 for segmentation-based detection) using only a 0.1B decoder trained from scratch, demonstrating that well-designed vision encoder pretraining outweighs the benefits of 7B+ pre-trained language models. Ablation studies show that progressive pretraining significantly improves F1, while multi-layer injection improves BLEU-mean. Code is available at https://github.com/yinghemedical/U-VLM.

---

### Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols

Authors: Xu Luo, Ji Zhang, Lianli Gao, Heng Tao Shen, Jingkuan Song
Published: 2026-02-28
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2603.00478v1

Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.However, there lacks a unified, rigorous evaluation protocol that is both challenging and realistic for real-world usage. In this work, we establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets, and propose the Hyperparameter Ensemble (HPE) protocol to overcome the "validation set illusion" in data-scarce regimes. Our empirical findings demonstrate that the choice of pre-trained model is the dominant factor for performance, while many sophisticated transfer methods offer negligible practical advantages over a simple full-parameter fine-tuning baseline. To explain this surprising effectiveness, we provide an in-depth mechanistic analysis showing that full fine-tuning succeeds via distributed micro-adjustments and more flexible reshaping of high-level semantic presentations without suffering from overfitting. Additionally, we quantify the performance collapse of multimodal models in specialized domains as a result of linguistic rarity using adjusted Zipf frequency scores. By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research. We make the FEWTRANS benchmark publicly available at https://github.com/Frankluox/FewTrans.

---

### Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents

Authors: Linxi Jiang, Zhijie Liu, Haotian Luo, Zhiqiang Lin
Published: 2026-02-28
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2603.00476v1

Browser-use agents are widely used for everyday tasks. They enable automated interaction with web pages through structured DOM based interfaces or vision language models operating on page screenshots. However, web pages often change between planning and execution, causing agents to execute actions based on stale assumptions. We view this temporal mismatch as a time of check to time of use (TOCTOU) vulnerability in browser-use agents. Dynamic or adversarial web content can exploit this window to induce unintended actions. We present a large scale empirical study of TOCTOU vulnerabilities in browser-use agents using a benchmark that spans synthesized and real world websites. Using this benchmark, we evaluate 10 popular open source agents and show that TOCTOU vulnerabilities are widespread. We design a lightweight mitigation based on pre-execution validation. It monitors DOM and layout changes during planning and validates the page state immediately before action execution. This approach reduces the risk of insecure execution and mitigates unintended side effects in browser-use agents.

---

### Wireless Power Control Based on Large Language Models

Authors: Jiacheng Wang, Yucheng Sheng, Le Liang, Hao Ye, Shi Jin
Published: 2026-02-28
Categories: cs.IT, cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2603.00474v2

This paper investigates the power control problem in wireless networks by repurposing pre-trained large language models (LLMs) as relational reasoning backbones. In hyper-connected interference environments, traditional optimization methods face high computational cost, while standard message passing neural networks suffer from aggregation bottlenecks that can obscure critical high-interference structures. In response, we propose PC-LLM, a physics-informed framework that augments a pre-trained LLM with an interference-aware attention bias. The proposed bias tuning mechanism injects the physical channel gain matrix directly into the self-attention scores, enabling explicit fusion of wireless topology with pre-trained relational priors without retraining the backbone from scratch. Extensive experiments demonstrate that PC-LLM consistently outperforms both traditional optimization methods and state-of-the-art graph neural network baselines, while exhibiting exceptional zero-shot generalization to unseen environments. We further observe that topology-relevant relational reasoning is concentrated in shallow layers, whereas deeper layers encode task-irrelevant semantic noise. Motivated by this finding, we develop a lightweight adaptation strategy that reduces model depth by 50%, significantly lowering inference cost while preserving state-of-the-art spectral efficiency.

---

### From Goals to Aspects, Revisited: An NFR Pattern Language for Agentic AI Systems

Authors: Yijun Yu
Published: 2026-02-28
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2603.00472v1

Agentic AI systems exhibit numerous crosscutting concerns -- security, observability, cost management, fault tolerance -- that are poorly modularized in current implementations, contributing to the high failure rate of AI projects in reaching production. The goals-to-aspects methodology proposed at RE 2004 demonstrated that aspects can be systematically discovered from i* goal models by identifying non-functional soft-goals that crosscut functional goals. This paper revisits and extends that methodology to the agentic AI domain. We present a pattern language of 12 reusable patterns organized across four NFR categories (security, reliability, observability, cost management), each mapping an i* goal model to a concrete aspect implementation using an AOP framework for Rust. Four patterns address agent-specific crosscutting concerns absent from traditional AOP literature: tool-scope sandboxing, prompt injection detection, token budget management, and action audit trails. We extend the V-graph model to capture how agent tasks simultaneously contribute to functional goals and non-functional soft-goals. We validate the pattern language through a case study analyzing an open-source autonomous agent framework, demonstrating how goal-driven aspect discovery systematically identifies and modularizes crosscutting concerns. The pattern language offers a principled approach for engineering reliable agentic AI systems through early identification of crosscutting concerns.

---