今日从 arXiv 订阅中筛选 10 篇论文。

Arxiv ID2605.00880幻觉翻译2605.00880

⚡ Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving

Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving
Arxiv ID2605.01393幻觉翻译2605.01393

⚡ Recall to Predict: Grounding Motion Forecasting in Interpretable Motion Bank

Recall to Predict: Grounding Motion Forecasting in Interpretable Motion Bank
Arxiv ID2605.01799幻觉翻译2605.01799

⚡ Embody4D: A Generalist 4D World Model for Embodied AI

Embody4D: A Generalist 4D World Model for Embodied AI
Arxiv ID2605.01324幻觉翻译2605.01324

⚡ Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs

Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs
Arxiv ID2605.01662幻觉翻译2605.01662

⚡ Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models

Video Active Perception: Effective Inference-Time Long-Form Video Understanding with Vision-Language Models
Arxiv ID2605.01901幻觉翻译2605.01901

⚡ Behavior-Grounded Lane Representation Learning for Multi-Task Traffic Digital Twins

Arxiv ID2605.01694幻觉翻译2605.01694

⚡ Latent State Design for World Models under Sufficiency Constraints

Arxiv ID2605.01896幻觉翻译2605.01896

⚡ Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models

Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
Arxiv ID2605.02762幻觉翻译2605.02762

⚡ Unified Map Prior Encoder for Mapping and Planning

Unified Map Prior Encoder for Mapping and Planning
Arxiv ID2605.01507幻觉翻译2605.01507

⚡ MILD: Mediator Agent System with Bidirectional Perception and Multi-Layered Alignment for Human-Vehicle Collaboration

自动生成于 2026-05-05 · 基于 arXiv Daily Digest