今日从 arXiv 订阅中筛选 8 篇论文。

Arxiv ID2604.22851幻觉翻译2604.22851

⚡ EgoDyn-Bench Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

Arxiv ID2604.24443幻觉翻译2604.24443

⚡ PhysNote Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model

PhysNote Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model
Arxiv ID2604.24514幻觉翻译2604.24514

⚡ SceneSelect Selective Learning for Trajectory Scene Classification and Expert Scheduling

SceneSelect Selective Learning for Trajectory Scene Classification and Expert Scheduling
Arxiv ID2604.23728幻觉翻译2604.23728

⚡ ESIA An Energy-Based Spatiotemporal Interaction-Aware Framework for Pedestrian Intention Prediction

ESIA An Energy-Based Spatiotemporal Interaction-Aware Framework for Pedestrian Intention Prediction
Arxiv ID2504.16054幻觉翻译2504.16054

⚡ CF-VLA Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies

CF-VLA Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
Arxiv ID2604.24562幻觉翻译2604.24562

⚡ Towards Lawful Autonomous Driving Deriving Scenario-Aware Driving Requirements from Traffic Laws and Regulations

Towards Lawful Autonomous Driving Deriving Scenario-Aware Driving Requirements from Traffic Laws and Regulations
Arxiv ID2604.24396幻觉翻译2604.24396

⚡ Global Context or Local Detail Adaptive Visual Grounding for Hallucination Mitigation

Global Context or Local Detail Adaptive Visual Grounding for Hallucination Mitigation
Arxiv ID2604.23145幻觉翻译2604.23145

⚡ UpstreamQA A Modular Framework for Explicit Reasoning on Video Question Answering Tasks

UpstreamQA A Modular Framework for Explicit Reasoning on Video Question Answering Tasks

自动生成于 2026-04-29 · 基于 arXiv Daily Digest