今日从 arXiv 订阅中筛选 8 篇论文。

Arxiv ID2604.28196幻觉翻译2604.28196

⚡ HERMES++ Toward a Unified Driving World Model for 3D Scene Understanding and Generation

HERMES++ Toward a Unified Driving World Model for 3D Scene Understanding and Generation
Arxiv ID2604.27620幻觉翻译2604.27620

⚡ SpaAct Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation

SpaAct Spatially-Activated Transition Learning with Curriculum Adaptation for Vision-Language Navigation
Arxiv ID2604.27366幻觉翻译2604.27366

⚡ Judge, Then Drive A Critic-Centric Vision Language Action Framework for Autonomous Driving

Judge, Then Drive A Critic-Centric Vision Language Action Framework for Autonomous Driving
Arxiv ID2604.27414幻觉翻译2604.27414

⚡ Understanding Adversarial Transferability in Vision-Language Models for Autonomous Driving A Cross-Architecture Analysis

Arxiv ID2604.28001幻觉翻译2604.28001

⚡ A Pattern Language for Resilient Visual Agents

Arxiv ID2604.27472幻觉翻译2604.27472

⚡ PRTS A Primitive Reasoning and Tasking System via Contrastive Representations

PRTS A Primitive Reasoning and Tasking System via Contrastive Representations
Arxiv ID2604.27895幻觉翻译2604.27895

⚡ Graph World Models Concepts, Taxonomy, and Future Directions

Graph World Models Concepts, Taxonomy, and Future Directions
Arxiv ID2604.27411幻觉翻译2604.27411

⚡ Detecting is Easy, Adapting is Hard Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift

自动生成于 2026-05-02 · 基于 arXiv Daily Digest