今日从 arXiv 订阅中筛选 8 篇论文。

Arxiv ID2604.15291幻觉翻译2604.15291

⚡ AD4AD Benchmarking Visual Anomaly Detection Models for Safer Autonomous Driving

Arxiv ID2604.15308幻觉翻译2604.15308

⚡ RAD-2 Scaling Reinforcement Learning in a Generator-Discriminator Framework

RAD-2 Scaling Reinforcement Learning in a Generator-Discriminator Framework
Arxiv ID2604.14692幻觉翻译2604.14692

⚡ Chain-of-Glimpse Search-Guided Progressive Object-Grounded Reasoning for Video Understanding

Chain-of-Glimpse Search-Guided Progressive Object-Grounded Reasoning for Video Understanding
Arxiv ID2604.14967幻觉翻译2604.14967

⚡ UniDoc-RL Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards

UniDoc-RL Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
Arxiv ID2604.14888幻觉翻译2604.14888

⚡ Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models
Arxiv ID2604.14902幻觉翻译2604.14902

⚡ ADAPT Benchmarking Commonsense Planning under Unspecified Affordance Constraints

ADAPT Benchmarking Commonsense Planning under Unspecified Affordance Constraints
Arxiv ID2604.14268幻觉翻译2604.14268

⚡ HY-World 2.0 A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

HY-World 2.0 A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Arxiv ID2604.14568幻觉翻译2604.14568

⚡ Learning Adaptive Reasoning Paths for Efficient Visual Reasoning

Learning Adaptive Reasoning Paths for Efficient Visual Reasoning

自动生成于 2026-04-18 · 基于 arXiv Daily Digest