今日从 arXiv 订阅中筛选 8 篇论文。

Arxiv ID2604.19145幻觉翻译2604.19145

⚡ ST-Prune Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving

Arxiv ID2604.19710幻觉翻译2604.19710

⚡ SpanVLA Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model

SpanVLA Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
Arxiv ID2604.19689幻觉翻译2604.19689

⚡ A-MAR Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding

A-MAR Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding
Arxiv ID2604.18892幻觉翻译2604.18892

⚡ Prioritizing the Best Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness

Prioritizing the Best Incentivizing Reliable Multimodal Reasoning by Rewarding Beyond Answer Correctness
Arxiv ID2604.19741幻觉翻译2604.19741

⚡ CityRAG Stepping Into a City via Spatially-Grounded Video Generation

CityRAG Stepping Into a City via Spatially-Grounded Video Generation
Arxiv ID2604.19105幻觉翻译2604.19105

⚡ EgoMotion Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation

EgoMotion Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation
Arxiv ID2604.19193幻觉翻译2604.19193

⚡ How Far Are Video Models from True Multimodal Reasoning

How Far Are Video Models from True Multimodal Reasoning
Arxiv ID2604.19034幻觉翻译2604.19034

⚡ Explore Like Humans Autonomous Exploration with Online SG-Memo Construction for Embodied Agents

自动生成于 2026-04-22 · 基于 arXiv Daily Digest