今日从 arXiv 订阅中筛选 8 篇论文。

Arxiv ID2607.23909幻觉翻译2607.23909

⚡ WorldDiT: A Unified Diffusion Architecture for World and Action Modeling

WorldDiT: A Unified Diffusion Architecture for World and Action Modeling
Arxiv ID2607.23511幻觉翻译2607.23511

⚡ MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving

MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving
Arxiv ID2607.23472幻觉翻译2607.23472

⚡ VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation

VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation
Arxiv ID2607.23537幻觉翻译2607.23537

⚡ ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather

ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather
Arxiv ID2607.24431幻觉翻译2607.24431

⚡ InterOCF: Spatio-Temporal 2D-3D Interaction for Camera-Only 4D Occupancy Forecasting

Arxiv ID2607.24199幻觉翻译2607.24199

⚡ Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding

Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding
Arxiv ID2607.24582幻觉翻译2607.24582

⚡ CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding

CADER: Confidence-Aware Dynamic Evidence Reasoning for Long-Video Understanding
Arxiv ID2607.24407幻觉翻译2607.24407

⚡ Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding

Mixture-of-Thought-Tokens: Unifying Perception and Reasoning for Free-form Multimodal Grounding

自动生成于 2026-07-28 · 基于 arXiv Daily Digest