今日从 arXiv 订阅中筛选 8 篇论文。

Arxiv ID2604.22748幻觉翻译2604.22748

⚡ Agentic World Modeling Foundations, Capabilities, Laws, and Beyond

Agentic World Modeling Foundations, Capabilities, Laws, and Beyond
Arxiv ID2604.22240幻觉翻译2604.22240

⚡ OccDirector Language-Guided Behavior and Interaction Generation in 4D Occupancy Space

Arxiv ID2604.22260幻觉翻译2604.22260

⚡ Towards Safe Mobility A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset

Towards Safe Mobility A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset
Arxiv ID2604.22409幻觉翻译2604.22409

⚡ SpaMEM Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments

SpaMEM Benchmarking Dynamic Spatial Reasoning via Perception-Memory Integration in Embodied Environments
Arxiv ID2604.22560幻觉翻译2604.22560

⚡ Cross-Stage Coherence in Hierarchical Driving VQA Explicit Baselines and Learned Gated Context Projectors

Arxiv ID2604.22160幻觉翻译2604.22160

⚡ GenMatter Perceiving Physical Objects with Generative Matter Models

GenMatter Perceiving Physical Objects with Generative Matter Models
Arxiv ID2604.22498幻觉翻译2604.22498

⚡ CGC Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding

CGC Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding
Arxiv ID2604.22226幻觉翻译2604.22226

⚡ Towards Temporal Compositional Reasoning in Long-Form Sports Videos

自动生成于 2026-04-28 · 基于 arXiv Daily Digest