今日从 arXiv 订阅中筛选 10 篇论文。

Arxiv ID2608.20974幻觉翻译2608.20974

⚡ WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving

WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving
Arxiv ID2608.20430幻觉翻译2608.20430

⚡ RISE: Adaptive Imagination for World Action Models

RISE: Adaptive Imagination for World Action Models
Arxiv ID2608.20735幻觉翻译2608.20735

⚡ ForeTime-VLA: Causal Future-Token Distillation from a World Action Model for Conveyor-Belt Manipulation

ForeTime-VLA: Causal Future-Token Distillation from a World Action Model for Conveyor-Belt Manipulation
Arxiv ID2608.20890幻觉翻译2608.20890

⚡ A Collaborative Multi-Modality Interaction for VLA-based End-to-End Autonomous Driving

A Collaborative Multi-Modality Interaction for VLA-based End-to-End Autonomous Driving
Arxiv ID2608.20720幻觉翻译2608.20720

⚡ AffordAny: Open-World 3D Affordance Grounding from Monocular RGB Images

AffordAny: Open-World 3D Affordance Grounding from Monocular RGB Images
Arxiv ID2608.21360幻觉翻译2608.21360

⚡ OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs

OmniAssistBench: Assistant-style Interaction Benchmark for Omni-LLMs
Arxiv ID2608.20814幻觉翻译2608.20814

⚡ Enhancing Localized Reasoning for Long Video Understanding via Efficient Segment-to-Video Supervision

Enhancing Localized Reasoning for Long Video Understanding via Efficient Segment-to-Video Supervision
Arxiv ID2608.21030幻觉翻译2608.21030

⚡ COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models

COMET: Contrastive Motion-Enhanced Temporal Reasoning for Video Multimodal Large Language Models
Arxiv ID2608.21160幻觉翻译2608.21160

⚡ Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates

Human-JEPA: A Human-Centric Vision Model that Perceives and Anticipates
Arxiv ID2608.20805幻觉翻译2608.20805

⚡ Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding

Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding

自动生成于 2026-08-24 · 基于 arXiv Daily Digest