今日从 arXiv 订阅中筛选 10 篇论文。

Arxiv ID2608.23486幻觉翻译2608.23486

⚡ GeoWAM: Visual Geometry World Action Models for Autonomous Driving

GeoWAM: Visual Geometry World Action Models for Autonomous Driving
Arxiv ID2608.21878幻觉翻译2608.21878

⚡ ViSMoE: Visual-Aware Sparse Mixture-of-Experts for Embodied Referring Expression Grounding

ViSMoE: Visual-Aware Sparse Mixture-of-Experts for Embodied Referring Expression Grounding
Arxiv ID2608.23329幻觉翻译2608.23329

⚡ Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents

Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
Arxiv ID2608.23526幻觉翻译2608.23526

⚡ Correcting a learned physical invariant improves world-model rollouts

Arxiv ID2608.23189幻觉翻译2608.23189

⚡ EchoWM: Open and Enterable Omnimodal World Models

EchoWM: Open and Enterable Omnimodal World Models
Arxiv ID2608.23565幻觉翻译2608.23565

⚡ ReWorld: An Interactive World Model with Long-Horizon Memory

ReWorld: An Interactive World Model with Long-Horizon Memory
Arxiv ID2608.22750幻觉翻译2608.22750

⚡ MOSH-WM: Mask-Grounded Soft-Hamiltonian Dynamics for Object-Centric World Models

MOSH-WM: Mask-Grounded Soft-Hamiltonian Dynamics for Object-Centric World Models
Arxiv ID2608.22364幻觉翻译2608.22364

⚡ WAM-OPD: On-Policy Distillation for World Action Models

WAM-OPD: On-Policy Distillation for World Action Models
Arxiv ID2608.21595幻觉翻译2608.21595

⚡ Perturb the Thought, Not the Pixels: Latent-Space Rollout Diversification for RLVR

Perturb the Thought, Not the Pixels: Latent-Space Rollout Diversification for RLVR
Arxiv ID2608.22197幻觉翻译2608.22197

⚡ On the Capability Separation Between World-Model Policy Learning and Imitated World-Action Models

自动生成于 2026-08-25 · 基于 arXiv Daily Digest