今日从 arXiv 订阅中筛选 8 篇论文。

Arxiv ID2607.16204幻觉翻译2607.16204

⚡ 2607.16204v1_Masked_Diffusion_Language_Models_are_Strong_and_Steerable_Text_Based_World_Model

2607.16204v1_Masked_Diffusion_Language_Models_are_Strong_and_Steerable_Text_Based_World_Model
Arxiv ID2607.16314幻觉翻译2607.16314

⚡ 2607.16314v1_Depth_Regularized_JEPA_World_Models_Learn_More_Transferable_Representations_from

Arxiv ID2607.16355幻觉翻译2607.16355

⚡ 2607.16355v1_PhysAgent_Reflective_Agentic_Physics_Control_for_Physically_Plausible_Video_Gene

2607.16355v1_PhysAgent_Reflective_Agentic_Physics_Control_for_Physically_Plausible_Video_Gene
Arxiv ID2607.16401幻觉翻译2607.16401

⚡ 2607.16401v1_Apple_π_Benchmarking_Thinking_with_Video_Towards_Law_Grounded_Physical_Intellige

2607.16401v1_Apple_π_Benchmarking_Thinking_with_Video_Towards_Law_Grounded_Physical_Intellige
Arxiv ID2607.16602幻觉翻译2607.16602

⚡ 2607.16602v1_PAVXploreRL_Physical_Action_Visual_World_Model_Reinforcement_Learning_with_Actio

2607.16602v1_PAVXploreRL_Physical_Action_Visual_World_Model_Reinforcement_Learning_with_Actio
Arxiv ID2607.16938幻觉翻译2607.16938

⚡ 2607.16938v1_What_Do_They_See_Interpreting_Complex_Road_Scenarios_Through_the_Eyes_of_Vision_

Arxiv ID2607.17523幻觉翻译2607.17523

⚡ 2607.17523v1_Thinking_in_Video_Can_Video_Generators_Really_Reason_About_the_Real_World

2607.17523v1_Thinking_in_Video_Can_Video_Generators_Really_Reason_About_the_Real_World
Arxiv ID2607.17599幻觉翻译2607.17599

⚡ 2607.17599v1_ConsiSpace_Learning_Geometric_Consistency_Matters_for_Video_Spatial_Reasoning

2607.17599v1_ConsiSpace_Learning_Geometric_Consistency_Matters_for_Video_Spatial_Reasoning

自动生成于 2026-07-22 · 基于 arXiv Daily Digest