This directory is auto-generated from paperAnalysis/ and is used for agent-side fast filtering, statistical overview, Obsidian jumps, and backlink-friendly browsing.

• [[paperCollection/_AllPapers.md|All papers (grouped)]]
• By task
  • [[paperCollection/by_task/3ster_based_Diffusion_Video.md|3ster_based_Diffusion_Video]]
  • [[paperCollection/by_task/Building_World_Models_from_2D_Vision_Priors.md|Building_World_Models_from_2D_Vision_Priors]]
  • [[paperCollection/by_task/Code_rendered_Video_Generation.md|Code_rendered_Video_Generation]]
  • [[paperCollection/by_task/Controllable_Video_video_generation_with_other_conditions_Image_guided_Video_Generation.md|Controllable_Video_video_generation_with_other_conditions_Image_guided_Video_Generation]]
  • [[paperCollection/by_task/Evaluation.md|Evaluation]]
  • [[paperCollection/by_task/Evaluation_Benchmarks_and_Metrics.md|Evaluation_Benchmarks_and_Metrics]]
  • [[paperCollection/by_task/Foundation_Models.md|Foundation_Models]]
  • [[paperCollection/by_task/Highlights_MME_Series_MLLM_Benchmarks.md|Highlights_MME_Series_MLLM_Benchmarks]]
  • [[paperCollection/by_task/Highlights_Surveys_of_MLLMs.md|Highlights_Surveys_of_MLLMs]]
  • [[paperCollection/by_task/Highlights_VITA_Series_Omni_MLLMs.md|Highlights_VITA_Series_Omni_MLLMs]]
  • [[paperCollection/by_task/Human_Human_Interaction.md|Human_Human_Interaction]]
  • [[paperCollection/by_task/Human_Object_Interaction.md|Human_Object_Interaction]]
  • [[paperCollection/by_task/Human_Scene_Interaction.md|Human_Scene_Interaction]]
  • [[paperCollection/by_task/LLM_Aided_Visual_Reasoning.md|LLM_Aided_Visual_Reasoning]]
  • [[paperCollection/by_task/Motion_Generation_Text_Speech_Music_Driven.md|Motion_Generation_Text_Speech_Music_Driven]]
  • [[paperCollection/by_task/Multimodal_Chain_of_Thought.md|Multimodal_Chain_of_Thought]]
  • [[paperCollection/by_task/Multimodal_Hallucination.md|Multimodal_Hallucination]]
  • [[paperCollection/by_task/Multimodal_In_Context_Learning.md|Multimodal_In_Context_Learning]]
  • [[paperCollection/by_task/Multimodal_Instruction_Tuning_and_Latest_Works.md|Multimodal_Instruction_Tuning_and_Latest_Works]]
  • [[paperCollection/by_task/Multimodal_RLHF.md|Multimodal_RLHF]]
  • [[paperCollection/by_task/Open_source_Toolboxes_and_Foundation_Models.md|Open_source_Toolboxes_and_Foundation_Models]]
  • [[paperCollection/by_task/Others.md|Others]]
  • [[paperCollection/by_task/Speech_Audio_Language_Models.md|Speech_Audio_Language_Models]]
  • [[paperCollection/by_task/Video_Generation.md|Video_Generation]]
• By technique (Technique tags)
  • [[paperCollection/by_technique/_Index.md|Technique index]]
• By venue/journal
  • [[paperCollection/by_venue/_Index.md|Venue index]]

• index.jsonl is the fast filter layer for agents; the Markdown pages are for human navigation.
• This index links out by default and does not embed PDFs (to avoid heavy pages).
• paperAnalysis remains the primary evidence layer; paperCollection adds generated index and navigation outputs.

• papers: 549
• tasks: 24
• venues: 24
• technique tags: 1859