DeepRead

Popular Tags
#agentic-RL#VLM#gui-agent#LLM#task-planning#VLA#web-agent#manipulation#computer-use#world-model
Home

ReadPaperMachine

Nov 13, 20261 min read

A research knowledge management system for AI-assisted paper reading, note-taking, and research ideation.

Inspired by MindFlow.


1256Papers17Ideas14Topics6Domain Maps3Projects

Recent

  • World Model SurveyTopicsNov 13, 2026
  • Web Agent RL 训练:live rollout、离线动作匹配、环境供给与奖励来源的取舍TopicsNov 13, 2026
  • VLM SurveyTopicsNov 13, 2026
  • Vision-Language Navigation SurveyTopicsNov 13, 2026
  • Deep Research / Information-Seeking Agent 专题TopicsNov 13, 2026
  • Vision-Language-Action ModelsTopicsNov 13, 2026
  • Self-Evolving and Self-Improving Agents: A Unified Survey of Evolution Targets, Feedback, Gating, and SafetyTopicsNov 13, 2026
  • Step-Level Credit Assignment:从 trajectory-level reward 反推步级监督TopicsNov 13, 2026
  • Embodied AI SurveyTopicsNov 13, 2026
  • Agent Harness 的组件归因:外置 state、fresh-context 执行与独立验证,哪一个在起作用TopicsNov 13, 2026

Popular Tags

#agentic-RL305#VLM305#gui-agent285#LLM225#task-planning207#VLA188#web-agent184#manipulation181#computer-use173#world-model147#spatial-reasoning108#imitation-learning106#embodied-reasoning94#scene-understanding88#navigation81#RL66#3D-representation53#GUI-Agent39#video-LLM39#video-understanding38

Created with Quartz v4.5.2 © 2026

  • GitHub