Zhen Fang

Zhen Fang on Hugging Face Daily Papers: 19 papers, 4 in the top 3 of their day, 970 upvotes.

  1. GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis 144 upvotes, #3 of 2026-10-02
  2. FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis 119 upvotes, #2 of 2026-08-19
  3. Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent 50 upvotes, #5 of 2026-08-05
  4. VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System 70 upvotes, #6 of 2026-07-31
  5. AsyncTool: Evaluating the Asynchronous Function Calling Capability under Multi-Task Scenarios 16 upvotes, #22 of 2026-05-29
  6. ACC: Compiling Agent Trajectories for Long-Context Training 59 upvotes, #6 of 2026-05-22
  7. SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering 7 upvotes, #28 of 2026-05-21
  8. VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation 27 upvotes, #12 of 2026-05-19
  9. SCOPE: Structured Decomposition and Conditional Skill Orchestration for Complex Image Generation 10 upvotes, #25 of 2026-05-11
  10. Flow-OPD: On-Policy Distillation for Flow Matching Models 95 upvotes, #2 of 2026-05-11
  11. SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents 22 upvotes, #10 of 2026-04-21
  12. Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning 41 upvotes, #8 of 2026-04-08
  13. Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models 19 upvotes, #11 of 2026-02-12
  14. Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models 149 upvotes, #3 of 2026-02-03
  15. Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models 124 upvotes, #4 of 2026-02-03
  16. UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision 44 upvotes, #4 of 2026-01-07
  17. DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action 21 upvotes, #12 of 2025-12-01
  18. CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios 10 upvotes, #16 of 2025-06-18
  19. MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance 10 upvotes, #9 of 2023-12-19

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.