xiaodong gu

xiaodong gu on Hugging Face Daily Papers: 14 papers, 3 in the top 3 of their day, 326 upvotes.

  1. SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents 87 upvotes, #2 of 2026-01-26
  2. GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts 27 upvotes, #7 of 2026-01-13
  3. Fed-SE: Federated Self-Evolution for Privacy-Constrained Multi-Environment LLM Agents 3 upvotes, #19 of 2025-12-12
  4. HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication 4 upvotes, #26 of 2025-10-16
  5. GraphTracer: Graph-Guided Failure Tracing in LLM Agents for Robust Multi-Turn Deep Search 2 upvotes, #31 of 2025-10-16
  6. LongCodeZip: Compress Long Context for Code Language Models 102 upvotes, #1 of 2025-10-03
  7. Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models 12 upvotes, #24 of 2025-10-01
  8. SWE-QA: Can Language Models Answer Repository-level Code Questions? 34 upvotes, #5 of 2025-09-24
  9. Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal 18 upvotes, #5 of 2025-08-11
  10. EVOC2RUST: A Skeleton-guided Framework for Project-Level C-to-Rust Translation 6 upvotes, #23 of 2025-08-07
  11. SWE-Exp: Experience-Driven Software Issue Resolution 12 upvotes, #6 of 2025-08-04
  12. SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution 10 upvotes, #7 of 2025-08-04
  13. LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds 25 upvotes, #13 of 2025-03-21
  14. From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging 30 upvotes, #3 of 2024-10-03

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.