Xiaodong Gu
- Papers
- 12
Cite
Notes
Only stored in your browser.
Authored papers
12CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
arXiv 2026
GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts
arXiv 2026
SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
arXiv 2026
LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
arXiv 2025
MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models
arXiv 2025
Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal
arXiv 2025
SWE-QA: Can Language Models Answer Repository-level Code Questions?
arXiv 2025
SWE-Exp: Experience-Driven Software Issue Resolution
arXiv 2025
SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
arXiv 2025
LongCodeZip: Compress Long Context for Code Language Models
arXiv 2025
From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging
arXiv 2024
Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers
arXiv 2024
Affiliations
Frequent co-authors
10from 12 papers