GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
Paper
•
2508.18993
•
Published
•
4
•
1
Huacan Wang
Huacan-Wang
AI & ML interests
None yet
Recent Activity
authored
a paper
21 days ago
JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for
Image Generation
authored
a paper
21 days ago
DR-LoRA: Dynamic Rank LoRA for Mixture-of-Experts Adaptation
Organizations
commented
a
paper
5 months ago