Changran Hu
Scholar

Changran Hu

Google Scholar ID: gba_0WoAAAAJ
University of California, Berkeley
LLMlong contextAgentic AIPost Training
Google Scholar↗
Citations & Impact
All-time
Citations
361
 
H-index
7
 
i10-index
7
 
Publications
20
 
Co-authors
8
list available
Contact
No contact links provided.
Publications
7 items
Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and Pitfalls
2026
Cited
0
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
2026
Cited
9
Adaptation of Agentic AI
2025
Cited
0
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
2025
Cited
0
Distilling Tool Knowledge into Language Models via Back-Translated Traces
2025
Cited
0
LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
2025
Cited
0
Training Domain Draft Models for Speculative Decoding: Best Practices and Insights
2025
Cited
0
Resume (English only)
Co-authors
8 total
Bo Li
Bo Li
Applied Math Ph.D., University of California Berkley
Qiantong Xu
Qiantong Xu
Google Deepmind
Co-author 3
Co-author 3
Xiaolin Hu
Xiaolin Hu
Associate Professor of Computer Science and Technology, Tsinghua University
Jonathan Li
Jonathan Li
Software Engineer, SambaNova Systems
Co-author 6
Co-author 6
Jian Wu
Jian Wu
Unknown affiliation
Jun Zhu
Jun Zhu
Professor of Computer Science, Tsinghua University