Penghui Qi
QPHutu
AI & ML interests
None yet
Organizations
LLM Agent
-
DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research
Paper • 2505.19253 • Published • 32 -
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
Paper • 2505.20411 • Published • 92 -
Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
Paper • 2505.21497 • Published • 109 -
Agentic Reinforced Policy Optimization
Paper • 2507.19849 • Published • 158
Pipeline Parallelism
-
Zero Bubble Pipeline Parallelism
Paper • 2401.10241 • Published • 25 -
Pipeline Parallelism with Controllable Memory
Paper • 2405.15362 • Published • 3 -
Balancing Pipeline Parallelism with Vocabulary Parallelism
Paper • 2411.05288 • Published • 20 -
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
Paper • 2503.01328 • Published • 16
LLM Self-Play
LLM Agent
-
DeepResearchGym: A Free, Transparent, and Reproducible Evaluation Sandbox for Deep Research
Paper • 2505.19253 • Published • 32 -
SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
Paper • 2505.20411 • Published • 92 -
Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers
Paper • 2505.21497 • Published • 109 -
Agentic Reinforced Policy Optimization
Paper • 2507.19849 • Published • 158
LLM Pretraining
Pipeline Parallelism
-
Zero Bubble Pipeline Parallelism
Paper • 2401.10241 • Published • 25 -
Pipeline Parallelism with Controllable Memory
Paper • 2405.15362 • Published • 3 -
Balancing Pipeline Parallelism with Vocabulary Parallelism
Paper • 2411.05288 • Published • 20 -
PipeOffload: Improving Scalability of Pipeline Parallelism with Memory Optimization
Paper • 2503.01328 • Published • 16