Minghao Yan

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

PLoRA: Efficient LoRA Hyperparameter Tuning for Large Language Models

What Limits Agentic Systems Efficiency?

Scaling Inference-Efficient Language Models

In-batch Ensemble Drafting: Toward Fast and Robust Speculative Decoding for Multimodal Language Models