StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling
Paper • 2608.15089 • Published • 436
Mingjia Shi
BDeM
AI & ML interests
Federated Learning, Transfer Learning, Multi-modal, Optimization and Generative Model
Recent Activity
upvoted a paper 10 months ago
SemCoT: Accelerating Chain-of-Thought Reasoning through
Semantically-Aligned Implicit Tokens liked a Space about 1 year ago
Jerrylz/Drag-and-Drop-LLMsOrganizations
