Mingjia Shi

BDeM

·

https://bdemo.github.io/homepage/

AI & ML interests

Federated Learning, Transfer Learning, Multi-modal, Optimization and Generative Model

Organizations

upvoted a paper 3 months ago

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Paper • 2608.15089 • Published Aug 15 • 106

upvoted a paper about 1 year ago

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

Paper • 2510.24940 • Published Oct 28, 2025 • 18

upvoted a paper over 1 year ago

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Paper • 2506.16406 • Published Jun 19, 2025 • 134