4 papers
Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
Yee Hin Chong, Jiaming Wu, Youhui Zhang +1
Large language models (LLMs) have shown strong empirical gains as self-evolving agents for CUDA kernel generation, driven by feedback-conditioned planning across generations. Howev…
The FM Agent
Annan Li, Chufan Wu, Zengle Ge +19
Large language models (LLMs) are catalyzing the development of autonomous AI research agents for scientific and engineering discovery. We present FM Agent, a novel and general-purp…
Singular Value Decomposition on Kronecker Adaptation for Large Language Model
Yee Hin Chong, Peng Qu
Large pre-trained Transformer models achieve state-of-the-art results across diverse language and reasoning tasks, but full fine-tuning incurs substantial storage, memory, and comp…
Pipelining Kruskal's: A Neuromorphic Approach for Minimum Spanning Tree
Yee Hin Chong, Peng Qu, Yuchen Li +1
Neuromorphic computing, characterized by its event-driven computation and massive parallelism, is particularly effective for handling data-intensive tasks in low-power environments…