2025
Harmonia: A Unified Architecture for Efficient Deep Symbolic Regression.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., February, 2025

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
CodeV: Empowering LLMs for Verilog Generation through Multi-Level Summarization.
CoRR, 2024

InverseCoder: Unleashing the Power of Instruction-Tuned Code LLMs with Inverse-Instruct.
CoRR, 2024

Cambricon-LLM: A Chiplet-Based Hybrid Architecture for On-Device Inference of 70B LLM.
Proceedings of the 57th IEEE/ACM International Symposium on Microarchitecture, 2024

2023
ANPL: Compiling Natural Programs with Interactive Decomposition.
CoRR, 2023

ANPL: Towards Natural Programming with Interactive Decomposition.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Online Symbolic Regression with Informative Query.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023