Zhuolun He

Architect of the Bits World: Masked Autoregressive Modeling for Circuit Generation Guided by Truth Table

GAKD: Generative Adversarial Knowledge Distillation For Large Language Models

ToTRL: Unlock LLM Tree-of-Thoughts Reasoning Potential through Puzzles Solving

Angular and Shell-Aware Deep Potential Energy Model for Molecular Dynamics

One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient

DC-LLM: HARDWARE-FRIENDLY LLM WEIGHT COMPRESSION VIA DYNAMIC LINEAR COMBINATION

On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding