10 papers
Reinforcement Learning Fine-Tuning Enhances Activation Intensity and Diversity in the Internal Circuitry of LLMs
Honglin Zhang, Qianyue Hao, Fengli Xu +1
Large language models (LLMs) acquire extensive prior knowledge through large-scale pretraining and can be further enhanced via supervised fine-tuning (SFT) or reinforcement learnin…
RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning
Qianyue Hao, Sibo Li, Jian Yuan +1
Despite rapid advancements in large language models (LLMs), the token-level autoregressive nature constrains their complex reasoning capabilities. To enhance LLM reasoning, inferen…
Artificial Intelligence Tools Expand Scientists' Impact but Contract Science's Focus (Just accepted by Nature, to be online soon)
Qianyue Hao, Fengli Xu, Yong Li +1
Development in Artificial Intelligence (AI) has accelerated scientific discovery. Alongside recent AI-oriented Nobel prizes, these trends establish the role of AI tools in science.…
LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models
Qianyue Hao, Yiwen Song, Qingmin Liao +2
Policy exploration is critical in reinforcement learning (RL), where existing approaches include greedy, Gaussian process, etc. However, these approaches utilize preset stochastic…
KeyWorld: Key Frame Reasoning Enables Effective and Efficient World Models
Sibo Li, Qianyue Hao, Yu Shang +1
Robotic world models are a promising paradigm for forecasting future environment states, yet their inference speed and the physical plausibility of generated trajectories remain cr…
CityLight: A Neighborhood-inclusive Universal Model for Coordinated City-scale Traffic Signal Control
Jinwei Zeng, Chao Yu, Xinyi Yang +6
City-scale traffic signal control (TSC) involves thousands of heterogeneous intersections with varying topologies, making cooperative decision-making across intersections particula…