papers

Publications (59)

cs.LG2024

Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective

Haoran He, Peilin Wu, Chenjia Bai +5

Reinforcement Learning (RL) has recently achieved remarkable success in robotic control. However, most works in RL operate in simulated environments where privileged knowledge (e.g…

cs.AI2023

Probabilistic Generative Modeling for Procedural Roundabout Generation for Developing Countries

Zarif Ikram, Ling Pan, Dianbo Liu

Due to limited resources and fast economic growth, designing optimal transportation road networks with traffic simulation and validation in a cost-effective manner is vital for dev…

cs.CL2026

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Jiakang Wang, Runze Liu, Qingpeng Cai +7

Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to maintain stability during optimiz…

cs.LG2023

Pre-Training and Fine-Tuning Generative Flow Networks

Ling Pan, Moksh Jain, Kanika Madan +1

Generative Flow Networks (GFlowNets) are amortized samplers that learn stochastic policies to sequentially generate compositional objects from a given unnormalized reward distribut…

cs.LG2026

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff

Runze Liu, Jiashun Liu, Xu Wan +2

Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training. SFT is expected to provide a usefu…

cs.LG2025

Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony

Han Lu, Zichen Liu, Shaopan Xiong +19

Synchronous Reinforcement Learning (RL) post-training has emerged as a crucial step for enhancing Large Language Models (LLMs) with diverse capabilities. However, many systems desi…