3 papers
cs.AI2026
Offline Diffusion Policy for Multi-User Delay-Constrained Scheduling
Zhuoran Li, Ruishuo Chen, Hai Zhong +1
Effective multi-user delay-constrained scheduling is crucial in various real-world applications, including embodied AI, instant messaging, live streaming, and data center managemen…
cs.CL2026
PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching
Ruishuo Chen, Yu Chen, Zhuoran Li +1
Unsupervised Reinforcement Learning from Internal Feedback (RLIF) has emerged as a promising paradigm for eliciting the latent capabilities of Large Language Models (LLMs) without…
cs.LG2026
Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
Ruishuo Chen, Xun Wang, Rui Hu +2
Generative Flow Networks (GFlowNets) excel at sampling diverse, high-reward objects. In many practical applications where active reward queries are infeasible, these models must be…