4 papers
Denoising Blocks, Not Tokens: Efficient Compressed Continuous Diffusion with Branching Token Realization
Xinsong Feng, Peng Du, Zhizhuo Yang +3
Diffusion language models (DLMs) generate text through iterative parallel refinement, offering the potential for higher throughput than autoregressive (AR) decoding. However, most…
Offline Reinforcement Learning with Generative Trajectory Policies
Xinsong Feng, Leshu Tang, Chenan Wang +1
Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, exis…
Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement Learning
Xinsong Feng, Zihan Yu, Yanhai Xiong +1
Reinforcement learning (RL) has emerged as a promising tool for combinatorial optimization (CO) problems due to its ability to learn fast, effective, and generalizable solutions. N…
Adaptive Cell Range Expansion in Multi-Band UAV Communication Networks
Xinsong Feng, Ian P. Roberts
This paper leverages stochastic geometry to model, analyze, and optimize multi-band unmanned aerial vehicle (UAV) communication networks operating across low-frequency and millimet…