collaborators

7 papers

cs.CL2026

MetaState: Persistent Working Memory Enhances Reasoning in Discrete Diffusion Language Models

Kejing Xia, Mingzhe Li, Lixuan Wei +5

Discrete diffusion language models (dLLMs) generate text by iteratively denoising a masked sequence. However, standard dLLMs condition each denoising step solely on the current har…

cs.SE2026

ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance

Qirui Jin, Lingching Tung, Kenan Li +13

Language model (LM) agents are increasingly deployed to maintain codebases over extended periods, fixing streams of related defects while carrying context from one fix to the next.…

cs.CL2026

PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents

Zhenbang Du, Jun Luo, Zhiwei Zheng +8

Multi-turn tool-use agents must reason, call tools, and adapt to observations across several interaction turns. Post-training such agents is challenging, as reinforcement learning…

cs.CL2026

-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

Zhenbang Du, Kejing Xia, Xinrui Zhong +6

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding…

cs.CV2025

Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment

Zhenbang Du, Yonggan Fu, Lifu Wang +4

Diffusion models have shown remarkable success across generative tasks, yet their high computational demands challenge deployment on resource-limited platforms. This paper investig…

cs.CV2025

Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training

Lexington Whalen, Zhenbang Du, Haoran You +4

Training diffusion models (DMs) requires substantial computational resources due to multiple forward and backward passes across numerous timesteps, motivating research into efficie…