2 papers
cs.CV2026
TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video Generation
Jiaxing Song, Weiqi Yan, You Huang +4
In this paper, we present trajectory-aware reuse and adaptive correction (TRAC), a training-free framework for efficient autoregressive (AR) video generation. Existing acceleration…
cs.AI2026
ITC-MoE: Importance-guided Token-aware Compression for MoE Diffusion Language Models
Lianjun Liu, Shipeng Li, You Huang +5
Mixture-of-Experts (MoE) Diffusion Language Models (DLMs) offer flexible parallel decoding and increased model capacity, but their large number of expert parameters incurs substant…