Hanshuai Cui — accepted AI-conference papers

2026

BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching

Hanshuai Cui, Zhiqing Tang, Zhifei Xu, Zhi Yao, Wenyi Zeng, Weijia Jia

ICLR 2026poster

Recent advancements in Diffusion Transformers (DiTs) have established them as the state-of-the-art method for video generation. However, their inherently sequential denoising process results in inevitable latency, limiting real-world applicability. Existing acceleration methods either compromise vis…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching

Qianli Ma, Zhiqing Tang, Hanshuai Cui, Zhi Yao, Weijia Jia

ICML 2026poster

Disaggregated serving alleviates memory bottlenecks in Large Language Model (LLM) inference but creates a severe communication bottleneck: transmitting high-dimensional Key-Value (KV) caches often dominates time-to-first-token (TTFT). Moreover, reusing caches across heterogeneous models (e.g., base …

Cited by 0 Source ↗Scholar ↗