Chengruidong Zhang

TriangleMix: Accelerating Prefilling via Decoding-time Contribution Sparsity

Region-Adaptive Sampling for Diffusion Transformers

SortedRL: Accelerating RL Training for LLMs through Online Length-aware Scheduling

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention

Chain-of-Model Learning for Language Model

SCBench: A KV Cache-Centric Analysis of Long-Context Methods

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval