Juncheng Zhang — accepted AI-conference papers

2026

AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation

Haoyue Tan, Shengnan Wang, Yulin Qiao, Juncheng Zhang, Youhui Bai, Ping Gong +2

CVPR 2026

Video diffusion transformers (DiTs) suffer from prohibitive inference latency due to quadratic attention complexity. Existing sparse attention methods either overlook semantic similarity, or fail to adapt to heterogeneous token distributions across layers, leading to model performance degradation. W

Cited by 0 Source ↗code ↗Scholar ↗

2025

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference

Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou +10

ACL 2025finding

Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-k attention mechanisms have been proposed to accelerate LLM inference…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗