works on

From the 1 of 15 linked papers with an AI index.

collaborators

15 papers

cs.LG2026

MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention

Jianlin Yu, Jing Lin, Linghui Kong +13

The quadratic cost of attention is a major bottleneck in diffusion-based video generation models. MXFP4 attention provides a promising path toward efficient inference, but direct M…

cs.AR2026

Kaleido: Algorithm-Hardware Co-Design for Video Diffusion Transformers by Exploiting Latent Space Correlations

Wenxuan Miao, Haosong Liu, Weiming Hu +9

Kaleido introduces a hardware‑software co‑design that speeds up video diffusion transformers by reusing channel‑wise spatiotemporal information in the latent space, achieving large…

cs.LG2026

BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression

Yuantian Shao, Peisong Wang, Zhilei Liu +6

Large language models (LLMs) are increasingly constrained by memory capacity, weight bandwidth, and checkpoint storage during deployment. Existing low-bit compression methods mainl…

cs.LG2026

StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation

Guangda Liu, Yiquan Wang, Chengwei Li +6

Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, mod…

cs.LG2026

Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches

Shirin Alanova, Kristina Kazistova, Ekaterina Galaeva +7

The demand for efficient large language model (LLM) inference has intensified the focus on sparsification techniques. While semi-structured (N:M) pruning is well-established for we…

cs.CV2026

RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention

Aiyue Chen, Yaofu Liu, Junjian Huang +6

In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applicati…