Xinyu Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xinyu Yang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Beidi Chen
Carnegie Mellon University
2 shared publications - Ceyu Xu
The Hong Kong University of Science and Technology, Hong Kong, Hong Kong
2 shared publications - Danyang Zhuo
Duke University
2 shared publications - Lisa Wu Wills
Duke University, Durham, USA
2 shared publications - Matthew Lentz
Duke University
2 shared publications - Yongji Wu
Duke University
2 shared publications
Latest Publications
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 46 (5) , 20-28
The Rise of Tensor Codecs
Video codecs have been refined for decades to compress visual data efficiently. This paper revisits them as general-purpose tensor codecs for large language models. LLM training and inference are increasingly limited by memory footprint and communication bandwidth, while existing tensor-compression methods are often specialized for weights, activations, gradients, or KV cache. We show that standard video codecs can compress these tensors effectively because tensor layouts expose statistical structure that codec stages such as prediction, transform coding, quantization, and entropy coding can exploit. Building on this observation, LLM.265 repurposes existing GPU video engines to support compression during both inference and distributed training. We further show that video-codec hardware can be customized and enhanced to improve tensor encoding and decoding throughput without substantial cost, making it an effective path for large-scale model deployment without major changes to GPU architecture.
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Micro
- Vol. 46 (5) , 20-28
The Rise of Tensor Codecs
Video codecs have been refined for decades to compress visual data efficiently. This paper revisits them as general-purpose tensor codecs for large language models. LLM training and inference are increasingly limited by memory footprint and communication bandwidth, while existing tensor-compression methods are often specialized for weights, activations, gradients, or KV cache. We show that standard video codecs can compress these tensors effectively because tensor layouts expose statistical structure that codec stages such as prediction, transform coding, quantization, and entropy coding can exploit. Building on this observation, LLM.265 repurposes existing GPU video engines to support compression during both inference and distributed training. We further show that video-codec hardware can be customized and enhanced to improve tensor encoding and decoding throughput without substantial cost, making it an effective path for large-scale model deployment without major changes to GPU architecture.
- Open Access
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 445-460
LLM.265: Video Codecs are Secretly Tensor Codecs
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 445-460
Open AccessLLM.265: Video Codecs are Secretly Tensor Codecs