activity
20242026
collaborators

6 papers

cs.CV2026

Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption

Xiaomeng Fu, Jia Li, Yiming Hu +5

Autoregressive (AR) streaming models have emerged as a powerful paradigm for long video generation. However, the linearly growing Key-Value (KV) cache poses a significant bottlenec…

cs.CV2026

Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation

Jia Li, Xiaomeng Fu, Xurui Peng +7

Autoregressive video diffusion models have emerged as a scalable paradigm for long video generation. However, they often suffer from severe extrapolation failure, where rapid error…

cs.DC2026

Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod

Ao Xiao, Bangzheng He, Baoquan Zhang +125

Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentr…

cs.CL2026

Improving Variable-Length Generation in Diffusion Language Models via Length Regularization

Zicong Cheng, Ruixuan Jia, Jia Li +3

Diffusion Large Language Models (DLLMs) are inherently ill-suited for variable-length generation, as their inference is defined on a fixed-length canvas and implicitly assumes a kn…

cs.LG2025

DEER: Draft with Diffusion, Verify with Autoregressive Models

Zicong Cheng, Guo-Wei Yang, Jia Li +3

Efficiency, as a critical practical challenge for LLM-driven agentic and reasoning systems, is increasingly constrained by the inherent latency of autoregressive (AR) decoding. Spe…

cs.AR2024

TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture

Jiajun Wu, Mo Song, Jingmin Zhao +3

Modern transformer-based deep neural networks present unique technical challenges for effective acceleration in real-world applications. Apart from the vast amount of linear operat…