collaborators

5 papers

cs.CV2025

A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models

Duo Li, Zuhao Yang, Xiaoqin Zhang +2

Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding a…

cs.CV2025

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance

Duo Li, Zuhao Yang, Xiaoqin Zhang +2

Visual token pruning aims to compress and prune redundant visual tokens which play a critical role in efficient inference with large vision-language models (LVLMs). However, most e…

cs.DC2025

DeepCompile: A Compiler-Driven Approach to Optimizing Distributed Deep Learning Training

Masahiro Tanaka, Du Li, Umesh Chand +3

The rapid growth of deep learning models has increased the demand for efficient distributed training strategies. Fully sharded approaches like ZeRO-3 and FSDP partition model param…

cs.CV2024

Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators

Yifan Pu, Zhuofan Xia, Jiayi Guo +9

This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of…

cs.CL2024

MCSD: An Efficient Language Model with Diverse Fusion

Hua Yang, Duohai Li, Shiman Li

Transformers excel in Natural Language Processing (NLP) due to their prowess in capturing long-term dependencies but suffer from exponential resource consumption with increasing se…