← Search

Tenglong Ao

2 accepted papers

2025

DeltaFormer: Unlock the state space of Transformer

NeurIPS 2025poster

In recent years, large language models with Transformer architecture as the core have made breakthrough progress in many fields. At the same time, there are also some weaknesses in the large language model that have prompted people to reflect, among which the most fundamental one is the reflection o…

Cited by 0SourceScholar
2025

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens

CVPR 2025award

Recent endeavors in Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation by combining LLM and diffusion models, the state-of-the-art in each task, respectively. Existing approaches rely on spatial visual tokens, where image patches are encoded and arranged accord…