2 citations · 3 across the 5 of their papers we have counts for
5 papers
On the Limits of Token Reduction for Efficient Unified Vision Language Training
Siyi Chen, Weiming Zhuang, Jingtao Li +1
Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expe…
VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations
Maitreya Patel, Jingtao Li, Weiming Zhuang +2
We introduce an efficient, resolution-agnostic autoregressive (AR) image synthesis approach that generalizes to arbitrary resolutions and aspect ratios, narrowing the gap to diffus…
IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
Yuanshuai Li, Yuping Yan, Jirui Han +3
Hallucination remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While Direct Preference Optimization (DPO) is a key alignment framework, existing approa…
TARGET: Federated Class-Continual Learning via Exemplar-Free Distillation
Jie Zhang, Chen Chen, Weiming Zhuang +1
This paper focuses on an under-explored yet important problem: Federated Class-Continual Learning (FCCL), where new classes are dynamically added in federated learning. Existing FC…
sqSGD: Locally Private and Communication Efficient Federated Learning
Yan Feng, Tao Xiong, Ruofan Wu +2
Federated learning (FL) is a technique that trains machine learning models from decentralized data sources. We study FL under local notions of privacy constraints, which provides s…