From the 1 of 12 linked papers with an AI index.
12 papers
Argus-Unified: Towards A Compact and Economical Unified Model for Image Understanding and Generation
Weiming Zhuang, Jiabo Huang, Jingtao Li +4
The paper introduces Argus-Unified, a compact multimodal model that combines image understanding and generation by leveraging pretrained vision-language models and hybrid visual to…
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…
HyperVision: A Channel-Adaptive Ground-Based Hyperspectral Vision Pre-trained Backbone
Guanyiman Fu, Jingtao Li, Zihang Cheng +8
While hyperspectral imaging provides rich spatial-spectral information across hundreds of narrow wavelength bands for precise material identification, ground-based hyperspectral pr…
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…
StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
Zhizhong Li, Sina Sajadmanesh, Jingtao Li +1
Low-rank adaptation (LoRA) has been widely adopted as a parameter-efficient technique for fine-tuning large-scale pre-trained models. However, it still lags behind full fine-tuning…
Replay-Free Continual Low-Rank Adaptation with Dynamic Memory
Huancheng Chen, Jingtao Li, Weiming Zhuang +2
We revisit continual learning~(CL), which enables pre-trained vision transformers (ViTs) to sequentially fine-tune on new downstream tasks over time. However, as the scale of these…