4 papers
VEN-VL: A Visual Ensemble MoE Framework for Effective and Efficient Multi-Modal Understanding
Yinghao Wu, Zhuoyan Luo, Yiyao Yu +3
Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emph…
Scalable Image Tokenization with Index Backpropagation Quantization
Fengyuan Shi, Zhuoyan Luo, Yixiao Ge +3
Existing vector quantization (VQ) methods struggle with scalability, largely attributed to the instability of the codebook that undergoes partial updates during training. The codeb…
Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation
Zhuoyan Luo, Fengyuan Shi, Yixiao Ge +3
The Open-MAGVIT2 project produces an open-source replication of Google's MAGVIT-v2 tokenizer, a tokenizer with a super-large codebook (i.e., codes), and achieves the state…
CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation
Zhuoyan Luo, Yinghao Wu, Tianheng Cheng +5
The newly proposed Generalized Referring Expression Segmentation (GRES) amplifies the formulation of classic RES by involving complex multiple/non-target scenarios. Recent approach…