8 papers · 1 filter
Channel-wise Vector Quantization
Wei Song, Tianhang Wang, Yitong Chen +5
We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantiza…
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
Jiaqi Wang, Haoge Deng, Ting Pan +5
Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcement learning remains l…
ETCHR: Editing To Clarify and Harness Reasoning
Beichen Zhang, Yuhong Liu, Jinsong Li +3
Multimodal Large Language Models have advanced visual reasoning, yet a purely textual chain of thought remains a bottleneck for questions that require fine-grained focus or view tr…
DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders
Tianhang Wang, Yitong Chen, Wei Song +3
Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations that facilitate fast convergen…
SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
Zhixiong Zhang, Yizhuo Li, Shuangrui Ding +6
Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-category groups, or open-ended ta…
EasyVideoR1: Easier RL for Video Understanding
Chuanyu Qin, Chenxu Yang, Qingyi Si +6
Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large language models. As models evolve i…
Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
Dianyi Wang, Wei Song, Yikun Wang +4
Typical large vision-language models (LVLMs) apply autoregressive supervision solely to textual sequences, without fully incorporating the visual modality into the learning process…
DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
Wei Song, Yuran Wang, Zijia Song +6
The differing representation spaces required for visual understanding and generation pose a challenge in unifying them within the autoregressive paradigm of large language models.…