activity
20242026
collaborators

8 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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.…

cs.CV2026

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Dianyi Wang, Chaofan Ma, Feng Han +8

Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabil…

cs.CV2026

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Dianyi Wang, Ruihang Li, Feng Han +17

Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment foot…

cs.CV2026

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…