Longxiang Tang

Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model

RePlan: Reasoning-Guided Region Planning for Complex Instruction-Based Image Editing

DVT-LLaVA: Vision-Language Model Personalization with Disentangled Visual Tuning

Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model

RUN: Reversible Unfolding Network for Concealed Object Segmentation

The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control

InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences

UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment

Gamma: Toward Generic Image Assessment with Mixture of Assessment Experts