collaborators

7 papers

cs.CV2026

GroupVideo: Multi-Identity Customized Text-to-Video Generation

Xinyang Song, Libin Wang, Jianxin Sun +4

Current identity customized video generation methodologies are predominantly limited to single-identity scenarios, as the lack of explicit identity separation mechanisms often lead…

cs.CV2026

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders

Teng Li, Ziyuan Huang, Cong Chen +5

We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruc…

cs.CV2025

3SGen: Unified Subject, Style, and Structure-Driven Image Generation with Adaptive Task-specific Memory

Xinyang Song, Libin Wang, Weining Wang +6

Recent image generation approaches often address subject, style, and structure-driven conditioning in isolation, leading to feature entanglement and limited task transferability. I…

cs.CV2025

Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer

Ziyuan Huang, DanDan Zheng, Cheng Zou +13

Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in dis…

cs.CV2025

UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception

Xinyang Song, Libin Wang, Weining Wang +5

The remarkable success of diffusion models in text-to-image generation has sparked growing interest in expanding their capabilities to a variety of multi-modal tasks, including ima…

cs.CV2025

Reversing Flow for Image Restoration

Haina Qin, Wenyang Luo, Libin Wang +5

Image restoration aims to recover high-quality (HQ) images from degraded low-quality (LQ) ones by reversing the effects of degradation. Existing generative models for image restora…