collaborators

9 papers

cs.CV2026

When to Lock Attention: Training-Free KV Control in Video Diffusion

Tianyi Zeng, Jincheng Gao, Tianyi Wang +8

Maintaining background consistency while enhancing foreground quality remains a core challenge in video editing. Injecting full-image information often leads to background artifact…

cs.CV2025

Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Preference Understanding

Kun Li, Jianhui Wang, Yangfan He +10

Generative AI has significantly changed industries by enabling text-driven image generation, yet challenges remain in achieving high-resolution outputs that align with fine-grained…

cs.CL2025

MARS: Memory-Enhanced Agents with Reflective Self-improvement

Xuechen Liang, Meiling Tao, Yinghui Xia +8

Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making, lack of…

cs.CV2025

Twin Co-Adaptive Dialogue for Progressive Image Generation

Jianhui Wang, Yangfan He, Yan Zhong +12

Modern text-to-image generation systems have enabled the creation of remarkably realistic and high-quality visuals, yet they often falter when handling the inherent ambiguities in…

cs.CV2025

PromptLNet: Region-Adaptive Aesthetic Enhancement via Prompt Guidance in Low-Light Enhancement Net

Jun Yin, Yangfan He, Miao Zhang +4

Learning and improving large language models through human preference feedback has become a mainstream approach, but it has rarely been applied to the field of low-light image enha…

cs.CV2025

TSCnet: A Text-driven Semantic-level Controllable Framework for Customized Low-Light Image Enhancement

Miao Zhang, Jun Yin, Pengyu Zeng +3

Deep learning-based image enhancement methods show significant advantages in reducing noise and improving visibility in low-light conditions. These methods are typically based on o…