13 citations · 26 across the 18 of their papers we have counts for
8 papers · 1 filter
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning
Yucheng Zhou, Wei Tao, Yiwen Guo +1
World models and multimodal large language models (MLLMs) provide complementary capabilities for predicting future outcomes from static visual observations. World models can genera…
CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition
Hongji Yang, Songlian Li, Yucheng Zhou +4
Recent diffusion models achieve strong photorealism and fluency in video generation, yet remain fragile under abstract, sparse or complex conditions, leading to poor performance in…
HanMoVLM: Large Vision-Language Models for Professional Artistic Painting Evaluation
Hongji Yang, Yucheng Zhou, Wencheng Han +3
While Large Vision-Language Models (VLMs) demonstrate impressive general visual capabilities, they remain artistically blind and unable to offer professional evaluation of artworks…
Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs
Huan Zheng, Yucheng Zhou, Tianyi Yan +6
Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis. However, their application in gastrointestinal endoscopy is currently hin…
Sim4Seg: Boosting Multimodal Multi-disease Medical Diagnosis Segmentation with Region-Aware Vision-Language Similarity Masks
Lingran Song, Yucheng Zhou, Jianbing Shen
Despite significant progress in pixel-level medical image analysis, existing medical image segmentation models rarely explore medical segmentation and diagnosis tasks jointly. Howe…
Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation
Hongji Yang, Yucheng Zhou, Wencheng Han +1
Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this,…
DC-ControlNet: Decoupling Inter- and Intra-Element Conditions in Image Generation with Diffusion Models
Hongji Yang, Wencheng Han, Yucheng Zhou +1
In this paper, we introduce DC (Decouple)-ControlNet, a highly flexible and precisely controllable framework for multi-condition image generation. The core idea behind DC-ControlNe…
Visual In-Context Learning for Large Vision-Language Models
Yucheng Zhou, Xiang Li, Qianning Wang +1
In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities. To over…