7 papers
FocusDiT: Masking Queries in Diffusion Transformers for Fine-grained Image Generation
Xueji Fang, Liyuan Ma, Jianhao Zeng +3
Diffusion transformer (DiT) has been widely adopted in the generative diffusion field, advancing the denoising of query tokens through attention and Feed-Forward (\text{FFN}) layer…
Equilibrated Diffusion: Frequency-aware Textual Embedding for Equilibrated Image Customization
Liyuan Ma, Xueji Fang, Guo-Jun Qi
Image customization learns target subjects from reference concept images and generates conditioned images per text prompts, mainly modifying styles or backgrounds. Prevailing metho…
Traj2Action: A Co-Denoising Framework for Trajectory-Guided Human-to-Robot Skill Transfer
Han Zhou, Jinjin Cao, Liyuan Ma +2
Learning diverse manipulation skills for real-world robots is severely bottlenecked by the reliance on costly and hard-to-scale teleoperated demonstrations. While human videos offe…
When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance
Jinjin Cao, Zhiyang Chen, Zijun Wang +3
Vision-Language Models (VLMs) have shown solid ability for multimodal understanding of both visual and language contexts. However, existing VLMs often face severe challenges of hal…
C-Evolve: Consensus-based Evolution for Prompt Groups
Tiancheng Li, Yuhang Wang, Zhiyang Chen +3
Prompt evolution algorithms offer a powerful paradigm for enhancing AI systems based on closed-source models, while few work explores whether aggregating results from multiple prom…
Self-Guidance: Boosting Flow and Diffusion Generation on Their Own
Tiancheng Li, Weijian Luo, Zhiyang Chen +2
Proper guidance strategies are essential to achieve high-quality generation results without retraining diffusion and flow-based text-to-image models. Existing guidance either requi…