6 papers
VISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action Models
Yiye Chen, Yanan Jian, Xiaoyi Dong +5
Vision-Language-Action (VLA) models have demonstrated strong performance across a wide range of robotic manipulation tasks. Despite the success, extending large pretrained Vision-L…
Bridging Online and Offline RL: Contextual Bandit Learning for Multi-Turn Code Generation
Ziru Chen, Dongdong Chen, Ruinan Jin +3
Recently, there have been significant research interests in training large language models (LLMs) with reinforcement learning (RL) on real-world tasks, such as multi-turn code gene…
Rethinking the Vulnerability of Concept Erasure and a New Method
Alex D. Richardson, Kaicheng Zhang, Lucas Beerens +1
The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In…
VLM4D: Towards Spatiotemporal Awareness in Vision Language Models
Shijie Zhou, Alexander Vilesov, Xuehai He +7
Vision language models (VLMs) have shown remarkable capabilities in integrating linguistic and visual reasoning but remain fundamentally limited in understanding dynamic spatiotemp…
FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing
Tianyi Wei, Yifan Zhou, Dongdong Chen +1
The integration of Rotary Position Embedding (RoPE) in Multimodal Diffusion Transformer (MMDiT) has significantly enhanced text-to-image generation quality. However, the fundamenta…
Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation
Tianyi Wei, Dongdong Chen, Yifan Zhou +1
Representing the cutting-edge technique of text-to-image models, the latest Multimodal Diffusion Transformer (MMDiT) largely mitigates many generation issues existing in previous m…