9 papers
ReSim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation
Xiaoshen Han, Junqiu Yu, Minghuan Liu +6
Real-world data collection for robotics is costly and resource-intensive, requiring skilled operators and expensive hardware. Simulations offer a scalable alternative but often fai…
MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
Yujie Wei, Yujin Han, Zhekai Chen +20
Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However, evaluating such frontier mo…
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
Quanhao Li, Junqiu Yu, Kaixun Jiang +7
Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Exte…
AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation
Zhaohe Liao, Kaixun Jiang, Zhihang Liu +11
Although image generation has boosted various applications via its rapid evolution, whether the state-of-the-art models are able to produce ready-to-use academic illustrations for…
Aligned Stable Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency
Yikai Wang, Junqiu Yu, Chenjie Cao +2
Generative image inpainting can produce realistic results even with large, irregular masks, but existing methods still suffer from two common problems: (1) Unwanted object insertio…
ST4VLA: Spatially Guided Training for Vision-Language-Action Models
Jinhui Ye, Fangjing Wang, Ning Gao +9
Large vision-language models (VLMs) excel at multimodal understanding but fall short when extended to embodied tasks, where instructions must be transformed into low-level motor ac…