Pretrained diffusion models provide powerful generative priors for extreme image compression, but their stochastic, iterative generation processes are not designed to decode compressed representations directly. We present PrismCodec, which recasts a pretrained Diffusion Transformer (DiT) as a bitstream-grounded one-ste...
Yu-Nuo Chen, Jing-Nan Gao, Bing He et al.· 0 citations
Post-training is crucial for improving text-to-image models, yet existing pipelines typically rely on manually curated training data and fixed training distributions. We introduce APT (Agentic Post-Training), a fully automated framework that adaptively post-trains a base model according to its evolving capability profi...
Si-Rui Zhang, Fang-Yun Wei, Dong Chen et al.· 0 citations
DressAgent is introduced, a hierarchical agentic system that recovers garment sewing patterns through planning and closed-loop refinement grounded in physical simulation that outperforms feed-forward methods by a large margin, surpasses or matches differentiable optimization in a fraction of the time, and generalizes t...
Nan-Xiang Jiang, Yu-Nuo Chen, Zeng Tao et al.· 0 citations
Reconstructing 3D scenes from sparse views without per-scene optimization remains highly challenging, especially for recovering accurate geometry and fine textures. While recent feedforward approaches leverage generalizable 3D Gaussian Splatting (3DGS) for scene generation, they typically assign one or multiple Gaussia...
Bing He, Jing-Nan Gao, Yu-Nuo Chen et al.· 0 citations
Transferring robotic skills from simulation to reality requires task knowledge that remains usable across differences in perception, dynamics, and embodiment. We introduce Skill2Real, an agentic policy framework that learns executable skills through a shared application programming interface (API). A Proposer-Verifier-...
Xin-Chen He, Si-Yu Ma, Chang Yu et al.· 1 citation
In text-guided image editing, describing the desired change is often straightforward, but identifying the intended object or region can be cumbersome, especially when several objects look alike. We introduce a new image editing interface that lets users place spatial marks and optional short notes directly on the image...
Jin-Jing Zhao, Fang-Yun Wei, Yi-Tong Wang et al.· 0 citations
RoboEdit is presented, a human-to-robot video editing suite that transforms human manipulation videos into action-consistent, physically plausible robot videos with aligned 3D hand states, providing scalable, high-fidelity visual and 3D motion supervision for generalizable robot learning.
Yaowei Guo, Zeng Tao, Yuxin Jiang et al.· 2 citations
Agentic Real2Sim is introduced, a framework for generalized physical world modeling with vision-language agents, converting a real-world recording of object-robot interaction into a simulatable episodic twin which preserves observations, geometries, robot interactions, and object states.
