Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision-language models to judge memory and consistency, leaving systematic 3D evaluati...
Dong-Yue Lu, Guian Fang, Hur Lim et al.· 0 citations
Vision-language-action (VLA) models adapted through supervised fine-tuning (SFT) inherit a structural asymmetry: expert demonstrations teach the policy where success behavior lies, but provide no signal about where it ceases to be reliable. We argue that robust VLA adaptation should therefore be viewed not as further d...
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for end-to-end autonomous driving by jointly integrating perception, reasoning, and decision making within a unified multimodal framework. However, most existing VLA models formulate end-to-end autonomous driving as a visual question answering task...
Jing-Tao Sun, Xiaohai He, Yi-Ke Zhang et al.· 0 citations
We present PAI-Actor, a cinematic multi-character animation framework for character replacement in dynamic movie scenes. Unlike conventional animation systems that mainly drive a single static image or a single subject, our goal is to replace and animate multiple characters within real video clips while preserving the...
Bang Tang, He-Yuan Gao, Yi-Ren Song et al.· 0 citations
Autoresearch agents are reshaping the research ecosystem, but they can also let flawed claims enter the literature at scale. Human advisors catch such issues in drafts through careful, traceable feedback, yet advisor-style assessment requires extensive manual effort and does not scale. To shift automated paper assessme...
Show-Harness, an Embodied Harness that enables VLMs to"play" robots through a compact semantic interface linking intent to action, and develops GUMI (GUI Manipulation Interface), which extends the same semantic action space to GUI-based demonstration collection, allowing humans and agents to"play"robots across embodime...
Yan-Zhe Chen, Ze-Chen Bai, Zhi-Jun Cao et al.· 26 citations· ⚡2
SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference, is introduced, providing a reproducible and extensible foundation for interactive world-model research.
Jun-Chao Huang, Guian Fang, Sheng-Ju Qian et al.· 12 citations
This work introduces StreamTTT, which writes long-range history into online-updated fast weights outside the attention context, leaving a short sliding key-value cache dedicated to recent evidence, mitigating attention dilution.
Examination of the proposed FigTree system produces high-quality figures, while also enabling more effective editing than existing raster-based methods, and proposes a multi-agent system that automatically transforms a scientific paper into a structured vector figure.
Yepeng Liu, Da-Sen Dai, Cheng-Zhi Liu et al.· 2 citations
MANGO-Grasp is proposed, an anisotropic interaction framework that represents objects as geometry-oriented 3D Gaussian primitives and robot hands as surface keypoints encoded into morpho-kinematic descriptors and achieves 86% success in real-world experiments.
Heng Zhang, K. Ma, M. Shou et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
