DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
- 类型:arxiv
- 标识:2608.13489
- 链接:https://arxiv.org/abs/2608.13489
- 主分类:multimodal
- 形态:method
- 被引:0
- 被引来源:Semantic Scholar
- S2被引:0
- 影响力被引:0
- TLDR:An action-conditioned video world model for robotic manipulation that, given an observed frame, a language instruction, and a prescribed action sequence comprising end-effector poses and gripper states, predicts the resulting future observations is presented.
- 待LLM分类:否
- 标题中文:DreamX-Phi 1.0:面向机器人操作的动作条件视频世界模型
- TLDR中文:本文提出一种用于机器人操作的动作条件视频世界模型,给定观测帧、语言指令以及由末端执行器位姿和夹爪状态组成的预定动作序列,预测对应的未来观测结果。
- 来源文件:
- /inbox/tom/_candidates/2026-08-14-agent-rag-longcontext-candidates.json
- [S2 enrich]