13 papers
WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions
Haoyi Duan, Liliang Chen, Nan Wang +13
We introduce WorldOracle, a benchmark specifically designed to evaluate action-conditioned world models (ACWMs) against paired real-world executions. Given the same initial observa…
GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation
AgiBot Research Team, Renhang Liu, Wenzhi Zhao +42
World-action models (WAM) predict future states to guide robot actions, enabling learning from both action-free video and action-labeled interaction. Most inherit pretrained video…
Physical Object Understanding with a Physically Controllable World Model
Rahul Venkatesh, Klemen Kotar, Lilian Naing Chen +9
A central challenge in visual intelligence is learning the physical structure of scenes from raw videos: how regions form objects and the laws that govern their interactions. Solvi…
GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation
Boxiang Qiu, Liliang Chen, Yue Liao +12
We introduce GE-Sim 2.0 (Genie Envisioner World Simulator 2.0), a closed-loop video world simulator for robotic manipulation. Building on the action-conditioned video generation fr…
Zero-shot World Models Are Developmentally Efficient Learners
Khai Loong Aw, Klemen Kotar, Wanhee Lee +6
Young children demonstrate early abilities to understand their physical world, estimating depth, motion, object coherence, interactions, and many other aspects of physical scene un…
Act2Goal: From World Model To General Goal-conditioned Policy
Pengfei Zhou, Liliang Chen, Shengcong Chen +5
Specifying robotic manipulation tasks in a manner that is both expressive and precise remains a central challenge. While visual goals provide a compact and unambiguous task specifi…
Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-training
Yi Liu, Sukai Wang, Dafeng Wei +10
General-purpose robotic systems operating in open-world environments must achieve both broad generalization and high-precision action execution, a combination that remains challeng…
Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface
Yujie Zhao, Hongwei Fan, Di Chen +5
Recent progress in robot learning has been driven by large-scale datasets and powerful visuomotor policy architectures, yet policy robustness remains limited by the substantial cos…
Fidelity-Aware Data Composition for Robust Robot Generalization
Zizhao Tong, Di Chen, Sicheng Hu +6
Generalist robot policies trained on large-scale, visually homogeneous datasets can be susceptible to shortcut learning, which impairs their out-of-distribution (OOD) generalizatio…
Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation
Yue Liao, Pengfei Zhou, Siyuan Huang +11
We introduce Genie Envisioner (GE), a unified world foundation platform for robotic manipulation that integrates policy learning, evaluation, and simulation within a single video-g…
EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models
Hu Yue, Siyuan Huang, Yue Liao +5
Recent advances in creative AI have enabled the synthesis of high-fidelity images and videos conditioned on language instructions. Building on these developments, text-to-video dif…
EnerVerse-AC: Envisioning Embodied Environments with Action Condition
Yuxin Jiang, Shengcong Chen, Siyuan Huang +8
Robotic imitation learning has advanced from solving static tasks to addressing dynamic interaction scenarios, but testing and evaluation remain costly and challenging due to the n…
EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation
Siyuan Huang, Liliang Chen, Pengfei Zhou +8
We introduce EnerVerse, a generative robotics foundation model that constructs and interprets embodied spaces. EnerVerse employs a chunk-wise autoregressive video diffusion framewo…