ReactWorld: Structuring Interaction Responses for Embodied Video Generation
Overview
This research presents ReactWorld, an embodied video generation model guided by structured interaction anticipation. It predicts scene changes caused by robot actions while ensuring object responses align with task intent and contact dynamics. The model uses an interaction response field predictor to anticipate future motion and a response feedback adapter to update object features based on predicted displacements. ReactWorld achieves an average score of 77.51 on RBench, surpassing PhysisForcing by 3.29 points across all nine categories, and scores 86.98 on the Domain metric and 81.87 on average on EZS-Bench.
Generated from attributed reports · Updated 22 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · average score on RBench: 77.51 other · Basis not reported
“oed local dynamics inputs. It also converts predicted displacements into positional biases for temporal attention. These two mechanisms guide object feature updates and information retrieval across frames, respectively. Through interaction anticipation and generative feedback, ReactWorld achieves an average score of 77.51 on RBench, outperforming PhysisForcing by 3.29 points with improvements in all nine categories.”
Exact source · revision 1Source owner not reported
Reported quantity · Domain score on EZS-Bench: 86.98 other · Basis not reported
“On EZS-Bench, it achieves a Domain score of 86.98 and an average score of 81.87.”
Exact source · revision 1Source owner not reported
Reported quantity · average score on EZS-Bench: 81.87 other · Basis not reported
“On EZS-Bench, it achieves a Domain score of 86.98 and an average score of 81.87.”
Exact source · revision 1Source owner not reported
Reported quantity · improvement over PhysisForcing on RBench: 3.29 other · Basis not reported
“oed local dynamics inputs. It also converts predicted displacements into positional biases for temporal attention. These two mechanisms guide object feature updates and information retrieval across frames, respectively. Through interaction anticipation and generative feedback, ReactWorld achieves an average score of 77.51 on RBench, outperforming PhysisForcing by 3.29 points with improvements in all nine categories.”
Exact source · revision 1Source owner not reported
Reported quantity · score on RBench (category unspecified): 77.51 other · Basis not reported
“oed local dynamics inputs. It also converts predicted displacements into positional biases for temporal attention. These two mechanisms guide object feature updates and information retrieval across frames, respectively. Through interaction anticipation and generative feedback, ReactWorld achieves an average score of 77.51 on RBench, outperforming PhysisForcing by 3.29 points with improvements in all nine categories.”
Exact source · revision 1Source owner not reported
Evidence dependency changes (1)
- 2026-11-09T03:40:34.867Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalReactWorld: Structuring Interaction Responses for Embodied Video Generation
This research presents ReactWorld, an embodied video generation model guided by structured interaction anticipation. It predicts scene changes caused by robot actions while ensuring object responses align with task intent and contact dynamics. The model uses an interaction response field predictor to anticipate future motion and a response feedback adapter to update object features based on predicted displacements. ReactWorld achieves an average score of 77.51 on RBench, surpassing PhysisForcing by 3.29 points across all nine categories, and scores 86.98 on the Domain metric and 81.87 on average on EZS-Bench.
Event coverage history
Current attention 3·Peak within the comparable range 3（2026-11-07 01:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).