Datasets
AgentRoboCritic-Bench
400 held-out robot manipulation actions annotated by humans, including 264 failed actions. CC BY 4.0 covers the annotations. Images remain subject to their source benchmarks’ licenses.
Related models
- AgentRoboCritic-Muse-Glimmer-30BEvaluation
- AgentRoboCritic-Muse-Glimmer-30B: Chenyan Xiong Research Group at CMU
- AgentRoboCritic-Muse-Glimmer-30B: Chenyan Xiong Research Group at CMU
Submit a source or correction