Unverified50% confidenceFactExact time
LIBERO-PeRM is the first controlled benchmark for preference learning in embodied agents, specifically evaluating task completion and preference satisfaction separately.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMultiple instance learning (MIL) represents each student as a bag containing a large amount of weakly labeled interaction behavior data, with a reinforcement learning agent responsible for selecting the most informative instances for use by the downstream classifier.67% similarUnverifiedXiaomi's MiMo series is an open-source reasoning model released by Xiaomi; MiMo-V2.5 demonstrates strong performance on code and mathematical reasoning tasks and employs reinforcement learning for post-training optimization61% similarUnverifiedThe study adopts Multi-Agent Reinforcement Learning (MARL) as the training framework.59% similarUnverifiedThe MiMo team used repetition data to train a specialized model to fix the repetition issue, representing a targeted post-training approach.59% similarUnverifiedMiMo training employs intra-group credit assignment combined with test-case rewards and rubric rewards, following an RLVR style rather than the classic RM+PPO approach.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1041738API
curl https://kongchang.com/api/v1/knowledge/claims/1041738MCP
get_claim(id=1041738)