Model collection for ICLR 2026 Paper "LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision".
Jundong Xu
Aiden0526
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 21 hours ago
Memento-Skills: Let Agents Design Agents new activity about 2 months ago
Aiden0526/LogicReward-Qwen3-8B:Improve model card: fix metadata, add pipeline tag and library name upvoted a collection about 2 months ago
LogicRewardOrganizations
