Omni-Thinker: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards
Paper
• 2507.14783 • Published
• 4
riddick zhou
riddickz
·
AI & ML interests
None yet
Recent Activity
updated
a model 16 days ago
riddickz/LLaDA-8B-Instruct published
a model 16 days ago
riddickz/LLaDA-8B-Instruct updated
a dataset about 2 months ago
riddickz/sudoku-verbalized_tiny Organizations
None yet
upvoted a paper 7 months ago