Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Paper • 2601.08763 • Published • 150
🔄 In a Training Loop
ar0cket1
ar0cket1
AI & ML interests
None yet
Recent Activity
updated a dataset 28 days ago
ar0cket1/qwen3-4b-base-self-distillation-hints published a dataset 28 days ago
ar0cket1/qwen3-4b-base-self-distillation-hints updated a model 2 months ago
ar0cket1/qwen3-30b-a3b-base-reasoning-sft-nemotron-math-v4-500mOrganizations
upvoted 2
papers 9 months ago