apps
Interactive AI products backed by a repository. CoolFace lists them; the app itself runs at the source.
RLVR-vs-SFT-Qwen2.5-1.5bRLVR-Reasoning-Agentagent-rlvrbaba-rlvrnanogpt-rlvr-slm-tinystoriesrepro-rlvr-backtracking-separationrepro-beyond-normalization-rethinking-the-partition-function-as-a-difficulty-scheduler-for-rlvrrepro-single-rollout-hidden-state-dynamics-for-training-free-rlvr-data-selectionrepro-provable-benefits-of-rlvr-over-sft-for-reasoning-models-learning-to-backtrack-efficientlyrepro-provable-benefits-of-rlvr-over-sft-for-reasoning-models-learning-to-backtrack-efficientlyrepro-grpo-rlvrrlvr-sft-backtracking-separation-reprorepro-provable-benefits-of-rlvr-over-sft-for-reasoning-models-learning-to-backtrack-efrepro-provable-benefits-of-rlvr-over-sft-for-reasoning-models-learning-to-backtrack-efficientlyrepro-grpo-rlvr-loss-dynamics-success-amplificationrepro-grpo-rlvr-loss-dynamics-success-amplificationrepro-probing-rlvr-training-instability-through-the-lens-of-objective-level-hackingrepro-rlvr-vs-sft-backtrackrepro-z9Bo4eXSpW-grpo-rlvr-dynamicsdeft-rlvr-autonomous-driving