Running 13 Defeating the trainer-generator precision mismatch in TRL 🎯 13 Download research PDF (Pro access required)
Running 113 The Eiffel Tower Llama 📝 113 Explore the Eiffel Tower Llama experiment with open-source models
Running 6 Robotics research should think (and do) more about sustainability! 📝 6 Explore robotics papers mapped to UN Sustainable Development Goals
Running Featured 99 Cohere Transcribe WebGPU ⚡ 99 Run Cohere Transcribe locally in your browser on WebGPU.
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics Paper • 2602.19313 • Published Feb 22 • 26