paper / david_sontag / May 22 / failedLLMs can construct powerful representations and streamline sample-efficient supervised learning
paper / david_sontag / May 18 / failedDR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
paper / david_sontag / May 14 / failedDiagnosing our datasets: How does my language model learn clinical information?
paper / david_sontag / May 14 / failedCompletion $\neq$ Collaboration: Scaling Collaborative Effort with Agents
paper / david_sontag / May 14 / failedDR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
paper / david_sontag / May 14 / failedLLMs can construct powerful representations and streamline sample-efficient supervised learning