Tag
The PACE method proposed by Carnegie Mellon University selects a subset of atomic capabilities from cheap non-agentic benchmarks to predict model performance on expensive agentic benchmarks, with prediction error below 4% and cost reduced to less than 1%.
Carnegie Mellon University is offering a new fall course on AI Agents, covering scaffolding, evals, and training agentic LLMs using reinforcement learning, balancing theory and practice.
An introductory resource on parallel algorithms, covering fundamental concepts and techniques, from Carnegie Mellon University.
A new paper from Meta, CMU, and other labs presents Self-play SWE-RL, a method where coding agents train themselves by manufacturing and fixing bugs in real codebases, achieving significant gains on SWE-bench benchmarks without relying on human-written tasks.
Tairan He joined OpenAI after completing his PhD at CMU, with a research background primarily focused on robotics.
CMU Advanced NLP lecture clarifies how reinforcement learning optimizes whole-output rewards (correctness, helpfulness, safety) rather than next-token prediction used in pretraining/fine-tuning.