cmu

Tag

Cards List
#cmu

@Xudong07452910: Evaluating agent capabilities is way too expensive these days! Running an agentic benchmark like SWE-Bench or GAIA often requires complex environments, toolchains, long rollouts, and can cost hundreds or thousands of dollars. This PACE paper from CMU asks a very practical question...

X AI KOLs Timeline · 2026-07-06 Cached

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%.

0 favorites 0 likes
#cmu

@gneubig: This Fall at CMU we're teaching a new course on AI Agents! The goal is that you learn how to create a scaffold, build e…

X AI KOLs Timeline · 2026-07-02 Cached

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.

0 favorites 0 likes
#cmu

@vivekgalatage: Introduction to Parallel Algorithms https://cs.cmu.edu/~guyb/paralg/paralg/parallel.pdf…

X AI KOLs Timeline · 2026-06-14 Cached

An introductory resource on parallel algorithms, covering fundamental concepts and techniques, from Carnegie Mellon University.

1 favorites 1 likes
#cmu

@rohanpaul_ai: Brilliant new paper from Meta, CMU and other labs. Shows that coding agents improve faster by manufacturing their own s…

X AI KOLs Following · 2026-05-26 Cached

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.

0 favorites 0 likes
#cmu

@Phoenixyin13: A thinker I deeply admire, @TairanHe99 (Tairan He), has joined OpenAI! I really enjoy the WhyNot Channel; I’ve been watching it since 2025. Although the episodes are long, I always finish them. Tairan holds a PhD from CMU, and his research likely relates to robotics. …

X AI KOLs Timeline · 2026-05-13

Tairan He joined OpenAI after completing his PhD at CMU, with a research background primarily focused on robotics.

0 favorites 0 likes
#cmu

@ickma2311: CMU Advanced NLP: Reinforcement Learning I had been curious about how RL works on top of LLMs, and this CMU lecture mad…

X AI KOLs Timeline · 2026-04-21 Cached

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.

0 favorites 0 likes
← Back to home

Submit Feedback