Unfortunately, I had to miss out on attending in person in Vienna, but glad to see the recognition. We need more research on understanding data and posttraining of LLMs.
Always a pleasure working with @alan and @JunmoKang
Unfortunately, I had to miss out on attending in person in Vienna, but glad to see the recognition. We need more research on understanding data and posttraining of LLMs.
Always a pleasure working with @alan and @JunmoKang
🤔 How do we train LLMs on real-world tasks where it’s hard to define a single verifiable answer?
Our work at @scale_AI introduces Rubrics as Rewards (RaR) — a framework for on-policy post-training that uses structured, checklist-style rubrics as interpretable reward signals. 🧵
5K Followers 1K FollowingComputing professor at Georgia Tech - natural language processing, language models, machine learning, information extraction, dialogue
2K Followers 5K FollowingI run @PopVaxIndia (https://t.co/dOKb3wZ7pr) – we develop mRNA vaccines and therapeutics using computational protein design. I write at https://t.co/reAXhjkSrU
10K Followers 850 FollowingI want to understand things deeply and explain them well. Building friendly AI @AnthropicAI
Give me anonymous feedback: https://t.co/7aBNrpbad8
15K Followers 6K FollowingI build tough benchmarks for LMs and then I get the LMs to solve them. SWE-bench & SWE-agent. Postdoc @Princeton. PhD @nlpnoah @UW.
13K Followers 687 FollowingResearch @Meta Superintelligence Labs, RL/post-training/agents; Previously Research @OpenAI on multimodal and RL; Opinions are my own.
892 Followers 229 FollowingAI Research scientist at Meta. Previous worked on ChatGPT AVM at OpenAI. Was a Postdoc at MIT on NLP and brain. Stanford PhD on CV and neuroscience.
102K Followers 920 FollowingTechnology's daily show. Hosted by @johncoogan and @jordihays. Streaming live 11AM-2PM PT every weekday and available on Apple, Spotify, and YouTube.
80K Followers 926 FollowingBuilding https://t.co/NaZlVKanzd | cofounder of @backendcapital @hf0residency @scale_ai | some would say i'm a part time promoter