Keya Hu (@hulillian39250) 's Twitter Profile
Keya Hu

@hulillian39250

Cornell 24 fall research intern
SJTU 25' CS
Senior undergraduate student

ID: 1682047729634279426

linkhttps://lillian039.github.io/ calendar_today20-07-2023 15:20:22

8 Tweet

160 Followers

42 Following

Kevin Ellis (@ellisk_kellis) 's Twitter Profile Photo

New ARC-AGI paper ARC Prize w/ fantastic collaborators Wen-Ding Li @ ICLR'25 Keya Hu Zenna Tavares evanthebouncy Basis For few-shot learning: better to construct a symbolic hypothesis/program, or have a neural net do it all, ala in-context learning? cs.cornell.edu/~ellisk/docume…

New ARC-AGI paper 
 <a href="/arcprize/">ARC Prize</a>  w/ fantastic collaborators <a href="/xu3kev/">Wen-Ding Li @ ICLR'25</a>  <a href="/HuLillian39250/">Keya Hu</a>  <a href="/ZennaTavares/">Zenna Tavares</a>  <a href="/evanthebouncy/">evanthebouncy</a> <a href="/BasisOrg/">Basis</a> 
For few-shot learning: better to construct a symbolic hypothesis/program, or have a neural net do it all, ala in-context learning?
cs.cornell.edu/~ellisk/docume…
Keya Hu (@hulillian39250) 's Twitter Profile Photo

🎊 New work and new SOTA on ARC-AGI public evaluation dataset!! We finetune Llama3.1-8B on the 400k synthetic dataset generated by our pipeline and do both transduction (directly output grid) and induction (output transform programs) that complement each other.

Zenna Tavares (@zennatavares) 's Twitter Profile Photo

Thrilled that joint work by Kevin Ellis's lab and Basis won 1st prize in ARC Prize Paper Awards and 2nd prize in ARC-AGI-PUB (w/ MIT) This is our first result from Project MARA: an effort to build Modeling, Abstraction, and Reasoning Agents capable of "everyday science"

Zhiyuan Zeng (@zhiyuanzeng_) 's Twitter Profile Photo

Is a single accuracy number all we can get from model evals?🤔 🚨Does NOT tell where the model fails 🚨Does NOT tell how to improve it Introducing EvalTree🌳 🔍identifying LM weaknesses in natural language 🚀weaknesses serve as actionable guidance (paper&demo 🔗in🧵) [1/n]

Keyon Vafa (@keyonv) 's Twitter Profile Photo

AI models appear to mimic the real world. But how can we tell if they truly understand it? Excited to announce the ICML 2025 Workshop on Assessing World Models! Working on related questions? Submit a paper (max. 4 pages) by May 20!

AI models appear to mimic the real world. But how can we tell if they truly understand it? 

Excited to announce the ICML 2025 Workshop on Assessing World Models!

Working on related questions? Submit a paper (max. 4 pages) by May 20!