Robert:)
@robertljg.bsky.social
PhD Math & CS @Caltech
www.robertj1.com
www.robertj1.com
This is great! Thanks :)
November 22, 2024 at 10:48 PM
This is great! Thanks :)
Lastly, I hope to post here more and engage with like-minded people and discuss more research and exchange ideas: ) I will also be at NeurIPS 2024 and am happy to meet in person if any of you are interested.
November 22, 2024 at 10:32 PM
Lastly, I hope to post here more and engage with like-minded people and discuss more research and exchange ideas: ) I will also be at NeurIPS 2024 and am happy to meet in person if any of you are interested.
3. Optimization and Efficient training of Foundational models for science and math. We introduced two works: iFNO - Efficiently training large-scale neural operator models and Tensor-GaLore - GaLore extended to the tensor case. arxiv.org/abs/2211.15188
arxiv.org
November 22, 2024 at 10:32 PM
3. Optimization and Efficient training of Foundational models for science and math. We introduced two works: iFNO - Efficiently training large-scale neural operator models and Tensor-GaLore - GaLore extended to the tensor case. arxiv.org/abs/2211.15188
2. AI4Math (Theorem proving in Lean + Autoformalization + LLM reasoning). One of our recent work includes creating LeanAgent: arxiv.org/abs/2410.06209 which is a novel lifelong learning framework for theorem proving.
LeanAgent: Lifelong Learning for Formal Theorem Proving
Large Language Models (LLMs) have been successful in mathematical reasoning tasks such as formal theorem proving when integrated with interactive proof assistants like Lean. Existing approaches involv...
arxiv.org
November 22, 2024 at 10:32 PM
2. AI4Math (Theorem proving in Lean + Autoformalization + LLM reasoning). One of our recent work includes creating LeanAgent: arxiv.org/abs/2410.06209 which is a novel lifelong learning framework for theorem proving.