Accessing Math Solutions via Monte Carlo Self-Refine with LLaMa-3 8B (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Accessing Math Solutions via Monte Carlo Self-Refine with LLaMa-3 8B

First screen, captured 2 years ago.

Looks similar

Screenshot of arxiv.org: Gold-Medalist Performance in Solving Olympiad Geometry with AlphaGeometry2

Gold-Medalist Performance in Solving Olympiad Geometry with AlphaGeometry2 (arxiv.org)

38 points by hnhn34 1 year ago | 2 comments

Screenshot of arxiv.org: DeepSeek: Advancing theorem proving in LLMs through large-scale synthetic data

DeepSeek: Advancing theorem proving in LLMs through large-scale synthetic data (arxiv.org)

167 points by hhs 2 years ago | 48 comments

Screenshot of arxiv.org: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing

Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing (arxiv.org)

118 points by omarsar 1 year ago | 22 comments

Screenshot of arxiv.org: AI for Scientific Search

AI for Scientific Search (arxiv.org)

108 points by omarsar 1 year ago | 26 comments

Screenshot of arxiv.org: Scalable MatMul-Free Language Modeling

Scalable MatMul-Free Language Modeling (arxiv.org)

177 points by lykahb 2 years ago | 27 comments

Screenshot of arxiv.org: Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR (arxiv.org)

38 points by getnormality 1 year ago | 9 comments