6 12 3

Sean McLeish

smcleish

https://mcleish7.github.io/

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

upvoted a paper 8 days ago

Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

updated a model 16 days ago

tomg-group-umd/Gemstone-1536x50_cooldown

View all activity

Organizations

smcleish's activity

upvoted a paper 2 days ago

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Paper • 2503.07572 • Published 4 days ago • 31

upvoted a paper 8 days ago

Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Paper • 2503.01307 • Published 11 days ago • 31

upvoted a paper 21 days ago

Has My System Prompt Been Used? Large Language Model Prompt Membership Inference

Paper • 2502.09974 • Published 28 days ago • 10

upvoted a paper 29 days ago

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning

Paper • 2502.06533 • Published Feb 10 • 18

upvoted a collection 30 days ago

Recurrent Models

Collection

These are checkpoints for recurrent LLMs developed to scale test-time compute by recurring in latent space. • 14 items • Updated Feb 10 • 5

upvoted a paper 30 days ago

Gemstones: A Model Suite for Multi-Faceted Scaling Laws

Paper • 2502.06857 • Published Feb 7 • 25

upvoted 2 papers about 1 month ago

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7 • 124

Great Models Think Alike and this Undermines AI Oversight

Paper • 2502.04313 • Published Feb 6 • 31

upvoted a collection about 1 month ago

Gemstone Models

Collection

Our 22 open source Gemstone models for scaling laws range from 50M to 2B parameters, spanning 11 widths from 256 to 3072 and 18 depths from 3 to 80. • 59 items • Updated 16 days ago • 5

upvoted 2 papers 9 months ago

From Pixels to Prose: A Large Dataset of Dense Image Captions

Paper • 2406.10328 • Published Jun 14, 2024 • 18

Transformers meet Neural Algorithmic Reasoners

Paper • 2406.09308 • Published Jun 13, 2024 • 44

upvoted a paper 10 months ago

Transformers Can Do Arithmetic with the Right Embeddings

Paper • 2405.17399 • Published May 27, 2024 • 53