7 25 3

Sean McLeish

smcleish

https://mcleish7.github.io/

AI & ML interests

None yet

Recent Activity

upvoted a paper about 10 hours ago

ARGUS: Hallucination and Omission Evaluation in Video-LLMs

upvoted a paper 1 day ago

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

upvoted a paper 4 days ago

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

View all activity

Organizations

smcleish's activity

upvoted a paper about 10 hours ago

ARGUS: Hallucination and Omission Evaluation in Video-LLMs

Paper • 2506.07371 • Published 2 days ago • 8

upvoted a paper 1 day ago

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

Paper • 2506.05523 • Published 5 days ago • 31

upvoted a paper 4 days ago

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

Paper • 2506.04245 • Published 12 days ago • 4

upvoted 2 papers 5 days ago

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published 5 days ago • 35

Zero-Shot Vision Encoder Grafting via LLM Surrogates

Paper • 2505.22664 • Published 13 days ago • 6

upvoted 2 papers 7 days ago

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Paper • 2505.24273 • Published 12 days ago • 4

Pitfalls in Evaluating Language Model Forecasters

Paper • 2506.00723 • Published 10 days ago • 3

upvoted a paper 22 days ago

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Paper • 2505.13308 • Published 22 days ago • 26

upvoted 3 papers about 1 month ago

upvoted a paper about 2 months ago

Antidistillation Sampling

Paper • 2504.13146 • Published Apr 17 • 61

upvoted an article 3 months ago

Article

Mixture of Depth is Vibe

•

Apr 22, 2024

• 47

upvoted 2 papers 3 months ago

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Paper • 2503.07572 • Published Mar 10 • 46

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

Paper • 2503.01307 • Published Mar 3 • 39

upvoted 2 papers 4 months ago

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

Paper • 2502.09974 • Published Feb 14 • 9

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

Paper • 2502.06533 • Published Feb 10 • 18

upvoted a collection 4 months ago

Recurrent Models

Collection

These are checkpoints for recurrent LLMs developed to scale test-time compute by recurring in latent space. • 15 items • Updated 20 days ago • 7

upvoted 2 papers 4 months ago

Gemstones: A Model Suite for Multi-Faceted Scaling Laws

Paper • 2502.06857 • Published Feb 7 • 25

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

Paper • 2502.05171 • Published Feb 7 • 142