Kevin King's picture

Kevin King PRO

NeoCodes-dev

·

king112

AI & ML interests

Deep RL, RL for LLMs

Recent Activity

updated a collection about 9 hours ago

Research Papers

upvoted a paper about 9 hours ago

Qwen2.5-Omni Technical Report

updated a collection about 9 hours ago

View all activity

Organizations

NeoCodes-dev's activity

upvoted a paper about 9 hours ago

Qwen2.5-Omni Technical Report

Paper • 2503.20215 • Published 2 days ago • 62

upvoted a paper about 11 hours ago

Visual-RFT: Visual Reinforcement Fine-Tuning

Paper • 2503.01785 • Published 24 days ago • 71

upvoted a collection 6 days ago

SmolDocling

3 items • Updated 9 days ago • 3

upvoted an article 7 days ago

Article

Train your first Decision Transformer

Sep 8, 2022

• 11

upvoted a collection 7 days ago

Physical AI

Collection of commercial-grade datasets for physical AI developers • 10 items • Updated 1 day ago • 27

upvoted 2 articles 15 days ago

Article

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

Feb 4

• 123

Article

LeRobot goes to driving school: World’s largest open-source self-driving dataset

17 days ago

• 68

upvoted a paper 16 days ago

Solving math word problems with process- and outcome-based feedback

Paper • 2211.14275 • Published Nov 25, 2022 • 9

upvoted a collection 16 days ago

LLaVA-Critic

as a general evaluator for assessing model performance • 6 items • Updated Oct 6, 2024 • 10

upvoted an article 17 days ago

Article

We now support VLMs in smolagents!

Jan 24

• 98

upvoted an article 29 days ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.19k

upvoted a collection about 1 month ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 46 items • Updated 30 days ago • 574

upvoted 2 articles about 1 month ago

Article

Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models

Mar 20, 2024

• 82

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16, 2024

• 346

upvoted a collection 2 months ago

LLM Training Datasets

A collection of datasets for training LLMs. • 109 items • Updated 5 days ago • 18