Kevin King's picture

Kevin King PRO

NeoCodes-dev

·

king112

AI & ML interests

Deep RL, RL for LLMs

Recent Activity

updated a collection 5 days ago

Research Papers

updated a collection 8 days ago

Research Papers

upvoted a paper 8 days ago

ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning

View all activity

Organizations

upvoted 3 papers 8 days ago

ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning

Paper • 2511.14366 • Published 9 days ago • 14

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

Paper • 2511.14659 • Published 9 days ago • 12

MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation

Paper • 2511.09611 • Published 15 days ago • 67

upvoted an article about 1 month ago

Article

Building the Open Agent Ecosystem Together: Introducing OpenEnv

Oct 23

•

133

upvoted a collection about 2 months ago

LocalAI

Fine-tuned models for LocalAI finetuned by me • 14 items • Updated Feb 5 • 2

upvoted a paper about 2 months ago

Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR

Paper • 2509.23808 • Published Sep 28 • 47

upvoted a collection 3 months ago

MCP Tools 4 AI

A collections of spaces that you can using for building AI with AI via MCP • 7 items • Updated Jun 26 • 37

upvoted a paper 3 months ago

CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

Paper • 2508.21046 • Published Aug 28 • 9

upvoted a collection 3 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21 • 389

upvoted a collection 4 months ago

xLAM models

xLAM: A Family of Large Action Models to Empower AI Agent Systems: https://github.com/SalesforceAIResearch/xLAM • 22 items • Updated 22 days ago • 59

upvoted 2 papers 4 months ago

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos

Paper • 2507.15597 • Published Jul 21 • 34

The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs

Paper • 2507.11097 • Published Jul 15 • 64

upvoted 2 articles 5 months ago

Article

Asynchronous Robot Inference: Decoupling Action Prediction and Execution

Jul 10

•

44

Article

SmolLM3: smol, multilingual, long-context reasoner

Jul 8

•

732

upvoted an article 6 months ago

Article

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

Jun 3

•

285

upvoted a paper 6 months ago

ATLAS: Learning to Optimally Memorize the Context at Test Time

Paper • 2505.23735 • Published May 29 • 22

upvoted 2 articles 6 months ago

Article

nanoVLM: The simplest repository to train your VLM in pure PyTorch

May 21

•

231

Article

Vision Language Models (Better, faster, stronger)

May 12

•

566

upvoted a collection 7 months ago

Bamba

Collection of Bamba - hybrid Mamba2 model architecture based models trained on open data • 9 items • Updated Apr 28 • 24

upvoted an article 7 months ago

Article

Bamba-9B-v2 - Fast and powerful!

Apr 29

•

36