In a Training Loop 🔄

2 19 36

Dakota Kim PRO

GhostScientist

http://dakota.kim

GhostScientist

AI & ML interests

Human-Computer Interfaces, Reasoning, Self/World-Modeling, Embodied intelligence / Robotics "I believe in you and me. I believe in the machines."

Recent Activity

upvoted an article 1 day ago

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

upvoted an article 1 day ago

The Great Classification Showdown: OSS vs BERT on Consumer Hardware

liked a model 6 days ago

sweepai/sweep-next-edit-1.5B

View all activity

Organizations

upvoted 2 articles 1 day ago

Article

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

2 days ago

•

Article

The Great Classification Showdown: OSS vs BERT on Consumer Hardware

3 days ago

•

upvoted a changelog 6 days ago

Changelog

MLX Hardware Compatibility

6 days ago

• 31

upvoted a paper 16 days ago

Can We Predict Before Executing Machine Learning Agents?

Paper • 2601.05930 • Published 19 days ago • 26

upvoted an article 21 days ago

Article

CUGA on Hugging Face: Democratizing Configurable AI Agents

Dec 15, 2025

•

upvoted an article 25 days ago

Article

The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator

Dec 17, 2025

•

upvoted a paper 26 days ago

DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models

Paper • 2512.24165 • Published 29 days ago • 50

upvoted a paper about 1 month ago

SkillFactory: Self-Distillation For Learning Cognitive Behaviors

Paper • 2512.04072 • Published Dec 3, 2025 • 5

upvoted 2 articles about 1 month ago

Article

LLM based Audio models

Dec 18, 2025

•

Article

Make and publish your Reachy Mini App

Dec 3, 2025

•

upvoted a collection about 1 month ago

NVIDIA Nemotron v3

Collection

Open, Production-ready Enterprise Models • 7 items • Updated 8 days ago • 128

upvoted an article about 2 months ago

Article

We Got Claude to Fine-Tune an Open Source LLM

Dec 4, 2025

•

583

upvoted 2 papers 3 months ago

TheMCPCompany: Creating General-purpose Agents with Task-specific Tools

Paper • 2510.19286 • Published Oct 22, 2025 • 9

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

Paper • 2510.15870 • Published Oct 17, 2025 • 91

upvoted a collection 4 months ago

RDT 2

Collection

RDT 2, the sequel to RDT-1B, is the first foundation model that achieves zero-shot deployment on unseen embodiments for simple open-vocabulary tasks. • 4 items • Updated Sep 26, 2025 • 16

upvoted a collection 5 months ago

EmbeddingGemma

Collection

3 items • Updated Sep 11, 2025 • 109

upvoted a collection 8 months ago

V-JEPA 2

Collection

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13, 2025 • 190

upvoted a paper 8 months ago

SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics

Paper • 2506.01844 • Published Jun 2, 2025 • 148

upvoted an article 8 months ago

Article

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

Jun 3, 2025

•

315

Dakota Kim PRO

AI & ML interests

Recent Activity

Organizations

GhostScientist's activity

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

The Great Classification Showdown: OSS vs BERT on Consumer Hardware

MLX Hardware Compatibility

CUGA on Hugging Face: Democratizing Configurable AI Agents

The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator

LLM based Audio models

Make and publish your Reachy Mini App

We Got Claude to Fine-Tune an Open Source LLM

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