👋 Open to Work

D B PRO

d-s-b

16 21

AI & ML interests

Exploring

Recent Activity

upvoted a paper about 8 hours ago

Polar: Agentic RL on Any Harness at Scale

upvoted a paper about 17 hours ago

OpenForgeRL: Train Harness-native Agents in Any Environment

upvoted an article about 17 hours ago

Agentic RL: Token-In, Token-Out Done Right

View all activity

Organizations

liked a Space about 17 hours ago

The ultimate guide to multi-harness RL

🔀

105

Train open models with RL inside real agent harnesses

liked a Space 3 days ago

Qwen3-TTS Demo

🎙

2.28k

Generate speech from text with voice design, cloning, or presets

liked a dataset 3 days ago

nvidia/Nemotron-Personas-India

Viewer • Updated Dec 16, 2025 • 3M • 1.79k • 57

liked a model 15 days ago

bosonai/higgs-tts-3-4b

Text-to-Speech • 5B • Updated Sep 4 • 103k • 789

liked a Space about 2 months ago

Distilling 100B+ Models 40x Faster with TRL

📝

TRL distillation for 100B+ teachers, 40x faster

liked a dataset 2 months ago

markov-ai/gaming-500-hours

Viewer • Updated Jun 30 • 776 • 8.5k • 259

liked a Space 2 months ago

Mage-Flow

🎨

126

Efficient native-resolution image generation and editing

liked a model 3 months ago

facebook/tribev2

Updated Mar 27 • 16.5k • 719

liked a Space 3 months ago

Don't Train the Model, Evolve the Harness

🌿

Evolving an agent's harness, not its model, on Harvey's LAB

liked a dataset 4 months ago

ai4bharat/IndicVoices

Viewer • Updated Jun 15 • 6.38M • 21.8k • 122

liked a model 4 months ago

nvidia/LocateAnything-3B

Image-Text-to-Text • 4B • Updated Jun 12 • 110k • 3.09k

liked a model 5 months ago

google/translategemma-12b-it

Image-Text-to-Text • 13B • Updated Jan 28 • 9.49k • 347

liked a Space 5 months ago

The ultimate guide to RL environments: building and scaling them in the LLM era

📝

252

Building and scaling RL environments for LLM training

liked a model 6 months ago

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

Image-Text-to-Text • 28B • Updated Jul 7 • 21.7k • • 2.95k

liked a Space 7 months ago

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

📝

281

Explore synthetic data experiments as a visual bookshelf

liked a model 8 months ago

mistralai/Voxtral-Mini-4B-Realtime-2602

Automatic Speech Recognition • 4B • Updated Mar 11 • 1.89M • 999

liked 3 Spaces 11 months ago

FineWeb: decanting the web for the finest text data at scale

🍷

1.45k

Explore and download the FineWeb web‑scale text dataset

The Ultra-Scale Playbook

🌌

4.06k

The ultimate guide to training LLM on large GPU Clusters

The Smol Training Playbook

📚

3.32k

The secrets to building world-class LLMs

liked a model about 1 year ago

Qwen/Qwen-Image-Edit

Image-to-Image • 20B • Updated Aug 25, 2025 • 110k • • 2.54k