NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks
By
and 4 others
•
•
56
NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks
By
and 4 others
•
•
56How To Build a News Agent with GPT-OSS, Hugging Face Inference & Gradio
By
•
•
17ChatML vs Harmony: Understanding the new Format from OpenAI 🔍
By
•
•
24Supercharge Edge AI With High‑Accuracy Reasoning Using NVIDIA Nemotron Nano 2 9B
By
and 9 others
•
•
14Announcing the Synthetic Online Conversations Dataset (SOC)
By
•
•
11What’s MXFP4? The 4-Bit Secret Powering OpenAI’s GPT‑OSS Models on Modest Hardware
By
•
•
12Code a simple RAG from scratch
By
•
•
156RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
By
and 9 others
•
•
25Kimina-Prover-RL
By
and 18 others
•
•
8Uncensor any LLM with abliteration
By
•
•
654DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge
By
•
•
208KV Caching Explained: Optimizing Transformer Inference Efficiency
By
•
•
115Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm
By
and 5 others
•
•
80Building Enterprise-Ready Text Classifiers in Minutes with Adaptive Learning
By
•
•
12Magpie Speech — Applying an LLM Data Synthesis Method to an LLM-Based TTS Model to Synthesize a Speech Dataset
By
•
•
5RynnEC: Bringing MLLMs into Embodied World
By
and 6 others
•
•
5Introducing Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training
By
•
•
9How to Run a Hugging Face Model in JAX (Part 1)
By
•
•
21AWorld Multi-Agent System Hits #1 on GAIA Leaderboard
By
•
•
25The GPT-OSS models are here… and they’re energy-efficient!
By
•
•
19