NVIDIA

Enterprise +

company

Verified

https://www.nvidia.com/

nvidia

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

VibhuJawa new activity about 2 hours ago

nvidia/nemotron-page-elements-v3:vjawa_ensure_device_side_preprocessing

VibhuJawa new activity about 2 hours ago

nvidia/nemotron-table-structure-v1:vjawa_move_preprocessing_to_device

VibhuJawa new activity about 2 hours ago

nvidia/nemotron-graphic-elements-v1:vjawa_move_preprocessing_to_device

View all activity

Papers

SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL

BlurDM: A Blur Diffusion Model for Image Deblurring

View all Papers

Articles

Custom Policy Enforcement with Reasoning: Faster, Safer AI Applications

9 days ago

•

How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare

Oct 28

•

NVIDIA Releases 8 Million Sample Open Dataset and Tooling for OCR, Image Reasoning, Image and Video QA Tasks

Oct 28

•

Cosmos Predict 2.5 & Transfer 2.5: Evolving the World Foundation Models for Physical AI

Oct 28

•

Nemotron’s Open Secret: Accelerating AI Development with Open Models, Data, and Recipes

Oct 22

•

Llama‑Embed‑Nemotron‑8B Text Embedding Model Ranks First on Multilingual MTEB Leaderboard

Oct 21

•

Scaling Test-Time Compute to Achieve Gold Medal at IOI 2025 with Open-Weight Models

Oct 20

•

Nemotron-Personas-India: Synthesized Data for Sovereign AI

Oct 13

•

Nemotron-Personas-Japan: ソブリン AI のための合成データセット

Sep 26

•

Nemotron-Personas-Japan: Synthesized Data for Sovereign AI

Sep 23

•

NVIDIA Releases 6 Million Multi-Lingual Reasoning Dataset

Aug 20

•

Supercharge Edge AI With High‑Accuracy Reasoning Using NVIDIA Nemotron Nano 2 9B

Aug 18

•

📢 NVIDIA Releases Nemotron-CC-Math Pre-Training Dataset: A High-Quality, Web-Scale Math Corpus for Pretraining Large Language Models

Aug 18

•

NVIDIA Releases Improved Pretraining Dataset: Preserves High Value Math & Code, and Augments with Multi-Lingual

Aug 18

•

NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks

Aug 11

•

Measuring Open-Source Llama Nemotron Models on DeepResearch Bench

Aug 4

•

Accelerate a World of LLMs on Hugging Face with NVIDIA NIM

Jul 21

•

OpenReasoning-Nemotron: A Family of State-of-the-Art Distilled Reasoning Models

Jul 18

•

Llama-NeMoRetriever-ColEmbed: Developer-Focused Guide to NVIDIA's State-of-the-Art Text-Image Retrieval

Jul 9

•

Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub

Jun 27

•

Introducing Cosmos Predict-2: A Foundation For Your Own World Model

Jun 17

•

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

Jun 11

•

119

Supercharge Edge AI with High Accuracy Reasoning Using Llama Nemotron Nano 4B

Jun 10

•

Nemotron-Personas: Improve AI Training With the First Synthetic Personas Dataset Aligned to Real-World Distributions

Jun 10

•

Explore, Build, and Innovate AI Reasoning with NVIDIA’s Open Models and Recipes

Jun 4

•

Mastering Long Contexts in LLMs with KVPress

Jan 23

•

VibhuJawa

in nvidia/nemotron-page-elements-v3 about 2 hours ago

vjawa_ensure_device_side_preprocessing

#8 opened about 3 hours ago by

VibhuJawa

in nvidia/nemotron-table-structure-v1 about 2 hours ago

vjawa_move_preprocessing_to_device

#5 opened about 3 hours ago by

VibhuJawa

in nvidia/nemotron-graphic-elements-v1 about 2 hours ago

vjawa_move_preprocessing_to_device

#8 opened about 2 hours ago by

VibhuJawa

shengliangx

in nvidia/Qwen2.5-VL-7B-Instruct-FP8 about 11 hours ago

update config for exclude modules

#3 opened about 12 hours ago by

shengliangx

in nvidia/Llama-4-Scout-17B-16E-Instruct-NVFP4 about 11 hours ago

update config for exclude modules

#3 opened about 12 hours ago by

shengliangx

in nvidia/Llama-4-Scout-17B-16E-Instruct-FP8 about 11 hours ago

update config for exclude modules

#1 opened about 12 hours ago by

shengliangx

nv-spectralflight

updated a model about 13 hours ago

nvidia/Cosmos-Predict2.5-2B

Updated 6 days ago • 24.2k • 31

Mujojojo

published a model about 14 hours ago

nvidia/Riva-Translate-4B-Instruct-v1.1

Text Generation • 4B • Updated about 17 hours ago • 69 • 4

fsiino

in nvidia/Nemotron-RL-math-OpenMathReasoning about 16 hours ago

Upload validation

#1 opened about 16 hours ago by

fsiino

in nvidia/Nemotron-RL-instruction_following-structured_outputs about 16 hours ago

Upload validation

#1 opened about 16 hours ago by

fsiino

in nvidia/Nemotron-RL-agent-workplace_assistant about 16 hours ago

Upload validation

#2 opened about 16 hours ago by

fsiino

Mujojojo

updated 2 models about 17 hours ago

nvidia/Riva-Translate-4B-Instruct

Text Generation • 4B • Updated about 17 hours ago • 686 • 12

nvidia/Riva-Translate-4B-Instruct-v1.1

Text Generation • 4B • Updated about 17 hours ago • 69 • 4

shizhediao2

in nvidia/ToolScale about 18 hours ago

Add metadata and refactor to ToolScale Dataset Card

#3 opened 7 days ago by

nielsr

abercovich

authored a paper 4 months ago

NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model

Paper • 2508.14444 • Published Aug 20 • 38

chintankp

posted an update 4 months ago

Post

1630

We’re excited to share that Llama Nemotron Super v1.5 -- our latest open reasoning model -- is leading the Artificial Analysis Intelligence Index - a leaderboard that spans advanced math, science, and agentic tasks, for models running on a single NVIDIA H100.
Super v1.5 is trained with high-quality reasoning synthetic data generated from models like Qwen3-235B and DeepSeek R1. Besides leading accuracy, it also delivers high throughput.
Key features:
- Leading accuracy on multi-step reasoning, math, coding, and function-calling
- Post-trained using RPO, DPO, and RLVR across 26M+ synthetic examples
- Fully transparent training data on HF (Nemotron-Post-Training-Dataset-v1)

Try Super v1.5 on build.nvidia.com or download from Hugging Face

chintankp

posted an update 5 months ago

Post

1690

We are incredibly proud to be among the top contributors to the AI community with our leading open models and permissive licensed datasets for reasoning, Physical AI, speech, vision, and more.

See huggingface.co/spaces/cfahlgren1/org-activity-heatmap

Download the latest models and datasets from huggingface.co/nvidia

mdabbah-nvidia

authored a paper 9 months ago

FFN Fusion: Rethinking Sequential Computation in Large Language Models

Paper • 2503.18908 • Published Mar 24 • 19

abercovich

authored a paper 9 months ago

FFN Fusion: Rethinking Sequential Computation in Large Language Models

Paper • 2503.18908 • Published Mar 24 • 19

zhiqilinv

authored a paper 9 months ago

Token-Efficient Long Video Understanding for Multimodal LLMs

Paper • 2503.04130 • Published Mar 6 • 96

AI & ML interests

Recent Activity

Papers

Articles

Custom Policy Enforcement with Reasoning: Faster, Safer AI Applications

How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare

🛡️ Nemotron PII: Synthesized Data for Privacy-Preserving AI

Nemotron-Personas-USA: Synthesized Data for Sovereign AI

NVIDIA Isaac GR00T in LeRobot

Can Your LLM Think Like a Professional? Introducing ProfBench

NVIDIA Releases 8 Million Sample Open Dataset and Tooling for OCR, Image Reasoning, Image and Video QA Tasks

Cosmos Predict 2.5 & Transfer 2.5: Evolving the World Foundation Models for Physical AI

Nemotron’s Open Secret: Accelerating AI Development with Open Models, Data, and Recipes

Llama‑Embed‑Nemotron‑8B Text Embedding Model Ranks First on Multilingual MTEB Leaderboard

Scaling Test-Time Compute to Achieve Gold Medal at IOI 2025 with Open-Weight Models

Nemotron-Personas-India: Synthesized Data for Sovereign AI

Nemotron-Personas-Japan: ソブリン AI のための合成データセット

Nemotron-Personas-Japan: Synthesized Data for Sovereign AI

NVIDIA Releases 6 Million Multi-Lingual Reasoning Dataset

Supercharge Edge AI With High‑Accuracy Reasoning Using NVIDIA Nemotron Nano 2 9B

📢 NVIDIA Releases Nemotron-CC-Math Pre-Training Dataset: A High-Quality, Web-Scale Math Corpus for Pretraining Large Language Models

NVIDIA Releases Improved Pretraining Dataset: Preserves High Value Math & Code, and Augments with Multi-Lingual

NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks

Measuring Open-Source Llama Nemotron Models on DeepResearch Bench

Accelerate a World of LLMs on Hugging Face with NVIDIA NIM

OpenReasoning-Nemotron: A Family of State-of-the-Art Distilled Reasoning Models

Llama-NeMoRetriever-ColEmbed: Developer-Focused Guide to NVIDIA's State-of-the-Art Text-Image Retrieval

Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub

Introducing Cosmos Predict-2: A Foundation For Your Own World Model

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

Supercharge Edge AI with High Accuracy Reasoning Using Llama Nemotron Nano 4B

Nemotron-Personas: Improve AI Training With the First Synthetic Personas Dataset Aligned to Real-World Distributions

Explore, Build, and Innovate AI Reasoning with NVIDIA’s Open Models and Recipes

Mastering Long Contexts in LLMs with KVPress

Team members 3,392

nvidia's activity

vjawa_ensure_device_side_preprocessing

vjawa_move_preprocessing_to_device

vjawa_move_preprocessing_to_device

update config for exclude modules

update config for exclude modules

update config for exclude modules

Upload validation

Upload validation

Upload validation

Add metadata and refactor to ToolScale Dataset Card