NVIDIA-Eagle

community

https://github.com/NVlabs/Eagle

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

di-zhang-fdu authored a paper 4 days ago

Chem-R: Learning to Reason as a Chemist

cmhungsteve authored a paper 18 days ago

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning

cmhungsteve authored a paper 25 days ago

TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control

View all activity

di-zhang-fdu

posted an update 1 day ago

Post

105

Let-BERT-SPEAK: Training-Free Block Diffusion Language Model with BERT

Code: https://github.com/trotsky1997/Let-BERT-SPEAK/blob/main/generate.py

Blog: https://trotsky1997.notion.site/Let-BERT-SPEAK-Training-Free-Block-Diffusion-Language-Model-with-BERT-2a2bbfcc4cdf802aa67dcba6a02a0c9f

di-zhang-fdu

authored a paper 4 days ago

Chem-R: Learning to Reason as a Chemist

Paper • 2510.16880 • Published 19 days ago • 52

di-zhang-fdu

posted an update 11 days ago

Post

1066

The training dataset of ChemVLM is open-sourced now, have a check!
di-zhang-fdu/chemvlm-sft-datasets

papers: Seeing and Understanding: Bridging Vision with Chemical Knowledge Via ChemVLM (2408.07246)

cmhungsteve

authored a paper 18 days ago

DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning

Paper • 2510.15110 • Published 22 days ago • 15

cmhungsteve

authored a paper 25 days ago

TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control

Paper • 2510.09561 • Published 28 days ago • 7

cmhungsteve

authored a paper 29 days ago

Temporal Prompting Matters: Rethinking Referring Video Object Segmentation

Paper • 2510.07319 • Published 30 days ago • 2

cmhungsteve

authored a paper about 1 month ago

LEAML: Label-Efficient Adaptation to Out-of-Distribution Visual Tasks for Multimodal Large Language Models

Paper • 2510.03232 • Published Oct 3 • 1

tsungyi

posted an update about 1 month ago

Post

3681

We’re excited to share that Cosmos Reason has surpassed 1 million downloads on Hugging Face!

Cosmos Reason is an open, customizable, commercial-ready 7B-parameter reasoning vision language model (VLM) designed for physical AI. By combining physics understanding, prior knowledge, and common sense reasoning, Cosmos Reason empowers AI agents and robots to operate intelligently in real-world environments.

Key applications already unlocked include:

✅ Automating large-scale dataset curation and annotation

🤖 Powering robot planning and vision-language action (VLA) decision-making

📊 Driving advanced video analytics and actionable insight generation

We’re proud to see a global community of developers using Cosmos Reason to teach robots to think like humans—and we’re just getting started.

⚡ Get started with Cosmos Reason 1 NIM, an easy-to-use microservice for AI model deployment: https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/cosmos-reason1-7b?version=1

📈 See the leaderboard: facebook/physical_reasoning_leaderboard

cmhungsteve

authored a paper about 1 month ago

V2V-GoT: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language Models and Graph-of-Thoughts

Paper • 2509.18053 • Published Sep 22 • 3

txiong23

authored 2 papers about 2 months ago

GPT-4 Vision on Medical Image Classification -- A Case Study on COVID-19 Dataset

Paper • 2310.18498 • Published Oct 27, 2023

LLaVA-Critic-R1: Your Critic Model is Secretly a Strong Policy Model

Paper • 2509.00676 • Published Aug 31 • 83

tsungyi

posted an update 2 months ago

Post

2016

Cosmos Reason just topped Physical Reasoning Leaderboard on Hugging Face. 👏🔥

Cosmos Reason is an open, customizable, commercial-ready 7B-parameter, reasoning vision language model (VLM) for physical AI and robotics. The VLM empowers robots and vision AI agents to reason like humans, leveraging prior knowledge, physics understanding, and common sense to understand and operate intelligently in the real world.

This model unlocks advanced capabilities for robotics, autonomous vehicles, and real-world operations—from cities to high-tech factories.

Key use cases include:
Data curation & annotation: Automate high-quality dataset curation and annotation at scale.
Robot planning & reasoning: Serve as the "brain" for deliberate, methodical decision-making with vision language action (VLA) models.
Video analytics AI agents: Extract actionable insights and perform root-cause analysis on massive video datasets.

Ready to build the next generation of physical AI? Get started 👉 nvidia/Cosmos-Reason1-7B
Try the preview here: https://build.nvidia.com/nvidia/cosmos-reason1-7b