Article
Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action
nvidia
• • 71Jiancheng Pan
jaychempan
AI & ML interests
I am interested in cutting-edge Visual Intelligence, focusing on Multimodal Learning, Foundation Models and MLLMs, Data-centric AI, and their applications across, e.g., Egocentric Vision, Earth Observation, and AI for Sustainability.
Recent Activity
updated a bucket 3 days ago
ML4Sustain/EarthSynth-bucket published a bucket 3 days ago
ML4Sustain/EarthSynth-bucket updated a bucket 3 days ago
ML4Sustain/LAE-DINO-bucketOrganizations
upvoted an article 6 days ago
upvoted a paper 8 days ago
upvoted a paper 10 days ago
upvoted a paper 25 days ago
upvoted an article about 1 month ago
Article
NEO-unify: Building Native Multimodal Unified Models End to End
sensenova
• • 164 upvoted a collection about 1 month ago
upvoted 4
papers 4 months ago
Action100M: A Large-scale Video Action Dataset
Paper • 2601.10592 • Published • 32
PaperBanana: Automating Academic Illustration for AI Scientists
Paper • 2601.23265 • Published • 228
Advancing Open-source World Models
Paper • 2601.20540 • Published • 135
V^{2}-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence
Paper • 2511.20886 • Published • 1
upvoted 2
papers 6 months ago
upvoted a paper 8 months ago
upvoted 5
papers 9 months ago
RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events
Paper • 2509.01907 • Published • 2
SegEarth-OV: Towards Traning-Free Open-Vocabulary Segmentation for Remote Sensing Images
Paper • 2410.01768 • Published • 4
PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
Paper • 2509.12989 • Published • 28
EarthSynth: Generating Informative Earth Observation with Diffusion Models
Paper • 2505.12108 • Published • 2
Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community
Paper • 2408.09110 • Published • 2