Maozhou Ge

Gmc2's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 8 days ago

Scaling Native Multimodal Pre-Training From Scratch

Paper • 2607.22043 • Published Jul 24 • 30

Beyond Language Modeling: An Exploration of Multimodal Pretraining

Paper • 2603.03276 • Published Mar 3 • 109

upvoted a collection 15 days ago

Cosmos-Embed1

Collection

Joint video-text embedding for physical AI • 5 items • Updated Aug 11 • 9

upvoted a paper 17 days ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 20 days ago • 224

upvoted a collection 19 days ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.8k

upvoted a paper 29 days ago

On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability

Paper • 2608.30320 • Published Aug 31 • 63

upvoted a paper about 1 month ago

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

Paper • 2609.00111 • Published Aug 31 • 316

upvoted a collection about 1 month ago

Cosmos-Reason2

Collection

⚠️ This collection is archived. 👉 https://huggingface.co/collections/nvidia/cosmos3 • 8 items • Updated Aug 11 • 29

upvoted an article about 1 month ago

view article

Article

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

• 

nvidia

•

Jun 1

• 91

upvoted 3 collections about 1 month ago

Cosmos3

Collection

Omnimodal World Models for Physical AI • 6 items • Updated Aug 28 • 207

DFlash 2

Collection

Keep Drafting Parallel • 4 items • Updated 25 days ago • 30

DFlash 2

Collection

Keep Drafting Parallel • 6 items • Updated Aug 28 • 49

upvoted 2 collections about 2 months ago

Qwen3.8

Collection

4 items • Updated Aug 13 • 552

NVIDIA OmniDreams

Collection

NVIDIA OmniDreams model checkpoints and sample datasets. • 3 items • Updated Aug 11 • 10

upvoted 2 articles 2 months ago

view article

Article

Ulysses Sequence Parallelism: Training with Million-Token Contexts

• 
• 

kashif, stas

•

Mar 9

• 33

view article

Article

NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics

• 

nvidia

•

Jul 27

• 77

upvoted a paper 2 months ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 526

upvoted 3 papers 3 months ago

Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better

Paper • 2505.23705 • Published May 29, 2025 • 1

LingoQA: Video Question Answering for Autonomous Driving

Paper • 2312.14115 • Published Dec 21, 2023 • 4

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published Jul 10 • 83