Mai

Guangcan's activity

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

upvoted 5 papers about 1 month ago

When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better

Paper • 2610.11291 • Published Oct 8 • 26

Less from More: Reinforcing Sparse Video Reasoning from Dense References

Paper • 2610.10893 • Published Oct 7 • 9

WorldSonus: Bringing Sound to Worlds

Paper • 2610.08760 • Published Oct 6 • 25

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

Paper • 2610.05608 • Published Oct 4 • 161

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

Paper • 2610.01780 • Published Oct 1 • 43

upvoted a collection 2 months ago

BVD: Big Video Dataset

Collection

A 10-Million-Hour Open Video Dataset for Multimodal Pre-training • 11 items • Updated Aug 26 • 9

upvoted a paper 2 months ago

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

Paper • 2609.07108 • Published 12 days ago • 18

upvoted a paper 3 months ago

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

Paper • 2608.20958 • Published Aug 21 • 60

upvoted a paper 5 months ago

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Paper • 2606.19534 • Published Jun 17 • 66

upvoted a collection 11 months ago

NVIDIA Nemotron V2

Collection

Open, Production-ready Enterprise Models. Nvidia Open Model license. • 9 items • Updated 1 day ago • 109

upvoted a paper about 1 year ago

Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs

Paper • 2510.18876 • Published Oct 21, 2025 • 37

upvoted a collection about 1 year ago

Nemotron-Pre-Training-Datasets

Collection

Large scale pre-training datasets used in the Nemotron family of models. • 17 items • Updated 1 day ago • 200