Fangzhou

Fzz1's activity

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

upvoted a paper 1 day ago

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

Paper • 2604.06916 • Published 3 days ago • 12

upvoted a collection 29 days ago

M2RNN

Collection

Note that the 7B models are MoE with 1.1B active parameters and 400M models are dense models • 14 items • Updated 29 days ago • 7

upvoted a paper 29 days ago

Flash-KMeans: Fast and Memory-Efficient Exact K-Means

Paper • 2603.09229 • Published Mar 10 • 82

upvoted a paper about 1 month ago

K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model

Paper • 2602.19128 • Published Feb 22 • 7

upvoted a paper 2 months ago

VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents

Paper • 2601.16973 • Published Jan 23 • 40

upvoted 2 papers 5 months ago

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Paper • 2511.19399 • Published Nov 24, 2025 • 63

UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity

Paper • 2511.13714 • Published Nov 17, 2025 • 12