weize

weizechen's activity

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

liked a dataset 18 days ago

openai/frontierscience

Viewer • Updated 18 days ago • 160 • 7.19k • 143

upvoted a paper about 2 months ago

P1: Mastering Physics Olympiads with Reinforcement Learning

Paper • 2511.13612 • Published Nov 17, 2025 • 134

updated a model 3 months ago

weizechen/RL-Compositionality-Stage-1-Model

8B • Updated Oct 17, 2025 • 15 • 1

updated 4 datasets 3 months ago

weizechen/RL-Compositionality-Stage2-RL-Level8-TestData

Viewer • Updated Oct 17, 2025 • 2.05k • 25 • 1

weizechen/RL-Compositionality-Stage2-RL-Level2-TrainData

Viewer • Updated Oct 17, 2025 • 500k • 15 • 1

weizechen/RL-Compositionality-Stage2-RL-Level1-TrainData

Viewer • Updated Oct 17, 2025 • 500k • 21 • 1

weizechen/RL-Compositionality-Stage1-RFT-Data

Viewer • Updated Oct 17, 2025 • 118k • 35 • 1

updated a collection 3 months ago

RL Compositionality

Collection

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones. https://huggingface.co/papers/2509.25123 • 5 items • Updated Oct 17, 2025 • 1

published a model 3 months ago

weizechen/RL-Compositionality-Stage-1-Model

8B • Updated Oct 17, 2025 • 15 • 1

updated a collection 3 months ago

RL Compositionality

Collection

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones. https://huggingface.co/papers/2509.25123 • 5 items • Updated Oct 17, 2025 • 1

published 4 datasets 3 months ago

weizechen/RL-Compositionality-Stage2-RL-Level8-TestData

Viewer • Updated Oct 17, 2025 • 2.05k • 25 • 1

weizechen/RL-Compositionality-Stage2-RL-Level2-TrainData

Viewer • Updated Oct 17, 2025 • 500k • 15 • 1

weizechen/RL-Compositionality-Stage2-RL-Level1-TrainData

Viewer • Updated Oct 17, 2025 • 500k • 21 • 1

weizechen/RL-Compositionality-Stage1-RFT-Data

Viewer • Updated Oct 17, 2025 • 118k • 35 • 1

upvoted a paper 3 months ago

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones

Paper • 2509.25123 • Published Sep 29, 2025 • 20

commented a paper 3 months ago

From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones

Paper • 2509.25123 • Published Sep 29, 2025 • 20 •

2

authored a paper 3 months ago

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

Paper • 2509.18154 • Published Sep 16, 2025 • 52