Tianyu Zhang

TianyuZhang's activity

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

published a model 12 days ago

TianyuZhang/Qwen2.5-1.5B-Open-R1-DAPO

Updated 12 days ago

published a model 13 days ago

TianyuZhang/Qwen2.5-1.5B-Open-R1-GRPO

Updated 13 days ago

updated a model 17 days ago

TianyuZhang/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Text Generation • 2B • Updated 17 days ago • 19

upvoted a paper 18 days ago

Evolving Programmatic Skill Networks

Paper • 2601.03509 • Published 19 days ago • 81

published a model 19 days ago

TianyuZhang/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

Text Generation • 2B • Updated 17 days ago • 19

upvoted an article about 2 months ago

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

Dec 4, 2025

•

582

upvoted 2 papers 2 months ago

AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning

Paper • 2511.19304 • Published Nov 24, 2025 • 91

Don't Waste It: Guiding Generative Recommenders with Structured Human Priors via Multi-head Decoding

Paper • 2511.10492 • Published Nov 13, 2025 • 6

upvoted a paper 3 months ago

The Underappreciated Power of Vision Models for Graph Structural Understanding

Paper • 2510.24788 • Published Oct 27, 2025 • 36

liked 4 models 3 months ago

ByteDance/Ouro-2.6B-Thinking

Text Generation • Updated 8 days ago • 236 • 72

ByteDance/Ouro-2.6B

Text Generation • Updated 8 days ago • 394 • 50

ByteDance/Ouro-1.4B-Thinking

Text Generation • Updated 8 days ago • 1.69k • 28

ByteDance/Ouro-1.4B

Text Generation • Updated 8 days ago • 13.9k • 58

authored 7 papers 3 months ago

ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods

Paper • 2110.02871 • Published Oct 6, 2021

MuPT: A Generative Symbolic Music Pretrained Transformer

Paper • 2404.06393 • Published Apr 9, 2024 • 16

Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation

Paper • 2211.06687 • Published Nov 12, 2022 • 5

BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks

Paper • 2412.04626 • Published Dec 5, 2024 • 13

STRICT: Stress Test of Rendering Images Containing Text

Paper • 2505.18985 • Published May 25, 2025

A Single Merging Suffices: Recovering Server-based Learning Performance in Decentralized Learning

Paper • 2507.06542 • Published Jul 9, 2025

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

Paper • 2406.07529 • Published Jun 11, 2024