Xin Wen

xwen99's activity

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

upvoted a paper 3 days ago

Self-Evaluation Unlocks Any-Step Text-to-Image Generation

Paper • 2512.22374 • Published 7 days ago • 14

liked a dataset 21 days ago

Ritvik19/Sudoku-Dataset

Viewer • Updated Mar 22, 2024 • 17M • 823 • 12

upvoted a paper 2 months ago

Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

Paper • 2510.23607 • Published Oct 27, 2025 • 177

upvoted a paper 3 months ago

QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs

Paper • 2510.11696 • Published Oct 13, 2025 • 176

liked a Space 4 months ago

Running

215

FineVision: Open Data is All You Need

📝

215

A new open-source dataset for training VLMs

upvoted a paper 5 months ago

The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements

Paper • 2506.22419 • Published Jun 27, 2025 • 15

upvoted 2 papers 6 months ago

Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models

Paper • 2507.07104 • Published Jul 9, 2025 • 45

Scaling Laws for Optimal Data Mixtures

Paper • 2507.09404 • Published Jul 12, 2025 • 36

authored a paper 6 months ago

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Paper • 2507.08441 • Published Jul 11, 2025 • 61

upvoted a paper 6 months ago

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Paper • 2507.08441 • Published Jul 11, 2025 • 61

commented a paper 6 months ago

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Paper • 2507.08441 • Published Jul 11, 2025 • 61 •

2

upvoted a paper 6 months ago

Holistic Tokenizer for Autoregressive Image Generation

Paper • 2507.02358 • Published Jul 3, 2025 • 4

authored 2 papers 10 months ago

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning

Paper • 2503.06960 • Published Mar 10, 2025 • 3

"Principal Components" Enable A New Language of Images

Paper • 2503.08685 • Published Mar 11, 2025 • 12

upvoted a paper 10 months ago

"Principal Components" Enable A New Language of Images

Paper • 2503.08685 • Published Mar 11, 2025 • 12

commented a paper 10 months ago

"Principal Components" Enable A New Language of Images

Paper • 2503.08685 • Published Mar 11, 2025 • 12 •

2

upvoted a paper 10 months ago

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning

Paper • 2503.06960 • Published Mar 10, 2025 • 3

commented a paper 10 months ago

A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning

Paper • 2503.06960 • Published Mar 10, 2025 • 3 •

2

updated a model 11 months ago

xwen99/mar-vae-kl16

Image-to-Image • Updated Feb 11, 2025 • 17

published a model 11 months ago

xwen99/mar-vae-kl16

Image-to-Image • Updated Feb 11, 2025 • 17