Xin Wen

xwen99's activity

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

upvoted a paper about 3 hours ago

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

Paper • 2510.23607 • Published about 13 hours ago • 58

upvoted a paper 14 days ago

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

Paper • 2510.11696 • Published 15 days ago • 167

liked a Space about 2 months ago

Running

188

188

FineVision: Open Data is All You Need

📝

A new open-source dataset for training VLMs

upvoted 3 papers 3 months ago

The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements

Paper • 2506.22419 • Published Jun 27 • 14

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

Paper • 2507.07104 • Published Jul 9 • 45

Scaling Laws for Optimal Data Mixtures

Paper • 2507.09404 • Published Jul 12 • 35

authored a paper 3 months ago

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Paper • 2507.08441 • Published Jul 11 • 61

upvoted a paper 4 months ago

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Paper • 2507.08441 • Published Jul 11 • 61

commented a paper 4 months ago

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation

Paper • 2507.08441 • Published Jul 11 • 61 •

1

upvoted a paper 4 months ago

Holistic Tokenizer for Autoregressive Image Generation

Paper • 2507.02358 • Published Jul 3 • 4

authored 2 papers 8 months ago

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

Paper • 2503.06960 • Published Mar 10 • 3

"Principal Components" Enable A New Language of Images

Paper • 2503.08685 • Published Mar 11 • 12

upvoted a paper 8 months ago

"Principal Components" Enable A New Language of Images

Paper • 2503.08685 • Published Mar 11 • 12

commented a paper 8 months ago

"Principal Components" Enable A New Language of Images

Paper • 2503.08685 • Published Mar 11 • 12 •

2

upvoted a paper 8 months ago

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

Paper • 2503.06960 • Published Mar 10 • 3

commented a paper 8 months ago

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

Paper • 2503.06960 • Published Mar 10 • 3 •

2

updated a model 9 months ago

xwen99/mar-vae-kl16

Image-to-Image • Updated Feb 11 • 55

published a model 9 months ago

xwen99/mar-vae-kl16

Image-to-Image • Updated Feb 11 • 55

authored 2 papers about 1 year ago

Can OOD Object Detectors Learn from Foundation Models?

Paper • 2409.05162 • Published Sep 8, 2024 • 9

Generalization Beyond Data Imbalance: A Controlled Study on CLIP for Transferable Insights

Paper • 2405.21070 • Published May 31, 2024