Jihan Yang PRO

jihanyang's activity

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

upvoted a paper 9 days ago

Beyond Language Modeling: An Exploration of Multimodal Pretraining

Paper • 2603.03276 • Published 9 days ago • 88

upvoted a paper 14 days ago

Solaris: Building a Multiplayer Video World Model in Minecraft

Paper • 2602.22208 • Published 15 days ago • 28

liked a dataset 23 days ago

nyu-visionx/scale-rae-data

Updated Jan 24 • 11.5k • 2

liked a dataset 27 days ago

allenai/Molmo2-VideoCapQA

Viewer • Updated 30 days ago • 951k • 247 • 6

liked a dataset 29 days ago

jasonzhango/SPAR-7M

Viewer • Updated Sep 28, 2025 • 16.3M • 7.47k • 6

authored a paper about 2 months ago

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

Paper • 2601.16208 • Published Jan 22 • 54

upvoted a paper about 2 months ago

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders

Paper • 2601.16208 • Published Jan 22 • 54

upvoted 2 collections 2 months ago

Cambrian-S Models

Collection

18 items • Updated 11 days ago • 8

Cambrian-S-Data

Collection

Data used during Cambrian-S's 4-stage training • 4 items • Updated 13 days ago • 5

authored 2 papers 4 months ago

Cambrian-S: Towards Spatial Supersensing in Video

Paper • 2511.04670 • Published Nov 6, 2025 • 38

Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts

Paper • 2511.04655 • Published Nov 6, 2025 • 9

upvoted a collection 4 months ago

VSI-SUPER

Collection

VSI-SUPER benchmark proposed in Cambrian-S • 2 items • Updated 11 days ago • 3

upvoted 2 papers 4 months ago

Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts

Paper • 2511.04655 • Published Nov 6, 2025 • 9

Cambrian-S: Towards Spatial Supersensing in Video

Paper • 2511.04670 • Published Nov 6, 2025 • 38

commented a paper 4 months ago

Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts

Paper • 2511.04655 • Published Nov 6, 2025 • 9 •

2

upvoted 4 papers 5 months ago

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

Paper • 2510.23607 • Published Oct 27, 2025 • 179

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

Paper • 2510.11696 • Published Oct 13, 2025 • 181

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13, 2025 • 168

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26, 2025 • 188

upvoted a paper 7 months ago

MetaCLIP 2: A Worldwide Scaling Recipe

Paper • 2507.22062 • Published Jul 29, 2025 • 37