Forty-Two AI Lab

Seed42Lab's activity

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

marstin 

updated 3 datasets about 1 month ago

Seed42Lab/RefBlock

Viewer • Updated Jul 11 • 1.25k • 36 • 1

Seed42Lab/RefOI-TLHF

Viewer • Updated Jul 11 • 10.6k • 430 • 2

Seed42Lab/RefOI

Viewer • Updated Jul 11 • 1.49k • 175 • 1

wonderwind271 

updated a model about 1 month ago

Seed42Lab/trabank-vl

Updated Jul 9

marstin 

authored a paper about 2 months ago

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation

Paper • 2506.21876 • Published Jun 27 • 28

marstin 

updated a collection about 2 months ago

Vision-Language Datasets

Collection

7 items • Updated Jul 4

marstin 

authored 2 papers about 2 months ago

Can Vision Language Models Infer Human Gaze Direction? A Controlled Study

Paper • 2506.05412 • Published Jun 4 • 4

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

Paper • 2506.18890 • Published Jun 23 • 6

XueyangY 

authored 4 papers about 2 months ago

Learning Video Representations without Natural Videos

Paper • 2410.24213 • Published Oct 31, 2024 • 16

VCA: Video Curious Agent for Long Video Understanding

Paper • 2412.10471 • Published Dec 12, 2024

Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens

Paper • 2506.17218 • Published Jun 20 • 27

GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation

Paper • 2504.07962 • Published Apr 10

cheryyunl 

authored a paper 2 months ago

ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs

Paper • 2506.10128 • Published Jun 11 • 23

Xuweiyi 

authored a paper 3 months ago

Frame In-N-Out: Unbounded Controllable Image-to-Video Generation

Paper • 2505.21491 • Published May 27 • 17

JaneDing2025 

updated a dataset 3 months ago

Seed42Lab/RefOI

Viewer • Updated Jul 11 • 1.49k • 175 • 1

cheryyunl 

updated a model 3 months ago

Seed42Lab/Avocado

Updated May 21

marstin 

authored 2 papers 4 months ago

VEGGIE: Instructional Editing and Reasoning of Video Concepts with Grounded Generation

Paper • 2503.14350 • Published Mar 18

Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation

Paper • 2504.16060 • Published Apr 22

marstin 

authored 2 papers 6 months ago

DriVLMe: Enhancing LLM-based Autonomous Driving Agents with Embodied and Social Experiences

Paper • 2406.03008 • Published Jun 5, 2024

Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models

Paper • 2407.07035 • Published Jul 9, 2024