Kaican Li PRO

m-Just's activity

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

updated a dataset about 18 hours ago

m-Just/InfoVQA_RegionLocalization

Viewer • Updated about 18 hours ago • 10.2k • 34 • 1

updated a model about 18 hours ago

m-Just/InSight-o3-vS

Image-Text-to-Text • 8B • Updated about 18 hours ago • 3

updated a dataset about 18 hours ago

m-Just/VisCoT_VStar_Collage

Viewer • Updated about 18 hours ago • 15.3k • 6.78k • 2

updated a dataset 3 days ago

m-Just/O3-Bench

Viewer • Updated 3 days ago • 345 • 1.33k • 16

upvoted 3 papers 14 days ago

OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization

Paper • 2106.03721 • Published Jun 7, 2021 • 1

CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving

Paper • 2203.07724 • Published Mar 15, 2022 • 1

Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models

Paper • 2411.19757 • Published Nov 29, 2024 • 1

updated a collection 14 days ago

InSight-o3

Collection

Empowering Multimodal Foundation Models with Generalized Visual Search • 4 items • Updated 14 days ago • 1

liked 2 datasets 14 days ago

m-Just/InfoVQA_RegionLocalization

Viewer • Updated about 18 hours ago • 10.2k • 34 • 1

m-Just/VisCoT_VStar_Collage

Viewer • Updated about 18 hours ago • 15.3k • 6.78k • 2

published a dataset 14 days ago

m-Just/InfoVQA_RegionLocalization

Viewer • Updated about 18 hours ago • 10.2k • 34 • 1

published a dataset 15 days ago

m-Just/VisCoT_VStar_Collage

Viewer • Updated about 18 hours ago • 15.3k • 6.78k • 2

upvoted a paper 16 days ago

MapTrace: Scalable Data Generation for Route Tracing on Maps

Paper • 2512.19609 • Published Dec 22, 2025 • 1

liked a dataset 16 days ago

google/MapTrace

Viewer • Updated 27 days ago • 19.8k • 4.66k • 17

upvoted a collection 18 days ago

InSight-o3

Collection

Empowering Multimodal Foundation Models with Generalized Visual Search • 4 items • Updated 14 days ago • 1

updated a collection 18 days ago

InSight-o3

Collection

Empowering Multimodal Foundation Models with Generalized Visual Search • 4 items • Updated 14 days ago • 1

liked a model 18 days ago

m-Just/InSight-o3-vS

Image-Text-to-Text • 8B • Updated about 18 hours ago • 3

published a model 18 days ago

m-Just/InSight-o3-vS

Image-Text-to-Text • 8B • Updated about 18 hours ago • 3

submitted a paper to Daily Papers about 1 month ago

InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search

Paper • 2512.18745 • Published Dec 21, 2025 • 12