Glab Caltech

community

https://gkioxari.github.io/

AI & ML interests

None defined yet.

Recent Activity

dmarsili new activity about 8 hours ago

glab-caltech/FGVQA:[bot] Conversion to Parquet

dmarsili updated a dataset about 1 month ago

glab-caltech/TWIN

aadarsh99 submitted a paper 3 months ago

Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision

View all activity

in glab-caltech/FGVQA about 8 hours ago

[bot] Conversion to Parquet

#1 opened 4 months ago by

parquet-converter

updated a dataset about 1 month ago

glab-caltech/TWIN

Viewer • Updated Mar 30 • 562k • 38 • 3

submitted a paper to Daily Papers 3 months ago

Conversational Image Segmentation: Grounding Abstract Concepts with Scalable Supervision

Paper • 2602.13195 • Published Feb 13 • 4

updated 2 collections 3 months ago

VALOR

[ICLR 2026] Models from the paper "No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers" • 3 items • Updated Feb 22 • 1

TWIN

[CVPR 2026] Datasets and models from the paper "Same or Not? Enhancing Visual Perception in Vision-Language Models" • 5 items • Updated Feb 22 • 2

in glab-caltech/TWIN-InternVL3_5-1B 4 months ago

Add pipeline tag, library name, and improve model card

#1 opened 4 months ago by

in glab-caltech/TWIN-Qwen2.5-VL-3B 4 months ago

Add pipeline tag, library name, and dataset metadata

#1 opened 4 months ago by

updated a dataset 4 months ago

glab-caltech/FGVQA

Viewer • Updated Dec 30, 2025 • 12k • 13 • 1

updated 2 models 4 months ago

glab-caltech/TWIN-InternVL3_5-1B

Image-Text-to-Text • 1B • Updated Dec 30, 2025 • 10 • 1

glab-caltech/TWIN-Qwen2.5-VL-3B

Image-Text-to-Text • 4B • Updated Dec 30, 2025 • 4 • 2

published 2 models 4 months ago

glab-caltech/TWIN-InternVL3_5-1B

Image-Text-to-Text • 1B • Updated Dec 30, 2025 • 10 • 1

glab-caltech/TWIN-Qwen2.5-VL-3B

Image-Text-to-Text • 4B • Updated Dec 30, 2025 • 4 • 2

in glab-caltech/TWIN 4 months ago

[bot] Conversion to Parquet

#1 opened 5 months ago by

parquet-converter

published 2 datasets 5 months ago

glab-caltech/TWIN

Viewer • Updated Mar 30 • 562k • 38 • 3

glab-caltech/FGVQA

Viewer • Updated Dec 30, 2025 • 12k • 13 • 1

updated 2 collections 5 months ago

TWIN

[CVPR 2026] Datasets and models from the paper "Same or Not? Enhancing Visual Perception in Vision-Language Models" • 5 items • Updated Feb 22 • 2

VALOR

[ICLR 2026] Models from the paper "No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers" • 3 items • Updated Feb 22 • 1