Adhiraj Ghosh

adhirajghosh's activity

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

updated a dataset about 1 month ago

bethgelab/dataconcept_128M

Viewer • Updated Aug 25 • 144M • 3.36k • 6

liked a dataset about 1 month ago

mlfoundations/dcvlm-baseline-200b

Viewer • Updated Jul 26 • 10k • 114k • 8

upvoted a collection about 1 month ago

DCVLM

Collection

Raw data pools, pre-mixed ready-to-train datasets and checkpoints for DataComp-VLM. • 14 items • Updated Jul 27 • 7

authored 2 papers about 2 months ago

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Paper • 2606.28551 • Published Jun 26 • 52

Concept-Aware Batch Sampling Improves Language-Image Pretraining

Paper • 2511.20643 • Published Nov 25, 2025 • 4

updated a dataset 2 months ago

adhirajghosh/unlearning

Updated Jul 19 • 2

published a dataset 2 months ago

adhirajghosh/unlearning

Updated Jul 19 • 2

upvoted a paper 3 months ago

DataComp-VLM: Improved Open Datasets for Vision-Language Models

Paper • 2606.28551 • Published Jun 26 • 52

upvoted a collection 3 months ago

Concept-Aware Batch Sampling

Collection

Collection of model checkpoints and training datasets for CABS (CVPR 2026). • 7 items • Updated Feb 21 • 2

upvoted a paper 4 months ago

DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning

Paper • 2606.08035 • Published Jun 6 • 16

liked a dataset 4 months ago

michaelyuanqwq/roboseg

Updated Sep 19, 2025 • 83 • 6

upvoted an article 5 months ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

sensenova

•

Mar 5

• 182

upvoted a paper 6 months ago

LoST: Level of Semantics Tokenization for 3D Shapes

Paper • 2603.17995 • Published Mar 18 • 32

upvoted a paper 7 months ago

Concept-Aware Batch Sampling Improves Language-Image Pretraining

Paper • 2511.20643 • Published Nov 25, 2025 • 4

updated a collection 7 months ago

Concept-Aware Batch Sampling

Collection

Collection of model checkpoints and training datasets for CABS (CVPR 2026). • 7 items • Updated Feb 21 • 2