Arijit

array's activity

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

updated a model about 8 hours ago

array/Qwen2.5-VL-SIMS

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

published a model about 8 hours ago

array/Qwen2.5-VL-SIMS

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

updated a model 2 days ago

array/Qwen2.5-VL-SAT

Image-to-Text • 8B • Updated 2 days ago • 16

published a model 2 days ago

array/Qwen2.5-VL-SAT

Image-to-Text • 8B • Updated 2 days ago • 16

updated a model 2 days ago

array/Qwen2.5-VL-SATBase

Image-to-Text • 8B • Updated 2 days ago • 12

published a model 2 days ago

array/Qwen2.5-VL-SATBase

Image-to-Text • 8B • Updated 2 days ago • 12

updated a model 2 days ago

array/Qwen2.5-VL-Mull

Image-to-Text • 8B • Updated 2 days ago • 17

published a model 2 days ago

array/Qwen2.5-VL-Mull

Image-to-Text • 8B • Updated 2 days ago • 17

updated a model 2 days ago

array/Qwen2.5-VL-MullGRPO

Image-to-Text • 8B • Updated 2 days ago • 16

published a model 2 days ago

array/Qwen2.5-VL-MullGRPO

Image-to-Text • 8B • Updated 2 days ago • 16

updated a model 2 days ago

array/Qwen2.5-VL-Latent-Custom

Image-to-Text • 8B • Updated 2 days ago • 9

published a model 2 days ago

array/Qwen2.5-VL-Latent-Custom

Image-to-Text • 8B • Updated 2 days ago • 9

updated a dataset 23 days ago

array/SAT_cameramotions_v2

Viewer • Updated 23 days ago • 16k • 47

liked a dataset about 1 month ago

array/SAT

Preview • Updated Aug 6 • 618 • 12

authored 3 papers about 1 month ago

Sunny and Dark Outside?! Improving Answer Consistency in VQA through Entailed Question Generation

Paper • 1909.04696 • Published Sep 10, 2019

GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation

Paper • 2505.13441 • Published May 19 • 1

SIMS-V: Simulated Instruction-Tuning for Spatial Video Understanding

Paper • 2511.04668 • Published Nov 6 • 4

published a dataset about 1 month ago

array/SAT_cameramotions_v2

Viewer • Updated 23 days ago • 16k • 47

upvoted 2 papers about 1 month ago

Cambrian-S: Towards Spatial Supersensing in Video

Paper • 2511.04670 • Published Nov 6 • 36

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

Paper • 2511.04655 • Published Nov 6 • 7