🔄 In a Training Loop

Hunar Batra

hunarbatra

·

https://hunarbatra.com

AI & ML interests

RL, Reasoning, Interpretability and Control, Embodied AI

Recent Activity

liked a dataset 8 days ago

aidigestorg/ai-village

liked a model 30 days ago

Experimental-Orange/trajectory-diffing-rl-adapters

updated a collection about 2 months ago

Multimodal Model Diffing

View all activity

Organizations

hunarbatra 's datasets 72

hunarbatra/clevr-cogent-pixl-r1-3k

Viewer • Updated Apr 27, 2025 • 3k • 44

hunarbatra/clevr-cogent-baseline-3k

Viewer • Updated Apr 27, 2025 • 3k • 12

hunarbatra/clevr-cogent-pixl-r1-1k

Viewer • Updated Apr 27, 2025 • 1k • 18

hunarbatra/clevr_r1

Viewer • Updated Apr 3, 2025 • 50 • 117

hunarbatra/PiXLLaVA-finetune-665k-roi

Updated Nov 28, 2024 • 23

hunarbatra/PiXLLaVA-pretrain-558k-roi

Viewer • Updated Nov 28, 2024 • 558k • 7

hunarbatra/LLaVA-pretrain558k

Viewer • Updated Oct 4, 2024 • 100 • 37 • 1

hunarbatra/llava-finetune-665k-object-coords

Updated Oct 3, 2024 • 16

hunarbatra/llava-pretrain-558k-object-coords

Viewer • Updated Oct 2, 2024 • 558k • 14 • 1

hunarbatra/LLaVA-finetune665k

Updated Sep 28, 2024 • 22

hunarbatra/imagenet1k_val_3k

Viewer • Updated Jun 27, 2024 • 3k • 686

hunarbatra/CLIP-LLaVA-Instruct-COCO-13k

Viewer • Updated May 15, 2024 • 16.8k • 61