🔄 In a Training Loop
Hunar Batra
hunarbatra
AI & ML interests
RL, Reasoning, Interpretability and Control, Embodied AI
Recent Activity
liked a dataset about 16 hours ago
aletheias-quest/datasets liked a dataset 24 days ago
aidigestorg/ai-village liked a model about 2 months ago
Experimental-Orange/trajectory-diffing-rl-adaptersOrganizations
models 42
hunarbatra/MMDiff_SAEs
Updated
hunarbatra/SpatialThinker-30B
Image-Text-to-Text • 31B • Updated • 31
hunarbatra/vlm_scope_paligemma2_sae
Updated
hunarbatra/4dreasoner_v2_cot_merged
9B • Updated • 9
hunarbatra/4dreasoner_v2_no_cot_merged
9B • Updated • 9
hunarbatra/4dreasoner_v2_cot
Text Generation • Updated • 6
hunarbatra/4dreasoner_v2_no_cot
Text Generation • Updated • 9
hunarbatra/4dreasoner_v1_cot
Text Generation • Updated • 8
hunarbatra/4dreasoner_v1_no_cot_merged
Image-Text-to-Text • 9B • Updated • 19
hunarbatra/4dreasoner_v1_cot_merged
Image-Text-to-Text • 9B • Updated • 10
datasets 72
hunarbatra/VStarBench
Viewer • Updated • 191 • 41
hunarbatra/4DReasoner_v51_train_100k
Viewer • Updated • 90.7k • 11
hunarbatra/4DReasoner_v5_train_100k
Viewer • Updated • 99.9k • 22 • 1
hunarbatra/4DReasoner_v5_train_20k
Viewer • Updated • 20k • 49
hunarbatra/4DReasoner_v5_20K_no_cot
Viewer • Updated • 20k • 21
hunarbatra/4DReasoner_v4_test
Viewer • Updated • 1.82k • 1.44k
hunarbatra/4DReasoner_v3_full
Viewer • Updated • 17k • 25
hunarbatra/4DReasoner_v3_part4
Viewer • Updated • 4.05k • 9
hunarbatra/4DReasoner_v3_part5
Viewer • Updated • 799 • 19
hunarbatra/4DReasoner_v3_part3
Viewer • Updated • 4.02k • 12