hunarbatra/pixl_r1_stage2_clevr_3k_grpo_v6
4B • Updated • 5
Hunar Batra PRO
hunarbatra
AI & ML interests
RL, Reasoning, Interpretability and Control, Embodied AI
Recent Activity
updated a collection 4 days ago
Multimodal Model Diffing updated a collection 4 days ago
Multimodal Model Diffing upvoted a paper 4 days ago
Multimodal Model Diffing for Feature Discovery and ControlOrganizations
hunarbatra/pixl_r1_clevr_3k_grpo_v6
4B • Updated • 5
hunarbatra/pixl_r1_clevr_1k_grpo_v4
4B • Updated • 5
hunarbatra/qwen25_vl_lora_sft_cs_clevrr1
4B • Updated • 6
hunarbatra/qwen25vl3b_grpo_cs_clevr_sat_3k_v2
4B • Updated • 9
hunarbatra/qwen25vl3b_grpo_clevr_sat_3k_v2
4B • Updated • 7
hunarbatra/PiXLLaVAPhi35-3b-merged-210225
Updated • 6
hunarbatra/PiXLLaVAPhi35-3b-merged-200225
Updated • 7
hunarbatra/PiXLLaVAPhi35-3b-merged-2
Updated • 4
hunarbatra/PiXLLaVAPhi35-3b-merged
Updated • 4
hunarbatra/PiXLLaVAPhi35-v2-3b-merged
Updated • 4
hunarbatra/CoVBERT
Fill-Mask • 44.9M • Updated • 14 • 3