Hunar Batra

hunarbatra's activity

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

updated a model 8 days ago

hunarbatra/pixlr1_base_clevr3k_sft

Updated 8 days ago • 8

published a model 8 days ago

hunarbatra/pixlr1_base_clevr3k_sft

Updated 8 days ago • 8

updated a model 8 days ago

hunarbatra/pixl_r1_baseline_clevr_3k_grpo_v6

Updated 8 days ago • 1

published a model 8 days ago

hunarbatra/pixl_r1_baseline_clevr_3k_grpo_v6

Updated 8 days ago • 1

updated a model 8 days ago

hunarbatra/pixl_r1_stage2_clevr_3k_grpo_v6

Updated 8 days ago • 1

published a model 8 days ago

hunarbatra/pixl_r1_stage2_clevr_3k_grpo_v6

Updated 8 days ago • 1

updated a model 8 days ago

hunarbatra/pixl_r1_clevr_3k_grpo_v6

Updated 8 days ago • 1

published a model 8 days ago

hunarbatra/pixl_r1_clevr_3k_grpo_v6

Updated 8 days ago • 1

liked 2 datasets 8 days ago

detek/spatial-awareness-coordinates

Viewer • Updated Jun 20, 2024 • 100k • 22 • 2

dmarsili/Omni3D-Bench

Viewer • Updated Feb 17 • 501 • 49 • 7

updated a dataset 9 days ago

hunarbatra/clevr-cogent-pixl-r1-1k-stage2

Viewer • Updated 9 days ago • 1k • 22

published a dataset 9 days ago

hunarbatra/clevr-cogent-pixl-r1-1k-stage2

Viewer • Updated 9 days ago • 1k • 22

upvoted a paper 9 days ago

Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning

Paper • 2504.16656 • Published 16 days ago • 54

upvoted a collection 9 days ago

VisionLM

Collection

1013 items • Updated 3 days ago • 62

upvoted 5 papers 9 days ago

Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)

Paper • 2504.03151 • Published Apr 4 • 14

MMC: Iterative Refinement of VLM Reasoning via MCTS-based Multimodal Critique

Paper • 2504.11009 • Published 24 days ago • 1

VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search

Paper • 2504.09130 • Published 27 days ago • 12

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

Paper • 2501.07542 • Published Jan 13 • 1

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models

Paper • 2501.18533 • Published Jan 30 • 1

updated a dataset 9 days ago

hunarbatra/clevr-cogent-pixl-r1-2k-text

Viewer • Updated 9 days ago • 4.17k • 16