CraftJarvis

CraftJarvis's activity

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

phython96 

authored 3 papers 4 days ago

Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

Paper • 2509.22601 • Published Sep 26, 2025 • 29

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published Dec 2, 2025 • 244

SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents

Paper • 2512.22322 • Published 9 days ago • 37

hkc20 

updated a collection 27 days ago

RLHA

Collection

A Series of Open-Source RL-Finetuned Hierarchical Agentic Models • 4 items • Updated 27 days ago

limuyu011 

updated 13 models about 2 months ago

CraftJarvis/TextHA-RL-qwen2vl-7b

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/CrossAgent-qwen2vl-7b

Image-to-Text • 8B • Updated Nov 15, 2025 • 341

CraftJarvis/text_coa_1030_rl_global_step_50

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/mix_coa_251103_rl_global_step_100

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/text_coa_1030_rl_global_step_140

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/mix_coa_251103_1030_rl_global_step_50

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/MotionHA-RL-qwen2vl-7b

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/mix_coa_1030_rl_global_step_50

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/motion_coa_1030_rl_global_step_50

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/GroundingHA-RL-qwen2vl-7b

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/mix_coa_rl_global_step_90

Image-to-Text • 8B • Updated Nov 15, 2025 • 3

CraftJarvis/grounding_coa_rl_global_step_100

Image-to-Text • 8B • Updated Nov 15, 2025

CraftJarvis/grounding_coa_1030_rl_global_step_50

Image-to-Text • 8B • Updated Nov 15, 2025