Training GUI agents with augmented reasoning data and a tailored post-training recipe
Rui Yang PRO
Ray2333
AI & ML interests
Deep Reinforcement Learning
Recent Activity
updated a model about 11 hours ago
Ray2333/Qwen3.5-4B-game-sft-lora-r64-step1000-fulldata published a model about 11 hours ago
Ray2333/Qwen3.5-4B-game-sft-lora-r64-step1000-fulldata upvoted a paper 1 day ago
Agent World Model in the Wild: Computer-Use Agent Environment SynthesisOrganizations
Generalizable Reward Models
-
Ray2333/GRM-llama3-8B-sftreg
Text Classification • 8B • Updated • 94 • 5 -
Ray2333/GRM-llama3-8B-distill
Text Classification • 8B • Updated • 252 • 6 -
Ray2333/GRM-Gemma-2B-sftreg
Text Classification • 3B • Updated • 4.94k • 3 -
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Paper • 2406.10216 • Published • 3
Training GUI agents with augmented reasoning data and a tailored post-training recipe
Generalizable Reward Models
-
Ray2333/GRM-llama3-8B-sftreg
Text Classification • 8B • Updated • 94 • 5 -
Ray2333/GRM-llama3-8B-distill
Text Classification • 8B • Updated • 252 • 6 -
Ray2333/GRM-Gemma-2B-sftreg
Text Classification • 3B • Updated • 4.94k • 3 -
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Paper • 2406.10216 • Published • 3
models 30
Ray2333/Qwen3.5-4B-game-sft-lora-r64-step1000-fulldata
Image-Text-to-Text • Updated • 1
Ray2333/models-qwen3vl-4b-memoryv27-boundaryv7-combined-ep2
4B • Updated • 3
Ray2333/models-qwen3vl-4b-memoryv27-boundaryv7-combined
Updated
Ray2333/androidworld
Updated
Ray2333/Qwen3-VL-3B-sft-reasoning_and_grounding_changecoord_mixnoreasoning_cpt636
4B • Updated • 6
Ray2333/Qwen3-VL-7B-sft-reasoning_and_grounding_changecoord_mixnoreasoning_cpt636
8B • Updated • 9
Ray2333/Qwen3-VL-4B-weighted_sft_ratio2-reasoning_and_grounding_changecoord_mixnoreasoning_cpt637
4B • Updated • 9
Ray2333/Qwen3-VL-8B-weighted_sft_ratio2-reasoning_and_grounding_changecoord_mixnoreasoning_cpt637
9B • Updated • 11
Ray2333/Qwen3-VL-4B-sft-reasoning_and_grounding_changecoord_mixnoreasoning_cpt637
4B • Updated • 8
Ray2333/Qwen3-VL-8B-sft-reasoning_and_grounding_changecoord_mixnoreasoning_cpt637
9B • Updated • 9