👋 Open to Work
Chengxuan Qian
Raymond-Qiancx
AI & ML interests
Vision-Language Models
Recent Activity
upvoted a paper about 5 hours ago
Video2Skill: From Streaming Experience to Reusable Embodied Skills upvoted a paper about 6 hours ago
ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context upvoted a paper 7 days ago
RRSI: Regularized Recursive Self-Improvement of Agent HarnessesOrganizations
None yet
models 8
Raymond-Qiancx/ProgressLM-3B-SFT
4B • Updated • 16 • 2
Raymond-Qiancx/ProgressLM-3B-RL
4B • Updated • 32 • 2
Raymond-Qiancx/Prog-3B-RL-retrain
4B • Updated • 9 • 1
Raymond-Qiancx/Prog-3B-RL-deep
4B • Updated • 6 • 1
Raymond-Qiancx/FRM_7B_SFT
8B • Updated • 11
Raymond-Qiancx/FRM_3B_SFT
4B • Updated • 9
Raymond-Qiancx/RiR_Agent
Updated
Raymond-Qiancx/RiR_Agent_Cold
Updated
datasets 10
Raymond-Qiancx/Casual-DiaWorld-data
Viewer • Updated • 155M • 4
Raymond-Qiancx/ProgressLM-Dataset
Preview • Updated • 168 • 1
Raymond-Qiancx/VLHUbs
Updated • 1
Raymond-Qiancx/MSCOCO
Viewer • Updated • 291k • 1
Raymond-Qiancx/COCO
Viewer • Updated • 275k • 1
Raymond-Qiancx/RiR-Data
Preview • Updated • 1 • 1
Raymond-Qiancx/MMSearch_Train
Viewer • Updated • 4.86k • 91
Raymond-Qiancx/RiR_Agent_Cold_2k
Updated • 10
Raymond-Qiancx/RiR_Agent_Train_20k
Viewer • Updated • 20k • 22
Raymond-Qiancx/RiR_Agent_Data
Preview • Updated • 14