q1716523669/mllm-mmr1-gt-qwen25vl7b-mmupt-full
Updated
Logan Yang PRO
q1716523669
·
AI & ML interests
Multimodal, Context Engineering, NLP, CogSci
Recent Activity
updated a model 1 day ago
q1716523669/mllm-mmr1-gt-qwen25vl7b-mmupt-full published a model 1 day ago
q1716523669/mllm-mmr1-gt-qwen25vl7b-mmupt-full upvoted a paper 1 day ago
Self-Supervised Visual On-Policy DistillationOrganizations
q1716523669/mllm-cogrpo-heter-internvl35-2b-x-gemma3-4b-mmr1-groupB-gemma3-4b
769k • Updated • 13
q1716523669/mllm-cogrpo-heter-qwen25vl-3b-x-gemma3-4b-mmr1-groupB-gemma3-4b
769k • Updated • 47
q1716523669/mllm-cogrpo-heter-qwen25vl-3b-x-gemma3-4b-mmr1-groupA-qwen25vl-3b
756k • Updated • 14
q1716523669/mllm-cogrpo-heter-qwen25vl-3b-x-gemma3-4b-openr1-groupB-gemma3-4b
769k • Updated • 17
q1716523669/mllm-cogrpo-heter-qwen25vl-3b-x-gemma3-4b-openr1-groupA-qwen25vl-3b
756k • Updated • 15
q1716523669/mllm-cogrpo-heter-internvl35-2b-x-gemma3-4b-openr1-groupB-gemma3-4b
769k • Updated • 17
q1716523669/mllm-mmr1-gt-internvl35-8b
Image-Text-to-Text • 695k • Updated • 58
q1716523669/mllm-mmr1-gt-gemma3-12b
Image-Text-to-Text • 1.17M • Updated • 58
q1716523669/mllm-cogrpo-heter-internvl35-8b-x-gemma3-12b-mmr1-mmupt-groupB-full
Updated
q1716523669/visionopd-archive
Updated
q1716523669/cogrpo-homo-llama31-8b-math345-groupB-llama31-8b-b-end
Reinforcement Learning • 266k • Updated • 11
q1716523669/cogrpo-homo-llama31-8b-math345-groupB-llama31-8b-b-best
Reinforcement Learning • 266k • Updated • 12
q1716523669/cogrpo-homo-llama31-8b-math345-groupA-llama31-8b-a-end
Reinforcement Learning • 266k • Updated • 12
q1716523669/cogrpo-homo-llama31-8b-math345-groupA-llama31-8b-a-best
Reinforcement Learning • 266k • Updated • 14
q1716523669/visionopd-best-ckpts
Updated
q1716523669/mllm-mmr1-gt-internvl35-2b-full-end-s722
Reinforcement Learning • 2B • Updated • 11
q1716523669/mllm-mmr1-gt-internvl35-2b-full-best-s440
Reinforcement Learning • 2B • Updated • 12
q1716523669/cogrpo-w2s-qwen25-3b-x-qwen25-7b-math345-groupB-qwen25-7b-end
Reinforcement Learning • 333k • Updated • 15 • 1
q1716523669/cogrpo-w2s-qwen25-3b-x-qwen25-7b-math345-groupB-qwen25-7b-best
Reinforcement Learning • 333k • Updated • 13
q1716523669/cogrpo-w2s-qwen25-3b-x-qwen25-7b-math345-groupA-qwen25-3b-end
Reinforcement Learning • 242k • Updated • 17
q1716523669/cogrpo-w2s-qwen25-3b-x-qwen25-7b-math345-groupA-qwen25-3b-best
Reinforcement Learning • 242k • Updated • 14
q1716523669/cogrpo-n3-strict-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-end
Reinforcement Learning • 2B • Updated • 9
q1716523669/cogrpo-n3-strict-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-best
Reinforcement Learning • 2B • Updated • 14 • 1
q1716523669/cogrpo-n3-strict-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupB-llama32-end
Reinforcement Learning • 175k • Updated • 11 • 1
q1716523669/cogrpo-n3-strict-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupB-llama32-best
Reinforcement Learning • 175k • Updated • 13
q1716523669/cogrpo-n3-strict-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupA-qwen25-end
Reinforcement Learning • 242k • Updated • 10 • 1
q1716523669/cogrpo-n3-strict-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupA-qwen25-best
Reinforcement Learning • 242k • Updated • 12
q1716523669/cogrpo-n3-ring-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-end
Reinforcement Learning • 2B • Updated • 15
q1716523669/cogrpo-n3-ring-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-best
Reinforcement Learning • 2B • Updated • 45