logan7000/cogrpo-n3-randompeer-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupA-qwen25-best
Reinforcement Learning • 242k • Updated • 10
Logan Yang PRO
logan7000
·
AI & ML interests
Multimodal, Context Engineering, NLP, CogSci
Recent Activity
updated a model 11 days ago
logan7000/qwen25-7b-selfcertainty-math345-eb128 updated a model 11 days ago
logan7000/qwen25-7b-unmaj-math345-eb128-lr3e-6 published a model 11 days ago
logan7000/qwen25-7b-unmaj-math345-eb128-lr3e-6Organizations
logan7000/cogrpo-n3-pooledmaj-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-end
Reinforcement Learning • 2B • Updated • 10
logan7000/cogrpo-n3-pooledmaj-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-best
Reinforcement Learning • 2B • Updated • 20
logan7000/cogrpo-n3-pooledmaj-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupB-llama32-end
Reinforcement Learning • 175k • Updated • 10
logan7000/cogrpo-n3-pooledmaj-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupB-llama32-best
Reinforcement Learning • 175k • Updated • 8
logan7000/cogrpo-n3-pooledmaj-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupA-qwen25-end
Reinforcement Learning • 242k • Updated • 10
logan7000/cogrpo-n3-pooledmaj-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupA-qwen25-best
Reinforcement Learning • 242k • Updated • 15
logan7000/mllm-cogrpo-heter-internvl35-8b-x-gemma3-12b-mmr1-mmupt-groupA-full
Updated
logan7000/mllm-cogrpo-heter-qwen25vl-7b-x-gemma3-12b-mmr1-mmupt-groupB-full
Updated
logan7000/mllm-cogrpo-heter-qwen25vl-7b-x-gemma3-12b-mmr1-mmupt-groupA-full
Updated
logan7000/mllm-cogrpo-heter-internvl35-8b-x-gemma3-12b-mmr1-groupB-full
Updated
logan7000/mllm-cogrpo-heter-internvl35-8b-x-gemma3-12b-mmr1-groupA-full
Updated
logan7000/mllm-cogrpo-heter-qwen25vl-7b-x-gemma3-12b-mmr1-groupB-full
Updated
logan7000/mllm-cogrpo-heter-qwen25vl-7b-x-gemma3-12b-mmr1-groupA-full
Updated
logan7000/mllm-cogrpo-homo-internvl35-8b-mmr1-groupB-full
Updated
logan7000/mllm-cogrpo-homo-internvl35-8b-mmr1-groupA-full
Updated
logan7000/mllm-cogrpo-homo-gemma3-12b-mmr1-groupB-full
Updated
logan7000/mllm-cogrpo-homo-gemma3-12b-mmr1-groupA-full
Updated
logan7000/mllm-cogrpo-homo-qwen25vl-7b-mmr1-groupB-full
Updated
logan7000/mllm-cogrpo-homo-qwen25vl-7b-mmr1-groupA-full
Updated
logan7000/mllm-mmr1-ttrl-internvl35-8b-mmupt-full
Updated
logan7000/mllm-mmr1-ttrl-gemma3-12b-mmupt-full
Updated
logan7000/mllm-mmr1-ttrl-qwen25vl7b-mmupt-full
Updated
logan7000/mllm-mmr1-ttrl-qwen25vl-3b-full-end-s722
Reinforcement Learning • 756k • Updated • 13
logan7000/mllm-mmr1-ttrl-qwen25vl-3b-full-best-s100
Reinforcement Learning • 756k • Updated • 8
logan7000/mllm-mmr1-gt-qwen25vl-3b-full-end-s722
Reinforcement Learning • 756k • Updated • 13
logan7000/mllm-mmr1-gt-qwen25vl-3b-full-best-s140
Reinforcement Learning • 756k • Updated • 11
logan7000/mllm-cogrpo-heter-qwen25vl-7b-x-internvl35-8b-mmr1-mmupt-groupB-internvl35-8b
Image-Text-to-Text • 695k • Updated • 21
logan7000/mllm-cogrpo-heter-qwen25vl-7b-x-internvl35-8b-mmr1-mmupt-groupA-qwen25vl-7b
Image-Text-to-Text • 849k • Updated • 25
logan7000/mllm-cogrpo-heter-qwen25vl-7b-x-internvl35-8b-mmr1-groupB-internvl35-8b
Image-Text-to-Text • 695k • Updated • 19