logan7000/mllm-cogrpo-heter-qwen25vl-7b-x-internvl35-8b-mmr1-groupA-qwen25vl-7b
Image-Text-to-Text • 849k • Updated • 15
Logan Yang PRO
logan7000
·
AI & ML interests
Multimodal, Context Engineering, NLP, CogSci
Recent Activity
updated a model 12 days ago
logan7000/qwen25-7b-selfcertainty-math345-eb128 updated a model 13 days ago
logan7000/qwen25-7b-unmaj-math345-eb128-lr3e-6 published a model 13 days ago
logan7000/qwen25-7b-unmaj-math345-eb128-lr3e-6Organizations
logan7000/mllm-cogrpo-homo-internvl35-8b-mmr1-groupB-internvl35-8b
Image-Text-to-Text • 695k • Updated • 13
logan7000/mllm-cogrpo-homo-internvl35-8b-mmr1-groupA-internvl35-8b
Image-Text-to-Text • 695k • Updated • 17
logan7000/mllm-mmr1-ttrl-internvl35-8b-mmupt
Image-Text-to-Text • 695k • Updated • 19
logan7000/mllm-mmr1-ttrl-qwen25vl7b-mmupt
Image-Text-to-Text • 849k • Updated • 19
logan7000/mllm-mmr1-ttrl-internvl35-8b
Image-Text-to-Text • 695k • Updated • 16
logan7000/mllm-mmr1-ttrl-qwen25vl7b
Image-Text-to-Text • 849k • Updated • 12
logan7000/mllm-mmr1-ttrl-gemma3-12b
Image-Text-to-Text • 1.17M • Updated • 9
logan7000/mllm-mmr1-gt-qwen25vl-7b
Image-Text-to-Text • 849k • Updated • 25
logan7000/openr1-gemma3-4b-gt-mllm-repro
Reinforcement Learning • Updated
logan7000/openr1-gemma3-4b-ttrl-mllm-repro
Reinforcement Learning • Updated
logan7000/mllm-mmr1-ttrl-gemma3-4b-full-end-s722
Reinforcement Learning • 769k • Updated • 10
logan7000/mllm-mmr1-ttrl-gemma3-4b-full-best-s540
Reinforcement Learning • 769k • Updated • 10
logan7000/mllm-mmr1-gt-gemma3-4b-full-end-s722
Reinforcement Learning • 769k • Updated • 11
logan7000/mllm-mmr1-gt-gemma3-4b-full-best-s140
Reinforcement Learning • 769k • Updated • 7
logan7000/openr1-qwen25vl3b-gt-mllm-repro
Reinforcement Learning • Updated
logan7000/mllm-open-r1-ttrl-internvl35-2b-full-end-s961
2B • Updated • 6
logan7000/mllm-open-r1-ttrl-internvl35-2b-full-best-s480
2B • Updated • 8
logan7000/mllm-open-r1-ttrl-qwen25vl-3b-full-end-s961
756k • Updated • 9
logan7000/mllm-open-r1-ttrl-qwen25vl-3b-full-best-s520
756k • Updated • 15
logan7000/unmaj-qwen3-1p7b-math345-end
Reinforcement Learning • 2B • Updated • 8
logan7000/unmaj-qwen3-1p7b-math345-best
Reinforcement Learning • 2B • Updated • 9
logan7000/grpo-qwen3-1p7b-math345-end
Reinforcement Learning • 2B • Updated • 18
logan7000/grpo-qwen3-1p7b-math345-best
Reinforcement Learning • 2B • Updated • 16
logan7000/cogrpo-n3-selfpeers-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-end
Reinforcement Learning • 2B • Updated • 13
logan7000/cogrpo-n3-selfpeers-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupC-qwen3-best
Reinforcement Learning • 2B • Updated • 8
logan7000/cogrpo-n3-selfpeers-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupB-llama32-end
Reinforcement Learning • 175k • Updated • 5
logan7000/cogrpo-n3-selfpeers-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupB-llama32-best
Reinforcement Learning • 175k • Updated • 11
logan7000/cogrpo-n3-selfpeers-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupA-qwen25-end
Reinforcement Learning • 242k • Updated • 10
logan7000/cogrpo-n3-selfpeers-qwen25-3b-x-llama32-3b-x-qwen3-1p7b-math345-groupA-qwen25-best
Reinforcement Learning • 242k • Updated • 17