arxiv:2502.01618
Guangxuan Xu
gx-ai-architect
AI & ML interests
None yet
Organizations
datasets 30
gx-ai-architect/ultrafeedback-dice-iter1-sft-drsow-first-half-vanilla-router
Viewer
• Updated
• 60.9k • 7
gx-ai-architect/ultrafeedback-qwen-32b-instruct-vanilla-router-alpha-normalize-0.04-bo32-correct-long
Viewer
• Updated
• 52k • 3
gx-ai-architect/ultrafeedback-qwen-32b-instruct-vanilla-router-length-normalize-bo32-correct
Viewer
• Updated
• 52k • 8
gx-ai-architect/ultrafeedback-qwen-32b-instruct-vanilla-router-length-normalize-bo32
Viewer
• Updated
• 60.9k • 5
gx-ai-architect/ultrafeedback-qwen-32b-instruct-vanilla-router-alpha-normalize-0.04-bo32
Viewer
• Updated
• 60.9k • 3
gx-ai-architect/ultrafeedback-eurus-7b-classifier-annotation-bo32
Viewer
• Updated
• 60.8k • 5
gx-ai-architect/ultrafeedback-qwen32b-instruct-vs-base-vanilla-router-filter-minus50-bo32
Viewer
• Updated
• 57.9k • 5
gx-ai-architect/ultrafeedback-new-trl
Viewer
• Updated
• 63.1k • 14
gx-ai-architect/ultrafeedback-llama-rdpo-vs-sft-dpo-vanilla-router-filter-minus50-bo32
Viewer
• Updated
• 58.4k • 6
gx-ai-architect/ultrafeedback-mistral-rdpo-vs-base-dpo-vanilla-router-filter-minus50-bo32
Viewer
• Updated
• 58.4k • 5