-
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper • 2510.00526 • Published • 11 -
gaotang/figlet_font
Viewer • Updated • 45k • 59 -
gaotang/medical_sft_processed
Viewer • Updated • 23.5k • 37 -
gaotang/numina-cot-subset-67k
Viewer • Updated • 67.6k • 28
Gaotang Li
gaotang
AI & ML interests
None yet
Recent Activity
upvoted a paper 11 days ago
Learning from Teacher Continuations at Student States upvoted a paper 11 days ago
Selecting Diverse SFT Traces Improves Post-RL Generalization upvoted a paper about 1 month ago
Scaling Automatic Research Agents via World ModelsOrganizations
None yet
-
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper • 2510.00526 • Published • 11 -
gaotang/figlet_font
Viewer • Updated • 45k • 59 -
gaotang/medical_sft_processed
Viewer • Updated • 23.5k • 37 -
gaotang/numina-cot-subset-67k
Viewer • Updated • 67.6k • 28
RM-R1: Reward Modeling as Reasoning
models 11
gaotang/deepseek-math-7b-base
Text Generation • 7B • Updated • 28
gaotang/RM-R1-DeepSeek-Distilled-Qwen-7B
Text Generation • 8B • Updated • 465 • 3
gaotang/RM-R1-Qwen2.5-Instruct-7B
Text Generation • 8B • Updated • 78 • 4
gaotang/RM-R1-DeepSeek-Distilled-Qwen-14B
Text Generation • 15B • Updated • 38 • 1
gaotang/RM-R1-Qwen2.5-Instruct-14B
Text Generation • 15B • Updated • 26 • 1
gaotang/RM-R1-Qwen2.5-Instruct-32B
Text Generation • 33B • Updated • 35 • 1
gaotang/RM-R1-DeepSeek-Distilled-Qwen-32B
Text Generation • 33B • Updated • 41 • 3
gaotang/qwen_7b_sky_filtered_code8k_math_10k_distilled_Claude_o3_0419
8B • Updated • 4
gaotang/qwen_7b_sky_filtered_code8k_math_10k_distilled_OpenAI
8B • Updated • 7
gaotang/qwen_14b_sky_filtered_code8k_math_10k_distilled_OpenAI
15B • Updated • 5
datasets 40
gaotang/loopmoe-fineweb-edu-100bt-mcore
Viewer • Updated • 65 • 85
gaotang/knowledge_memorization_openbookqa
Updated • 7
gaotang/mix_magpie_evol_instruct_140k
Viewer • Updated • 140k • 10
gaotang/coder_sft
Viewer • Updated • 75.5k • 8
gaotang/low_resource_language
Updated • 18
gaotang/figlet_font
Viewer • Updated • 45k • 59
gaotang/figlet_font_train
Viewer • Updated • 5 • 15
gaotang/huatuo_medical_sft_processed
Viewer • Updated • 19.7k • 11
gaotang/medical_sft_processed
Viewer • Updated • 23.5k • 37
gaotang/ParaConflict
Viewer • Updated • 2.15k • 164