-
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper • 2510.00526 • Published • 9 -
gaotang/figlet_font
Viewer • Updated • 45k • 15 -
gaotang/medical_sft_processed
Viewer • Updated • 23.5k • 9 -
gaotang/numina-cot-subset-67k
Viewer • Updated • 67.6k • 10
Gaotang Li
gaotang
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 9 hours ago
MARS: Modular Agent with Reflective Search for Automated AI Research
upvoted
a
paper
14 days ago
Agentic Reasoning for Large Language Models
upvoted
a
paper
21 days ago
Your Group-Relative Advantage Is Biased
Organizations
None yet
-
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper • 2510.00526 • Published • 9 -
gaotang/figlet_font
Viewer • Updated • 45k • 15 -
gaotang/medical_sft_processed
Viewer • Updated • 23.5k • 9 -
gaotang/numina-cot-subset-67k
Viewer • Updated • 67.6k • 10
RM-R1: Reward Modeling as Reasoning
models
11
gaotang/deepseek-math-7b-base
Text Generation
•
7B
•
Updated
•
1
gaotang/RM-R1-DeepSeek-Distilled-Qwen-7B
Text Generation
•
8B
•
Updated
•
24
•
2
gaotang/RM-R1-Qwen2.5-Instruct-7B
Text Generation
•
8B
•
Updated
•
89
•
4
gaotang/RM-R1-DeepSeek-Distilled-Qwen-14B
Text Generation
•
15B
•
Updated
•
3
•
1
gaotang/RM-R1-Qwen2.5-Instruct-14B
Text Generation
•
15B
•
Updated
•
12
•
1
gaotang/RM-R1-Qwen2.5-Instruct-32B
Text Generation
•
33B
•
Updated
•
9
•
1
gaotang/RM-R1-DeepSeek-Distilled-Qwen-32B
Text Generation
•
33B
•
Updated
•
44
•
•
2
gaotang/qwen_7b_sky_filtered_code8k_math_10k_distilled_Claude_o3_0419
8B
•
Updated
gaotang/qwen_7b_sky_filtered_code8k_math_10k_distilled_OpenAI
8B
•
Updated
gaotang/qwen_14b_sky_filtered_code8k_math_10k_distilled_OpenAI
15B
•
Updated
•
1
datasets
35
gaotang/figlet_font
Viewer
•
Updated
•
45k
•
15
gaotang/figlet_font_train
Viewer
•
Updated
•
5
•
6
gaotang/huatuo_medical_sft_processed
Viewer
•
Updated
•
19.7k
•
14
gaotang/medical_sft_processed
Viewer
•
Updated
•
23.5k
•
9
gaotang/ParaConflict
Viewer
•
Updated
•
2.15k
•
11
gaotang/numina-cot-subset-val
Viewer
•
Updated
•
128
•
11
gaotang/numina-cot-subset-67k
Viewer
•
Updated
•
67.6k
•
10
gaotang/ParaConfilct
Viewer
•
Updated
•
2.15k
•
13
gaotang/RM-R1-Reasoning-RLVR
Viewer
•
Updated
•
73k
•
19
•
1
gaotang/RM-R1-Entire-RLVR-Train
Viewer
•
Updated
•
73k
•
41
•
2