Yanggan Gu

yanggangu

·

https://egangu.github.io/

egangu

AI & ML interests

Model Fusion · Model Merging · Trustworthy AI · Large Language Models

Recent Activity

authored a paper 24 days ago

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning

upvoted a paper 24 days ago

TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning

upvoted a paper about 1 month ago

Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs

View all activity

Organizations

yanggangu 's models 61

yanggangu/Llama-3.1-8B-Instruct-FT-NumGLUE-ds

Text Generation • 8B • Updated Sep 30 • 272

yanggangu/Llama-3.1-8B-Instruct-SMAT-20Minuten

Text Generation • 8B • Updated Sep 30 • 269

yanggangu/Llama-3.1-8B-Instruct-SMAT-NumGLUE-ds

Text Generation • 8B • Updated Sep 30 • 270

yanggangu/Llama-3.1-8B-Instruct-SMAT-NumGLUE-cm

Text Generation • 8B • Updated Sep 30 • 283

yanggangu/Llama-3.1-8B-Instruct-FT-NumGLUE-cm

Text Generation • 8B • Updated Sep 30 • 272

yanggangu/Llama-3.1-8B-Instruct-FT-ScienceQA

Text Generation • 8B • Updated Sep 30 • 281

yanggangu/Llama-3.1-8B-Instruct-SMAT-MeetingBank

Text Generation • 8B • Updated Sep 30 • 264

yanggangu/Llama-3.1-8B-Instruct-SMAT-ScienceQA

Text Generation • 8B • Updated Sep 30 • 264

yanggangu/Llama-3.1-8B-Instruct-FT-FOMC

Text Generation • 8B • Updated Sep 30 • 280

yanggangu/Llama-3.1-8B-Instruct-FT-MeetingBank

Text Generation • 8B • Updated Sep 30 • 267

yanggangu/Llama-3.1-8B-Instruct-SMAT-FOMC

Text Generation • 8B • Updated Sep 30 • 286

yanggangu/Llama-3.2-1B-Instruct-FT-20Minuten

Text Generation • 1B • Updated Sep 30 • 278

yanggangu/Llama-3.2-1B-Instruct-FT-NumGLUE-ds

Text Generation • 1B • Updated Sep 30 • 279

yanggangu/Llama-3.2-1B-Instruct-SMAT-20Minuten

Text Generation • 1B • Updated Sep 30 • 280

yanggangu/Llama-3.2-1B-Instruct-SMAT-NumGLUE-ds

Text Generation • 1B • Updated Sep 30 • 275

yanggangu/Llama-3.2-1B-Instruct-SMAT-NumGLUE-cm

Text Generation • 1B • Updated Sep 30 • 291

yanggangu/Llama-3.2-1B-Instruct-FT-MeetingBank

Text Generation • 1B • Updated Sep 30 • 279

yanggangu/Llama-3.2-1B-Instruct-FT-NumGLUE-cm

Text Generation • 1B • Updated Sep 30 • 231

yanggangu/Llama-3.2-1B-Instruct-FT-ScienceQA

Text Generation • 1B • Updated Sep 30 • 246

yanggangu/Llama-3.2-1B-Instruct-SMAT-MeetingBank

Text Generation • 1B • Updated Sep 30 • 239

yanggangu/Llama-3.2-1B-Instruct-SMAT-ScienceQA

Text Generation • 1B • Updated Sep 30 • 255

yanggangu/Llama-3.2-1B-Instruct-SMAT-FOMC

Text Generation • 1B • Updated Sep 30 • 239

yanggangu/Llama-3.2-1B-Instruct-FT-FOMC

Text Generation • 1B • Updated Sep 30 • 247

yanggangu/Llama-3.1-8B-Instruct-SMAT-C-STANCE

Text Generation • 8B • Updated Sep 30 • 243

yanggangu/Llama-3.1-8B-Instruct-FT-C-STANCE

Text Generation • 8B • Updated Sep 30 • 246

yanggangu/Llama-3.2-1B-Instruct-SMAT-C-STANCE

Text Generation • 1B • Updated Sep 30 • 232

yanggangu/Llama-3.2-1B-Instruct-FT-C-STANCE

Text Generation • 1B • Updated Sep 30 • 235

yanggangu/CLIP-ViT-large-patch14-SMAT-DTD

Image Classification • Updated Sep 30

yanggangu/CLIP-ViT-large-patch14-FT-RESISC45

Image Classification • Updated Sep 30

yanggangu/CLIP-ViT-base-patch32-SMAT-EuroSAT

Image Classification • Updated Sep 30