Resa

university

https://shangshangwang.notion.site/resa

AI & ML interests

None defined yet.

Recent Activity

deqing authored a paper 11 days ago

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

farukakgul authored a paper about 2 months ago

Resa: Transparent Reasoning Models via SAEs

willieneis authored a paper about 2 months ago

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

View all activity

Resa-Yi 's models 18

Resa-Yi/Resa-STILL-v1

Resa-Yi/Resa-STILL-v2

Resa-Yi/Resa-STILL-v3

Resa-Yi/Resa-STILL-v4

Resa-Yi/Resa-STILL-v5

Resa-Yi/Resa-DeepScaleR-v2

Resa-Yi/Resa-DeepScaleR-v3

Resa-Yi/Resa-DeepScaleR-v4

Resa-Yi/STILL-Fine-tuned-SAE-R1-Distill-Qwen-1.5B-65k

Updated Jun 10 • 4

Resa-Yi/DeepScaleR-Trained-from-Scratch-SAE-R1-Distill-Qwen-1.5B-65k

Updated Jun 10 • 1

Resa-Yi/STILL-Trained-from-Scratch-SAE-R1-Distill-Qwen-1.5B-65k

Updated Jun 10 • 1

Resa-Yi/Pre-trained-SAE-Qwen2.5-Math-1.5B-65k

Updated Jun 10 • 1

Resa-Yi/Pre-trained-SAE-Qwen2.5-1.5B-65k

Updated Jun 10 • 1

Resa-Yi/DeepScaleR-Fine-tuned-SAE-R1-Distill-Qwen-1.5B-65k

Resa-Yi/OpenThoughts-Fine-tuned-SAE-R1-Distill-Qwen-1.5B-65k

Resa-Yi/OpenR1-Fine-tuned-SAE-R1-Distill-Qwen-1.5B-65k

Resa-Yi/sae-R1-Distill-Qwen-1.5B-65k-Open-RS3

Resa-Yi/sae-R1-Distill-Qwen-1.5B-65k-LIMR