HyunseokLee's picture

4 2 26

HyunseokLee

hyunseoki

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics

liked a dataset 11 days ago

psiyum/winemag-feb-2019

upvoted a paper 19 days ago

Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models

View all activity

Organizations

spaces 1

ReMoDetect

Evaluate AI-generated text's likelihood

models 25

hyunseoki/qwen2.5-vl-7b-rft-crop

Image-Text-to-Text • Updated May 12 • 1.13k

hyunseoki/qwen2.5-vl-rft-crop0.3

Image-Text-to-Text • Updated May 12 • 36 • 1

hyunseoki/qwen2.5-vl-grpo-continue

Image-Text-to-Text • Updated Apr 22 • 12

hyunseoki/qwen2.5-vl-grpo

Image-Text-to-Text • Updated Apr 21 • 7

hyunseoki/finetune-llama-3.1-8b-gsm8k

Text Generation • Updated Mar 31 • 87

hyunseoki/Qwen2.5-1.5B-Open-R1-GRPO-test-new

hyunseoki/llama3.2-1b-Open-R1-GRPO-test0

Text Generation • Updated Feb 10 • 16 • 1

hyunseoki/Qwen2.5-1.5B-Open-R1-GRPO-metamath-test

Updated Feb 8 • 9

hyunseoki/llama3.2-1b-Open-R1-GRPO-test5

Updated Feb 7 • 11

hyunseoki/Qwen2.5-1.5B-Instruct-Open-R1-GRPO-test5

datasets 7

hyunseoki/gsm8k_cot_zeroshot_second

Viewer • Updated Jan 21 • 3.33k • 11

hyunseoki/gsm8k_cot_zeroshot_third

Viewer • Updated Jan 20 • 1.63k • 32

hyunseoki/gsm8k_cot_zeroshot_multiturn

Viewer • Updated Jan 16 • 2.64k • 33

hyunseoki/gsm8k_cot_zeroshot_oracle_classifier

Viewer • Updated Jan 16 • 3.96k • 56

hyunseoki/gsm240k_cot_zeroshot_oracle_classifier

Viewer • Updated Jan 12 • 2.75k • 59

hyunseoki/iself-gsm8k

Viewer • Updated Dec 27, 2024 • 106k • 9

hyunseoki/thesis_qa

Viewer • Updated Oct 17, 2024 • 49.4k • 105