Hyun Ryu

hyun1905's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 1 month ago

Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset

Paper • 2511.15186 • Published Nov 19 • 25

upvoted a paper 2 months ago

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

Paper • 2510.15346 • Published Oct 17 • 33

upvoted 3 papers 3 months ago

Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning

Paper • 2510.03259 • Published Sep 26 • 57

DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding

Paper • 2411.19527 • Published Nov 29, 2024 • 11

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

Paper • 2509.21880 • Published Sep 26 • 52

authored 4 papers 3 months ago

ReviewScore: Misinformed Peer Review Detection with Large Language Models

Paper • 2509.21679 • Published Sep 25 • 63

EMC2-Net: Joint Equalization and Modulation Classification based on Constellation Network

Paper • 2303.10934 • Published Mar 20, 2023

SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation

Paper • 2312.05790 • Published Dec 10, 2023

Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning

Paper • 2410.08047 • Published Oct 10, 2024

upvoted 2 papers 3 months ago

ARE: Scaling Up Agent Environments and Evaluations

Paper • 2509.17158 • Published Sep 21 • 35

ReviewScore: Misinformed Peer Review Detection with Large Language Models

Paper • 2509.21679 • Published Sep 25 • 63

commented a paper 3 months ago

ReviewScore: Misinformed Peer Review Detection with Large Language Models

Paper • 2509.21679 • Published Sep 25 • 63 •

2

upvoted an article 5 months ago

view article

Article

Argunauts Training Phase III: RLVF with Hindsight Instruction Relabeling, Self-Correction and Dynamic Curriculum

• 

Jul 24

•

2

liked a dataset 5 months ago

DebateLabKIT/arguments-and-debates

Viewer • Updated Jul 22 • 4.59k • 84 • 1

authored a paper 7 months ago

Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models

Paper • 2505.17225 • Published May 22 • 64

upvoted a paper 7 months ago

Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models

Paper • 2505.17225 • Published May 22 • 64

upvoted 4 articles 10 months ago

view article

Article

syncIAL🍏: A Multi-Purpose Synthetic Debate and Argument Mapping Corpus

• 

Feb 4

•

4

view article

Article

Argunauts Training Phase II: Selfplay Finetuning Line-By-Line

• 

Feb 19

•

5

view article

Article

Argunauts Training Phase I: Continual Pretraining on Synthetic Data

• 

Feb 18

•

2

view article

Article

Argunauts: Open LLMs that Master Argument Analysis with Argdown

• 

Feb 14

•

7