Soohyun Ryu

rsoohyun's activity

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

upvoted a paper 2 days ago

Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL

Paper • 2610.33512 • Published 6 days ago • 50

upvoted a paper 14 days ago

KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization

Paper • 2610.14448 • Published 20 days ago • 49

upvoted a paper 29 days ago

Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR

Paper • 2609.37868 • Published about 1 month ago • 65

upvoted 2 papers about 1 month ago

FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching

Paper • 2609.35673 • Published Sep 28 • 35

SentZero: An Enhanced Sentence-Centric Vision-Language Pretraining for Multi-Task Zero-Shot Chest X-Ray Analysis

Paper • 2609.34479 • Published Sep 28 • 30

upvoted 2 papers about 2 months ago

SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem

Paper • 2609.07064 • Published Sep 7 • 87

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Paper • 2609.08798 • Published Sep 8 • 82