Jimin Ryu

jimin-ryu's activity

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

upvoted a paper about 18 hours ago

Jeva: System One Models from First Principles

Paper • 2610.18773 • Published 4 days ago • 291

upvoted a paper 1 day ago

HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning

Paper • 2610.03039 • Published 15 days ago • 6

upvoted 2 papers 4 days ago

WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites

Paper • 2610.03036 • Published 10 days ago • 20

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 10 days ago • 40

upvoted a paper 7 days ago

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

Paper • 2610.08448 • Published 11 days ago • 213

upvoted 2 papers 8 days ago

Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing

Paper • 2609.37334 • Published 18 days ago • 46

How to Loop MoE: Flatten the Experts, Untie the Attention

Paper • 2609.35751 • Published 19 days ago • 13

upvoted a paper 10 days ago

Does Learning Protein Folding Generalize to Broader Reasoning?

Paper • 2609.38879 • Published 17 days ago • 63

upvoted a paper 11 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 16 days ago • 111

upvoted 2 papers 13 days ago

DepthBench: Measuring How Residual Connections Enable More Computational Depth

Paper • 2609.32534 • Published 21 days ago • 33

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

Paper • 2609.37868 • Published 18 days ago • 65

upvoted a paper 15 days ago

Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation

Paper • 2609.35347 • Published 19 days ago • 182

upvoted 2 papers 16 days ago

Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs

Paper • 2601.06362 • Published 27 days ago • 10

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 609

upvoted a paper 17 days ago

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Paper • 2609.31620 • Published 22 days ago • 144

upvoted 2 papers 18 days ago

Agent-Editing World Model: Rethinking World Modeling for LLM Agents

Paper • 2609.28416 • Published 24 days ago • 44

Calibration as a First-Class Criterion in LLM Evaluation

Paper • 2609.26489 • Published 25 days ago • 4