이영진

yeongceolgim's activity

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

upvoted a paper 7 days ago

Thinking Inertia: LLMs Keep Thinking When Told Not To

Paper • 2610.11765 • Published 12 days ago • 241

upvoted a paper 12 days ago

Semifactual Credit-Augmented Policy Optimization

Paper • 2609.40360 • Published 20 days ago • 37

upvoted a paper 17 days ago

Persona Dosing: Calibrated Activation Steering for Graded Trait Control

Paper • 2609.36388 • Published 22 days ago • 57

upvoted 2 papers about 1 month ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 369

Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation

Paper • 2609.06373 • Published Sep 6 • 17