When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models
Paper • 2605.28181 • Published • 3
Jungwon Park
JwonP
AI & ML interests
None yet
Recent Activity
submitted a paper 2 days ago
When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models authored a paper 10 months ago
ReFlex: Text-Guided Editing of Real Images in Rectified Flow via
Mid-Step Feature Extraction and Attention AdaptationOrganizations
None yet
upvoted a paper 5 days ago
upvoted 3
papers 10 months ago
ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation
Paper • 2507.01496 • Published • 4
Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models
Paper • 2412.02237 • Published • 1
Soft Injection of Task Embeddings Outperforms Prompt-Based In-Context Learning
Paper • 2507.20906 • Published • 2