The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 565
Victor Wijaya
VICTORWVW
AI & ML interests
Working on AI projects: transformers, datasets and fine-tuning.
Recent Activity
updated a model 13 days ago
VICTORWVW/hybrid-contrastive-tiny published a model 13 days ago
VICTORWVW/hybrid-contrastive-tiny liked a model 13 days ago
autotrust/JEV-27B-VLOrganizations
None yet