TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models

Makoto Shing, Kou Misaki, Han Bao, Sho Yokoi, Takuya Akiba. TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net, 2025. [doi]

Authors

Makoto Shing

This author has not been identified. Look up 'Makoto Shing' in Google

Kou Misaki

This author has not been identified. Look up 'Kou Misaki' in Google

Han Bao

This author has not been identified. Look up 'Han Bao' in Google

Sho Yokoi

This author has not been identified. Look up 'Sho Yokoi' in Google

Takuya Akiba

This author has not been identified. Look up 'Takuya Akiba' in Google