PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairsby Rongzhi Zhang, Jiaming Shen, Tianqi Liu,…
X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructionsby Chong Li, Wen Yang,…
LeDex: Training LLMs to Better Self-Debug and Explain Codeby Nan Jiang, Xiaopeng Li, Shiqi Wang,…
Learning to Project for Cross-Task Knowledge Distillationby Dylan Auty, Roy Miles, Benedikt Kolbeinsson, Krystian MikolajczykFirst…
Information-Theoretic Distillation for Reference-less Summarizationby Jaehun Jung, Ximing Lu, Liwei Jiang, Faeze Brahman, Peter West,…
On Explaining Knowledge Distillation: Measuring and Visualising the Knowledge Transfer Processby Gereziher Adhane, Mohammad Mahdi…
A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networksby Saptarshi Mandal, Xiaojun Lin,…
Diffusion-based Data Augmentation and Knowledge Distillation with Generated Soft Labels Solving Data Scarcity Problems of…
Enhancing CLIP Conceptual Embedding through Knowledge Distillationby Kuei-Chun KaoFirst submitted to arxiv on: 4 Dec…
Mutli-View 3D Reconstruction using Knowledge Distillationby Aditya Dutt, Ishikaa Lunawat, Manpreet KaurFirst submitted to arxiv…