Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillationby Jonibek Mansurov, Akhmed Sakip, Alham Fikri…
Inference-Time Diffusion Model Distillationby Geon Yeong Park, Sang Wan Lee, Jong Chul YeFirst submitted to…
Local vs. Global: Local Land-Use and Land-Cover Models Deliver Higher Quality Mapsby Girmaw Abebe Tadesse, Caleb…
When Babies Teach Babies: Can student knowledge sharing outperform Teacher-Guided Distillation on small datasets?by Srikrishna…
Adversarial Prompt Distillation for Vision-Language Modelsby Lin Luo, Xin Wang, Bojia Zi, Shihao Zhao, Xingjun…
Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillationby Yu-Liang Zhan, Zhong-Yi Lu, Hao Sun,…
Self-supervised cross-modality learning for uncertainty-aware object detection and recognition in applications which lack pre-labelled training…
Self-Supervised Keypoint Detection with Distilled Depth Keypoint Representationby Aman Anand, Elyas Rashno, Amir Eskandari, Farhana…
Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillationby Shuai Zhao, Xiaobao Wu, Cong-Duy Nguyen,…
TAS: Distilling Arbitrary Teacher and Student via a Hybrid Assistantby Guopeng Li, Qiang Wang, Ke…