TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Abilityby Fengji Ma, Li…
Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devicesby Baiyu Pan,…
A review on discriminative self-supervised learning methodsby Nikolaos Giakoumoglou, Tania StathakiFirst submitted to arxiv on:…
Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applicationsby Colby Banbury,…
Efficient Compression of Multitask Multilingual Speech Modelsby Thomas Palmeira FerrazFirst submitted to arxiv on: 2…
A Novel Spike Transformer Network for Depth Estimation from Event Cameras via Cross-modality Knowledge Distillationby…
From LLM to NMT: Advancing Low-Resource Machine Translation with Claudeby Maxim Enis, Mark HopkinsFirst submitted…
Do We Really Need a Complex Agent System? Distill Embodied Agent into a Single Modelby…
Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thoughtby Jooyoung Lee, Fan…
Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Modelsby Taiqiang Wu, Chaofan Tao, Jiahao…