Lillama: Large Language Models Compression via Low-Rank Feature Distillationby Yaya Sy, Christophe Cerisara, Irina IllinaFirst…
Never Reset Again: A Mathematical Framework for Continual Inference in Recurrent Neural Networksby Bojian Yin,…
LEDA: Log-Euclidean Diffeomorphic Autoencoder for Efficient Statistical Analysis of Diffeomorphismby Krithika Iyer, Shireen Elhabian, Sarang…
Difficulty-aware Balancing Margin Loss for Long-tailed Recognitionby Minseok Son, Inyong Koo, Jinyoung Park, Changick KimFirst…
PCA-Featured Transformer for Jamming Detection in 5G UAV Networksby Joseanne Viana, Hamed Farkhari, Pedro Sebastiao,…
On Calibration in Multi-Distribution Learningby Rajeev Verma, Volker Fischer, Eric NalisnickFirst submitted to arxiv on:…
Improving Generalization Performance of YOLOv8 for Camera Trap Object Detectionby Aroj SubediFirst submitted to arxiv…
Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Modelby Yuzhong Hong, Hanshan…
SSE-SAM: Balancing Head and Tail Classes Gradually through Stage-Wise SAMby Xingyu Lyu, Qianqian Xu, Zhiyong…
Content-aware Balanced Spectrum Encoding in Masked Modeling for Time Series Classificationby Yudong Han, Haocong Wang,…