EMOCPD: Efficient Attention-based Models for Computational Protein Design Using Amino Acid Microenvironmentby Xiaoqi Ling, Cheng…
Federated Time Series Generation on Feature and Temporally Misaligned Databy Chenrui Fan, Zhi Wen Soi,…
Skip2-LoRA: A Lightweight On-device DNN Fine-tuning Method for Low-cost Edge Devicesby Hiroki Matsutani, Masaaki Kondo,…
Robust Estimation for Kernel Exponential Families with Smoothed Total Variation Distancesby Takafumi Kanamori, Kodai Yokoyama,…
Scaling-based Data Augmentation for Generative Models and its Theoretical Extensionby Yoshitaka Koike, Takumi Nakagawa, Hiroki…
MrT5: Dynamic Token Merging for Efficient Byte-level Language Modelsby Julie Kallini, Shikhar Murty, Christopher D.…
Introducing Spectral Attention for Long-Range Dependency in Time Series Forecastingby Bong Gyun Kang, Dongjun Lee,…
KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillationby Rambod Azimi, Rishav…
Graph-based Uncertainty Metrics for Long-form Language Model Outputsby Mingjian Jiang, Yangjun Ruan, Prasanna Sattigeri, Salim…
SCULPT: Systematic Tuning of Long Promptsby Shanu Kumar, Akhila Yesantarao Venkata, Shubhanshu Khandelwal, Bishal Santra,…