Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Modelsby…
Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuningby Haobo Song, Hao…
Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studiesby Ivan DrokinFirst submitted to arxiv on: 1 Jul…
Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuningby Arijit Sehanobish, Avinava Dubey, Krzysztof Choromanski, Somnath Basu…
A Comprehensive Solution to Connect Speech Encoder and Large Language Model for ASRby Van Tung…
Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentationby Markus Frohmann,…
Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuningby Somnath Basu Roy Chowdhury, Krzysztof Choromanski, Arijit…
Geneverse: A collection of Open-source Multimodal Large Language Models for Genomic and Proteomic Researchby Tianyu…
Mitigate Negative Transfer with Similarity Heuristic Lifelong Prompt Tuningby Chenyuan Wu, Gangwei Jiang, Defu LianFirst…
Initial Investigation of Kolmogorov-Arnold Networks (KANs) as Feature Extractors for IMU Based Human Activity Recognitionby…