Accepted Papers
QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning
Hossein Rajabzadeh, Mojtaba Valipour, Marzieh Tahaei, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, and Mehdi Rezagholizadeh
Paper | Poster Best Paper Award
SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners
Feng Liang, Yangguang Li, and Diana Marculescu
Paper | Poster Best Poster Award
Characterizing Video Question Answering with Sparsified Inputs
Shiyuan Huang, Robinson Piramuthu, Vicente Ordonez, Shih-Fu Chang, and Gunnar A Sigurdsson
Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation
Junsung Park and Hyunjung Shim
When Parameter-efficient Tuning Meets General-purpose Vision-language Models
Yihang Zhai, Haixin Wang, Jianlong Chang, Xinlong Yang, Jinan Sun, Shikun Zhang, and Qi Tian
Distilled ChatGPT Topic & Sentiment Modeling with Applications in Finance
Mouloud Belbahri and Olivier Gandouet
GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer
Urchade Zaratiana, Thierry Charnois, Nadi Tomeh, and Pierre Holat
Hyperparameter Optimization for Large Language Model Instruction-Tuning
Christophe Tribes, Sacha Benarroch-Lelong, Peng Lu, and Ivan Kobyzev
Faster Inference of Integer SWIN Transformer by Removing the GELU Activation
Mohammadreza Tayaranian, Seyyed Hasan Mozafari, James J. Clark, Brett H Meyer, and Warren Gross
SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search
Sharath Nittur Sridhar, Maciej Szankin, Fang Chen, Sairam Sundaresan, and Anthony Sarah
Robustness to distribution shifts of compressed networks for edge devices
Lulan Shen, Ali Edalati, Brett H Meyer, Warren Gross, and James J. Clark
SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection
Foozhan Ataiefard, Walid Ahmed, Habib Hajimolahoseini, Saina Asani, Farnoosh Javadi, Mohammad Hassanpour, Omar Mohamed Awad, Austin Wen, Kangling Liu, and Yang Liu
Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels
Seungho Lee, Seoungyoon Kang, and Hyunjung Shim