Treasure Trove

"Treasure Trove" in research refers to the efficient and effective utilization of existing data and resources to improve various machine learning tasks. Current research focuses on developing methods to enhance the speed and accuracy of large language models, improve the robustness of adversarial detectors, and address challenges in multimodal learning with limited data. These advancements are significant because they improve the efficiency and reliability of AI systems across diverse applications, ranging from medical image analysis and video processing to natural language processing and program synthesis. The ultimate goal is to unlock the full potential of existing data, leading to more powerful and practical AI solutions.

Papers

August 16, 2024

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling
Xianzhen Luo, Yixuan Wang, Qingfu Zhu, Zhiming Zhang, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che
Large Language Model Scientific Inference Speculative Decoding Inference Latency N Gram Treasure Trove

April 18, 2024

Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors
Raz Lapid, Almog Dubin, Moshe Sipper
Adversarial Detection Treasure Trove Adversarial Retraining Adaptive Adversarial Attack

March 14, 2024

Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity
Zhuo Zhi, Ziquan Liu, Moe Elbadawi, Adam Daneshmend, Mine Orlu, Abdul Basit, Andreas Demosthenous, Miguel Rodrigues
Multi Task Multimodal Learning Different Context Missing Modality Data Scarcity Modality Data Missing Modality Data Treasure Trove

February 21, 2024

ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents
Zhipeng Xu, Zhenghao Liu, Yukun Yan, Shuo Wang, Shi Yu, Zheni Zeng, Chaojun Xiao, Zhiyuan Liu, Ge Yu, Chenyan Xiong
Active Learning Retrieval Augmented Generation Knowledge Based Passive Learning Knowledge Construction Treasure Trove

January 23, 2024

TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks
Zhiruo Wang, Daniel Fried, Graham Neubig
Language Model Flexible Toolkit Programming Task Table Question Answering Digital Tool Treasure Trove Function Calling

September 7, 2023

Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation
Xiaohan Cui, Long Ma, Tengyu Ma, Jinyuan Liu, Xin Fan, Risheng Liu
Low Light High Detection Scene Decomposition Treasure Trove Decomposition Derived Indicator

May 31, 2023

Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation
Ziyang Chen, Yongsheng Pan, Yiwen Ye, Hengfei Cui, Yong Xia
Medical Image Segmentation Task Domain Invariant Representation Product Distribution Domain Randomization Target Domain Data Multi Source Domain Generalization Treasure Trove

May 10, 2023

Treasure What You Have: Exploiting Similarity in Deep Neural Networks for Efficient Video Processing
Hadjer Benmeziane, Halima Bouzidi, Hamza Ouarnoughi, Ozcan Ozturk, Smail Niar
Deep Learning Deep Neural Network High Similarity Similarity Learning Video Processing Treasure Trove Layer Regularization

February 1, 2023

Trash to Treasure: Using text-to-image models to inform the design of physical artefacts
Amy Smith, Hope Schroeder, Ziv Epstein, Michael Cook, Simon Colton, Andrew Lippman
Generative Model Product Design Arbitrary Object Text to Image Model Creative Task Artifact Design Treasure Trove

August 16, 2022

TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments
Shubham Dokania, Anbumani Subramanian, Manmohan Chandraker, C. V. Jawahar
Synthetic Data Simulated Data Multi Modal Generation Synthetic Data Generation Pipeline Treasure Trove KITTI Scene Flow

February 18, 2022

REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening
Huihui Fang, Fei Li, Junde Wu, Huazhu Fu, Xu Sun, Jaemin Son, Shuang Yu, Menglu Zhang, Chenglang Yuan, Cheng Bian, Baiying Lei, Benjian Zhao, Xinxing Xu, Shaohua Li, Francisco Fumero, José Sigut, Haidar Almubarak, Yakoub Bazi, Yuanhao Guo, Yating Zhou, Ujjwal Baid, Shubham Innani, Tianjiao Guo, Jie Yang, José Ignacio Orlando, Hrvoje Bogunović, Xiulan Zhang, Yanwu Xu
Global Evaluation Fundus Image Image Analysis Color Fundus Retinal Fundus Glaucoma Challenge Treasure Trove

Treasure Trove

Papers

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors

Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity

ActiveRAG: Autonomously Knowledge Assimilation and Accommodation through Retrieval-Augmented Agents

TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks

Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation

Treasure in Distribution: A Domain Randomization based Multi-Source Domain Generalization for 2D Medical Image Segmentation

Treasure What You Have: Exploiting Similarity in Deep Neural Networks for Efficient Video Processing

Trash to Treasure: Using text-to-image models to inform the design of physical artefacts

TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments

REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening