Search Results for author:
Found 31 papers, 9 papers with code
LatentLLM: Attention-Aware Joint Tensor Compression
Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources.
WHALES: A Multi-agent Scheduling Dataset for Enhanced Cooperation in Autonomous Driving
Achieving high levels of safety and reliability in autonomous driving remains a critical challenge, especially due to occlusion and limited perception ranges in standalone systems.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Question Answering
on PeerQA
SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules
Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models for computer vision.
Harmonizing the Generation and Pre-publication Stewardship of FAIR Image Data
Together with the molecular knowledge of genes and proteins, biological images promise to significantly enhance the scientific understanding of complex cellular systems and to advance predictive and personalized therapeutic products for human health.
Episodic Multi-Task Learning with Heterogeneous Neural Processes
This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup.
Towards Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference
In this work, we investigate the feasibility of inferring myocardial tissue properties from the electrocardiogram (ECG) within a CDT platform.
MOPO-LSI: A User Guide
MOPO-LSI is an open-source Multi-Objective Portfolio Optimization Library for Sustainable Investments.
A Cross-direction Task Decoupling Network for Small Logo Detection
The aggregation of small logos also brings a great challenge to the classification and localization of logos.
Influence of Myocardial Infarction on QRS Properties: A Simulation Study
However, the influence of various MI properties on the QRS is not intuitively predictable. In this work, we have systematically investigated the effects of 17 post-MI scenarios, varying the location, size, transmural extent, and conductive level of scarring and border zone area, on the forward-calculated QRS.
The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation
In particular, each client extracts and sends to the server the means of local data representations and the corresponding soft predictions -- information that we refer to as ``hyper-knowledge".
Modeling Human Eye Movements with Neural Networks in a Maze-Solving Task
This not only provides a generative model of eye movements in this task but also suggests a computational theory for how humans solve the task, namely that humans use mental simulation.
Masked Co-attentional Transformer reconstructs 100x ultra-fast/low-dose whole-body PET from longitudinal images and anatomically guided MRI
In this study, we utilize the global similarity between baseline and follow-up PET and magnetic resonance (MR) images to develop Masked-LMCTrans, a longitudinal multi-modality co-attentional CNN-Transformer that provides interaction and joint reasoning between serial PET/MRs of the same patient.
Dynamic Structure in Four-strategy Game: Theory and Experiment
Game dynamics theory, as a field of science, the consistency of theory and experiment is essential.
Multi-Modal Recurrent Fusion for Indoor Localization
This paper considers indoor localization using multi-modal wireless signals including Wi-Fi, inertial measurement unit (IMU), and ultra-wideband (UWB).
Multi-Band Wi-Fi Sensing with Matched Feature Granularity
The granularity matching is realized by pairing two feature maps from the CSI and beam SNR at different granularity levels and linearly combining all paired feature maps into a fused feature map with learnable weights.
LibFewShot: A Comprehensive Library for Few-shot Learning
Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks.
Source Class Selection with Label Propagation for Partial Domain Adaptation
The outlier classes can be detected if no target-domain data are labeled as these classes.
Ranked #2 on
Partial Domain Adaptation
on Office-31
Multi-Objective Recommendations: A Tutorial
Recommender systems (RecSys) have been well developed to assist user decision making.
Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss
To achieve high detection accuracy on imbalanced data, we design a novel attack-sharing loss function that can effectively move the decision boundary towards the attack classes and eliminates the bias towards the majority/benign class.
Temporal Cross-Effects in Knowledge Tracing
To the best of our knowledge, we are the first to introduce Hawkes process to model temporal cross-effects in KT.
A Light Transformer For Speech-To-Intent Applications
Spoken language understanding (SLU) systems can make life more agreeable, safer (e. g. in a car) or can increase the independence of physically challenged users.
An adversarial learning framework for preserving users' anonymity in face-based emotion recognition
Image and video-capturing technologies have permeated our every-day life.
High Dimensional Latent Panel Quantile Regression with an Application to Asset Pricing
We propose a generalization of the linear panel quantile regression model to accommodate both \textit{sparse} and \textit{dense} parts: sparse means while the number of covariates available is large, potentially only a much smaller number of them have a nonzero impact on each conditional quantile of the response variable; while the dense part is represent by a low-rank matrix that can be approximated by latent factors and their loadings.
Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Models
First, such attacks must acquire the outputs from the models by multiple times before actually launching attacks, which is difficult for the MitM adversary in practice.
Improved Super-Resolution Convolution Neural Network for Large Images
Single image super-resolution (SISR) is a very popular topic nowadays, which has both research value and practical value.
Through-Wall Object Recognition and Pose Estimation
Yet unlike optical images, RF images are difficult to understand by a human.
Connectionist Temporal Fusion for Sign Language Translation
Continuous sign language translation (CSLT) is a weakly supervised problem aiming at translating vision-based videos into natural languages under complicated sign linguistics, where the ordered words in a sentence label have no exact boundary of each sign action in the video.
Ranked #21 on
Sign Language Recognition
on RWTH-PHOENIX-Weather 2014
Future Semantic Segmentation with Convolutional LSTM
We propose a novel model that uses convolutional LSTM (ConvLSTM) to encode the spatiotemporal information of observed frames for future prediction.
Alternative Objective Functions for Deep Clustering
The recently proposed deep clustering framework represents a significant step towards solv-ing the cocktail party problem.
Ranked #38 on
Speech Separation
on WSJ0-2mix
High Dimensional Data Modeling Techniques for Detection of Chemical Plumes and Anomalies in Hyperspectral Images and Movies
We briefly review recent progress in techniques for modeling and analyzing hyperspectral images and movies, in particular for detecting plumes of both known and unknown chemicals.
