160 citations · 285 across the 21 of their papers we have counts for
21 papers
Aligning Dense Retrievers with LLM Utility via Distillation
Rajinder Sandhu, Di Mu, Cheng Chang +4
Dense vector retrieval is the practical backbone of Retrieval- Augmented Generation (RAG), but similarity search can suffer from precision limitations. Conversely, utility-based ap…
TabDPT: Scaling Tabular Foundation Models on Real Data
Junwei Ma, Valentin Thomas, Rasa Hosseinzadeh +7
Tabular data is one of the most ubiquitous sources of information worldwide, spanning a wide variety of domains. This inherent heterogeneity has slowed the development of Tabular F…
Retrieval & Fine-Tuning for In-Context Tabular Models
Valentin Thomas, Junwei Ma, Rasa Hosseinzadeh +4
Tabular data is a pervasive modality spanning a wide range of domains, and the inherent diversity poses a considerable challenge for deep learning. Recent advancements using transf…
Data-Efficient Multimodal Fusion on a Single GPU
Noël Vouitsis, Zhaoyan Liu, Satya Krishna Gorti +5
The goal of multimodal alignment is to learn a single latent space that is shared between multimodal inputs. The most powerful models in this space have been trained using massive…
MultiResFormer: Transformer with Adaptive Multi-Resolution Modeling for General Time Series Forecasting
Linfeng Du, Ji Xin, Alex Labach +3
Transformer-based models have greatly pushed the boundaries of time series forecasting recently. Existing methods typically encode time series data into using on…
Self-supervised Representation Learning From Random Data Projectors
Yi Sui, Tongzi Wu, Jesse C. Cresswell +5
Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations. Whil…
DuETT: Dual Event Time Transformer for Electronic Health Records
Alex Labach, Aslesha Pokhrel, Xiao Shi Huang +5
Electronic health records (EHRs) recorded in hospital settings typically contain a wide range of numeric time series data that is characterized by high sparsity and irregular obser…
DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation
Sajad Norouzi, Rasa Hosseinzadeh, Felipe Perez +1
The computational benefits of iterative non-autoregressive transformers decrease as the number of decoding steps increases. As a remedy, we introduce Distill Multiple Steps (DiMS),…
X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
Satya Krishna Gorti, Noel Vouitsis, Junwei Ma +4
In text-video retrieval, the objective is to learn a cross-modal similarity function between a text and a video that ranks relevant text-video pairs higher than irrelevant pairs. H…
Decentralized Federated Learning through Proxy Model Sharing
Shivam Kalra, Junfeng Wen, Jesse C. Cresswell +2
Institutions in highly regulated domains such as finance and healthcare often have restrictive rules around data sharing. Federated learning is a distributed learning framework tha…
Temporal Dependencies in Feature Importance for Time Series Predictions
Kin Kwan Leung, Clayton Rooke, Jonathan Smith +2
Time series data introduces two key challenges for explainability methods: firstly, observations of the same feature over subsequent time steps are not independent, and secondly, t…
Weakly Supervised Action Selection Learning in Video
Junwei Ma, Satya Krishna Gorti, Maksims Volkovs +1
Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only…
Probabilistic Simulation of Quantum Circuits with the Transformer
Juan Carrasquilla, Di Luo, Felipe Pérez +4
The fundamental question of how to best simulate quantum systems using conventional computational resources lies at the forefront of condensed matter and quantum computation. It im…
Learning Effective Visual Relationship Detector on 1 GPU
Yichao Lu, Cheng Chang, Himanshu Rai +2
We present our winning solution to the Open Images 2019 Visual Relationship challenge. This is the largest challenge of its kind to date with nearly 9 million training images. Chal…
Cross-Class Relevance Learning for Temporal Concept Localization
Junwei Ma, Satya Krishna Gorti, Maksims Volkovs +2
We present a novel Cross-Class Relevance Learning approach for the task of temporal concept localization. Most localization architectures rely on feature extraction layers followed…
Semi-Supervised Exploration in Image Retrieval
Cheng Chang, Himanshu Rai, Satya Krishna Gorti +4
We present our solution to Landmark Image Retrieval Challenge 2019. This challenge was based on the large Google Landmarks Dataset V2[9]. The goal was to retrieve all database imag…
Diabetes Mellitus Forecasting Using Population Health Data in Ontario, Canada
Mathieu Ravaut, Hamed Sadeghi, Kin Kwan Leung +2
Leveraging health administrative data (HAD) datasets for predicting the risk of chronic diseases including diabetes has gained a lot of attention in the machine learning community…
Noise Contrastive Estimation for Scalable Linear Models for One-Class Collaborative Filtering
Ga Wu, Maksims Volkovs, Chee Loong Soon +2
Previous highly scalable one-class collaborative filtering methods such as Projected Linear Recommendation (PLRec) have advocated using fast randomized SVD to embed items into a la…
Unsupervised Document Embedding With CNNs
Chundi Liu, Shunan Zhao, Maksims Volkovs
We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult t…
Context Models For Web Search Personalization
Maksims Volkovs
We present our solution to the Yandex Personalized Web Search Challenge. The aim of this challenge was to use the historical search logs to personalize top-N document rankings for…
Loss-sensitive Training of Probabilistic Conditional Random Fields
Maksims N. Volkovs, Hugo Larochelle, Richard S. Zemel
We consider the problem of training probabilistic conditional random fields (CRFs) in the context of a task where performance is measured using a specific loss function. While maxi…