16 citations · 60 across the 19 of their papers we have counts for
19 papers
Oculi: A Conversational Agentic Platform for Automated Credit Risk Analysis
Vennise Ho, Kristian Diana, Sandy Mourad +3
Credit risk analysis in financial institutions traditionally requires analysts to manually write SQL queries, run statistical computations, and build visualization dashboards. This…
TabReason: A Reinforcement Learning-Enhanced Reasoning LLM for Explainable Tabular Data Prediction
Tommy Xu, Zhitian Zhang, Xiangyu Sun +3
Predictive modeling on tabular data is the cornerstone of many real-world applications. Although gradient boosting machines and some recent deep models achieve strong performance o…
Were RNNs All We Needed?
Leo Feng, Frederick Tung, Mohamed Osama Ahmed +2
The introduction of Transformers in 2017 reshaped the landscape of deep learning. Originally proposed for sequence modelling, Transformers have since achieved widespread success ac…
Attention as an RNN
Leo Feng, Frederick Tung, Hossein Hajimirsadeghi +3
The advent of Transformers marked a significant breakthrough in sequence modelling, providing a highly performant architecture capable of leveraging GPU parallelism. However, Trans…
Tree Cross Attention
Leo Feng, Frederick Tung, Hossein Hajimirsadeghi +2
Cross Attention is a popular method for retrieving information from a set of context tokens for making predictions. At inference time, for each prediction, Cross Attention scans th…
Constant Memory Attention Block
Leo Feng, Frederick Tung, Hossein Hajimirsadeghi +2
Modern foundation model architectures rely on attention mechanisms to effectively capture context. However, these methods require linear or quadratic memory in terms of the number…
Memory Efficient Neural Processes via Constant Memory Attention Block
Leo Feng, Frederick Tung, Hossein Hajimirsadeghi +2
Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty. Recent state-of-the-art methods, however, leverage expensive attention me…
Training a Vision Transformer from scratch in less than 24 hours with 1 GPU
Saghar Irandoust, Thibaut Durand, Yunduz Rakhmangulova +2
Transformers have become central to recent advances in computer vision. However, training a vision Transformer (ViT) model from scratch can be resource intensive and time consuming…
Latent Bottlenecked Attentive Neural Processes
Leo Feng, Hossein Hajimirsadeghi, Yoshua Bengio +1
Neural Processes (NPs) are popular methods in meta-learning that can estimate predictive uncertainty on target datapoints by conditioning on a context dataset. Previous state-of-th…
Towards Better Selective Classification
Leo Feng, Mohamed Osama Ahmed, Hossein Hajimirsadeghi +1
We tackle the problem of Selective Classification where the objective is to achieve the best performance on a predetermined ratio (coverage) of the dataset. Recent state-of-the-art…
Monotonicity Regularization: Improved Penalties and Novel Applications to Disentangled Representation Learning and Robust Classification
Joao Monteiro, Mohamed Osama Ahmed, Hossein Hajimirsadeghi +1
We study settings where gradient penalties are used alongside risk minimization with the goal of obtaining predictors satisfying different notions of monotonicity. Specifically, we…
TD-GEN: Graph Generation With Tree Decomposition
Hamed Shirzad, Hossein Hajimirsadeghi, Amir H. Abdi +1
We propose TD-GEN, a graph generation framework based on tree decomposition, and introduce a reduced upper bound on the maximum number of decisions needed for graph generation. The…
Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data
Yu Gong, Hossein Hajimirsadeghi, Jiawei He +2
Learning from heterogeneous data poses challenges such as combining data from various sources and of different types. Meanwhile, heterogeneous data are often associated with missin…
Adapting Grad-CAM for Embedding Networks
Lei Chen, Jianhui Chen, Hossein Hajimirsadeghi +1
The gradient-weighted class activation mapping (Grad-CAM) method can faithfully highlight important regions in images for deep model prediction in image classification, image capti…
Graph Generation with Variational Recurrent Neural Network
Shih-Yang Su, Hossein Hajimirsadeghi, Greg Mori
Generating graph structures is a challenging problem due to the diverse representations and complex dependencies among nodes. In this paper, we introduce Graph Variational Recurren…
Learning to Detect Blue-white Structures in Dermoscopy Images with Weak Supervision
Ali Madooei, Mark S. Drew, Hossein Hajimirsadeghi
We propose a novel approach to identify one of the most significant dermoscopic criteria in the diagnosis of Cutaneous Melanoma: the Blue-whitish structure. In this paper, we achie…
Discovering Human Interactions in Videos with Limited Data Labeling
Mehran Khodabandeh, Arash Vahdat, Guang-Tong Zhou +4
We present a novel approach for discovering human interactions in videos. Activity understanding techniques usually require a large number of labeled examples, which are not availa…
Visual Recognition by Counting Instances: A Multi-Instance Cardinality Potential Kernel
Hossein Hajimirsadeghi, Wang Yan, Arash Vahdat +1
Many visual recognition problems can be approached by counting instances. To determine whether an event is present in a long internet video, one could count how many frames seem to…
Multiple Instance Learning by Discriminative Training of Markov Networks
Hossein Hajimirsadeghi, Jinling Li, Greg Mori +2
We introduce a graphical framework for multiple instance learning (MIL) based on Markov networks. This framework can be used to model the traditional MIL definition as well as more…