18 accepted papers
Graph coarsening is a fundamental dimensionality reduction technique for scaling large graphs while preserving structural and feature information. However, most existing coarsening methods are designed for static graphs and do not extend well to dynamic settings where nodes, edges, and connectivity …
Large Language Models (LLMs) can produce biased responses that can cause representational harms. However, conventional studies are insufficient to thoroughly evaluate biases across LLM responses for different demographic groups (a.k.a. counterfactual bias), as they do not scale to large number of in…
Warning: This paper contains offensive language.Ensuring that large language models (LLMs) do not generate harmful text is critical for their safe deployment. A common failure mode involves producing toxic responses to otherwise innocuous prompts. While various detoxification methods have been propo…
Training a linear classifier or lightweight model on top of pretrained vision model outputs so-called 'frozen features' leads to impressive performance on a number of downstream few-shot tasks. Currently frozen features are not modified during training. On the other hand when networks are trained di…
In data-intensive applications, graphs serve as foundational structures across various domains. However, the increasing size of datasets poses significant challenges to performing downstream tasks. To address this problem, techniques such as graph coarsening, condensation, and summarization have bee…
Graph coarsening is a dimensionality reduction technique that aims to learn a smaller-tractable graph while preserving the properties of the original input graph. However, many real-world graphs also have features or contexts associated with each node. The existing graph coarsening methods do not co…
Contrastive pretraining on image-text pairs from the web is one of the most popular large-scale pretraining strategies for vision backbones, especially in the context of large multimodal models. At the same time, image captioning on this type of data is commonly considered an inferior pretraining st…
The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the same architecture to image and video modelling, but these have not yet been suc…
Use of synthetic data is rapidly emerging as a realistic alternative to manually annotating live traffic for industry-scale model building. Manual data annotation is slow, expensive and not preferred for meeting customer privacy expectations. Further, commercial natural language applications are req…
This paper presents an approach to identify samples from live traffic where the customer implicitly communicated satisfaction with Alexa’s responses, by leveraging interpretations of model behavior. Such customer signals are noisy and adding a large number of samples from live traffic to training se…
One of the major challenges of training Natural Language Understanding (NLU) production models lies in the discrepancy between the distributions of the offline training data and of the online live data, due to, e.g., biased sampling scheme, cyclic seasonality shifts, annotated training data coming f…
We present the Colorization Transformer, a novel approach for diverse high fidelity image colorization based on self-attention. Given a grayscale image, the colorization proceeds in three steps. We first use a conditional autoregressive transformer to produce a low resolution coarse coloring of the…
Predicting the speaker’s identity of short speech segments in human dialogue has been considered one of the most challenging problems in speech signal processing. Speaker representations of short speech segments tend to be unreliable, resulting in poor fidelity of speaker representations in tasks re…
Diagnostic procedures for ASD (autism spectrum disorder) involve semi-naturalistic interactions between the child and a clinician. Computational methods to analyze these sessions require an end-to-end speech and language processing pipeline that goes from raw audio to clinically-meaningful behaviora…
Computational modeling of naturalistic conversations in clinical applications has seen growing interest in the past decade. An important use-case involves child-adult interactions within the autism diagnosis and intervention domain. In this paper, we address a specific sub-problem of speaker diariza…
In this work, we propose deep latent space clustering for speaker diarization using generative adversarial network (GAN) back-projection with the help of an encoder network. The proposed diarization system is trained jointly with GAN loss, latent variable recovery loss, and a clustering-specific los…
Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is highly uncertain: a sequence of past observations of events…
We propose a semi-supervised learning method to improve classification performance in scenarios with limited labeled data. We employ adaptation strategies such as entropy-filtering and self-training, and show that our method achieves up to 17.2% relative improvement in UAR for a multi-class problem.…