5 citations · 10 across the 17 of their papers we have counts for
17 papers
Generalizing the Geometry of Model Merging Through Frechet Averages
Marvin F. da Silva, Mohammed Adnan, Felix Dangel +1
Model merging aims to combine multiple models into one without additional training. Naïve parameter-space averaging can be fragile under architectural symmetries, as their geometry…
Self-Distillation of Hidden Layers for Self-Supervised Representation Learning
Scott C. Lowe, Anthony Fuller, Sageev Oore +2
The landscape of self-supervised learning (SSL) is currently dominated by generative approaches (e.g. MAE) that reconstruct raw low-level data, and predictive approaches (e.g. I-JE…
Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It
Marvin F. da Silva, Felix Dangel, Sageev Oore
The concept of sharpness has been successfully applied to traditional architectures like MLPs and CNNs to predict their generalization. For transformers, however, recent work repor…
Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models
Sri Harsha Dumpala, David Arps, Sageev Oore +2
Vision-language models (VLMs), serve as foundation models for multi-modal applications such as image captioning and text-to-image generation. Recent studies have highlighted limita…
Sensitivity of Generative VLMs to Semantically and Lexically Altered Prompts
Sri Harsha Dumpala, Aman Jaiswal, Chandramouli Sastry +3
Despite the significant influx of prompt-tuning techniques for generative vision-language models (VLMs), it remains unclear how sensitive these models are to lexical and semantic a…
Self-Supervised Embeddings for Detecting Individual Symptoms of Depression
Sri Harsha Dumpala, Katerina Dikaios, Abraham Nunes +3
Depression, a prevalent mental health disorder impacting millions globally, demands reliable assessment systems. Unlike previous studies that focus solely on either detecting depre…
Predicting Individual Depression Symptoms from Acoustic Features During Speech
Sebastian Rodriguez, Sri Harsha Dumpala, Katerina Dikaios +3
Current automatic depression detection systems provide predictions directly without relying on the individual symptoms/items of depression as denoted in the clinical depression rat…
SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations
Sri Harsha Dumpala, Aman Jaiswal, Chandramouli Sastry +3
Despite their remarkable successes, state-of-the-art large language models (LLMs), including vision-and-language models (VLMs) and unimodal language models (ULMs), fail to understa…
An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders
Scott C. Lowe, Joakim Bruslund Haurum, Sageev Oore +2
Can pretrained models generalize to new datasets without any retraining? We deploy pretrained image models on datasets they were not trained for, and investigate whether their embe…
VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations
Sri Harsha Dumpala, Aman Jaiswal, Chandramouli Sastry +3
Despite their remarkable successes, state-of-the-art language models face challenges in grasping certain important semantic details. This paper introduces the VISLA (Variance and I…
Test-Time Training for Depression Detection
Sri Harsha Dumpala, Chandramouli Shama Sastry, Rudolf Uher +1
Previous works on depression detection use datasets collected in similar environments to train and test the models. In practice, however, the train and test distributions cannot be…
Test-Time Training for Speech
Sri Harsha Dumpala, Chandramouli Sastry, Sageev Oore
In this paper, we study the application of Test-Time Training (TTT) as a solution to handling distribution shifts in speech applications. In particular, we introduce distribution-s…
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
Chandramouli Sastry, Sri Harsha Dumpala, Sageev Oore
We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers for the crucial yet challenging goal of improved classifier robustnes…
Generative Extraction of Audio Classifiers for Speaker Identification
Tejumade Afonja, Lucas Bourtoule, Varun Chandrasekaran +2
It is perhaps no longer surprising that machine learning models, especially deep neural networks, are particularly vulnerable to attacks. One such vulnerability that has been well…
Echofilter: A Deep Learning Segmentation Model Improves the Automation, Standardization, and Timeliness for Post-Processing Echosounder Data in Tidal Energy Streams
Scott C. Lowe, Louise P. McGarry, Jessica Douglas +4
Understanding the abundance and distribution of fish in tidal energy streams is important to assess risks presented by introducing tidal energy devices to the habitat. However tida…
LogAvgExp Provides a Principled and Performant Global Pooling Operator
Scott C. Lowe, Thomas Trappenberg, Sageev Oore
We seek to improve the pooling operation in neural networks, by applying a more theoretically justified operator. We demonstrate that LogSumExp provides a natural OR operator for l…
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators
Scott C. Lowe, Robert Earle, Jason d'Eon +2
The choice of activation functions and their motivation is a long-standing issue within the neural network community. Neuronal representations within artificial neural networks are…