649 citations · 780 across the 20 of their papers we have counts for
21 papers
Muse Glimmer 30B: An On-Device Agentic Model
Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed +327
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Muse Glimmer…
Privacy Blur: Quantifying Privacy and Utility for Image Data Release
Saeed Mahloujifar, Narine Kokhlikyan, Chuan Guo +1
Image data collected in the wild often contains private information such as faces and license plates, and responsible data release must ensure that this information stays hidden. A…
CIMemories: A Compositional Benchmark for Contextual Integrity of Persistent Memory in LLMs
Niloofar Mireshghallah, Neal Mangaokar, Narine Kokhlikyan +4
Large Language Models (LLMs) increasingly use persistent memory from past interactions to enhance personalization and task performance. However, this memory introduces critical ris…
Z0-Inf: Zeroth Order Approximation for Data Influence
Narine Kokhlikyan, Kamalika Chaudhuri, Saeed Mahloujifar
A critical aspect of analyzing and improving modern machine learning systems lies in understanding how individual training examples influence a model's predictive behavior. Estimat…
RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection
Yuxin Wen, Arman Zharmagambetov, Ivan Evtimov +4
Prompt injection poses a serious threat to the reliability and safety of LLM agents. Recent defenses against prompt injection, such as Instruction Hierarchy and SecAlign, have show…
Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
Wannan, Yang, Xinchi Qiu +6
Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown tha…
How much do language models memorize?
John X. Morris, Chawin Sitawarin, Chuan Guo +5
We propose a new method for estimating how much a model knows about a datapoint and use it to measure the capacity of modern language models. Prior studies of language model memori…
On Symmetries in Convolutional Weights
Bilal Alsallakh, Timothy Wroge, Vivek Miglani +1
We explore the symmetry of the mean k x k weight kernel in each layer of various convolutional neural networks. Unlike individual neurons, the mean kernels in internal layers tend…
Measuring Déjà vu Memorization Efficiently
Narine Kokhlikyan, Bargav Jayaraman, Florian Bordes +2
Recent research has shown that representation learning models may accidentally memorize their training data. For example, the déjà vu method shows that for certain representation l…
Explainable Interfaces for Rapid Gaze-Based Interactions in Mixed Reality
Mengjie Yu, Dustin Harris, Ian Jones +12
Gaze-based interactions offer a potential way for users to naturally engage with mixed reality (XR) interfaces. Black-box machine learning models enabled higher accuracy for gaze-b…
Using Captum to Explain Generative Language Models
Vivek Miglani, Aobo Yang, Aram H. Markosyan +2
Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users' understanding of PyTorch m…
Error Discovery by Clustering Influence Embeddings
Fulton Wang, Julius Adebayo, Sarah Tan +2
We present a method for identifying groups of test examples -- slices -- on which a model under-performs, a task now known as slice discovery. We formalize coherence -- a requireme…
XAIR: A Framework of Explainable AI in Augmented Reality
Xuhai Xu, Mengjie Yu, Tanya R. Jonker +15
Explainable AI (XAI) has established itself as an important component of AI-driven interactive systems. With Augmented Reality (AR) becoming more integrated in daily lives, the rol…
Bias Mitigation Framework for Intersectional Subgroups in Neural Networks
Narine Kokhlikyan, Bilal Alsallakh, Fulton Wang +3
We propose a fairness-aware learning framework that mitigates intersectional subgroup bias associated with protected attributes. Prior research has primarily focused on mitigating…
Prescriptive and Descriptive Approaches to Machine-Learning Transparency
David Adkins, Bilal Alsallakh, Adeel Cheema +7
Specialized documentation techniques have been developed to communicate key facts about machine-learning (ML) systems and the datasets and models they rely on. Techniques such as D…
A Tour of Visualization Techniques for Computer Vision Datasets
Bilal Alsallakh, Pamela Bhattacharya, Vanessa Feng +4
We survey a number of data visualization techniques for analyzing Computer Vision (CV) datasets. These techniques help us understand properties and latent patterns in such data, by…
Investigating sanity checks for saliency maps with image and text classification
Narine Kokhlikyan, Vivek Miglani, Bilal Alsallakh +2
Saliency maps have shown to be both useful and misleading for explaining model predictions especially in the context of images. In this paper, we perform sanity checks for text mod…
Fine-grained Interpretation and Causation Analysis in Deep NLP Models
Hassan Sajjad, Narine Kokhlikyan, Fahim Dalvi +1
This paper is a write-up for the tutorial on "Fine-grained Interpretation and Causation Analysis in Deep NLP Models" that we are presenting at NAACL 2021. We present and discuss th…
Investigating Saturation Effects in Integrated Gradients
Vivek Miglani, Narine Kokhlikyan, Bilal Alsallakh +2
Integrated Gradients has become a popular method for post-hoc model interpretability. De-spite its popularity, the composition and relative impact of different regions of the integ…
Mind the Pad -- CNNs can Develop Blind Spots
Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani +2
We show how feature maps in convolutional networks are susceptible to spatial bias. Due to a combination of architectural choices, the activation at certain locations is systematic…
Captum: A unified and generic model interpretability library for PyTorch
Narine Kokhlikyan, Vivek Miglani, Miguel Martin +8
In this paper we introduce a novel, unified, open-source model interpretability library for PyTorch [12]. The library contains generic implementations of a number of gradient and p…