Publications
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Our teams aspire to make discoveries that impact everyone, and core to our approach is sharing our research and tools to fuel progress in the field.
Sort By
1 - 15 of 10133 publications
Preview abstract
In this paper, we present SCOREQ, a novel approach for speech quality prediction. SCOREQ is a triplet loss function for contrastive regression that addresses the domain generalisation shortcoming exhibited by state of the art no-reference speech quality metrics. In the paper we: (i) illustrate the problem of L2 loss training failing at capturing the continuous nature of the mean opinion score (MOS) labels; (ii) demonstrate the lack of generalisation through a benchmarking evaluation across several speech domains; (iii) outline our approach and explore the impact of the architectural design decisions through incremental evaluation; (iv) evaluate the final model against state of the art models for a wide variety of data and domains. The results show that the lack of generalisation observed in state of the art speech quality metrics is addressed by SCOREQ. We conclude that using a triplet loss function
View details
ImageInWords: Unlocking Hyper-Detailed Image Descriptions
Andrew Bunner
Ranjay Krishna
(2024)
Preview abstract
Despite the longstanding adage "an image is worth a thousand words," creating accurate and hyper-detailed image descriptions for training Vision-Language models remains challenging.
Current datasets typically have web-scraped descriptions that are short, low-granularity, and often contain details unrelated to the visual content. As a result, models trained on such data generate descriptions replete with missing information, visual inconsistencies, and hallucinations. To address these issues, we introduce ImageInWords (IIW), a carefully designed human-in-the-loop annotation framework for curating hyper-detailed image descriptions and a new dataset resulting from this process.
We validate the framework through evaluations focused on the quality of the dataset and its utility for fine-tuning with considerations for readability, comprehensiveness, specificity, hallucinations, and human-likeness. Our dataset significantly improves across these dimensions compared to recently released datasets (+66%) and GPT-4V outputs (+48%). Furthermore, models fine-tuned with IIW data excel by +31% against prior work along the same human evaluation dimensions. Given our fine-tuned models, we also evaluate text-to-image generation and vision-language reasoning. Our model's descriptions can generate images closest to the original, as judged by both automated and human metrics. We also find our model produces more compositionally rich descriptions, outperforming the best baseline by up to 6% on ARO, SVO-Probes, and Winoground datasets.
View details
Preview abstract
This paper discusses a method to inject text when training an ASR system without the need for up sampling the text sequence to match the length of the speech sequence.
View details
Rambler: Supporting Writing With Speech via LLM-Assisted Gist Manipulation
Susan Lin
Jeremy Warner
J.D. Zamfirescu-Pereira
Matthew G Lee
Sauhard Jain
Michael Xuelin Huang
Bjoern Hartmann
Can Liu
Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, Association for Computing Machinery, New York, NY, USA
Preview abstract
Dictation enables efficient text input on mobile devices. However, writing with speech can produce disfluent, wordy, and incoherent text and thus requires heavy post-processing. This paper presents Rambler, an LLM-powered graphical user interface that supports gist-level manipulation of dictated text with two main sets of functions: gist extraction and macro revision. Gist extraction generates keywords and summaries as anchors to support the review and interaction with spoken text. LLM-assisted macro revisions allow users to respeak, split, merge, and transform dictated text without specifying precise editing locations. Together they pave the way for interactive dictation and revision that help close gaps between spontaneously spoken words and well-structured writing. In a comparative study with 12 participants performing verbal composition tasks, Rambler outperformed the baseline of a speech-to-text editor + ChatGPT, as it better facilitates iterative revisions with enhanced user control over the content while supporting surprisingly diverse user strategies.
View details
LFM-3D: Learnable Feature Matching Across Wide Baselines Using 3D Signals
Arjun Karpur
Guilherme Perrotta
Ricardo Martin-Brualla
Proc. 3DV'24 (2024) (to appear)
Preview abstract
Finding localized correspondences across different images of the same object is crucial to understand its geometry. In recent years, this problem has seen remarkable progress with the advent of deep learning-based local image features and learnable matchers. Still, learnable matchers often underperform when there exists only small regions of co-visibility between image pairs (i.e. wide camera baselines). To address this problem, we leverage recent progress in coarse single-view geometry estimation methods. We propose LFM-3D, a Learnable Feature Matching framework that uses models based on graph neural networks and enhances their capabilities by integrating noisy, estimated 3D signals to boost correspondence estimation. When integrating 3D signals into the matcher model, we show that a suitable positional encoding is critical to effectively make use of the low-dimensional 3D information. We experiment with two different 3D signals - normalized object coordinates and monocular depth estimates - and evaluate our method on large-scale (synthetic and real) datasets containing object-centric image pairs across wide baselines. We observe strong feature matching improvements compared to 2D-only methods, with up to +6% total recall and +28% precision at fixed recall. Additionally, we demonstrate that the resulting improved correspondences lead to much higher relative posing accuracy for in-the-wild image pairs - up to 8.6% compared to the 2D-only approach.
View details
Preview abstract
Knowledge-grounded dialogue generation is a challenging task because it requires satisfying two fundamental yet often competing constraints: being responsive in a manner that is specific to what the conversation partner has said while also being attributable to an underlying source document. In this work, we bring this trade-off between these two objectives (specificity and attribution) to light and ask the question: Can explicit content planning before the response generation help the model to address this challenge? To answer this question, we design a framework called PLEDGE, which allows us to experiment with various plan variables explored in prior work, supporting both metric-agnostic and metric-aware approaches. While content planning shows promise, our results on whether it can actually help to navigate this trade-off are mixed -- planning mechanisms that are metric-aware (use automatic metrics during training) are better at automatic evaluations but underperform in human judgment compared to metric-agnostic mechanisms. We discuss how this may be caused by over-fitting to automatic metrics and the need for future work to better calibrate these metrics towards human judgment. We hope the observations from our analysis will inform future work that aims to apply content planning in this context.
View details
Preview abstract
Sequence labeling is a core task in text understanding for IE/IR systems. Text generation models have increasingly become the go-to solution for such tasks (e.g., entity extraction and dialog slot filling). While most research has focused on the labeling accuracy, a key aspect -- of vital practical importance -- has slipped through the cracks: understanding model confidence. More specifically, we lack a principled understanding of how to reliably gauge the confidence of a model in its predictions for each labeled span. This paper aims to provide some empirical insights on estimating model confidence for generative sequence labeling. Most notably, we find that simply using the decoder's output probabilities is not the best in realizing well-calibrated confidence estimates. As verified over six public datasets of different tasks, we show that our proposed approach -- which leverages statistics from top-k predictions by a beam search -- significantly reduces calibration errors of the predictions of a generative sequence labeling model.
View details
“They only care to show us the wheelchair”: disability representation in text-to-image AI models
Avery Mack
Rida Qadri
CHI Conference on Human-Computer Interaction (2024)
Preview abstract
This paper reports on disability representation in images output from text-to-image (T2I) generative AI systems. Through eight focus groups with 25 people
with disabilities, we found that models repeatedly presented reductive archetypes for different disabilities. Often these representations reflected broader
societal stereotypes and biases, which our participants were concerned to see reproduced through T2I. Our participants discussed further challenges with
using these models including the current reliance on prompt engineering to reach satisfactorily diverse results. Finally, they offered suggestions for
how to improve disability representation with solutions like showing multiple, heterogeneous images for a single prompt and including the prompt with images
generated. Our discussion reflects on tensions and tradeoffs we found among the diverse perspectives shared to inform future research on representation-oriented
generative AI system evaluation metrics and development processes.
View details
FP-Fed: Privacy-Preserving Federated Detection of Browser Fingerprinting
Meenatchi Sundaram Muthu Selva Annamalai
Emiliano De Cristofaro
Network and Distributed System Security (NDSS) Symposium (2024)
Preview abstract
Browser fingerprinting often provides an attractive alternative to third-party cookies for tracking users across the web. In fact, the increasing restrictions on third-party cookies placed by common web browsers and recent regulations like the GDPR may accelerate the transition. To counter browser fingerprinting, previous work proposed several techniques to detect its prevalence and severity. However, these rely on 1) centralized web crawls and/or 2) computationally intensive operations to extract and process signals (e.g., information-flow and static analysis).
To address these limitations, we present FP-Fed, the first distributed system for browser fingerprinting detection. Using FP-Fed, users can collaboratively train on-device models based on their real browsing patterns, without sharing their training data with a central entity, by relying on Differentially Private Federated Learning (DP-FL). To demonstrate its feasibility and effectiveness, we evaluate FP-Fed’s performance on a set of 18.3k popular websites with different privacy levels, numbers of participants, and features extracted from the scripts. Our experiments show that FP-Fed achieves reasonably high detection performance and can perform both training and inference efficiently, on-device, by only relying on runtime signals extracted from the execution trace, without requiring any resource-intensive operation.
View details
KATch: A Fast Symbolic Verifier for NetKAT
Mark Moeller
Jules Jacobs
Olivier Savary Belanger
David Darais
Cole Schlesinger
Nate Foster
Alexandra Silva
Programming Languages and Implementation (PLDI) (2024) (to appear)
Preview abstract
We develop new data structures and algorithms for checking verification queries in NetKAT, a domain-specific language for specifying the behavior of network data planes. Our results extend the techniques obtained in prior work on symbolic automata and provide a framework for building efficient and scalable verification tools. We present \KATch, an implementation of these ideas in Scala, including extended logical operators that are useful for expressing network-wide specifications and optimizations that construct a bisimulation quickly or generate a counter-example showing that none exists. We evaluate the performance of our implementation on real-world and synthetic benchmarks, verifying properties such as reachability and slice isolation, typically returning a result in well under a second, which is orders of magnitude faster than previous approaches.
View details
Large Language Models as a Proxy For Human Evaluation in Assessing the Comprehensibility of Disordered Speech Transcription
Richard Cave
Katie Seaver
Jordan Green
Rus Heywood
Proceedings of ICASSP, IEEE (2024)
Preview abstract
Automatic Speech Recognition (ASR) systems, despite significant advances in recent years, still have much room for improvement particularly in the recognition of disordered speech. Even so, erroneous transcripts from ASR models can help people with disordered speech be better understood, especially if the transcription doesn’t significantly change the intended meaning. Evaluating the efficacy of ASR for this use case requires a methodology for measuring the impact of transcription errors on the intended meaning and comprehensibility. Human evaluation is the gold standard for this, but it can be laborious, slow, and expensive. In this work, we tune and evaluate large language models for this task and find them to be a much better proxy for human evaluators than other metrics commonly used. We further present a case-study using the presented approach to assess the quality of personalized ASR models to make model deployment decisions and correctly set user expectations for model quality as part of our trusted tester program.
View details
Making Images from Images: Tightly Constrained Parallel Denoising
Ashwin Baluja
European Conference on Computer Vision, AI for Visual Arts Workshop and Challenges (2024)
Preview abstract
We present methods to transform an image into a novel one of any subject matter simply by rearranging the image’s tiles. Our method extends and improves recent work in the generation of optical illusions by discovering the optimal arrangement of the image’s tiles simultaneously with the image generation. In addition to producing images that more accurately represent the subject matter, this technique allows us to address a much broader class of problems than previously possible. By learning the image transforms, we allow any source image to be pre- specified; any existing image (e.g. the Mona Lisa) can be transformed to a novel subject. We formulate this as a tightly constrained optimization problem and address it through alternating the steps of image diffusion and energy minimization using optimal matching. Under our formulation, a simple method to extend this to infinite copies of the source image is also given. Unlike previous methods, as the number of tiles grows the problem becomes easier and the results become better.
View details
ASTRA-5G: Automated Over-the-Air Security Testing and Research Architecture for 5G SA Devices
Aanjhan Ranganathan
Christina Pöpper
Evangelos Bitsikas
Michele Guerra
Roger Piqueras Jover
Syed Khandker
WiSec '24: Proceedings of the 17th ACM Conference on Security and Privacy in Wireless and Mobile Networks, ACM (2024)
Preview abstract
Despite the widespread deployment of 5G technologies, there exists a critical gap in security testing for 5G Standalone (SA) devices. Existing methods, largely manual and labor-intensive, are ill-equipped to fully uncover the state of security in the implementations of 5G-SA protocols and standards on devices, severely limiting the ability to conduct comprehensive evaluations. To address this issue, in this work, we introduce an novel, open-source framework that auto-
mates the security testing process for 5G SA devices. By leveraging enhanced functionalities of 5G SA core and Radio Access Network (RAN) software, our framework offers a streamlined approach to generating, executing, and evaluating test cases, specifically focusing on the Non-Access Stratum (NAS) layer. Our application of this framework across multiple 5G SA devices provides in-depth security insights, significantly improving testing efficiency and breadth.
View details
DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems
Yair Schiff
Jeff Parker
Volodymyr Kuleshov
International Conference on Machine Learning (ICML) (2024)
Preview abstract
Learning dynamics from dissipative chaotic systems is notoriously difficult due to their inherent instability, as formalized by their positive Lyapunov exponents, which exponentially amplify errors in the learned dynamics. However, many of these systems exhibit ergodicity and an attractor: a compact and highly complex manifold, to which trajectories converge in finite-time, that supports an invariant measure, i.e., a probability distribution that is invariant under the action of the dynamics, which dictates the long-term statistical behavior of the system. In this work, we leverage this structure to propose a new framework that targets learning the invariant measure as well as the dynamics, in contrast with typical methods that only target the misfit between trajectories, which often leads to divergence as the trajectories’ length increases. We use our framework to propose a tractable and sample efficient objective that can be used with any existing learning objectives. Our Dynamics Stable Learning by Invariant Measure (DySLIM) objective enables model training that achieves better point-wise tracking and long-term statistical accuracy relative to other learning objectives. By targeting the distribution with a scalable regularization term, we hope that this approach can be extended to more complex systems exhibiting slowly-variant distributions, such as weather and climate models. Code to reproduce our experiments is available here: https://github.com/google-research/swirl-dynamics/tree/main/swirl_dynamics/projects/ergodic.
View details
Preview abstract
Generative AI (GAI) is proliferating, and among its many applications are to support creative work (e.g., generating text, images, music) and to enhance accessibility (e.g., captions of images and audio). As GAI evolves, creatives must consider how (or how not) to incorporate these tools into their practices. In this paper, we present interviews at the intersection of these applications. We learned from 10 creatives with disabilities who intentionally use and do not use GAI in and around their creative work. Their mediums ranged from audio engineering to leatherwork, and they collectively experienced a variety of disabilities, from sensory to motor to invisible disabilities. We share cross-cutting themes of their access hacks, how creative practice and access work become entangled, and their perspectives on how GAI should and should not fit into their workflows. In turn, we offer qualities of accessible creativity with responsible AI that can inform future research.
View details
