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 10129 publications
Preview abstract
This paper presents a Multifunctional wearable
sensing system that integrates flexible Laser-Induced-Graphene
(LIG) based sensors and an Open-Source Analog Front-End
(AFE) chip. The LIG sensors are fabricated on polyimide (PI)
Flexible Printed Circuit Board (FPCB) through CO2 infrared
laser direct-write method. The LIG sensors provide repeatable
high-precision temperature sensing, humidity measurement, and
strain detection capabilities. The temperature sensing charac-
terization shows the resistive LIG sensor has a sensitivity of
-0.0493 %/°C, the linear fit R-square factors ≥ 0.9973 across -40
°C to 125 °C. The capacitive humidity sensor achieves a 23.6
times capacitance at 95% relative humidity (RH) compared to
the value observed in a dry environment. Our proposed AFE
chip contains a hybrid folded-cascode Operational Amplifier
(OPAMP) and a Successive Approximation Register Analog-
to-Digital Converter (SAR ADC). Designed using open-source
analog flow and fabricated in GF180 OpenPDK, the AFE chip
serves as a flexible and universal readout platform, adaptable for
various sensing applications. A real-time demonstration of finger
bending detection is performed to validate the functionality.
The multifunctional sensing capability provide by the wearable
system is attractive for personal healthcare application. This
work underscores the integration of the LIG sensors and the
AFE chip, developed using open-source tools which facilitate
rapid and affordable prototyping for a multifunctional flexible
wearable sensing system.
View details
Assessing Web Fingerprinting Risk
Robert Busa-Fekete
Antonio Sartori
Proceedings of the ACM Web Conference (WWW 2024)
Preview abstract
Modern Web APIs allow developers to provide extensively customized experiences for website visitors, but the richness of the device information they provide also make them vulnerable to being abused by malign actors to construct browser fingerprints, device-specific identifiers that enable covert tracking of users even when cookies are disabled.
Previous research has established entropy, a measure of information, as the key metric for quantifying fingerprinting risk. Earlier studies that estimated the entropy of Web APIs were based on data from a single website or were limited to an extremely small sample of clients. They also analyzed each Web API separately and then summed their entropies to quantify overall fingerprinting risk, an approach that can lead to gross overestimates.
We provide the first study of browser fingerprinting which addresses the limitations of prior work. Our study is based on actual visited pages and Web API function calls reported by tens of millions of real Chrome browsers in-the-wild. We accounted for the dependencies and correlations among Web APIs, which is crucial for obtaining more realistic entropy estimates. We also developed a novel experimental design that accurately estimates entropy while never observing too much information from any single user. Our results provide an understanding of the distribution of entropy for different website categories, confirm the utility of entropy as a fingerprinting proxy, and offer a method for evaluating browser enhancements which are intended to mitigate fingerprinting.
View details
Model-based Optimization of Superconducting Qubit Readout
Alex Opremcak
Alexandre Bourassa
Alexander Korotkov
Jimmy Chen
Physical Review Letters, 132 (2024), pp. 100603
Preview abstract
Measurement is one of the essential components of quantum algorithms, and for superconducting qubits it is often the most error prone. Here, we demonstrate a model-based readout optimization achieving low measurement errors while avoiding detrimental side-effects. For simultaneous and mid-circuit measurements across 17 qubits we observe 1.5% error per qubit with a duration of 500 ns end-to-end and minimal excess reset error from residual resonator photons. We also suppress measurement-induced state transitions and achieve a qubit leakage rate limited by natural heating.This technique can scale to hundreds of qubits, and be used to enhance performance of error-correcting codes as well as near-term applications
View details
Understanding Use Cases for AI-Powered Visual Interpretation Services
Ricardo Gonzalez
Jazmin Collins
Shiri Azenkot
CHI Conference on Human-Computer Interaction (2024)
Preview abstract
"Scene description" applications that describe visual content in a photo are useful daily tools for blind and low vision (BLV) people. Researchers have
studied their use, but they have only explored those that leverage remote sighted assistants; little is known about applications that use AI to generate
their descriptions. Thus, to investigate their use cases, we conducted a two-week diary study where 16 BLV participants used an AI-powered scene description
application we designed. Through their diary entries and follow-up interviews, users shared their information goals and assessments of the visual descriptions
they received. We analyzed the entries and found frequent use cases, such as identifying visual features of known objects, and surprising ones, such as avoiding contact with dangerous objects. We also found users scored the descriptions relatively low on average,
2.76 out of 5 (SD=1.49) for satisfaction and 2.43 out of 4 (SD=1.16) for trust, showing that descriptions still need signifcant improvements to deliver
satisfying and trustworthy experiences. We discuss future opportunities for AI as it becomes a more powerful accessibility tool for BLV users.
View details
VideoPoet: A Large Language Model for Zero-Shot Video Generation
Dan Kondratyuk
Xiuye Gu
Jonathan Huang
Grant Schindler
Rachel Hornung
Vighnesh Birodkar
Jimmy Yan
Ming-Chang Chiu
Hassan Akbari
Josh Dillon
Agrim Gupta
Meera Hahn
Anja Hauth
David Hendon
Alonso Martinez
Kihyuk Sohn
Xuan Yang
Huisheng Wang
Lu Jiang
ICML (2024)
Preview abstract
We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/
View details
Preview abstract
Recent significant advances in text-to-image models unlock the possibility of training vision systems using synthetic images, potentially overcoming the difficulty of collecting curated data at scale. It is unclear, however, how these models behave at scale, as more synthetic data is added to the training set. In this paper we study the scaling laws of synthetic images generated by state of the art text-to-image models, for the training of supervised models: image classifiers with label supervision, and CLIP with language supervision. We identify several factors, including text prompts, classifier-free guidance scale, and types of text-to-image models, that significantly affect scaling behavior. After tuning these factors, we observe that synthetic images demonstrate a scaling trend similar to, but slightly less effective than, real images in CLIP training, while they significantly underperform in scaling when training supervised image classifiers. Our analysis indicates that the main reason for this underperformance is the inability of off-the-shelf text-to-image models to generate certain concepts, a limitation that significantly impairs the training of image classifiers. Our findings also suggest that scaling synthetic data can be particularly effective in scenarios such as: (1) when there is a limited supply of real images for a supervised problem (e.g., fewer than 0.5 million images in ImageNet), (2) when the evaluation dataset diverges significantly from the training data, indicating the out-of-distribution scenario, or (3) when synthetic data is used in conjunction with real images, as demonstrated in the training of CLIP models.
View details
Preview abstract
In-Context Learning (ICL) is an emergent capability of Large Language Models (LLMs).
Only a few demonstrations enable LLMs to be used as blackbox for new tasks. Previous studies have shown that using LLMs' outputs as labels is effective in training models to select demonstrations. Such a label is expected to estimate utility of a demonstration in ICL;
however, it has not been well understood how different labeling strategies affect results on target tasks. This paper presents an analysis on different utility functions by focusing on LLMs' output probability given ground-truth output, and task-specific reward given LLMs' prediction. Unlike the previous work, we introduce a novel labeling method, incremental utility, which estimates how much incremental knowledge is brought into the LLMs by a demonstration. We conduct experiments with instruction-tuned LLMs on binary/multi-class classification, segmentation, and translation across Arabic, English, Finnish, Japanese, and Spanish. Our results show that (1) the probability is effective when the probability values are distributed across the whole value range (on the classification tasks), and (2) the downstream metric is more robust when nuanced reward values are provided with long outputs (on the segmentation and translation tasks). We then show that the proposed incremental utility further helps ICL by contrasting how the LLMs perform with and without the demonstrations.
View details
Preview abstract
Structured Complex Task Decomposition (SCTD) is the problem of breaking down a complex real-world task (such as planning a wedding) into a directed acyclic graph over individual steps that contribute to achieving the task, with edges specifying temporal dependencies between them. SCTD is an important component of assistive planning tools, and a challenge for commonsense reasoning systems. We probe how accurately SCTD can be done with the knowledge extracted from Large Language Models (LLMs). We introduce a high-quality human-annotated dataset for this problem and novel metrics to fairly assess performance of LLMs against several baselines. Our experiments reveal that LLMs are able to decompose complex tasks into individual steps effectively, with a relative improvement of 15% to 280% over the best baseline. We also propose a number of approaches to further improve their performance, with a relative improvement of 7% to 37% over the base model. However, we find that LLMs still struggle to predict pairwise temporal dependencies, which reveals a gap in their understanding of complex tasks.
View details
Preview abstract
For Extended Reality (XR) headsets, a key aim is the natural interaction in 3D space beyond what traditional methods of keyboard, mouse, and touchscreen can offer. With the release of the Apple Vision Pro, a novel interaction paradigm is now widely available where users seamlessly navigate content through the combined use of their eyes and hands. However, blending these modalities poses unique design challenges due to their dynamic nature and the absence of established principles and standards.
In this article, we present five design principles and issues for the Gaze + Pinch interaction technique, informed by eye-hand research in the human-computer interaction field. The design principles encompass mechanisms like division of labor and minimalistic timing, which are crucial for usability, alongside enhancements for the manipulation of objects, indirect interactions, and drag & drop. Whether in design, technology, or research domains, this exploration offers valuable perspectives for navigating the evolving landscape of 3D interaction.
View details
Media Mix Model Calibration With Bayesian Priors
Mike Wurm
Brenda Price
Ying Liu
research.google (2024)
Preview abstract
Effective model calibration is a critical and indispensable component in developing Media Mix Models (MMMs). One advantage of Bayesian-based MMMs lies in their capacity to accommodate the information from experiment results and the modelers' domain knowledge about the ad effectiveness by setting priors for the model parameters. However, it remains ambiguous about how and which Bayesian priors should be tuned for calibration purpose. In this paper, we propose a new calibration method through model reparameterization. The reparameterized model includes Return on Ads Spend (ROAS) as a model parameter, enabling straightforward adjustment of its prior distribution to align with either experiment results or the modeler's prior knowledge. The proposed method also helps address several key challenges regarding combining MMMs and incrementality experiments. We use simulations to demonstrate that our approach can significantly reduce the bias and uncertainty in the resultant posterior ROAS estimates.
View details
Preview abstract
Specialized Large multi-modal models (LMMs) have exhibited remarkable performance across numerous tasks, however, generalist LMMs suffer from performance degradation when training with a large collection of tasks. Recent research suggests Mixture of Experts (MoE) Models help instruction tuning, however, for LMMs of parameter size around O(50-100B), the prohibitive cost of replicating and storing the expert models severely limits the number of experts we can use.
We propose Omni-SMoLA that softly mixes many multimodal low rank experts to large models without introducing significant new parameter count compared to conventional MoE models. The core idea is that the large model provides a foundational backbone and different lightweight experts learn specialized knowledge residually. Extensive experiments demonstrate that the SMoLA approach helps improve the generalist performance across a broad range of visual question answering and captioning tasks, achieving a new state-of-the-art generalist performance that matches or outperforms single specialized LMM baselines.
View details
FEDAQT: ACCURATE QUANTIZED TRAINING WITH FEDERATED LEARNING
Renkun Ni
Oleg Rybakov
Phoenix Meadowlark
Tom Goldstein
Preview abstract
Federated learning has been widely used to train automatic speech recognition models, where the training procedure is decentralized to client devices to avoid data privacy concerns by keeping the training data locally. However, the limited computation resources on client devices prevent training with large models. Recently, quantization-aware training has shown the potential to train a quantized neural network with similar performance to the full-precision model while keeping the model size small and inference faster. However, these quantization methods will not save memory during training since they still keep the full-precision model. To address this issue, we propose a new quantization training framework for federated learning which saves the memory usage by training with quantized variables directly on local devices. We empirically show that our method can achieve comparable WER while only using 60% memory of the full-precision model.
View details
Connecting Language Technologies with Rich, Diverse Data Sources Covering Thousands of Languages
Sebastian Ruder
Julia Kreutzer
Clara Rivera
Ishank Saxena
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Preview abstract
Contrary to common belief, there are rich and diverse data sources available for many thousands of languages, which can be used to develop technologies for these languages. In this paper, we provide an overview of some of the major online data sources, the types of data that they provide access to, potential applications of this data, and the number of languages that they cover. Even this covers only a small fraction of the data that exists; for example, printed books are published in many languages but few online aggregators exist.
View details
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting
Conference of the North American Chapter of the Association for Computational Linguistics (NAACL) (2024)
Preview abstract
Ranking documents using Large Language Models (LLMs) by directly feeding the query and candidate documents into the prompt is an interesting and practical problem. However, researchers have found it difficult to outperform fine-tuned baseline rankers on benchmark datasets. We analyze pointwise and listwise ranking prompts used by existing methods and argue that off-the-shelf LLMs do not fully understand these challenging ranking formulations. In this paper, we propose to significantly reduce the burden on LLMs by using a new technique called Pairwise Ranking Prompting (PRP). Our results are the first in the literature to achieve state-of-the-art ranking performance on standard benchmarks using moderate-sized open-sourced LLMs. On TREC-DL 2019&2020, PRP based on the Flan-UL2 model with 20B parameters performs favorably with the previous best approach in the literature, which is based on the blackbox commercial GPT-4 that has 50x (estimated) model size, while outperforming other LLM-based solutions, such as InstructGPT which has 175B parameters, by over 10% for all ranking metrics. By using the same prompt template on seven BEIR tasks, PRP outperforms supervised baselines and outperforms the blackbox commercial ChatGPT solution by 4.2% and pointwise LLM-based solutions by more than 10% on average NDCG@10. Furthermore, we propose several variants of PRP to improve efficiency and show that it is possible to achieve competitive results even with linear complexity.
View details
Levels of Multimodal Interaction
Chinmay Kulkarni
ICMI Companion '24: Companion Proceedings of the 26th International Conference on Multimodal Interaction (2024)
Preview abstract
Large Multimodal Models (LMMs) like OpenAI's GPT4o and Google's Gemini, introduced in 2024, process multiple modalities, enabling significant advances in multimodal interaction. Inspired by frameworks for self-driving cars and AGI, this paper proposes "Levels of Multimodal Interaction" to guide research and development. The four levels are: basic multimodality (0), single modalities in turn-taking; combined multimodality (1), fused interpretation of multiple modalities; humanlike (2), natural interaction flow with additional communication signals; and beyond humanlike (3), surpassing human capabilities and include underlying hidden signals with the potential for transformational human-AI integration. LMMs have progressed from Level 0 to 1, with Level 2 next.
Level 3 sets a speculative target that multimodal interaction research could help achieve, where interaction becomes more natural and ultimately surpasses human capabilities. Eventually, such Level 3 multimodal interaction could lead to greater human-AI integration and transform human performance. This anticipated shift, in turn, introduces considerations, particularly around safety, agency and control of AI systems.
View details
