Search

Practical superconducting nanowire single photon detectors (SNSPDs) demonstrate a strong trade-off between detection sensitivity and the reset time. Often, there are wide variations in sensitivity and response times from SNSPDs of the same superconducting material. Here, using detailed physical models, we show that the dirtiness in a superconductor enforces a sensitivity and bandwidth trade-off in all practical devices. More importantly, a certain degree of dirtiness is a necessary requirement for achieving single photon detection. Under typical bias conditions close to the transition setpoints, the minimum number of photons required to register a voltage pulse decreases by the dirtiness parameter (Ioffe-Regel parameter) and the reset time of SNSPD increases by the same dirtiness parameter, thereby giving a constant value for the sensitivity-bandwidth product. The constant is weakly modified by biasing current and the temperature. Since dirtiness in the superconducting nanowire is a physically controllable parameter with an important bearing on the final response of an SNSPD, this work opens new opportunities to develop SNSPD devices with engineered sensitivity-bandwidth setpoint as dictated by an application., Comment: 12 Pages, 05 Figures

While generative AI (GenAI) offers countless possibilities for creative and productive tasks, artificially generated media can be misused for fraud, manipulation, scams, misinformation campaigns, and more. To mitigate the risks associated with maliciously generated media, forensic classifiers are employed to identify AI-generated content. However, current forensic classifiers are often not evaluated in practically relevant scenarios, such as the presence of an attacker or when real-world artifacts like social media degradations affect images. In this paper, we evaluate state-of-the-art AI-generated image (AIGI) detectors under different attack scenarios. We demonstrate that forensic classifiers can be effectively attacked in realistic settings, even when the attacker does not have access to the target model and post-processing occurs after the adversarial examples are created, which is standard on social media platforms. These attacks can significantly reduce detection accuracy to the extent that the risks of relying on detectors outweigh their benefits. Finally, we propose a simple defense mechanism to make CLIP-based detectors, which are currently the best-performing detectors, robust against these attacks.

Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation. However, it is unclear how meaningful the notion of "zero-shot" generalization is for such multimodal models, as it is not known to what extent their pretraining datasets encompass the downstream concepts targeted for during "zero-shot" evaluation. In this work, we ask: How is the performance of multimodal models on downstream concepts influenced by the frequency of these concepts in their pretraining datasets? We comprehensively investigate this question across 34 models and five standard pretraining datasets (CC-3M, CC-12M, YFCC-15M, LAION-400M, LAION-Aesthetics), generating over 300GB of data artifacts. We consistently find that, far from exhibiting "zero-shot" generalization, multimodal models require exponentially more data to achieve linear improvements in downstream "zero-shot" performance, following a sample inefficient log-linear scaling trend. This trend persists even when controlling for sample-level similarity between pretraining and downstream datasets, and testing on purely synthetic data distributions. Furthermore, upon benchmarking models on long-tailed data sampled based on our analysis, we demonstrate that multimodal models across the board perform poorly. We contribute this long-tail test set as the "Let it Wag!" benchmark to further research in this direction. Taken together, our study reveals an exponential need for training data which implies that the key to "zero-shot" generalization capabilities under large-scale training paradigms remains to be found., Comment: Short version accepted at DPFM, ICLR'24; Full paper at NeurIPS'24

An important and difficult task in code-switched speech recognition is to recognize the language, as lots of words in two languages can sound similar, especially in some accents. We focus on improving performance of end-to-end Automatic Speech Recognition models by conditioning transformer layers on language ID of words and character in the output in an per layer supervised manner. To this end, we propose two methods of introducing language specific parameters and explainability in the multi-head attention mechanism, and implement a Temporal Loss that helps maintain continuity in input alignment. Despite being unable to reduce WER significantly, our method shows promise in predicting the correct language from just spoken data. We introduce regularization in the language prediction by dropping LID in the sequence, which helps align long repeated output sequences., Comment: Bachelor's thesis, 28 pages, includes appendix

We present MOSAIC, a modular architecture for home robots to perform complex collaborative tasks, such as cooking with everyday users. MOSAIC tightly collaborates with humans, interacts with users using natural language, coordinates multiple robots, and manages an open vocabulary of everyday objects. At its core, MOSAIC employs modularity: it leverages multiple large-scale pre-trained models for general tasks like language and image recognition, while using streamlined modules designed for task-specific control. We extensively evaluate MOSAIC on 60 end-to-end trials where two robots collaborate with a human user to cook a combination of 6 recipes. We also extensively test individual modules with 180 episodes of visuomotor picking, 60 episodes of human motion forecasting, and 46 online user evaluations of the task planner. We show that MOSAIC is able to efficiently collaborate with humans by running the overall system end-to-end with a real human user, completing 68.3% (41/60) collaborative cooking trials of 6 different recipes with a subtask completion rate of 91.6%. Finally, we discuss the limitations of the current system and exciting open challenges in this domain. The project's website is at https://portal-cornell.github.io/MOSAIC/, Comment: 22 pages, 13 figures; CoRL 2024

This work introduces a novel principle for disentanglement we call mechanism sparsity regularization, which applies when the latent factors of interest depend sparsely on observed auxiliary variables and/or past latent factors. We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors and the sparse causal graphical model that explains them. We develop a nonparametric identifiability theory that formalizes this principle and shows that the latent factors can be recovered by regularizing the learned causal graph to be sparse. More precisely, we show identifiablity up to a novel equivalence relation we call "consistency", which allows some latent factors to remain entangled (hence the term partial disentanglement). To describe the structure of this entanglement, we introduce the notions of entanglement graphs and graph preserving functions. We further provide a graphical criterion which guarantees complete disentanglement, that is identifiability up to permutations and element-wise transformations. We demonstrate the scope of the mechanism sparsity principle as well as the assumptions it relies on with several worked out examples. For instance, the framework shows how one can leverage multi-node interventions with unknown targets on the latent factors to disentangle them. We further draw connections between our nonparametric results and the now popular exponential family assumption. Lastly, we propose an estimation procedure based on variational autoencoders and a sparsity constraint and demonstrate it on various synthetic datasets. This work is meant to be a significantly extended version of Lachapelle et al. (2022)., Comment: 88 pages

An accurate differential diagnosis (DDx) is a cornerstone of medical care, often reached through an iterative process of interpretation that combines clinical history, physical examination, investigations and procedures. Interactive interfaces powered by Large Language Models (LLMs) present new opportunities to both assist and automate aspects of this process. In this study, we introduce an LLM optimized for diagnostic reasoning, and evaluate its ability to generate a DDx alone or as an aid to clinicians. 20 clinicians evaluated 302 challenging, real-world medical cases sourced from the New England Journal of Medicine (NEJM) case reports. Each case report was read by two clinicians, who were randomized to one of two assistive conditions: either assistance from search engines and standard medical resources, or LLM assistance in addition to these tools. All clinicians provided a baseline, unassisted DDx prior to using the respective assistive tools. Our LLM for DDx exhibited standalone performance that exceeded that of unassisted clinicians (top-10 accuracy 59.1% vs 33.6%, [p = 0.04]). Comparing the two assisted study arms, the DDx quality score was higher for clinicians assisted by our LLM (top-10 accuracy 51.7%) compared to clinicians without its assistance (36.1%) (McNemar's Test: 45.7, p < 0.01) and clinicians with search (44.4%) (4.75, p = 0.03). Further, clinicians assisted by our LLM arrived at more comprehensive differential lists than those without its assistance. Our study suggests that our LLM for DDx has potential to improve clinicians' diagnostic reasoning and accuracy in challenging cases, meriting further real-world evaluation for its ability to empower physicians and widen patients' access to specialist-level expertise.

Although modern neural networks often generalize to new combinations of familiar concepts, the conditions that enable such compositionality have long been an open question. In this work, we study the systematicity gap in visual question answering: the performance difference between reasoning on previously seen and unseen combinations of object attributes. To test, we introduce a novel diagnostic dataset, CLEVR-HOPE. We find that the systematicity gap is not reduced by increasing the quantity of training data, but is reduced by increasing the diversity of training data. In particular, our experiments suggest that the more distinct attribute type combinations are seen during training, the more systematic we can expect the resulting model to be., Comment: 36 pages, 27 figures, EMNLP 2024

Introduction: Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five challenges to address. Challenge #1: VCE data are stochastic and contains significant artifact. Challenge #2: VCE interpretation is cost-intensive. Challenge #3: VCE data are inherently imbalanced. Challenge #4: Existing VCE AIMLT are computationally cumbersome. Challenge #5: Clinicians are hesitant to accept AIMLT that cannot explain their process. Methods: An anatomic landmark detection model was used to test the application of convolutional neural networks (CNNs) to the task of classifying VCE data. We also created a tool that assists in expert annotation of VCE data. We then created more elaborate models using different approaches including a multi-frame approach, a CNN based on graph representation, and a few-shot approach based on meta-learning. Results: When used on full-length VCE footage, CNNs accurately identified anatomic landmarks (99.1%), with gradient weighted-class activation mapping showing the parts of each frame that the CNN used to make its decision. The graph CNN with weakly supervised learning (accuracy 89.9%, sensitivity of 91.1%), the few-shot model (accuracy 90.8%, precision 91.4%, sensitivity 90.9%), and the multi-frame model (accuracy 97.5%, precision 91.5%, sensitivity 94.8%) performed well. Discussion: Each of these five challenges is addressed, in part, by one of our AI-based models. Our goal of producing high performance using lightweight models that aim to improve clinician confidence was achieved.

Diffusive memristors owing to their ability to produce current spiking when a constant or slowly changing voltage is applied are competitive candidates for the development of artificial electronic neurons. These artificial neurons can be integrated into various prospective autonomous and robotic systems as sensors, e.g. ones implementing object grasping and classification. We report here Ag nanoparticle-based diffusive memristor prepared on a flexible polyethylene terephthalate (PET) substrate in which the electric spiking behaviour was induced by the electric voltage under an additional stimulus of external mechanical impact. By changing the magnitude and frequency of the mechanical impact, we are able to manipulate the spiking response of our artificial neuron. This functionality to control the spiking characterstics paves a pathway for the development of touch-perception sensors that can convert local pressure into electrical spikes for further processing in neural networks. We have proposed a mathematical model which captures the operation principle of the fabricated memristive sensors and qualitatively describes the measured spiking behaviour., Comment: 18 pages, 7 figures

Language instructions and demonstrations are two natural ways for users to teach robots personalized tasks. Recent progress in Large Language Models (LLMs) has shown impressive performance in translating language instructions into code for robotic tasks. However, translating demonstrations into task code continues to be a challenge due to the length and complexity of both demonstrations and code, making learning a direct mapping intractable. This paper presents Demo2Code, a novel framework that generates robot task code from demonstrations via an extended chain-of-thought and defines a common latent specification to connect the two. Our framework employs a robust two-stage process: (1) a recursive summarization technique that condenses demonstrations into concise specifications, and (2) a code synthesis approach that expands each function recursively from the generated specifications. We conduct extensive evaluation on various robot task benchmarks, including a novel game benchmark Robotouille, designed to simulate diverse cooking tasks in a kitchen environment. The project's website is available at https://portal-cornell.github.io/demo2code/, Comment: 10 pages (not including references and appendix), 14 figures (7 in main paper, 7 in appendix); (v3) camera-ready version

Learning structured representations of the visual world in terms of objects promises to significantly improve the generalization abilities of current machine learning models. While recent efforts to this end have shown promising empirical progress, a theoretical account of when unsupervised object-centric representation learning is possible is still lacking. Consequently, understanding the reasons for the success of existing object-centric methods as well as designing new theoretically grounded methods remains challenging. In the present work, we analyze when object-centric representations can provably be learned without supervision. To this end, we first introduce two assumptions on the generative process for scenes comprised of several objects, which we call compositionality and irreducibility. Under this generative process, we prove that the ground-truth object representations can be identified by an invertible and compositional inference model, even in the presence of dependencies between objects. We empirically validate our results through experiments on synthetic data. Finally, we provide evidence that our theory holds predictive power for existing object-centric models by showing a close correspondence between models' compositionality and invertibility and their empirical identifiability., Comment: Oral at ICML 2023. The first two authors as well as the last two authors contributed equally. Code is available at https://brendel-group.github.io/objects-identifiability

Motivated by quantum network applications over classical channels, we initiate the study of $n$-party resource states from which LOCC protocols can create EPR-pairs between any $k$ disjoint pairs of parties. We give constructions of such states where $k$ is not too far from the optimal $n/2$ while the individual parties need to hold only a constant number of qubits. In the special case when each party holds only one qubit, we describe a family of $n$-qubit states with $k$ proportional to $\log n$ based on Reed-Muller codes, as well as small numerically found examples for $k=2$ and $k=3$. We also prove some lower bounds, for example showing that if $k=n/2$ then the parties must have at least $\Omega(\log\log n)$ qubits each., Comment: 35 pages, 5 figures. Quantum journal submission. DOI links for all references

As large-scale training regimes have gained popularity, the use of pretrained models for downstream tasks has become common practice in machine learning. While pretraining has been shown to enhance the performance of models in practice, the transfer of robustness properties from pretraining to downstream tasks remains poorly understood. In this study, we demonstrate that the robustness of a linear predictor on downstream tasks can be constrained by the robustness of its underlying representation, regardless of the protocol used for pretraining. We prove (i) a bound on the loss that holds independent of any downstream task, as well as (ii) a criterion for robust classification in particular. We validate our theoretical results in practical applications, show how our results can be used for calibrating expectations of downstream robustness, and when our results are useful for optimal transfer learning. Taken together, our results offer an initial step towards characterizing the requirements of the representation function for reliable post-adaptation performance.

Two major causes of death in the United States and worldwide are stroke and myocardial infarction. The underlying cause of both is thrombi released from ruptured or eroded unstable atherosclerotic plaques that occlude vessels in the heart (myocardial infarction) or the brain (stroke). Clinical studies show that plaque composition plays a more important role than lesion size in plaque rupture or erosion events. To determine the plaque composition, various cell types in 3D cardiovascular immunofluorescent images of plaque lesions are counted. However, counting these cells manually is expensive, time-consuming, and prone to human error. These challenges of manual counting motivate the need for an automated approach to localize and count the cells in images. The purpose of this study is to develop an automatic approach to accurately detect and count cells in 3D immunofluorescent images with minimal annotation effort. In this study, we used a weakly supervised learning approach to train the HoVer-Net segmentation model using point annotations to detect nuclei in fluorescent images. The advantage of using point annotations is that they require less effort as opposed to pixel-wise annotation. To train the HoVer-Net model using point annotations, we adopted a popularly used cluster labeling approach to transform point annotations into accurate binary masks of cell nuclei. Traditionally, these approaches have generated binary masks from point annotations, leaving a region around the object unlabeled (which is typically ignored during model training). However, these areas may contain important information that helps determine the boundary between cells. Therefore, we used the entropy minimization loss function in these areas to encourage the model to output more confident predictions on the unlabeled areas. Our comparison studies indicate that the HoVer-Net model trained using our weakly ...

While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision. To address this, we propose Pixel-level Correspondence (PiCo), a method for dense contrastive learning from video. By tracking points with optical flow, we obtain a correspondence map which can be used to match local features at different points in time. We validate PiCo on standard benchmarks, outperforming self-supervised baselines on multiple dense prediction tasks, without compromising performance on image classification.

In this work, we propose a mutual information (MI) based unsupervised domain adaptation (UDA) method for the cross-domain nuclei segmentation. Nuclei vary substantially in structure and appearances across different cancer types, leading to a drop in performance of deep learning models when trained on one cancer type and tested on another. This domain shift becomes even more critical as accurate segmentation and quantification of nuclei is an essential histopathology task for the diagnosis/ prognosis of patients and annotating nuclei at the pixel level for new cancer types demands extensive effort by medical experts. To address this problem, we maximize the MI between labeled source cancer type data and unlabeled target cancer type data for transferring nuclei segmentation knowledge across domains. We use the Jensen-Shanon divergence bound, requiring only one negative pair per positive pair for MI maximization. We evaluate our set-up for multiple modeling frameworks and on different datasets comprising of over 20 cancer-type domain shifts and demonstrate competitive performance. All the recently proposed approaches consist of multiple components for improving the domain adaptation, whereas our proposed module is light and can be easily incorporated into other methods (Implementation: https://github.com/YashSharma/MaNi )., Comment: Accepted at MICCAI 2022

Exercise testing has been available for more than a half-century and is a remarkably versatile tool for diagnostic and prognostic information of patients for a range of diseases, especially cardiovascular and pulmonary. With rapid advancements in technology, wearables, and learning algorithm in the last decade, its scope has evolved. Specifically, Cardiopulmonary exercise testing (CPX) is one of the most commonly used laboratory tests for objective evaluation of exercise capacity and performance levels in patients. CPX provides a non-invasive, integrative assessment of the pulmonary, cardiovascular, and skeletal muscle systems involving the measurement of gas exchanges. However, its assessment is challenging, requiring the individual to process multiple time series data points, leading to simplification to peak values and slopes. But this simplification can discard the valuable trend information present in these time series. In this work, we encode the time series as images using the Gramian Angular Field and Markov Transition Field and use it with a convolutional neural network and attention pooling approach for the classification of heart failure and metabolic syndrome patients. Using GradCAMs, we highlight the discriminative features identified by the model., Comment: Accepted in NeurIPS 2021 - MLPH Workshop; EMBC 2022. Code: https://github.com/YashSharma/MultivariateTimeSeries

Bias mitigation in machine learning models is imperative, yet challenging. While several approaches have been proposed, one view towards mitigating bias is through adversarial learning. A discriminator is used to identify the bias attributes such as gender, age or race in question. This discriminator is used adversarially to ensure that it cannot distinguish the bias attributes. The main drawback in such a model is that it directly introduces a trade-off with accuracy as the features that the discriminator deems to be sensitive for discrimination of bias could be correlated with classification. In this work we solve the problem. We show that a biased discriminator can actually be used to improve this bias-accuracy tradeoff. Specifically, this is achieved by using a feature masking approach using the discriminator's gradients. We ensure that the features favoured for the bias discrimination are de-emphasized and the unbiased features are enhanced during classification. We show that this simple approach works well to reduce bias as well as improve accuracy significantly. We evaluate the proposed model on standard benchmarks. We improve the accuracy of the adversarial methods while maintaining or even improving the unbiasness and also outperform several other recent methods., Comment: AAAI 2022(Accepted)

Evolutionary algorithms provide gradient-free optimisation which is beneficial for models that have difficulty in obtaining gradients; for instance, geoscientific landscape evolution models. However, such models are at times computationally expensive and even distributed swarm-based optimisation with parallel computing struggles. We can incorporate efficient strategies such as surrogate-assisted optimisation to address the challenges; however, implementing inter-process communication for surrogate-based model training is difficult. In this paper, we implement surrogate-based estimation of fitness evaluation in distributed swarm optimisation over a parallel computing architecture. We first test the framework on a set of benchmark optimisation problems and then apply it to a geoscientific model that features a landscape evolution model. Our results demonstrate very promising results for benchmark functions and the Badlands landscape evolution model. We obtain a reduction in computational time while retaining optimisation solution accuracy through the use of surrogates in a parallel computing environment. The major contribution of the paper is in the application of surrogate-based optimisation for geoscientific models which can in the future help in a better understanding of paleoclimate and geomorphology.