Search

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

Food computing is both important and challenging in computer vision (CV). It significantly contributes to the development of CV algorithms due to its frequent presence in datasets across various applications, ranging from classification and instance segmentation to 3D reconstruction. The polymorphic shapes and textures of food, coupled with high variation in forms and vast multimodal information, including language descriptions and nutritional data, make food computing a complex and demanding task for modern CV algorithms. 3D food modeling is a new frontier for addressing food-related problems, due to its inherent capability to deal with random camera views and its straightforward representation for calculating food portion size. However, the primary hurdle in the development of algorithms for food object analysis is the lack of nutrition values in existing 3D datasets. Moreover, in the broader field of 3D research, there is a critical need for domain-specific test datasets. To bridge the gap between general 3D vision and food computing research, we propose MetaFood3D. This dataset consists of 637 meticulously labeled 3D food objects across 108 categories, featuring detailed nutrition information, weight, and food codes linked to a comprehensive nutrition database. The dataset emphasizes intra-class diversity and includes rich modalities such as textured mesh files, RGB-D videos, and segmentation masks. Experimental results demonstrate our dataset's significant potential for improving algorithm performance, highlight the challenging gap between video captures and 3D scanned data, and show the strength of the MetaFood3D dataset in high-quality data generation, simulation, and augmentation., Comment: Dataset is coming soon

Current strategies for solving image-based inverse problems apply latent diffusion models to perform posterior sampling.However, almost all approaches make no explicit attempt to explore the solution space, instead drawing only a single sample from a Gaussian distribution from which to generate their solution. In this paper, we introduce a particle-filtering-based framework for a nonlinear exploration of the solution space in the initial stages of reverse SDE methods. Our proposed particle-filtering-based latent diffusion (PFLD) method and proposed problem formulation and framework can be applied to any diffusion-based solution for linear or nonlinear inverse problems. Our experimental results show that PFLD outperforms the SoTA solver PSLD on the FFHQ-1K and ImageNet-1K datasets on inverse problem tasks of super resolution, Gaussian debluring and inpainting., Comment: Mohammad Hadi Sepanj, Nicholas Pellegrino, and Chris Czarnecki contributed equally

Autonomous vehicles require highly sophisticated decision-making to determine their motion. This paper describes how such functionality can be achieved with a practical rule engine learned from expert driving decisions. We propose an algorithm to create and maintain a rule-based behaviour planner, using a two-layer rule-based theory. The first layer determines a set of feasible parametrized behaviours, given the perceived state of the environment. From these, a resolution function chooses the most conservative high-level maneuver. The second layer then reconciles the parameters into a single behaviour. To demonstrate the practicality of our approach, we report results of its implementation in a level-3 autonomous vehicle and its field test in an urban environment., Comment: Use https://link.springer.com/chapter/10.1007/978-3-031-21541-4_17 for citations

Ellipse estimation is an important topic in food image processing because it can be leveraged to parameterize plates and bowls, which in turn can be used to estimate camera view angles and food portion sizes. Automatically detecting the elliptical rim of plates and bowls and estimating their ellipse parameters for data "in-the-wild" is challenging: diverse camera angles and plate shapes could have been used for capture, noisy background, multiple non-uniform plates and bowls in the image could be present. Recent advancements in foundational models offer promising capabilities for zero-shot semantic understanding and object segmentation. However, the output mask boundaries for plates and bowls generated by these models often lack consistency and precision compared to traditional ellipse fitting methods. In this paper, we combine ellipse fitting with semantic information extracted by zero-shot foundational models and propose WildEllipseFit, a method to detect and estimate the elliptical rim for plate and bowl. Evaluation on the proposed Yummly-ellipse dataset demonstrates its efficacy and zero-shot capability in real-world scenarios.

Monitoring dietary intake is a crucial aspect of promoting healthy living. In recent years, advances in computer vision technology have facilitated dietary intake monitoring through the use of images and depth cameras. However, the current state-of-the-art image-based food portion estimation algorithms assume that users take images of their meals one or two times, which can be inconvenient and fail to capture food items that are not visible from a top-down perspective, such as ingredients submerged in a stew. To address these limitations, we introduce an innovative solution that utilizes stationary user-facing cameras to track food items on utensils, not requiring any change of camera perspective after installation. The shallow depth of utensils provides a more favorable angle for capturing food items, and tracking them on the utensil's surface offers a significantly more accurate estimation of dietary intake without the need for post-meal image capture. The system is reliable for estimation of nutritional content of liquid-solid heterogeneous mixtures such as soups and stews. Through a series of experiments, we demonstrate the exceptional potential of our method as a non-invasive, user-friendly, and highly accurate dietary intake monitoring tool.

In stars that lie on the main sequence in the Hertzsprung Russel diagram, like our sun, hydrogen is fused to helium in a number of nuclear reaction chains and series, such as the proton-proton chain and the carbon-nitrogen-oxygen cycles. Precisely determined thermonuclear rates of these reactions lie at the foundation of the standard solar model. This review, the third decadal evaluation of the nuclear physics of hydrogen-burning stars, is motivated by the great advances made in recent years by solar neutrino observatories, putting experimental knowledge of the proton-proton chain neutrino fluxes in the few-percent precision range. The basis of the review is a one-week community meeting held in July 2022 in Berkeley, California, and many subsequent digital meetings and exchanges. Each of the relevant reactions of solar and quiescent stellar hydrogen burning is reviewed here, from both theoretical and experimental perspectives. Recommendations for the state of the art of the astrophysical S-factor and its uncertainty are formulated for each of them. Several other topics of paramount importance for the solar model are reviewed, as well: recent and future neutrino experiments, electron screening, radiative opacities, and current and upcoming experimental facilities. In addition to reaction-specific recommendations, also general recommendations are formed., Comment: 85 pages, 15 figures. To be submitted to Reviews of Modern Physics

With the increasing presence of autonomous vehicles (AVs) on public roads, developing robust control strategies to navigate the uncertainty of human-driven vehicles (HVs) is crucial. This paper introduces an advanced method for modeling HV behavior, combining a first-principles model with Gaussian process (GP) learning to enhance velocity prediction accuracy and provide a measurable uncertainty. We validated this innovative HV model using real-world data from field experiments and applied it to develop a GP-enhanced model predictive control (GP-MPC) strategy. This strategy aims to improve safety in mixed vehicle platoons by integrating uncertainty assessment into distance constraints. Comparative simulation studies with a conventional model predictive control (MPC) approach demonstrated that our GP-MPC strategy ensures more reliable safe distancing and fosters efficient vehicular dynamics, achieving notably higher speeds within the platoon. By incorporating a sparse GP technique in HV modeling and adopting a dynamic GP prediction within the MPC framework, we significantly reduced the computation time of GP-MPC, marking it only 4.6% higher than that of the conventional MPC. This represents a substantial improvement, making the process about 100 times faster than our preliminary work without these approximations. Our findings underscore the effectiveness of learning-based HV modeling in enhancing both safety and operational efficiency in mixed-traffic environments, paving the way for more harmonious AV-HV interactions., Comment: in IEEE Transactions on Intelligent Transportation Systems, 2024

While Neural Networks (NNs) have surpassed human accuracy in image classification on ImageNet, they often lack robustness against image corruption, i.e., corruption robustness. Yet such robustness is seemingly effortless for human perception. In this paper, we propose visually-continuous corruption robustness (VCR) -- an extension of corruption robustness to allow assessing it over the wide and continuous range of changes that correspond to the human perceptive quality (i.e., from the original image to the full distortion of all perceived visual information), along with two novel human-aware metrics for NN evaluation. To compare VCR of NNs with human perception, we conducted extensive experiments on 14 commonly used image corruptions with 7,718 human participants and state-of-the-art robust NN models with different training objectives (e.g., standard, adversarial, corruption robustness), different architectures (e.g., convolution NNs, vision transformers), and different amounts of training data augmentation. Our study showed that: 1) assessing robustness against continuous corruption can reveal insufficient robustness undetected by existing benchmarks; as a result, 2) the gap between NN and human robustness is larger than previously known; and finally, 3) some image corruptions have a similar impact on human perception, offering opportunities for more cost-effective robustness assessments. Our validation set with 14 image corruptions, human robustness data, and the evaluation code is provided as a toolbox and a benchmark.

This paper addresses motion forecasting in multi-agent environments, pivotal for ensuring safety of autonomous vehicles. Traditional as well as recent data-driven marginal trajectory prediction methods struggle to properly learn non-linear agent-to-agent interactions. We present SSL-Interactions that proposes pretext tasks to enhance interaction modeling for trajectory prediction. We introduce four interaction-aware pretext tasks to encapsulate various aspects of agent interactions: range gap prediction, closest distance prediction, direction of movement prediction, and type of interaction prediction. We further propose an approach to curate interaction-heavy scenarios from datasets. This curated data has two advantages: it provides a stronger learning signal to the interaction model, and facilitates generation of pseudo-labels for interaction-centric pretext tasks. We also propose three new metrics specifically designed to evaluate predictions in interactive scenes. Our empirical evaluations indicate SSL-Interactions outperforms state-of-the-art motion forecasting methods quantitatively with up to 8% improvement, and qualitatively, for interaction-heavy scenarios., Comment: Accepted at IV-2024. 13 pages, 5 figures

We consider the problem of cross-sensor domain adaptation in the context of LiDAR-based 3D object detection and propose Stationary Object Aggregation Pseudo-labelling (SOAP) to generate high quality pseudo-labels for stationary objects. In contrast to the current state-of-the-art in-domain practice of aggregating just a few input scans, SOAP aggregates entire sequences of point clouds at the input level to reduce the sensor domain gap. Then, by means of what we call quasi-stationary training and spatial consistency post-processing, the SOAP model generates accurate pseudo-labels for stationary objects, closing a minimum of 30.3% domain gap compared to few-frame detectors. Our results also show that state-of-the-art domain adaptation approaches can achieve even greater performance in combination with SOAP, in both the unsupervised and semi-supervised settings., Comment: Accepted by WACV 2024

Driving Automation Systems (DAS) are subject to complex road environments and vehicle behaviors and increasingly rely on sophisticated sensors and Artificial Intelligence (AI). These properties give rise to unique safety faults stemming from specification insufficiencies and technological performance limitations, where sensors and AI introduce errors that vary in magnitude and temporal patterns, posing potential safety risks. The Safety of the Intended Functionality (SOTIF) standard emerges as a promising framework for addressing these concerns, focusing on scenario-based analysis to identify hazardous behaviors and their causes. Although the current standard provides a basic cause-and-effect model and high-level process guidance, it lacks concepts required to identify and evaluate hazardous errors, especially within the context of AI. This paper introduces two key contributions to bridge this gap. First, it defines the SOTIF Temporal Error and Failure Model (STEAM) as a refinement of the SOTIF cause-and-effect model, offering a comprehensive system-design perspective. STEAM refines error definitions, introduces error sequences, and classifies them as error sequence patterns, providing particular relevance to systems employing advanced sensors and AI. Second, this paper proposes the Model-based SOTIF Analysis of Failures and Errors (MoSAFE) method, which allows instantiating STEAM based on system-design models by deriving hazardous error sequence patterns at module level from hazardous behaviors at vehicle level via weakest precondition reasoning. Finally, the paper presents a case study centered on an automated speed-control feature, illustrating the practical applicability of the refined model and the MoSAFE method in addressing complex safety challenges in DAS., Comment: 23 pages, 13 figures, 5 tables

Skin cancer is the most common type of cancer in the United States and is estimated to affect one in five Americans. Recent advances have demonstrated strong performance on skin cancer detection, as exemplified by state of the art performance in the SIIM-ISIC Melanoma Classification Challenge; however these solutions leverage ensembles of complex deep neural architectures requiring immense storage and compute costs, and therefore may not be tractable. A recent movement for TinyML applications is integrating Double-Condensing Attention Condensers (DC-AC) into a self-attention neural network backbone architecture to allow for faster and more efficient computation. This paper explores leveraging an efficient self-attention structure to detect skin cancer in skin lesion images and introduces a deep neural network design with DC-AC customized for skin cancer detection from skin lesion images. The final model is publicly available as a part of a global open-source initiative dedicated to accelerating advancement in machine learning to aid clinicians in the fight against cancer. Future work of this research includes iterating on the design of the selected network architecture and refining the approach to generalize to other forms of cancer.

We clarify two issues related to the so-called $D$-term in matrix elements of the energy-momentum tensor. First, we show that in a stable system, the $D$-term can have either sign, contrary to claims that it must be negative. Second, we demonstrate a logarithmic enhancement of the $\mathcal{\alpha}$ correction to the $D$-term in any state of the hydrogen atom. We contrast this enhancement with the Lamb shift where it is present only in S-states.

StarCraft II is one of the most challenging simulated reinforcement learning environments; it is partially observable, stochastic, multi-agent, and mastering StarCraft II requires strategic planning over long time horizons with real-time low-level execution. It also has an active professional competitive scene. StarCraft II is uniquely suited for advancing offline RL algorithms, both because of its challenging nature and because Blizzard has released a massive dataset of millions of StarCraft II games played by human players. This paper leverages that and establishes a benchmark, called AlphaStar Unplugged, introducing unprecedented challenges for offline reinforcement learning. We define a dataset (a subset of Blizzard's release), tools standardizing an API for machine learning methods, and an evaluation protocol. We also present baseline agents, including behavior cloning, offline variants of actor-critic and MuZero. We improve the state of the art of agents using only offline data, and we achieve 90% win rate against previously published AlphaStar behavior cloning agent., Comment: 32 pages, 13 figures, previous version published as a NeurIPS 2021 workshop: https://openreview.net/forum?id=Np8Pumfoty

We investigate the effective Lande factor in semiconductor nanowires with strong Rashba spin-orbit coupling. Using the $\mathbf{k}\cdot\mathbf{p}$ theory and the envelope function approach we derive a conduction band Hamiltonian where the tensor $g^*$ is explicitly related to the spin-orbit coupling constant $\alpha_R$. Our model includes orbital effects from the Rashba spin-orbit term, leading to a significant enhancement of the effective Lande factor which is naturally anisotropic. For nanowires based on the low-gap, high spin-orbit coupled material InSb, we investigate the anisotropy of the effective Lande factor with respect to the magnetic field direction, exposing a twofold symmetry for the bottom gate architecture. The anisotropy results from the competition between the localization of the envelope function and the spin polarization of the electronic state, both determined by the magnetic field direction., Comment: 14 pages, 15 figures

Prevention is better than cure. This old truth applies not only to the prevention of diseases but also to the prevention of issues with AI models used in medicine. The source of malfunctioning of predictive models often lies not in the training process but reaches the data acquisition phase or design of the experiment phase. In this paper, we analyze in detail a single use case - a Kaggle competition related to the detection of abnormalities in X-ray lung images. We demonstrate how a series of simple tests for data imbalance exposes faults in the data acquisition and annotation process. Complex models are able to learn such artifacts and it is difficult to remove this bias during or after the training. Errors made at the data collection stage make it difficult to validate the model correctly. Based on this use case, we show how to monitor data and model balance (fairness) throughout the life cycle of a predictive model, from data acquisition to parity analysis of model scores.

Object re-identification (ReID) from images plays a critical role in application domains of image retrieval (surveillance, retail analytics, etc.) and multi-object tracking (autonomous driving, robotics, etc.). However, systems that additionally or exclusively perceive the world from depth sensors are becoming more commonplace without any corresponding methods for object ReID. In this work, we fill the gap by providing the first large-scale study of object ReID from point clouds and establishing its performance relative to image ReID. To enable such a study, we create two large-scale ReID datasets with paired image and LiDAR observations and propose a lightweight matching head that can be concatenated to any set or sequence processing backbone (e.g., PointNet or ViT), creating a family of comparable object ReID networks for both modalities. Run in Siamese style, our proposed point cloud ReID networks can make thousands of pairwise comparisons in real-time ($10$ Hz). Our findings demonstrate that their performance increases with higher sensor resolution and approaches that of image ReID when observations are sufficiently dense. Our strongest network trained at the largest scale achieves ReID accuracy exceeding $90\%$ for rigid objects and $85\%$ for deformable objects (without any explicit skeleton normalization). To our knowledge, we are the first to study object re-identification from real point cloud observations.

Attention-based models have been a key element of many recent breakthroughs in deep learning. Two key components of Attention are the structure of its input (which consists of keys, values and queries) and the computations by which these three are combined. In this paper we explore the space of models that share said input structure but are not restricted to the computations of Attention. We refer to this space as Keys-Values-Queries (KVQ) Space. Our goal is to determine whether there are any other stackable models in KVQ Space that Attention cannot efficiently approximate, which we can implement with our current deep learning toolbox and that solve problems that are interesting to the community. Maybe surprisingly, the solution to the standard least squares problem satisfies these properties. A neural network module that is able to compute this solution not only enriches the set of computations that a neural network can represent but is also provably a strict generalisation of Linear Attention. Even more surprisingly the computational complexity of this module is exactly the same as that of Attention, making it a suitable drop in replacement. With this novel connection between classical machine learning (least squares) and modern deep learning (Attention) established we justify a variation of our model which generalises regular Attention in the same way. Both new modules are put to the test an a wide spectrum of tasks ranging from few-shot learning to policy distillation that confirm their real-worlds applicability.

A central design problem in game theoretic analysis is the estimation of the players' utilities. In many real-world interactive situations of human decision making, including human driving, the utilities are multi-objective in nature; therefore, estimating the parameters of aggregation, i.e., mapping of multi-objective utilities to a scalar value, becomes an essential part of game construction. However, estimating this parameter from observational data introduces several challenges due to a host of unobservable factors, including the underlying modality of aggregation and the possibly boundedly rational behaviour model that generated the observation. Based on the concept of rationalisability, we develop algorithms for estimating multi-objective aggregation parameters for two common aggregation methods, weighted and satisficing aggregation, and for both strategic and non-strategic reasoning models. Based on three different datasets, we provide insights into how human drivers aggregate the utilities of safety and progress, as well as the situational dependence of the aggregation process. Additionally, we show that irrespective of the specific solution concept used for solving the games, a data-driven estimation of utility aggregation significantly improves the predictive accuracy of behaviour models with respect to observed human behaviour.

Predicting the future motion of road agents is a critical task in an autonomous driving pipeline. In this work, we address the problem of generating a set of scene-level, or joint, future trajectory predictions in multi-agent driving scenarios. To this end, we propose FJMP, a Factorized Joint Motion Prediction framework for multi-agent interactive driving scenarios. FJMP models the future scene interaction dynamics as a sparse directed interaction graph, where edges denote explicit interactions between agents. We then prune the graph into a directed acyclic graph (DAG) and decompose the joint prediction task into a sequence of marginal and conditional predictions according to the partial ordering of the DAG, where joint future trajectories are decoded using a directed acyclic graph neural network (DAGNN). We conduct experiments on the INTERACTION and Argoverse 2 datasets and demonstrate that FJMP produces more accurate and scene-consistent joint trajectory predictions than non-factorized approaches, especially on the most interactive and kinematically interesting agents. FJMP ranks 1st on the multi-agent test leaderboard of the INTERACTION dataset., Comment: CVPR 2023

Explainable AI (XAI) methods are frequently applied to obtain qualitative insights about deep models' predictions. However, such insights need to be interpreted by a human observer to be useful. In this paper, we aim to use explanations directly to make decisions without human observers. We adopt two gradient-based explanation methods, Integrated Gradients (IG) and backprop, for the task of 3D object detection. Then, we propose a set of quantitative measures, named Explanation Concentration (XC) scores, that can be used for downstream tasks. These scores quantify the concentration of attributions within the boundaries of detected objects. We evaluate the effectiveness of XC scores via the task of distinguishing true positive (TP) and false positive (FP) detected objects in the KITTI and Waymo datasets. The results demonstrate an improvement of more than 100\% on both datasets compared to other heuristics such as random guesses and the number of LiDAR points in the bounding box, raising confidence in XC's potential for application in more use cases. Our results also indicate that computationally expensive XAI methods like IG may not be more valuable when used quantitatively compare to simpler methods., Comment: Accepted at 1st Workshop on eXplainable AI approaches for debugging and diagnosis (XAI4Debugging@NeurIPS2021)

In adversarial machine learning, the popular $\ell_\infty$ threat model has been the focus of much previous work. While this mathematical definition of imperceptibility successfully captures an infinite set of additive image transformations that a model should be robust to, this is only a subset of all transformations which leave the semantic label of an image unchanged. Indeed, previous work also considered robustness to spatial attacks as well as other semantic transformations; however, designing defense methods against the composition of spatial and $\ell_{\infty}$ perturbations remains relatively underexplored. In the following, we improve the understanding of this seldom investigated compositional setting. We prove theoretically that no linear classifier can achieve more than trivial accuracy against a composite adversary in a simple statistical setting, illustrating its difficulty. We then investigate how state-of-the-art $\ell_{\infty}$ defenses can be adapted to this novel threat model and study their performance against compositional attacks. We find that our newly proposed TRADES$_{\text{All}}$ strategy performs the strongest of all. Analyzing its logit's Lipschitz constant for RT transformations of different sizes, we find that TRADES$_{\text{All}}$ remains stable over a wide range of RT transformations with and without $\ell_\infty$ perturbations., Comment: 16 pages, 5 figures, and 3 tables

Imagine experiencing a crash as the passenger of an autonomous vehicle. Wouldn't you want to know why it happened? Current end-to-end optimizable deep neural networks (DNNs) in 3D detection, multi-object tracking, and motion forecasting provide little to no explanations about how they make their decisions. To help bridge this gap, we design an end-to-end optimizable multi-object tracking architecture and training protocol inspired by the recently proposed method of interchange intervention training (IIT). By enumerating different tracking decisions and associated reasoning procedures, we can train individual networks to reason about the possible decisions via IIT. Each network's decisions can be explained by the high-level structural causal model (SCM) it is trained in alignment with. Moreover, our proposed model learns to rank these outcomes, leveraging the promise of deep learning in end-to-end training, while being inherently interpretable.

3D object detection is an essential part of automated driving, and deep neural networks (DNNs) have achieved state-of-the-art performance for this task. However, deep models are notorious for assigning high confidence scores to out-of-distribution (OOD) inputs, that is, inputs that are not drawn from the training distribution. Detecting OOD inputs is challenging and essential for the safe deployment of models. OOD detection has been studied extensively for the classification task, but it has not received enough attention for the object detection task, specifically LiDAR-based 3D object detection. In this paper, we focus on the detection of OOD inputs for LiDAR-based 3D object detection. We formulate what OOD inputs mean for object detection and propose to adapt several OOD detection methods for object detection. We accomplish this by our proposed feature extraction method. To evaluate OOD detection methods, we develop a simple but effective technique of generating OOD objects for a given object detection model. Our evaluation based on the KITTI dataset shows that different OOD detection methods have biases toward detecting specific OOD objects. It emphasizes the importance of combined OOD detection methods and more research in this direction., Comment: Accepted at ITSC 2022

Decay rates of the positronium hydride PsH, a bound state of a proton, a positron, and two electrons, are determined for two rare channels, PsH $\to p^+ e^- \gamma$ and PsH $\to p^+ e^-$. Previous studies overestimated these rates by factors of about 2 and 700, respectively. We explain the physics underlying these wrong predictions. We confirm a range of static PsH properties, including the non-relativistic ground state energy, expectation values of inter-particle distances and their powers, and the three and four particle coalescence probabilities, using a variational method in the Gaussian basis.