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.

Agent-Based Model (ABM) validation is crucial as it helps ensuring the reliability of simulations, and causal discovery has become a powerful tool in this context. However, current causal discovery methods often face accuracy and robustness challenges when applied to complex and noisy time series data, which is typical in ABM scenarios. This study addresses these issues by proposing a Robust Cross-Validation (RCV) approach to enhance causal structure learning for ABM validation. We develop RCV-VarLiNGAM and RCV-PCMCI, novel extensions of two prominent causal discovery algorithms. These aim to reduce the impact of noise better and give more reliable causal relation results, even with high-dimensional, time-dependent data. The proposed approach is then integrated into an enhanced ABM validation framework, which is designed to handle diverse data and model structures. The approach is evaluated using synthetic datasets and a complex simulated fMRI dataset. The results demonstrate greater reliability in causal structure identification. The study examines how various characteristics of datasets affect the performance of established causal discovery methods. These characteristics include linearity, noise distribution, stationarity, and causal structure density. This analysis is then extended to the RCV method to see how it compares in these different situations. This examination helps confirm whether the results are consistent with existing literature and also reveals the strengths and weaknesses of the novel approaches. By tackling key methodological challenges, the study aims to enhance ABM validation with a more resilient valuation framework presented. These improvements increase the reliability of model-driven decision making processes in complex systems analysis.

We analyze the feasibility of cooling of classical motion of a micro- to nano-sized magnetic particle, levitated inside a hollow-core photonic crystal fiber. The cooling action is implemented by means of controlling the phase of one of the counter-propagating fiber guided waves. Direct imaging of the particle's position, followed by the subsequent updating of the control laser's phase leads to Stokes type of cooling force. We provide estimates of cooling efficiency and final achievable temperature, taking into account thermal and detection noise sources. Our results bring forward an important step towards using trapped micro-magnets in sensing, testing the fundamental physics and preparing the quantum states of magnetization.

We provide an exact analytical solution for the time evolution of an initially inverted ensemble of identical $N$ two-level quantum emitters, i.e. to the Dicke superradiance problem. It is asumed that the system undergoes collective decay with a symmetric collapse operator, thus reducing the time evolution of the density operator to the fully symmetric subspace spanned by $N+1$ Dicke states. In this collective basis, the system relaxes from the fully excited state to the zero excitation ground state as a full mixture of Dicke states. The solution derived here is exact for any value of $N$ and any time time $t$ during the evolution.

This study presents BanStereoSet, a dataset designed to evaluate stereotypical social biases in multilingual LLMs for the Bangla language. In an effort to extend the focus of bias research beyond English-centric datasets, we have localized the content from the StereoSet, IndiBias, and Kamruzzaman et. al.'s datasets, producing a resource tailored to capture biases prevalent within the Bangla-speaking community. Our BanStereoSet dataset consists of 1,194 sentences spanning 9 categories of bias: race, profession, gender, ageism, beauty, beauty in profession, region, caste, and religion. This dataset not only serves as a crucial tool for measuring bias in multilingual LLMs but also facilitates the exploration of stereotypical bias across different social categories, potentially guiding the development of more equitable language technologies in Bangladeshi contexts. Our analysis of several language models using this dataset indicates significant biases, reinforcing the necessity for culturally and linguistically adapted datasets to develop more equitable language technologies.

As the deployment of large language models (LLMs) expands, there is an increasing demand for personalized LLMs. One method to personalize and guide the outputs of these models is by assigning a persona -- a role that describes the expected behavior of the LLM (e.g., a man, a woman, an engineer). This study investigates whether an LLM's understanding of social norms varies across assigned personas. Ideally, the perception of a social norm should remain consistent regardless of the persona, since acceptability of a social norm should be determined by the region the norm originates from, rather than by individual characteristics such as gender, body size, or race. A norm is universal within its cultural context. In our research, we tested 36 distinct personas from 12 sociodemographic categories (e.g., age, gender, beauty) across four different LLMs. We find that LLMs' cultural norm interpretation varies based on the persona used and the norm interpretation also varies within a sociodemographic category (e.g., a fat person and a thin person as in physical appearance group) where an LLM with the more socially desirable persona (e.g., a thin person) interprets social norms more accurately than with the less socially desirable persona (e.g., a fat person). We also discuss how different types of social biases may contribute to the results that we observe., Comment: Preprint, Under Review

Despite the recent advance in self-supervised representations, unsupervised phonetic segmentation remains challenging. Most approaches focus on improving phonetic representations with self-supervised learning, with the hope that the improvement can transfer to phonetic segmentation. In this paper, contrary to recent approaches, we show that peak detection on Mel spectrograms is a strong baseline, better than many self-supervised approaches. Based on this finding, we propose a simple hidden Markov model that uses self-supervised representations and features at the boundaries for phone segmentation. Our results demonstrate consistent improvements over previous approaches, with a generalized formulation allowing versatile design adaptations., Comment: Accepted to SLT 2024

This work presents WarmSwap, a novel provider-side cold-start optimization for serverless computing. This optimization reduces cold-start time when booting and loading dependencies at runtime inside a function container. Previous approaches to the optimization of cold starts tend to fall into two categories: optimizing the infrastructure of serverless computing to benefit all serverless functions; or function-specific tuning for individual serverless functions. In contrast, WarmSwap offers a broad middle ground, which optimizes entire categories of serverless functions. WarmSwap eliminates the need to initialize middleware or software dependencies when launching a new serverless container, by migrating a pre-initialized live dependency image to the new function instance. WarmSwap respects the provider's cache constraints, as a single pre-warmed dependency image in the cache is shared among all serverless functions requiring that software dependency image. WarmSwap has been tested on seven representative functions from FunctionBench. In those tests, WarmSwap accelerates dependency loading for serverless functions with large dependency requirements by a factor ranging from 2.2 to 3.2. Simulation experiments using Azure traces indicate that WarmSwap can save 88\% of optimization space when sharing a dependency image among ten different functions., Comment: 15 pages, 7 figures

Signed graphs are equipped with both positive and negative edge weights, encoding pairwise correlations as well as anti-correlations in data. A balanced signed graph has no cycles of odd number of negative edges. Laplacian of a balanced signed graph has eigenvectors that map simply to ones in a similarity-transformed positive graph Laplacian, thus enabling reuse of well-studied spectral filters designed for positive graphs. We propose a fast method to learn a balanced signed graph Laplacian directly from data. Specifically, for each node $i$, to determine its polarity $\beta_i \in \{-1,1\}$ and edge weights $\{w_{i,j}\}_{j=1}^N$, we extend a sparse inverse covariance formulation based on linear programming (LP) called CLIME, by adding linear constraints to enforce ``consistent" signs of edge weights $\{w_{i,j}\}_{j=1}^N$ with the polarities of connected nodes -- i.e., positive/negative edges connect nodes of same/opposing polarities. For each LP, we adapt projections on convex set (POCS) to determine a suitable CLIME parameter $\rho > 0$ that guarantees LP feasibility. We solve the resulting LP via an off-the-shelf LP solver in $\mathcal{O}(N^{2.055})$. Experiments on synthetic and real-world datasets show that our balanced graph learning method outperforms competing methods and enables the use of spectral filters and graph convolutional networks (GCNs) designed for positive graphs on signed graphs., Comment: 5 pages, 1 figure. Submitted to ICASSP 2025

We present a sample of 50 H-alpha detected broad-line active galactic nuclei (BLAGN) at redshifts 3.50), independent of the contributions of emission lines to the broadband photometry. We construct the black hole (BH) mass function at 3.5

An image denoiser can be used for a wide range of restoration problems via the Plug-and-Play (PnP) architecture. In this paper, we propose a general framework to build an interpretable graph-based deep denoiser (GDD) by unrolling a solution to a maximum a posteriori (MAP) problem equipped with a graph Laplacian regularizer (GLR) as signal prior. Leveraging a recent theorem showing that any (pseudo-)linear denoiser $\boldsymbol \Psi$, under mild conditions, can be mapped to a solution of a MAP denoising problem regularized using GLR, we first initialize a graph Laplacian matrix $\mathbf L$ via truncated Taylor Series Expansion (TSE) of $\boldsymbol \Psi^{-1}$. Then, we compute the MAP linear system solution by unrolling iterations of the conjugate gradient (CG) algorithm into a sequence of neural layers as a feed-forward network -- one that is amenable to parameter tuning. The resulting GDD network is "graph-interpretable", low in parameter count, and easy to initialize thanks to $\mathbf L$ derived from a known well-performing denoiser $\boldsymbol \Psi$. Experimental results show that GDD achieves competitive image denoising performance compared to competitors, but employing far fewer parameters, and is more robust to covariate shift.

Leavitt path algebras, which are algebras associated to directed graphs, were first introduced about 20 years ago. They have strong connections to such topics as symbolic dynamics, operator algebras, non-commutative geometry, representation theory, and even chip firing. In this article we invite the reader to sneak a peek at these fascinating algebras and their interplay with several seemingly disparate parts of mathematics.

Multimodal large language models (LLMs) have achieved notable success across various domains, while research in the medical field has largely focused on unimodal images. Meanwhile, current general-domain multimodal models for videos still lack the capabilities to understand and engage in conversations about surgical videos. One major contributing factor is the absence of datasets in the surgical field. In this paper, we create a new dataset, Surg-QA, consisting of 102,000 surgical video-instruction pairs, the largest of its kind so far. To build such a dataset, we propose a novel two-stage question-answer generation pipeline with LLM to learn surgical knowledge in a structured manner from the publicly available surgical lecture videos. The pipeline breaks down the generation process into two stages to significantly reduce the task complexity, allowing us to use a more affordable, locally deployed open-source LLM than the premium paid LLM services. It also mitigates the risk of LLM hallucinations during question-answer generation, thereby enhancing the overall quality of the generated data. We further train LLaVA-Surg, a novel vision-language conversational assistant capable of answering open-ended questions about surgical videos, on this Surg-QA dataset, and conduct comprehensive evaluations on zero-shot surgical video question-answering tasks. We show that LLaVA-Surg significantly outperforms all previous general-domain models, demonstrating exceptional multimodal conversational skills in answering open-ended questions about surgical videos. We will release our code, model, and the instruction-tuning dataset.

MPI is the de facto standard for parallel computing on a cluster of computers. Checkpointing is an important component in any strategy for software resilience and for long-running jobs that must be executed by chaining together time-bounded resource allocations. This work solves an old problem: a practical and general algorithm for transparent checkpointing of MPI that is both efficient and compatible with most of the latest network software. Transparent checkpointing is attractive due to its generality and ease of use for most MPI application developers. Earlier efforts at transparent checkpointing for MPI, one decade ago, had two difficult problems: (i) by relying on a specific MPI implementation tied to a specific network technology; and (ii) by failing to demonstrate sufficiently low runtime overhead. Problem (i) (network dependence) was already solved in 2019 by MANA's introduction of split processes. Problem (ii) (efficient runtime overhead) is solved in this work. This paper introduces an approach that avoids these limitations, employing a novel topological sort to algorithmically determine a safe future synchronization point. The algorithm is valid for both blocking and non-blocking collective communication in MPI. We demonstrate the efficacy and scalability of our approach through both micro-benchmarks and a set of five real-world MPI applications, notably including the widely used VASP (Vienna Ab Initio Simulation Package), which is responsible for 11% of the workload on the Perlmutter supercomputer at Lawrence Berkley National Laboratory. VASP was previously cited as a special challenge for checkpointing, in part due to its multi-algorithm codes., Comment: 22 pages, 9 figures and 1 table, accepted to IEEE Cluster'24

User-generated videos (UGVs) uploaded from mobile phones to social media sites like YouTube and TikTok are short and non-repetitive. We summarize a transitory UGV into several keyframes in linear time via fast graph sampling based on Gershgorin disc alignment (GDA). Specifically, we first model a sequence of $N$ frames in a UGV as an $M$-hop path graph $\mathcal{G}^o$ for $M \ll N$, where the similarity between two frames within $M$ time instants is encoded as a positive edge based on feature similarity. Towards efficient sampling, we then "unfold" $\mathcal{G}^o$ to a $1$-hop path graph $\mathcal{G}$, specified by a generalized graph Laplacian matrix $\mathcal{L}$, via one of two graph unfolding procedures with provable performance bounds. We show that maximizing the smallest eigenvalue $\lambda_{\min}(\mathbf{B})$ of a coefficient matrix $\mathbf{B} = \textit{diag}\left(\mathbf{h}\right) + \mu \mathcal{L}$, where $\mathbf{h}$ is the binary keyframe selection vector, is equivalent to minimizing a worst-case signal reconstruction error. We maximize instead the Gershgorin circle theorem (GCT) lower bound $\lambda^-_{\min}(\mathbf{B})$ by choosing $\mathbf{h}$ via a new fast graph sampling algorithm that iteratively aligns left-ends of Gershgorin discs for all graph nodes (frames). Extensive experiments on multiple short video datasets show that our algorithm achieves comparable or better video summarization performance compared to state-of-the-art methods, at a substantially reduced complexity., Comment: 13 pages, 5 figures

We present the BoRG-JWST survey, a combination of two JWST Cycle 1 programs aimed at obtaining NIRSpec spectroscopy of representative, UV-bright $75$, highlighting the large abundance of high-redshift galaxies even in individual WFC3 pointings. The primary sample span an absolute magnitude range $-20.47$ sources currently known and comparable to the brightest sources at $z>10$. Prominent [O III]+H$\beta$ lines are found across the full sample, while a stack of sources reveals a plethora of other rest-optical lines and additional rest-UV C III]1909 \r{A} emission. Despite their luminosities, none of the low-resolution spectra display evidence for Type 1 AGN activity based on a search for broad-line emission. Lastly, we present a spectroscopic data release of 188 confirmed $0.5\lesssim z\lesssim5.0$ sources from filler MSA observations, highlighting the legacy value of the survey and a representative benchmark for comparisons to deep field observations., Comment: Submitted to ApJ, comments welcome

We consider the problem of counting and classifying symmetric informationally complete positive operator-valued measures (SICs or SIC-POVMs), that is, sets of $d^2$ equiangular lines in $\mathbb{C}^d$. For $4 \leq d \leq 90$, we show the number of known equivalence classes of Weyl--Heisenberg covariant SICs in dimension $d$ equals the cardinality of the ideal class monoid of (not necessarily invertible) ideal classes in the real quadratic order of discriminant $(d+1)(d-3)$. Equivalently, this is the number of $\mathbf{GL}_2(\mathbb{Z})$ conjugacy classes in $\mathbf{SL}_2(\mathbb{Z})$ of trace $d-1$. We conjecture the equality extends to all $d \geq 4$. We prove that this conjecture implies more that one equivalence class of Weyl--Heisenberg covariant SICs for every $d > 22$. We refine the "class field hypothesis" of Appleby, Flammia, McConnell, and Yard (arXiv:1604.06098) to predict the exact class field generated by the ratios of vector entries for the equiangular lines defining a Weyl--Heisenberg covariant SIC. The class fields conjecturally associated to SICs in dimension $d$ have a natural partial order under inclusion; we show the natural inclusions of these fields in the partial order are strict, except in a small family of cases., Comment: 49 pages, 3 tables

Secure and efficient multi-user access mechanisms are increasingly important for the growing number of Internet of Things (IoT) devices being used today. Kerberos is a well-known and time-tried security authentication and access control system for distributed systems wherein many users securely access various distributed services. Traditionally, these services are software applications or devices, such as printers. However, Kerberos is not directly suitable for IoT devices due to its relatively heavy-weight protocols and the resource-constrained nature of the devices. This paper presents KESIC, a system that enables efficient and secure multi-user access for IoT devices. KESIC aims to facilitate mutual authentication of IoT devices and users via Kerberos without modifying the latter's protocols. To facilitate that, KESIC includes a special Kerberized service, called IoT Server, that manages access to IoT devices. KESIC presents two protocols for secure and comprehensive multi-user access system for two types of IoT devices: general and severely power constrained. In terms of performance, KESIC onsumes $\approx~47$ times less memory, and incurs $\approx~135$ times lower run-time overhead than Kerberos.

Generic deep learning (DL) networks for image restoration like denoising and interpolation lack mathematical interpretability, require voluminous training data to tune a large parameter set, and are fragile in the face of covariate shift. To address these shortcomings, we build interpretable networks by unrolling variants of a graph-based optimization algorithm of different complexities. Specifically, for a general linear image formation model, we first formulate a convex quadratic programming (QP) problem with a new $\ell_2$-norm graph smoothness prior called gradient graph Laplacian regularizer (GGLR) that promotes piecewise planar (PWP) signal reconstruction. To solve the posed unconstrained QP problem, instead of computing a linear system solution straightforwardly, we introduce a variable number of auxiliary variables and correspondingly design a family of ADMM algorithms. We then unroll them into variable-complexity feed-forward networks, amenable to parameter tuning via back-propagation. More complex unrolled networks require more labeled data to train more parameters, but have better overall performance. The unrolled networks contain periodic insertions of a graph learning module, akin to a self-attention mechanism in a transformer architecture, to learn pairwise similarity structure inherent in data. Experimental results show that our unrolled networks perform competitively to generic DL networks in image restoration quality while using only a tiny fraction of parameters, and demonstrate improved robustness to covariate shift.

Many recent studies have investigated social biases in LLMs but brand bias has received little attention. This research examines the biases exhibited by LLMs towards different brands, a significant concern given the widespread use of LLMs in affected use cases such as product recommendation and market analysis. Biased models may perpetuate societal inequalities, unfairly favoring established global brands while marginalizing local ones. Using a curated dataset across four brand categories, we probe the behavior of LLMs in this space. We find a consistent pattern of bias in this space -- both in terms of disproportionately associating global brands with positive attributes and disproportionately recommending luxury gifts for individuals in high-income countries. We also find LLMs are subject to country-of-origin effects which may boost local brand preference in LLM outputs in specific contexts., Comment: Accepted at EMNLP-2024 (main)

Persona assignment has become a common strategy for customizing LLM use to particular tasks and contexts. In this study, we explore how evaluation of different nations change when LLMs are assigned specific nationality personas. We assign 193 different nationality personas (e.g., an American person) to four LLMs and examine how the LLM evaluations (or ''perceptions'')of countries change. We find that all LLM-persona combinations tend to favor Western European nations, though nation-personas push LLM behaviors to focus more on and treat the nation-persona's own region more favorably. Eastern European, Latin American, and African nations are treated more negatively by different nationality personas. We additionally find that evaluations by nation-persona LLMs of other nations correlate with human survey responses but fail to match the values closely. Our study provides insight into how biases and stereotypes are realized within LLMs when adopting different national personas. In line with the ''Blueprint for an AI Bill of Rights'', our findings underscore the critical need for developing mechanisms to ensure that LLM outputs promote fairness and avoid over-generalization., Comment: Pre-print, Under review

Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. Recently, pose-conditioned diffusion models have led to significant progress by extracting 3D information from 2D foundation models, but these methods are limited by the lack of scene-level training data. Common dataset choices either consist of isolated objects (Objaverse), or of object-centric scenes with limited pose distributions (DTU, CO3D). In this paper, we create a large-scale scene-level dataset from Internet photo collections, called MegaScenes, which contains over 100K structure from motion (SfM) reconstructions from around the world. Internet photos represent a scalable data source but come with challenges such as lighting and transient objects. We address these issues to further create a subset suitable for the task of NVS. Additionally, we analyze failure cases of state-of-the-art NVS methods and significantly improve generation consistency. Through extensive experiments, we validate the effectiveness of both our dataset and method on generating in-the-wild scenes. For details on the dataset and code, see our project page at https://megascenes.github.io., Comment: Accepted at ECCV 2024. Our project page is at https://megascenes.github.io

This data curation work introduces the first large-scale dataset of radial k-space and DICOM data for breast DCE-MRI acquired in diagnostic breast MRI exams. Our dataset includes case-level labels indicating patient age, menopause status, lesion status (negative, benign, and malignant), and lesion type for each case. The public availability of this dataset and accompanying reconstruction code will support research and development of fast and quantitative breast image reconstruction and machine learning methods.

We build interpretable and lightweight transformer-like neural networks by unrolling iterative optimization algorithms that minimize graph smoothness priors -- the quadratic graph Laplacian regularizer (GLR) and the $\ell_1$-norm graph total variation (GTV) -- subject to an interpolation constraint. The crucial insight is that a normalized signal-dependent graph learning module amounts to a variant of the basic self-attention mechanism in conventional transformers. Unlike "black-box" transformers that require learning of large key, query and value matrices to compute scaled dot products as affinities and subsequent output embeddings, resulting in huge parameter sets, our unrolled networks employ shallow CNNs to learn low-dimensional features per node to establish pairwise Mahalanobis distances and construct sparse similarity graphs. At each layer, given a learned graph, the target interpolated signal is simply a low-pass filtered output derived from the minimization of an assumed graph smoothness prior, leading to a dramatic reduction in parameter count. Experiments for two image interpolation applications verify the restoration performance, parameter efficiency and robustness to covariate shift of our graph-based unrolled networks compared to conventional transformers.

We consider a weakly supervised learning problem called Learning from Label Proportions (LLP), where examples are grouped into ``bags'' and only the average label within each bag is revealed to the learner. We study various learning rules for LLP that achieve PAC learning guarantees for classification loss. We establish that the classical Empirical Proportional Risk Minimization (EPRM) learning rule (Yu et al., 2014) achieves fast rates under realizability, but EPRM and similar proportion matching learning rules can fail in the agnostic setting. We also show that (1) a debiased proportional square loss, as well as (2) a recently proposed EasyLLP learning rule (Busa-Fekete et al., 2023) both achieve ``optimistic rates'' (Panchenko, 2002); in both the realizable and agnostic settings, their sample complexity is optimal (up to log factors) in terms of $\epsilon, \delta$, and VC dimension., Comment: Accepted to COLT 2024. Comments welcome