Showing 1–50 of 122 results for author: Brown, A

Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Mediated Reasoning

Authors: Hans-Martin Will, Allen L. Brown Jr., Matthew Fuchs

Abstract: As "AI Scientists" emerge to drive research via the Model Context Protocol (MCP), systems relying on ephemeral scripts will fail. The sheer scale of stateful, interconnected evidence requires a machine-walkable warranty grounded in a purpose-built database architecture. Eigenius is an open-source, typed knowledge-graph DBMS built on a single premise: answering the audit question ("what do you know… ▽ More As "AI Scientists" emerge to drive research via the Model Context Protocol (MCP), systems relying on ephemeral scripts will fail. The sheer scale of stateful, interconnected evidence requires a machine-walkable warranty grounded in a purpose-built database architecture. Eigenius is an open-source, typed knowledge-graph DBMS built on a single premise: answering the audit question ("what do you know, and what is your warranty?") requires a unified kernel. By tightly coupling the type system, storage engine, and integration protocol, Eigenius turns data provenance into a structural invariant rather than a property reconstructed across subsystem boundaries. The kernel rests on three pillars: a dependent type theory woven through the core, institutions acting as strongly typed integration boundaries, and a content-addressed immutable storage layer. On this foundation, epistemic status (declared/observed/derived/verified) is enforced as a strict commit-time invariant. Cross-system translations (comorphisms) are checked at commit and materialized directly into the graph as durable, first-class resources. To eliminate O(N^2) polystore bottlenecks, shared on-chain intermediate representations (IRs) collapse multi-system translations to identity. Crucially, this architecture unifies both domains of scientific epistemology: it relies on justification logic for empirical science, while embedding a fast, in-process term checker to safely evaluate formal mathematical proofs (via Lean 4) without IPC overhead. In an end-to-end recomputation of a published Nature study from fragile scripts to a materialized evidence graph, all 52 derived conclusions hold from pinned data, surfacing four machine-checked discrepancies in the original study. △ Less

Submitted 18 August, 2026; v1 submitted 5 August, 2026; originally announced August 2026.

Comments: Minor corrections to the previous version of the manuscript

A Comparison of Two Dynamic k-d Trees

Authors: Russell A. Brown

Abstract: Two methods have been proposed for building and modifying a dynamic k-d tree. One method stores the dynamic tree as a single k-d tree and rebalances that tree by rebuilding subtrees within the tree when those subtrees become unbalanced due to insertion of a k-dimensional tuple into the tree or deletion of a tuple from the tree. A second method composes a dynamic tree as a set of static k-d trees w… ▽ More Two methods have been proposed for building and modifying a dynamic k-d tree. One method stores the dynamic tree as a single k-d tree and rebalances that tree by rebuilding subtrees within the tree when those subtrees become unbalanced due to insertion of a k-dimensional tuple into the tree or deletion of a tuple from the tree. A second method composes a dynamic tree as a set of static k-d trees whose sizes are increasing integer powers of two; this tree's balance is maintained by rebuilding a static tree within the set upon insertion or deletion of a tuple. This article describes insertion and deletion algorithms for the second method, and compares the performance of the second method to the performance of the first method. △ Less

Submitted 27 July, 2026; v1 submitted 23 July, 2026; originally announced July 2026.

Comments: 14 pages, 6 figures

Two AI Metrics Diverged: Will it Make All the Difference?

Authors: Alex Fogelson, Zachary A. Brown, Hans Gundlach, Jayson Lynch, Neil Thompson

Abstract: As exponential compute scaling continues, will the capabilities of frontier AI models outstrip what is accessible to developers on a small fixed budget? Or will capabilities converge, with "meek models inheriting the earth"? Building on Gundlach et al. (2025b), we show that the answer depends on how we value and measure AI capabilities. We discuss conventional performance measures and show that, w… ▽ More As exponential compute scaling continues, will the capabilities of frontier AI models outstrip what is accessible to developers on a small fixed budget? Or will capabilities converge, with "meek models inheriting the earth"? Building on Gundlach et al. (2025b), we show that the answer depends on how we value and measure AI capabilities. We discuss conventional performance measures and show that, while validation loss shows a shrinking gap, on other metrics frontier models grow their lead forever. Classifying performance metrics by their functional forms in relation to training (and inference) compute, we provide tight mathematical conditions for determining which metrics favor meek models, and show that bounded performance metrics always do. But careful interpretation of performance metrics is essential: we show that many common bounded metrics have closely-related counterpart metrics that are unbounded (and vice versa). Determining the apt metric in a domain is a prerequisite for policy, since bounded and unbounded metrics may suggest opposing policy responses. If a particular capability -- like software engineering, synthetic biology, or rhetorical persuasiveness -- is unbounded when measured in the terms we care about, frontier-level capability will likely be concentrated in the hands of a few wealthy actors. Conversely, if that capability is instead bounded, frontier-level capabilities proliferate through meek models into the hands of the many. △ Less

Submitted 1 July, 2026; originally announced July 2026.

Comments: Accepted into 2026 ICML Technical AI Governance Research Workshop

Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA

Authors: Sterling Huang, Abigayle Brown, Jiyoo Noh, Jiakang Xu, Wantong Huo, Kaung Myat Kyaw, Jonathan Chan

Abstract: Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus mainly on autoregressive architectures. This study examines whether LLMLingua-2 transfers effectively to diffusion large language models (DLLMs), specifically LLaDA-8B-Instruct. We evaluate GSM8K, DUC2004, and ShareGPT using 250 prompts per dataset at an approximate 50\% compression r… ▽ More Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus mainly on autoregressive architectures. This study examines whether LLMLingua-2 transfers effectively to diffusion large language models (DLLMs), specifically LLaDA-8B-Instruct. We evaluate GSM8K, DUC2004, and ShareGPT using 250 prompts per dataset at an approximate 50\% compression ratio, covering mathematical reasoning, prompt reconstruction, and summarization. Outputs from original, compressed, and reconstructed prompts are compared using exact-match accuracy, BLEU, ROUGE, and BERTScore. Results show that high semantic preservation does not necessarily ensure stable downstream behavior in diffusion models. Summarization remains relatively robust, while mathematical reasoning degrades substantially despite high semantic similarity. Reconstruction further shows that semantically similar prompts may omit reasoning-critical information needed for stable denoising. Overall, compression failures are mainly driven by information omission rather than semantic drift, suggesting that autoregressive prompt compression methods may not transfer uniformly to DLLMs. These findings motivate diffusion-aware compression strategies. △ Less

Submitted 11 July, 2026; v1 submitted 18 May, 2026; originally announced May 2026.

Comments: Accepted to appear in The 14th International Conference on Advances in Information Technology (IAIT2026)

Image-Based Whole-Heart Cardiac Flow Simulations in Health and Congenital Heart Disease

Authors: Fanwei Kong, Aaron Brown, Michael Loecher, Perry S. Choi, Lei Shi, Michael Ma, Daniel B. Ennis, Alison Marsden

Abstract: Intracardiac flow patterns are shaped by the coupled motion of the cardiac chambers and heart valves and provide important information about cardiac function. However, clinical flow imaging remains limited by exam times, noise, resolution, and incomplete details of the three-dimensional flow. Computational fluid dynamics (CFD) can potentially provide detailed flow quantification and predictive ins… ▽ More Intracardiac flow patterns are shaped by the coupled motion of the cardiac chambers and heart valves and provide important information about cardiac function. However, clinical flow imaging remains limited by exam times, noise, resolution, and incomplete details of the three-dimensional flow. Computational fluid dynamics (CFD) can potentially provide detailed flow quantification and predictive insight into treatment outcomes, but clinical translation requires frameworks that reproduce patient-specific measurements while balancing physiological realism, computational cost, and modeling effort. Herein, we present an image-based, patient-specific computational framework for simulating whole-heart intracardiac hemodynamics that balances physiological fidelity with computational efficiency. The framework first employs machine learning-based segmentation and mesh propagation to reconstruct moving cardiac anatomies from time-resolved images. CFD simulations are then performed to resolve blood flow in deforming domains, while resistive immersed surfaces (RIS) are used to model all four cardiac valves with physiologically realistic opening and closing dynamics. The framework was applied to model hemodynamics in a healthy adult and a pediatric patient with complex congenital heart disease (CHD). In the healthy case, the simulations reproduced physiologic pressure-volume behavior, valve timing, and ventricular vortex formation. In the CHD case, simulated chamber and vessel pressures showed agreement with cardiac catheterization measurements. Simulated flow fields were qualitatively consistent with 4D-Flow MRI, while providing higher-resolution visualization of flow structures that were partially obscured by imaging artifacts. Comparison between the healthy and CHD cases further revealed altered diastolic flow organization and elevated normalized viscous dissipation in the CHD heart. △ Less

Submitted 10 May, 2026; originally announced May 2026.

A Nonparametric Adaptive EWMA Control Chart for Binary Monitoring of Multiple Stream Processes

Authors: Faruk Muritala, Austin Brown, Dhrubajyoti Ghosh, Sherry Ni

Abstract: Monitoring binomial proportions across multiple independent streams is a critical challenge in Statistical Process Control (SPC), with applications from manufacturing to cybersecurity. While EWMA charts offer sensitivity to small shifts, existing implementations rely on asymptotic variance approximations that fail during early-phase monitoring. We introduce a Cumulative Standardized Binomial EWMA… ▽ More Monitoring binomial proportions across multiple independent streams is a critical challenge in Statistical Process Control (SPC), with applications from manufacturing to cybersecurity. While EWMA charts offer sensitivity to small shifts, existing implementations rely on asymptotic variance approximations that fail during early-phase monitoring. We introduce a Cumulative Standardized Binomial EWMA (CSB-EWMA) chart that overcomes this limitation by deriving the exact time-varying variance of the EWMA statistic for binary multiple-stream data, enabling adaptive control limits that ensure statistical rigor from the first sample. Through extensive simulations, we identify optimal smoothing (λ) and limit (L) parameters to achieve target in-control average run length (ARL0) of 370 and 500. The CSB-EWMA chart demonstrates rapid shift detection across both ARL0 targets, with out-of-control average run length (ARL1) dropping to 3-7 samples for moderate shifts (δ=0.2), and exhibits exceptional robustness across different data distributions, with low ARL1 Coefficients of Variation (CV < 0.10 for small shifts) for both ARL0 = 370 and 500. This work provides practitioners with a distribution-free, sensitive, and theoretically sound tool for early change detection in binomial multiple-stream processes. △ Less

Submitted 13 April, 2026; originally announced April 2026.

The Potential for an Innovation Winter: Estimating Impact of Federal Research Reductions on Faculty Activity

Authors: Robert A. Brown

Abstract: The proposed reductions in federal research support proposed by the Trump Administration for 2026 would profoundly degrade the United States research universities, especially in the STEM fields and medicine (STEMM). A potentially devastating consequence would be on the funding distribution for individual faculty. Data and stochastic modeling demonstrate that the result would be large fractions of… ▽ More The proposed reductions in federal research support proposed by the Trump Administration for 2026 would profoundly degrade the United States research universities, especially in the STEM fields and medicine (STEMM). A potentially devastating consequence would be on the funding distribution for individual faculty. Data and stochastic modeling demonstrate that the result would be large fractions of previously research active faculty having subcritical research support. Research expenditure data from Boston University suggests that the funding distribution has a heavy tail (a Pareto like distribution)where a relatively small number of faculty have responsibility for a large fraction of the funding and that another fraction have minimal external support. A log normal distribution fits the expenditure data, and a multiplicative stochastic model replicates the spending distributions for the STEMM faculty and, separately, the engineering faculty. Using data for the average expenditures by 146 R1 (very research intensive) engineering schools, the model predicts that the 40 percent funding reduction proposed by the Administration would increase from 26 to 47 percent the number of R1 universities with over half their faculty with less than 100,000 dollars of annual expenditures, if the reduction affects all equally. If the most research intensive universities win a disproportionate share, this percentage of universities jumps to almost 60. In such an environment, and in the face of other cost pressures, it would be difficult to maintain quality research and doctoral programs across many institutions, raising important questions about their optimal research strategy and organization if faced with this declining support. Ideas for navigating such a future are presented. △ Less

Submitted 23 February, 2026; originally announced March 2026.

Comments: 28 pages, 8 figures

ICHOR: A Robust Representation Learning Approach for ASL CBF Maps with Self-Supervised Masked Autoencoders

Authors: Xavier Beltran-Urbano, Yiran Li, Xinglin Zeng, Katie R. Jobson, Manuel Taso, Christopher A. Brown, David A. Wolk, Corey T. McMillan, Ilya M. Nashrallah, Paul A. Yushkevich, Ze Wang, John A. Detre, Sudipto Dolui

Abstract: Arterial spin labeling (ASL) perfusion MRI allows direct quantification of regional cerebral blood flow (CBF) without exogenous contrast, enabling noninvasive measurements that can be repeated without constraints imposed by contrast injection. ASL is increasingly acquired in research studies and clinical MRI protocols. Building on successes in structural imaging, recent efforts have implemented de… ▽ More Arterial spin labeling (ASL) perfusion MRI allows direct quantification of regional cerebral blood flow (CBF) without exogenous contrast, enabling noninvasive measurements that can be repeated without constraints imposed by contrast injection. ASL is increasingly acquired in research studies and clinical MRI protocols. Building on successes in structural imaging, recent efforts have implemented deep learning based methods to improve image quality, enable automated quality control, and derive robust quantitative and predictive biomarkers with ASL derived CBF. However, progress has been limited by variable image quality, substantial inter-site, vendor and protocol differences, and limited availability of labeled datasets needed to train models that generalize across cohorts. To address these challenges, we introduce ICHOR, a self supervised pre-training approach for ASL CBF maps that learns transferable representations using 3D masked autoencoders. ICHOR is pretrained via masked image modeling using a Vision Transformer backbone and can be used as a general-purpose encoder for downstream ASL tasks. For pre-training, we curated one of the largest ASL datasets to date, comprising 11,405 ASL CBF scans from 14 studies spanning multiple sites and acquisition protocols. We evaluated the pre-trained ICHOR encoder on three downstream diagnostic classification tasks and one ASL CBF map quality prediction regression task. Across all evaluations, ICHOR outperformed existing neuroimaging self-supervised pre-training methods adapted to ASL. Pre-trained weights and code will be made publicly available. △ Less

Submitted 5 March, 2026; originally announced March 2026.

A Multivariate Bernoulli-Based Sampling Method for Multi-Label Data with Application to Meta-Research

Authors: Simon Chung, Colby J. Vorland, Donna L. Maney, Andrew W. Brown

Abstract: Datasets may contain observations with multiple labels. If the labels are not mutually exclusive, and if the labels vary greatly in frequency, obtaining a sample that includes sufficient observations with scarcer labels to make inferences about those labels, and which deviates from the population frequencies in a known manner, creates challenges. In this paper, we consider a multivariate Bernoulli… ▽ More Datasets may contain observations with multiple labels. If the labels are not mutually exclusive, and if the labels vary greatly in frequency, obtaining a sample that includes sufficient observations with scarcer labels to make inferences about those labels, and which deviates from the population frequencies in a known manner, creates challenges. In this paper, we consider a multivariate Bernoulli distribution as our underlying distribution of a multi-label problem. We present a novel sampling algorithm that takes label dependencies into account. It uses observed label frequencies to estimate multivariate Bernoulli distribution parameters and calculates weights for each label combination. This approach ensures the weighted sampling acquires target distribution characteristics while accounting for label dependencies. We applied this approach to a variety of datasets, including a sample of research articles from Web of Science labeled with 64 biomedical topic categories. We aimed to preserve category frequency order, reduce frequency differences between most and least common categories, and account for category dependencies. This approach produced a more balanced sub-sample, enhancing the representation of minority categories. △ Less

Submitted 25 May, 2026; v1 submitted 9 December, 2025; originally announced December 2025.

The relationship between offline partisan geographical segregation and online partisan segregation

Authors: Megan A. Brown, Tiago Ventura, Joshua A. Tucker, Jonathan Nagler

Abstract: Social media is often blamed for the creation of echo chambers. However, these claims fail to consider the prevalence of offline echo chambers resulting from high levels of partisan segregation in the United States. Our article empirically assesses these online versus offline dynamics by linking a novel dataset of voters' offline partisan segregation extracted from publicly available voter files f… ▽ More Social media is often blamed for the creation of echo chambers. However, these claims fail to consider the prevalence of offline echo chambers resulting from high levels of partisan segregation in the United States. Our article empirically assesses these online versus offline dynamics by linking a novel dataset of voters' offline partisan segregation extracted from publicly available voter files for 180 million US voters with their online network segregation on Twitter. We investigate offline and online partisan segregation using measures of geographical and network isolation of every matched voter-twitter user to their co-partisans online and offline. Our results show that while social media users tend to form politically homogeneous online networks, these levels of partisan sorting are significantly lower than those found in offline settings. Notably, Democrats are more isolated than Republicans in both settings, and only older Republicans exhibit higher online than offline segregation. Our results contribute to the emerging literature on political communication and the homophily of online networks, providing novel evidence on partisan sorting both online and offline. △ Less

Submitted 10 December, 2025; v1 submitted 7 December, 2025; originally announced December 2025.

tritonBLAS: Triton-based Analytical Approach for GEMM Kernel Parameter Selection

Authors: Ryan Swann, Muhammad Osama, Xiaohu Guo, Bryant Nelson, Lixun Zhang, Alex Brown, Yen Ong, Ali Yazdani, Sean Siddens, Ganesh Dasika, Alex Underwood

Abstract: We present tritonBLAS, a fast and deterministic analytical model that uses architectural parameters like the cache hierarchy, and relative code and data placement to generate performant GPU GEMM kernels. tritonBLAS explicitly models the relationship between architectural topology, matrix shapes, and algorithmic blocking behavior to predict near-optimal configurations without runtime autotuning. Ba… ▽ More We present tritonBLAS, a fast and deterministic analytical model that uses architectural parameters like the cache hierarchy, and relative code and data placement to generate performant GPU GEMM kernels. tritonBLAS explicitly models the relationship between architectural topology, matrix shapes, and algorithmic blocking behavior to predict near-optimal configurations without runtime autotuning. Based on this model, we developed and implemented a lightweight GEMM framework entirely within Triton. We evaluate the performance of tritonBLAS across a diverse set of GEMM problem sizes on modern GPUs. tritonBLAS achieves over 95% of the performance of autotuning solutions, while reducing autotuning time to zero. This makes tritonBLAS a practical drop-in replacement for empirical tuning in production HPC and ML workloads. △ Less

Submitted 3 December, 2025; originally announced December 2025.

Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant

Authors: Joseph Matveyenko, James Liu, John David Parsons, Ryan A. Brown, Alina Palimaru, Prateek Puri

Abstract: Qualitative research emphasizes constructing meaning through iterative engagement with textual data. Traditionally this human-driven process requires navigating coder fatigue and interpretative drift, thus posing challenges when scaling analysis to larger, more complex datasets. Computational approaches to augment qualitative research have been met with skepticism, partly due to their inability to… ▽ More Qualitative research emphasizes constructing meaning through iterative engagement with textual data. Traditionally this human-driven process requires navigating coder fatigue and interpretative drift, thus posing challenges when scaling analysis to larger, more complex datasets. Computational approaches to augment qualitative research have been met with skepticism, partly due to their inability to replicate the nuance, context-awareness, and sophistication of human analysis. Large language models, however, present new opportunities to automate aspects of qualitative analysis while upholding rigor and research quality in important ways. To assess their benefits and limitations - and build trust among qualitative researchers - these approaches must be rigorously benchmarked against human-generated datasets. In this work, we benchmark Muse, an interactive, AI-powered qualitative research system that allows researchers to identify themes and annotate datasets, finding an inter-rater reliability between Muse and humans of Cohen's $κ$ = 0.71 for well-specified codes. We also conduct robust error analysis to identify failure mode, guide future improvements, and demonstrate the capacity to correct for human bias. △ Less

Submitted 14 December, 2025; v1 submitted 14 October, 2025; originally announced December 2025.

Comments: 32 pages, 9 figures

ACM Class: I.2.7

A computational model and tool for generating more novel opportunities in professional innovation processes

Authors: Neil Maiden, Konstantinos Zachos, James Lockerbie, Kostas Petrianakis, Amanda Brown

Abstract: This paper presents a new computational model of creative outcomes, informed by creativity theories and techniques, which was implemented to generate more novel opportunities for innovation projects. The model implemented five functions that were developed to contribute to the generation of innovation opportunities with higher novelty without loss of usefulness. The model was evaluated using oppor… ▽ More This paper presents a new computational model of creative outcomes, informed by creativity theories and techniques, which was implemented to generate more novel opportunities for innovation projects. The model implemented five functions that were developed to contribute to the generation of innovation opportunities with higher novelty without loss of usefulness. The model was evaluated using opportunities generated for an innovation project in the hospitality sector. The evaluation revealed that the computational model generated outcomes that were more novel and/or useful than outcomes from Notebook LM and ChatGPT4o. However, not all model functions contributed to the generation of more novel opportunities, leading to new directions for further model development △ Less

Submitted 23 October, 2025; originally announced October 2025.

A Systematic Review on Crimes facilitated by Consumer Internet of Things Devices

Authors: Ashley Brown, Nilufer Tuptuk, Enrico Mariconti, Shane Johnson

Abstract: It is well documented that criminals use IoT devices to facilitate crimes. The review process follows a systematic approach with a clear search strategy, and study selection strategy. The review included a total of 543 articles and the findings from these articles were synthesised through thematic analysis. Identified security attacks targeting consumer IoT devices include man-in-the-middle (MiTM)… ▽ More It is well documented that criminals use IoT devices to facilitate crimes. The review process follows a systematic approach with a clear search strategy, and study selection strategy. The review included a total of 543 articles and the findings from these articles were synthesised through thematic analysis. Identified security attacks targeting consumer IoT devices include man-in-the-middle (MiTM) attacks, synchronisation attacks, Denial-of-Service (DoS), DNS poisoning and malware, alongside device-specific vulnerabilities. Besides security attacks, this review discusses mitigations. Furthermore, the literature also covers crime threat scenarios arising from these attacks, such as, fraud, identity theft, crypto jacking and domestic abuse. △ Less

Submitted 17 September, 2025; originally announced October 2025.

A Hybrid Co-Finetuning Approach for Visual Bug Detection in Video Games

Authors: Faliu Yi, Sherif Abdelfattah, Wei Huang, Adrian Brown

Abstract: Manual identification of visual bugs in video games is a resource-intensive and costly process, often demanding specialized domain knowledge. While supervised visual bug detection models offer a promising solution, their reliance on extensive labeled datasets presents a significant challenge due to the infrequent occurrence of such bugs. To overcome this limitation, we propose a hybrid Co-FineTuni… ▽ More Manual identification of visual bugs in video games is a resource-intensive and costly process, often demanding specialized domain knowledge. While supervised visual bug detection models offer a promising solution, their reliance on extensive labeled datasets presents a significant challenge due to the infrequent occurrence of such bugs. To overcome this limitation, we propose a hybrid Co-FineTuning (CFT) method that effectively integrates both labeled and unlabeled data. Our approach leverages labeled samples from the target game and diverse co-domain games, additionally incorporating unlabeled data to enhance feature representation learning. This strategy maximizes the utility of all available data, substantially reducing the dependency on labeled examples from the specific target game. The developed framework demonstrates enhanced scalability and adaptability, facilitating efficient visual bug detection across various game titles. Our experimental results show the robustness of the proposed method for game visual bug detection, exhibiting superior performance compared to conventional baselines across multiple gaming environments. Furthermore, CFT maintains competitive performance even when trained with only 50% of the labeled data from the target game. △ Less

Submitted 3 October, 2025; originally announced October 2025.

Comments: Accepted at the 21st AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE 2025)

Redesigning GROMACS Halo Exchange: Improving Strong Scaling with GPU-initiated NVSHMEM

Authors: Mahesh Doijade, Andrey Alekseenko, Ania Brown, Alan Gray, Szilárd Páll

Abstract: Improving time-to-solution in molecular dynamics simulations often requires strong scaling due to fixed-sized problems. GROMACS is highly latency-sensitive, with peak iteration rates in the sub-millisecond, making scalability on heterogeneous supercomputers challenging. MPI's CPU-centric nature introduces additional latencies on GPU-resident applications' critical path, hindering GPU utilization a… ▽ More Improving time-to-solution in molecular dynamics simulations often requires strong scaling due to fixed-sized problems. GROMACS is highly latency-sensitive, with peak iteration rates in the sub-millisecond, making scalability on heterogeneous supercomputers challenging. MPI's CPU-centric nature introduces additional latencies on GPU-resident applications' critical path, hindering GPU utilization and scalability. To address these limitations, we present an NVSHMEM-based GPU kernel-initiated redesign of the GROMACS domain decomposition halo-exchange algorithm. Highly tuned GPU kernels fuse data packing and communication, leveraging hardware latency-hiding for fine-grained overlap. We employ kernel fusion across overlapped data forwarding communication phases and utilize the asynchronous copy engine over NVLink to optimize latency and bandwidth. Our GPU-resident formulation greatly increases communication-computation overlap, improving GROMACS strong scaling performance across NVLink by up to 1.5x (intra-node) and 2x (multi-node), and up to 1.3x multi-node over NVLink+InfiniBand. This demonstrates the profound benefits of GPU-initiated communication for strong-scaling a broad range of latency-sensitive applications. △ Less

Submitted 25 September, 2025; originally announced September 2025.

Comments: 17 pages, 8 figures, submitted to PAW-ATM Workshop, SC 2025

A Dynamic, Self-balancing k-d Tree

Authors: Russell A. Brown

Abstract: The original description of the k-d tree recognized that rebalancing techniques, used for building an AVL or red-black tree, are not applicable to a k-d tree, because these techniques involve cyclic exchange of tree nodes that violates the invariant of the k-d tree. For this reason, a static, balanced k-d tree is often built from all of the k-dimensional data en masse. However, it is possible to b… ▽ More The original description of the k-d tree recognized that rebalancing techniques, used for building an AVL or red-black tree, are not applicable to a k-d tree, because these techniques involve cyclic exchange of tree nodes that violates the invariant of the k-d tree. For this reason, a static, balanced k-d tree is often built from all of the k-dimensional data en masse. However, it is possible to build a dynamic k-d tree that self-balances when necessary after insertion or deletion of each k-dimensional datum. This article describes insertion, deletion, and rebalancing algorithms for a dynamic, self-balancing k-d tree, and measures their performance. △ Less

Submitted 20 July, 2026; v1 submitted 9 September, 2025; originally announced September 2025.

Comments: 19 pages, 9 figures, 5 tables

Self-Organising Memristive Networks as Physical Learning Systems

Authors: Francesco Caravelli, Gianluca Milano, Adam Z. Stieg, Carlo Ricciardi, Simon Anthony Brown, Zdenka Kuncic

Abstract: Learning with physical systems is an emerging paradigm that seeks to harness the intrinsic nonlinear dynamics of physical substrates for learning. The impetus for a paradigm shift in how hardware is used for computational intelligence stems largely from the unsustainability of artificial neural network software implemented on conventional transistor-based hardware. This Perspective highlights one… ▽ More Learning with physical systems is an emerging paradigm that seeks to harness the intrinsic nonlinear dynamics of physical substrates for learning. The impetus for a paradigm shift in how hardware is used for computational intelligence stems largely from the unsustainability of artificial neural network software implemented on conventional transistor-based hardware. This Perspective highlights one promising approach using physical networks comprised of resistive memory nanoscale components with dynamically reconfigurable, self-organising electrical circuitry. Experimental advances have revealed the non-trivial interactions within these Self-Organising Memristive Networks (SOMNs), offering insights into their collective nonlinear and adaptive dynamics, and how these properties can be harnessed for learning using different hardware implementations. Theoretical approaches, including mean-field theory, graph theory, and concepts from disordered systems, reveal deeper insights into the dynamics of SOMNs, especially during transitions between different conductance states where criticality and other dynamical phase transitions emerge in both experiments and models. Furthermore, parallels between adaptive dynamics in SOMNs and plasticity in biological neuronal networks suggest the potential for realising energy-efficient, brain-like continual learning. SOMNs thus offer a promising route toward embedded edge intelligence, unlocking real-time decision-making for autonomous systems, dynamic sensing, and personalised healthcare, by embedding continuous learning in resource-constrained environments. The overarching aim of this Perspective is to show how the convergence of nanotechnology, statistical physics, complex systems, and self-organising principles offers a unique opportunity to advance a new generation of physical intelligence technologies. △ Less

Submitted 25 April, 2026; v1 submitted 31 August, 2025; originally announced September 2025.

Comments: Perspective paper on SOMN, to appear in NatRevPhys; 24 pages, double columns, 7 figures, 2 boxes;

Achieving detailed medial temporal lobe segmentation with upsampled isotropic training from implicit neural representation

Authors: Yue Li, Pulkit Khandelwal, Rohit Jena, Long Xie, Michael Duong, Amanda E. Denning, Christopher A. Brown, Laura E. M. Wisse, Sandhitsu R. Das, David A. Wolk, Paul A. Yushkevich

Abstract: Imaging biomarkers in magnetic resonance imaging (MRI) are important tools for diagnosing, tracking and treating Alzheimer's disease (AD). Neurofibrillary tau pathology in AD is closely linked to neurodegeneration and generally follows a pattern of spread in the brain, with early stages involving subregions of the medial temporal lobe (MTL). Accurate segmentation of MTL subregions is needed to ext… ▽ More Imaging biomarkers in magnetic resonance imaging (MRI) are important tools for diagnosing, tracking and treating Alzheimer's disease (AD). Neurofibrillary tau pathology in AD is closely linked to neurodegeneration and generally follows a pattern of spread in the brain, with early stages involving subregions of the medial temporal lobe (MTL). Accurate segmentation of MTL subregions is needed to extract granular biomarkers of AD progression. MTL subregions are often imaged using T2-weighted (T2w) MRI scans that are highly anisotropic due to constraints of MRI physics and image acquisition, making it difficult to reliably model MTL subregions geometrically and extract morphological measures, such as thickness. In this study, we used an implicit neural representation method to combine isotropic T1-weighted (T1w) and anisotropic T2w MRI to upsample an atlas set of expert-annotated MTL subregions, establishing a multi-modality, high-resolution training set of isotropic data for automatic segmentation with the nnU-Net framework. In an independent test set, the morphological measures extracted using this isotropic model showed stronger effect sizes than models trained on anisotropic in distinguishing participants with mild cognitive impairment (MCI) and cognitively unimpaired individuals. In test-retest analysis, morphological measures extracted using the isotropic model had greater stability. This study demonstrates improved reliability of MRI-derived MTL subregion biomarkers without additional atlas annotation effort, which may more accurately quantify and track the relationship between AD pathology and brain atrophy for monitoring disease progression. △ Less

Submitted 24 November, 2025; v1 submitted 23 August, 2025; originally announced August 2025.

SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokens

Authors: Alexandre Brown, Glen Berseth

Abstract: Visual reinforcement learning policies trained on pixel observations often struggle to generalize when visual conditions change at test time. Object-centric representations are a promising alternative, but most approaches use fixed-size slot representations, require image reconstruction, or need auxiliary losses to learn object decompositions. As a result, it remains unclear how to learn RL polici… ▽ More Visual reinforcement learning policies trained on pixel observations often struggle to generalize when visual conditions change at test time. Object-centric representations are a promising alternative, but most approaches use fixed-size slot representations, require image reconstruction, or need auxiliary losses to learn object decompositions. As a result, it remains unclear how to learn RL policies directly from object-level inputs without these constraints. We propose SegDAC, a Segmentation-Driven Actor-Critic that operates on a variable-length set of object token embeddings. At each timestep, text-grounded segmentation produces object masks from which spatially aware token embeddings are extracted. A transformer-based actor-critic processes these dynamic tokens, using segment positional encoding to preserve spatial information across objects. We ablate these design choices and show that both segment positional encoding and variable-length processing are individually necessary for strong performance. We evaluate SegDAC on 8 ManiSkill3 manipulation tasks under 12 visual perturbation types across 3 difficulty levels. SegDAC improves over prior visual generalization methods by 15% on easy, 66% on medium, and 88% on the hardest settings. SegDAC matches the sample efficiency of the state-of-the-art visual RL methods while achieving improved generalization under visual changes. Project Page: https://segdac.github.io/ △ Less

Submitted 13 March, 2026; v1 submitted 12 August, 2025; originally announced August 2025.

Comments: 12 pages

Benchmarking Self-Driving Labs

Authors: Adedire D. Adesiji, Jiashuo Wang, Cheng-Shu Kuo, Keith A. Brown

Abstract: A key goal of modern materials science is accelerating the pace of materials discovery. Self-driving labs, or systems that select experiments using machine learning and then execute them using automation, are designed to fulfil this promise by performing experiments faster, more intelligently, more reliably, and with richer metadata than conventional means. This review summarizes progress in under… ▽ More A key goal of modern materials science is accelerating the pace of materials discovery. Self-driving labs, or systems that select experiments using machine learning and then execute them using automation, are designed to fulfil this promise by performing experiments faster, more intelligently, more reliably, and with richer metadata than conventional means. This review summarizes progress in understanding the degree to which SDLs accelerate learning by quantifying how much they reduce the number of experiments required for a given goal. The review begins by summarizing the theory underlying two key metrics, namely acceleration factor AF and enhancement factor EF, which quantify how much faster and better an algorithm is relative to a reference strategy. Next, we provide a comprehensive review of the literature, which reveals a wide range of AFs with a median of 6, and that tends to increase with the dimensionality of the space, reflecting an interesting blessing of dimensionality. In contrast, reported EF values vary by over two orders of magnitude, although they consistently peak at 10-20 experiments per dimension. To understand these results, we perform a series of simulated Bayesian optimization campaigns that reveal how EF depends upon the statistical properties of the parameter space while AF depends on its complexity. Collectively, these results reinforce the motivation for using SDLs by revealing their value across a wide range of material parameter spaces and provide a common language for quantifying and understanding this acceleration. △ Less

Submitted 8 August, 2025; originally announced August 2025.

A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges

Authors: Andrew Brown, Muhammad Roman, Barry Devereux

Abstract: This systematic review of the research literature on retrieval-augmented generation (RAG) provides a focused analysis of the most highly cited studies published between 2020 and May 2025. A total of 128 articles met our inclusion criteria. The records were retrieved from ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect, and the Digital Bibliography and Library Project (DBLP). RAG couples a… ▽ More This systematic review of the research literature on retrieval-augmented generation (RAG) provides a focused analysis of the most highly cited studies published between 2020 and May 2025. A total of 128 articles met our inclusion criteria. The records were retrieved from ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect, and the Digital Bibliography and Library Project (DBLP). RAG couples a neural retriever with a generative language model, grounding output in up-to-date, non-parametric memory while retaining the semantic generalisation stored in model weights. Guided by the PRISMA 2020 framework, we (i) specify explicit inclusion and exclusion criteria based on citation count and research questions, (ii) catalogue datasets, architectures, and evaluation practices, and (iii) synthesise empirical evidence on the effectiveness and limitations of RAG. To mitigate citation-lag bias, we applied a lower citation-count threshold to papers published in 2025 so that emerging breakthroughs with naturally fewer citations were still captured. This review clarifies the current research landscape, highlights methodological gaps, and charts priority directions for future research. △ Less

Submitted 9 September, 2025; v1 submitted 8 August, 2025; originally announced August 2025.

Comments: 58 page

GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction

Authors: Eya Cherif, Arthur Ouaknine, Luke A. Brown, Phuong D. Dao, Kyle R. Kovach, Bing Lu, Daniel Mederer, Hannes Feilhauer, Teja Kattenborn, David Rolnick

Abstract: Plant traits such as leaf carbon content and leaf mass are essential variables in the study of biodiversity and climate change. However, conventional field sampling cannot feasibly cover trait variation at ecologically meaningful spatial scales. Machine learning represents a valuable solution for plant trait prediction across ecosystems, leveraging hyperspectral data from remote sensing. Neverthel… ▽ More Plant traits such as leaf carbon content and leaf mass are essential variables in the study of biodiversity and climate change. However, conventional field sampling cannot feasibly cover trait variation at ecologically meaningful spatial scales. Machine learning represents a valuable solution for plant trait prediction across ecosystems, leveraging hyperspectral data from remote sensing. Nevertheless, trait prediction from hyperspectral data is challenged by label scarcity and substantial domain shifts (\eg across sensors, ecological distributions), requiring robust cross-domain methods. Here, we present GreenHyperSpectra, a pretraining dataset encompassing real-world cross-sensor and cross-ecosystem samples designed to benchmark trait prediction with semi- and self-supervised methods. We adopt an evaluation framework encompassing in-distribution and out-of-distribution scenarios. We successfully leverage GreenHyperSpectra to pretrain label-efficient multi-output regression models that outperform the state-of-the-art supervised baseline. Our empirical analyses demonstrate substantial improvements in learning spectral representations for trait prediction, establishing a comprehensive methodological framework to catalyze research at the intersection of representation learning and plant functional traits assessment. All code and data are available at: https://github.com/echerif18/HyspectraSSL. △ Less

Submitted 26 November, 2025; v1 submitted 9 July, 2025; originally announced July 2025.

Comments: Accepted at the 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Authors: Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, Luke Marris, Sam Petulla, Colin Gaffney, Asaf Aharoni, Nathan Lintz, Tiago Cardal Pais, Henrik Jacobsson, Idan Szpektor, Nan-Jiang Jiang, Krishna Haridasan, Ahmed Omran, Nikunj Saunshi, Dara Bahri, Gaurav Mishra, Eric Chu , et al. (3410 additional authors not shown)

Abstract: In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal unde… ▽ More In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving. △ Less

Submitted 19 December, 2025; v1 submitted 7 July, 2025; originally announced July 2025.

Comments: 72 pages, 17 figures

Review of Three Algorithms That Build k-d Trees

Authors: Russell A. Brown

Abstract: The original description of the k-d tree recognized that rebalancing techniques, such as used to build an AVL tree or a red-black tree, are not applicable to a k-d tree. Hence, in order to build a balanced k-d tree, it is necessary to find the median of a set of data for each recursive subdivision of that set. The sort or selection used to find the median, and the technique used to partition the s… ▽ More The original description of the k-d tree recognized that rebalancing techniques, such as used to build an AVL tree or a red-black tree, are not applicable to a k-d tree. Hence, in order to build a balanced k-d tree, it is necessary to find the median of a set of data for each recursive subdivision of that set. The sort or selection used to find the median, and the technique used to partition the set about that median, strongly influence the computational complexity of building a k-d tree. This article describes and contrasts three k-d tree-building algorithms that differ in their technique used to partition the set, and compares the performance of the algorithms. In addition, dual-threaded execution is proposed for one of the three algorithms. △ Less

Submitted 28 December, 2025; v1 submitted 24 June, 2025; originally announced June 2025.

Comments: 26 pages, 11 figures, one listing, one table

Post-Post-API Age: Studying Digital Platforms in Scant Data Access Times

Authors: Kayo Mimizuka, Megan A Brown, Kai-Cheng Yang, Josephine Lukito

Abstract: Over the past decade, data provided by digital platforms has informed substantial research in HCI to understand online human interaction and communication. Following the closure of major social media APIs that previously provided free access to large-scale data (the "post-API age"), emerging data access programs required by the European Union's Digital Services Act (DSA) have sparked optimism abou… ▽ More Over the past decade, data provided by digital platforms has informed substantial research in HCI to understand online human interaction and communication. Following the closure of major social media APIs that previously provided free access to large-scale data (the "post-API age"), emerging data access programs required by the European Union's Digital Services Act (DSA) have sparked optimism about increased platform transparency and renewed opportunities for comprehensive research on digital platforms, leading to the "post-post-API age." However, it remains unclear whether platforms provide adequate data access in practice. To assess how platforms make data available under the DSA, we conducted a comprehensive survey followed by in-depth interviews with 19 researchers to understand their experiences with data access in this new era. Our findings reveal significant challenges in accessing social media data, with researchers facing multiple barriers including complex API application processes, difficulties obtaining credentials, and limited API usability. These challenges have exacerbated existing institutional, regional, and financial inequities in data access. Based on these insights, we provide actionable recommendations for platforms, researchers, and policymakers to foster more equitable and effective data access, while encouraging broader dialogue within the CSCW community around interdisciplinary and multi-stakeholder solutions. △ Less

Submitted 14 May, 2025; originally announced May 2025.

xTrace: A Facial Expressive Behaviour Analysis Tool for Continuous Affect Recognition

Authors: Mani Kumar Tellamekala, Shashank Jaiswal, Thomas Smith, Timur Alamev, Gary McKeown, Anthony Brown, Michel Valstar

Abstract: Recognising expressive behaviours in face videos is a long-standing challenge in Affective Computing. Despite significant advancements in recent years, it still remains a challenge to build a robust and reliable system for naturalistic and in-the-wild facial expressive behaviour analysis in real time. This paper addresses two key challenges in building such a system: (1). The paucity of large-scal… ▽ More Recognising expressive behaviours in face videos is a long-standing challenge in Affective Computing. Despite significant advancements in recent years, it still remains a challenge to build a robust and reliable system for naturalistic and in-the-wild facial expressive behaviour analysis in real time. This paper addresses two key challenges in building such a system: (1). The paucity of large-scale labelled facial affect video datasets with extensive coverage of the 2D emotion space, and (2). The difficulty of extracting facial video features that are discriminative, interpretable, robust, and computationally efficient. Toward addressing these challenges, this work introduces xTrace, a robust tool for facial expressive behaviour analysis and predicting continuous values of dimensional emotions, namely valence and arousal, from in-the-wild face videos. To address challenge (1), the proposed affect recognition model is trained on the largest facial affect video data set, containing $\sim$450k videos that cover most emotion zones in the dimensional emotion space, making xTrace highly versatile in analysing a wide spectrum of naturalistic expressive behaviours. To address challenge (2), xTrace uses facial affect descriptors that are not only explainable, but can also achieve a high degree of accuracy and robustness with low computational complexity. The key components of xTrace are benchmarked against three existing tools: MediaPipe, OpenFace, and Augsburg Affect Toolbox. On an in-the-wild benchmarking set composed of $\sim$50k videos, xTrace achieves 0.86 mean Concordance Correlation Coefficient (CCC) and on the SEWA test set it achieves 0.75 mean CCC, outperforming existing SOTA by $\sim$7.1\%. △ Less

Submitted 12 October, 2025; v1 submitted 8 May, 2025; originally announced May 2025.

Imaging Biomarkers for Neurodegenerative Diseases from Detailed Segmentation of Medial Temporal Lobe Subregions on in vivo Brain MRI Using Upsampling Strategy Guided by High-resolution ex vivo MRI

Authors: Yue Li, Pulkit Khandelwal, Long Xie, Laura E. M. Wisse, Amanda E. Denning, Christopher A. Brown, Emily McGrew, Sydney A. Lim, Niyousha Sadeghpour, Sadhana Ravikumar, Ranjit Ittyerah, Eunice Chung, Daniel T. Ohm, Nidhi S. Mundada, María Mercedes Íñiguez de Onzoño Martín, María del Mar Arroyo Jiménez, Monica Mũnoz, Maria del Pilar Marcos Rabal, David J. Irwin, Edward B. Lee, Ricardo Insausti, Sandhitsu R. Das, David A. Wolk, Paul A. Yushkevich

Abstract: The medial temporal lobe (MTL) is a region impacted extensively and non-uniformly in early stages of Alzheimer's disease (AD). Regional MTL morphometric measures extracted from magnetic resonance imaging (MRI) are supportive features for the diagnosis of AD and related disorders (ADRD). Different MRI modalities have distinct advantages for MTL morphometry. Anisotropic T2-weighted (T2w) MRI is pref… ▽ More The medial temporal lobe (MTL) is a region impacted extensively and non-uniformly in early stages of Alzheimer's disease (AD). Regional MTL morphometric measures extracted from magnetic resonance imaging (MRI) are supportive features for the diagnosis of AD and related disorders (ADRD). Different MRI modalities have distinct advantages for MTL morphometry. Anisotropic T2-weighted (T2w) MRI is preferred for hippocampal subfields due to its higher contrast between hippocampal layers. Isotropic T1-weighted (T1w) MRI is beneficial for thickness calculation of extra-hippocampal subregions due to its stable image quality and isotropic resolution. We propose a multi-modality MTL segmentation algorithm that bridges the T1w and T2w modalities by bringing both to a nearly isotropic voxel space. Guided by high-resolution ex vivo 9.4T MRI, an upsampling model was designed for the ground truth segmentations. Combined with non-local means upsampling, this model was used to construct a nearly iso-tropic T1w and T2w MTL subregion segmentation training set, which was used to train a nnUNet model. Morphometric biomarkers extracted by this model were compared to those extracted using conventional models operating in anisotropic spaces on downstream tasks. Biomarkers extracted using the proposed model had greater ability to discriminate between individuals with mild cognitive impairment and cognitively unimpaired; and had great-er longitudinal stability. These findings suggest that the biomarkers derived from T1w and T2w MRI unsampled to nearly isotropic resolution have sig-nificant potential for improving disease diagnosis and monitoring disease progression in ADRD. △ Less

Submitted 24 September, 2025; v1 submitted 25 April, 2025; originally announced April 2025.

Evaluating how LLM annotations represent diverse views on contentious topics

Authors: Megan A. Brown, Shubham Atreja, Libby Hemphill, Patrick Y. Wu

Abstract: Researchers have proposed the use of generative large language models (LLMs) to label data for research and applied settings. This literature emphasizes the improved performance of these models relative to other natural language models, noting that generative LLMs typically outperform other models and even humans across several metrics. Previous literature has examined bias across many application… ▽ More Researchers have proposed the use of generative large language models (LLMs) to label data for research and applied settings. This literature emphasizes the improved performance of these models relative to other natural language models, noting that generative LLMs typically outperform other models and even humans across several metrics. Previous literature has examined bias across many applications and contexts, but less work has focused specifically on bias in generative LLMs' responses to subjective annotation tasks. This bias could result in labels applied by LLMs that disproportionately align with majority groups over a more diverse set of viewpoints. In this paper, we evaluate how LLMs represent diverse viewpoints on these contentious tasks. Across four annotation tasks on four datasets, we show that LLMs do not show systematic substantial disagreement with annotators on the basis of demographics. Rather, we find that multiple LLMs tend to be biased in the same directions on the same demographic categories within the same datasets. Moreover, the disagreement between human annotators on the labeling task -- a measure of item difficulty -- is far more predictive of LLM agreement with human annotators. We conclude with a discussion of the implications for researchers and practitioners using LLMs for automated data annotation tasks. Specifically, we emphasize that fairness evaluations must be contextual, model choice alone will not solve potential issues of bias, and item difficulty must be integrated into bias assessments. △ Less

Submitted 15 June, 2025; v1 submitted 29 March, 2025; originally announced March 2025.

Scalable HPC Job Scheduling and Resource Management in SST

Authors: Abubeker Abdurahman, Abrar Hossain, Kevin A Brown, Kazutomo Yoshii, Kishwar Ahmed

Abstract: Efficient job scheduling and resource management contribute towards system throughput and efficiency maximization in high-performance computing (HPC) systems. In this paper, we introduce a scalable job scheduling and resource management component within the structural simulation toolkit (SST), a cycle-accurate and parallel discrete-event simulator. Our proposed simulator includes state-of-the-art… ▽ More Efficient job scheduling and resource management contribute towards system throughput and efficiency maximization in high-performance computing (HPC) systems. In this paper, we introduce a scalable job scheduling and resource management component within the structural simulation toolkit (SST), a cycle-accurate and parallel discrete-event simulator. Our proposed simulator includes state-of-the-art job scheduling algorithms and resource management techniques. Additionally, it introduces workflow management components that support the simulation of task dependencies and resource allocations, crucial for workflows typical in scientific computing and data-intensive applications. We present the validation and scalability results of our job scheduling simulator. Simulation shows that our simulator achieves good accuracy in various metrics (e.g., job wait times, number of nodes usage) and also achieves good parallel performance. △ Less

Submitted 30 January, 2025; originally announced January 2025.

Journal ref: 2024 Winter Simulation Conference (WSC)

Humanity's Last Exam

Authors: Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, Sean Shi, Michael Choi, Anish Agrawal, Arnav Chopra, Adam Khoja, Ryan Kim, Richard Ren, Jason Hausenloy, Oliver Zhang, Mantas Mazeika, Dmitry Dodonov, Tung Nguyen, Jaeho Lee, Daron Anderson, Mikhail Doroshenko, Alun Cennyth Stokes , et al. (1133 additional authors not shown)

Abstract: Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of… ▽ More Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai. △ Less

Submitted 28 July, 2026; v1 submitted 24 January, 2025; originally announced January 2025.

Comments: 29 pages, 6 figures

Normalizations of factorizations over convex cones and their effects on extension complexity

Authors: Adam Brown, Kanstantsin Pashkovich, Levent Tunçel

Abstract: Factorizations over cones and their duals play central roles for many areas of mathematics and computer science. One of the reasons behind this is the ability to find a representation for various objects using a well-structured family of cones, where the representation is captured by the factorizations over these cones. Several major questions about factorizations over cones remain open even for s… ▽ More Factorizations over cones and their duals play central roles for many areas of mathematics and computer science. One of the reasons behind this is the ability to find a representation for various objects using a well-structured family of cones, where the representation is captured by the factorizations over these cones. Several major questions about factorizations over cones remain open even for such well-structured families of cones as non-negative orthants and positive semidefinite cones. Having said that, we possess a far better understanding of factorizations over non-negative orthants and positive semidefinite cones than over other families of cones. One of the key properties that led to this better understanding is the ability to normalize factorizations, i.e., to guarantee that the norms of the vectors involved in the factorizations are bounded in terms of an input and in terms of a constant dependent on the given cone. Our work aims at understanding which cones guarantee that factorizations over them can be normalized, and how this effects extension complexity of polytopes over such cones. △ Less

Submitted 15 February, 2025; v1 submitted 6 January, 2025; originally announced January 2025.

From Ceilings to Walls: Universal Dynamic Perching of Small Aerial Robots on Surfaces with Variable Orientations

Authors: Bryan Habas, Aaron Brown, Donghyeon Lee, Mitchell Goldman, Bo Cheng

Abstract: This work demonstrates universal dynamic perching capabilities for quadrotors of various sizes and on surfaces with different orientations. By employing a non-dimensionalization framework and deep reinforcement learning, we systematically assessed how robot size and surface orientation affect landing capabilities. We hypothesized that maintaining geometric proportions across different robot scales… ▽ More This work demonstrates universal dynamic perching capabilities for quadrotors of various sizes and on surfaces with different orientations. By employing a non-dimensionalization framework and deep reinforcement learning, we systematically assessed how robot size and surface orientation affect landing capabilities. We hypothesized that maintaining geometric proportions across different robot scales ensures consistent perching behavior, which was validated in both simulation and experimental tests. Additionally, we investigated the effects of joint stiffness and damping in the landing gear on perching behaviors and performance. While joint stiffness had minimal impact, joint damping ratios influenced landing success under vertical approaching conditions. The study also identified a critical velocity threshold necessary for successful perching, determined by the robot's maneuverability and leg geometry. Overall, this research advances robotic perching capabilities, offering insights into the role of mechanical design and scaling effects, and lays the groundwork for future drone autonomy and operational efficiency in unstructured environments. △ Less

Submitted 27 December, 2024; originally announced December 2024.

Comments: 7 pages, 8 Figures

Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution

Authors: Qihao Liu, Xi Yin, Alan Yuille, Andrew Brown, Mannat Singh

Abstract: Diffusion models, and their generalization, flow matching, have had a remarkable impact on the field of media generation. Here, the conventional approach is to learn the complex mapping from a simple source distribution of Gaussian noise to the target media distribution. For cross-modal tasks such as text-to-image generation, this same mapping from noise to image is learnt whilst including a condi… ▽ More Diffusion models, and their generalization, flow matching, have had a remarkable impact on the field of media generation. Here, the conventional approach is to learn the complex mapping from a simple source distribution of Gaussian noise to the target media distribution. For cross-modal tasks such as text-to-image generation, this same mapping from noise to image is learnt whilst including a conditioning mechanism in the model. One key and thus far relatively unexplored feature of flow matching is that, unlike Diffusion models, they are not constrained for the source distribution to be noise. Hence, in this paper, we propose a paradigm shift, and ask the question of whether we can instead train flow matching models to learn a direct mapping from the distribution of one modality to the distribution of another, thus obviating the need for both the noise distribution and conditioning mechanism. We present a general and simple framework, CrossFlow, for cross-modal flow matching. We show the importance of applying Variational Encoders to the input data, and introduce a method to enable Classifier-free guidance. Surprisingly, for text-to-image, CrossFlow with a vanilla transformer without cross attention slightly outperforms standard flow matching, and we show that it scales better with training steps and model size, while also allowing for interesting latent arithmetic which results in semantically meaningful edits in the output space. To demonstrate the generalizability of our approach, we also show that CrossFlow is on par with or outperforms the state-of-the-art for various cross-modal / intra-modal mapping tasks, viz. image captioning, depth estimation, and image super-resolution. We hope this paper contributes to accelerating progress in cross-modal media generation. △ Less

Submitted 24 March, 2025; v1 submitted 19 December, 2024; originally announced December 2024.

Comments: CVPR 2025 camera-ready version. Project page: https://cross-flow.github.io/

Optimising Iteration Scheduling for Full-State Vector Simulation of Quantum Circuits on FPGAs

Authors: Youssef Moawad, Andrew Brown, René Steijl, Wim Vanderbauwhede

Abstract: As the field of quantum computing grows, novel algorithms which take advantage of quantum phenomena need to be developed. As we are currently in the NISQ (noisy intermediate scale quantum) era, quantum algorithm researchers cannot reliably test their algorithms on real quantum hardware, which is still too limited. Instead, quantum computing simulators on classical computing systems are used. In th… ▽ More As the field of quantum computing grows, novel algorithms which take advantage of quantum phenomena need to be developed. As we are currently in the NISQ (noisy intermediate scale quantum) era, quantum algorithm researchers cannot reliably test their algorithms on real quantum hardware, which is still too limited. Instead, quantum computing simulators on classical computing systems are used. In the quantum circuit model, quantum bits (qubits) are operated on by quantum gates. A quantum circuit is a sequence of such quantum gates operating on some number of qubits. A quantum gate applied to a qubit can be controlled by other qubits in the circuit. This applies the gate only to the states which satisfy the required control qubit state. We particularly target FPGAs as our main simulation platform, as these offer potential energy savings when compared to running simulations on CPUs/GPUs. In this work, we present a memory access pattern to optimise the number of iterations that need to be scheduled to execute a quantum gate such that only the iterations which access the required pairs (determined according to the control qubits imposed on the gate) are scheduled. We show that this approach results in a significant reduction in the time required to simulate a gate for each added control qubit. We also show that this approach benefits the simulation time on FPGAs more than CPUs and GPUs and allows to outperform both CPU and GPU platforms in terms of energy efficiency, which is the main factor for scalability of the simulations. △ Less

Submitted 27 November, 2024; originally announced November 2024.

Web Scraping for Research: Legal, Ethical, Institutional, and Scientific Considerations

Authors: Megan A. Brown, Andrew Gruen, Gabe Maldoff, Solomon Messing, Zeve Sanderson, Michael Zimmer

Abstract: Scientists across disciplines often use data from the internet to conduct research, generating valuable insights about human behavior. However, as generative AI relying on massive text corpora becomes increasingly valuable, platforms have greatly restricted access to data through official channels. As a result, researchers will likely engage in more web scraping to collect data, introducing new ch… ▽ More Scientists across disciplines often use data from the internet to conduct research, generating valuable insights about human behavior. However, as generative AI relying on massive text corpora becomes increasingly valuable, platforms have greatly restricted access to data through official channels. As a result, researchers will likely engage in more web scraping to collect data, introducing new challenges and concerns for researchers. This paper proposes a comprehensive framework for web scraping in social science research for U.S.-based researchers, examining the legal, ethical, institutional, and scientific factors that researchers should consider when scraping the web. We present an overview of the current regulatory environment impacting when and how researchers can access, collect, store, and share data via scraping. We then provide researchers with recommendations to conduct scraping in a scientifically legitimate and ethical manner. We aim to equip researchers with the relevant information to mitigate risks and maximize the impact of their research amidst this evolving data access landscape. △ Less

Submitted 19 December, 2024; v1 submitted 30 October, 2024; originally announced October 2024.

Movie Gen: A Cast of Media Foundation Models

Authors: Adam Polyak, Amit Zohar, Andrew Brown, Andros Tjandra, Animesh Sinha, Ann Lee, Apoorv Vyas, Bowen Shi, Chih-Yao Ma, Ching-Yao Chuang, David Yan, Dhruv Choudhary, Dingkang Wang, Geet Sethi, Guan Pang, Haoyu Ma, Ishan Misra, Ji Hou, Jialiang Wang, Kiran Jagadeesh, Kunpeng Li, Luxin Zhang, Mannat Singh, Mary Williamson, Matt Le , et al. (63 additional authors not shown)

Abstract: We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization,… ▽ More We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models. All videos from this paper are available at https://go.fb.me/MovieGenResearchVideos. △ Less

Submitted 26 February, 2025; v1 submitted 17 October, 2024; originally announced October 2024.

Fast and Modular Autonomy Software for Autonomous Racing Vehicles

Authors: Andrew Saba, Aderotimi Adetunji, Adam Johnson, Aadi Kothari, Matthew Sivaprakasam, Joshua Spisak, Prem Bharatia, Arjun Chauhan, Brendan Duff Jr., Noah Gasparro, Charles King, Ryan Larkin, Brian Mao, Micah Nye, Anjali Parashar, Joseph Attias, Aurimas Balciunas, Austin Brown, Chris Chang, Ming Gao, Cindy Heredia, Andrew Keats, Jose Lavariega, William Muckelroy III, Andre Slavescu , et al. (5 additional authors not shown)

Abstract: Autonomous motorsports aim to replicate the human racecar driver with software and sensors. As in traditional motorsports, Autonomous Racing Vehicles (ARVs) are pushed to their handling limits in multi-agent scenarios at extremely high ($\geq 150mph$) speeds. This Operational Design Domain (ODD) presents unique challenges across the autonomy stack. The Indy Autonomous Challenge (IAC) is an interna… ▽ More Autonomous motorsports aim to replicate the human racecar driver with software and sensors. As in traditional motorsports, Autonomous Racing Vehicles (ARVs) are pushed to their handling limits in multi-agent scenarios at extremely high ($\geq 150mph$) speeds. This Operational Design Domain (ODD) presents unique challenges across the autonomy stack. The Indy Autonomous Challenge (IAC) is an international competition aiming to advance autonomous vehicle development through ARV competitions. While far from challenging what a human racecar driver can do, the IAC is pushing the state of the art by facilitating full-sized ARV competitions. This paper details the MIT-Pitt-RW Team's approach to autonomous racing in the IAC. In this work, we present our modular and fast approach to agent detection, motion planning and controls to create an autonomy stack. We also provide analysis of the performance of the software stack in single and multi-agent scenarios for rapid deployment in a fast-paced competition environment. We also cover what did and did not work when deployed on a physical system the Dallara AV-21 platform and potential improvements to address these shortcomings. Finally, we convey lessons learned and discuss limitations and future directions for improvement. △ Less

Submitted 27 August, 2024; originally announced August 2024.

Comments: Published in Journal of Field Robotics

Journal ref: Field Robotics Volume 4 (2024) 1-45

Data-Driven Nonlinear Deformation Design of 3D-Printable Shells

Authors: Samuel Silverman, Kelsey L. Snapp, Keith A. Brown, Emily Whiting

Abstract: Designing and fabricating structures with specific mechanical properties requires understanding the intricate relationship between design parameters and performance. Understanding the design-performance relationship becomes increasingly complicated for nonlinear deformations. Though successful at modeling elastic deformations, simulation-based techniques struggle to model large elastoplastic defor… ▽ More Designing and fabricating structures with specific mechanical properties requires understanding the intricate relationship between design parameters and performance. Understanding the design-performance relationship becomes increasingly complicated for nonlinear deformations. Though successful at modeling elastic deformations, simulation-based techniques struggle to model large elastoplastic deformations exhibiting plasticity and densification. We propose a neural network trained on experimental data to learn the design-performance relationship between 3D-printable shells and their compressive force-displacement behavior. Trained on thousands of physical experiments, our network aids in both forward and inverse design to generate shells exhibiting desired elastoplastic and hyperelastic deformations. We validate a subset of generated designs through fabrication and testing. Furthermore, we demonstrate the network's inverse design efficacy in generating custom shells for several applications. △ Less

Submitted 27 August, 2024; originally announced August 2024.

Comments: Submitted to 3D Printing and Additive Manufacturing

The VoxCeleb Speaker Recognition Challenge: A Retrospective

Authors: Jaesung Huh, Joon Son Chung, Arsha Nagrani, Andrew Brown, Jee-weon Jung, Daniel Garcia-Romero, Andrew Zisserman

Abstract: The VoxCeleb Speaker Recognition Challenges (VoxSRC) were a series of challenges and workshops that ran annually from 2019 to 2023. The challenges primarily evaluated the tasks of speaker recognition and diarisation under various settings including: closed and open training data; as well as supervised, self-supervised, and semi-supervised training for domain adaptation. The challenges also provide… ▽ More The VoxCeleb Speaker Recognition Challenges (VoxSRC) were a series of challenges and workshops that ran annually from 2019 to 2023. The challenges primarily evaluated the tasks of speaker recognition and diarisation under various settings including: closed and open training data; as well as supervised, self-supervised, and semi-supervised training for domain adaptation. The challenges also provided publicly available training and evaluation datasets for each task and setting, with new test sets released each year. In this paper, we provide a review of these challenges that covers: what they explored; the methods developed by the challenge participants and how these evolved; and also the current state of the field for speaker verification and diarisation. We chart the progress in performance over the five installments of the challenge on a common evaluation dataset and provide a detailed analysis of how each year's special focus affected participants' performance. This paper is aimed both at researchers who want an overview of the speaker recognition and diarisation field, and also at challenge organisers who want to benefit from the successes and avoid the mistakes of the VoxSRC challenges. We end with a discussion of the current strengths of the field and open challenges. Project page : https://mm.kaist.ac.kr/datasets/voxceleb/voxsrc/workshop.html △ Less

Submitted 27 August, 2024; originally announced August 2024.

Comments: TASLP 2024

Comparative Performance of the AVL Tree and Three Variants of the Red-Black Tree

Authors: Russell A. Brown

Abstract: This article compares the performance of the AVL tree to the performance of the bottom-up, top-down, and left-leaning red-black trees. The bottom-up red-black tree is faster than the AVL tree for insertion and deletion of randomly ordered keys. The AVL tree is faster than the bottom-up red-black tree for insertion but slower for deletion of consecutively ordered keys. The top-down red-black tree i… ▽ More This article compares the performance of the AVL tree to the performance of the bottom-up, top-down, and left-leaning red-black trees. The bottom-up red-black tree is faster than the AVL tree for insertion and deletion of randomly ordered keys. The AVL tree is faster than the bottom-up red-black tree for insertion but slower for deletion of consecutively ordered keys. The top-down red-black tree is faster than the bottom-up red-black tree for insertion but slower for deletion of randomly ordered keys, and slower for insertion and deletion of consecutively ordered keys. The left-leaning red-black tree is slower than the three other trees for insertion and deletion of randomly and consecutively ordered keys. An alternative deletion algorithm, which reduces the number of rebalancing operations required by deletion, is analyzed. △ Less

Submitted 2 June, 2025; v1 submitted 6 June, 2024; originally announced June 2024.

Comments: 21 pages, 8 figures, 6 tables

Journal ref: Software: Practice and Experience, 55(9):1607,2025

Testing the simplicity of strategy-proof mechanisms

Authors: Alexander L. Brown, Daniel G. Stephenson, Rodrigo A. Velez

Abstract: This paper experimentally evaluates four mechanisms intended to achieve the Uniform outcome in rationing problems (Sprumont, 1991). Our benchmark is the dominant-strategy, direct-revelation mechanism of the Uniform rule. A strategically equivalent mechanism that provides non-binding feedback during the reporting period greatly improves performance. A sequential revelation mechanism produces modest… ▽ More This paper experimentally evaluates four mechanisms intended to achieve the Uniform outcome in rationing problems (Sprumont, 1991). Our benchmark is the dominant-strategy, direct-revelation mechanism of the Uniform rule. A strategically equivalent mechanism that provides non-binding feedback during the reporting period greatly improves performance. A sequential revelation mechanism produces modest improvements despite not possessing dominant strategies. A novel, obviously strategy-proof mechanism, devised by Arribillaga et al. (2023), does not improve performance. We characterize each alternative to the direct mechanism, finding general lessons about the advantages of real-time feedback and sequentiality of play as well as the potential shortcomings of an obviously strategy-proof mechanism. △ Less

Submitted 17 April, 2024; originally announced April 2024.

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Authors: Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, Soroosh Mariooryad, Yifan Ding, Xinyang Geng, Fred Alcober, Roy Frostig, Mark Omernick, Lexi Walker, Cosmin Paduraru, Christina Sorokin, Andrea Tacchetti, Colin Gaffney, Samira Daruki, Olcan Sercinoglu, Zach Gleicher, Juliette Love , et al. (1112 additional authors not shown)

Abstract: In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February… ▽ More In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content. △ Less

Submitted 16 December, 2024; v1 submitted 8 March, 2024; originally announced March 2024.

Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Model

Authors: Andrew Brown, Jiading Zhu, Mohamed Abdelwahab, Alec Dong, Cindy Wang, Jonathan Rose

Abstract: Large Foundational Language Models are capable of performing many tasks at a high level but are difficult to deploy in many applications because of their size and proprietary ownership. Many will be motivated to distill specific capabilities of foundational models into smaller models that can be owned and controlled. In the development of a therapeutic chatbot, we wish to distill a capability know… ▽ More Large Foundational Language Models are capable of performing many tasks at a high level but are difficult to deploy in many applications because of their size and proprietary ownership. Many will be motivated to distill specific capabilities of foundational models into smaller models that can be owned and controlled. In the development of a therapeutic chatbot, we wish to distill a capability known as reflective listening, in which a therapist produces reflections of client speech. These reflections either restate what a client has said, or connect what was said to a relevant observation, idea or guess that encourages and guides the client to continue contemplation. In this paper, we present a method for distilling the generation of reflections from a Foundational Language Model (GPT-4) into smaller models. We first show that GPT-4, using zero-shot prompting, can generate reflections at near 100% success rate, superior to all previous methods. Using reflections generated by GPT-4, we fine-tune different sizes of the GPT-2 family. The GPT-2-small model achieves 83% success on a hold-out test set and the GPT-2 XL achieves 90% success. We also show that GPT-4 can help in the labor-intensive task of evaluating the quality of the distilled models, using it as a zero-shot classifier. Using triple-human review as a guide, the classifier achieves a Cohen-Kappa of 0.66, a substantial inter-rater reliability figure. △ Less

Submitted 1 February, 2024; originally announced February 2024.

Comments: Accepted to EACL 2024 Long Paper

Maximizing the Minimum Eigenvalue in Constant Dimension

Authors: Adam Brown, Aditi Laddha, Mohit Singh

Abstract: In an instance of the minimum eigenvalue problem, we are given a collection of $n$ vectors $v_1,\ldots, v_n \subset {\mathbb{R}^d}$, and the goal is to pick a subset $B\subseteq [n]$ of given vectors to maximize the minimum eigenvalue of the matrix $\sum_{i\in B} v_i v_i^{\top} $. Often, additional combinatorial constraints such as cardinality constraint $\left(|B|\leq k\right)$ or matroid constra… ▽ More In an instance of the minimum eigenvalue problem, we are given a collection of $n$ vectors $v_1,\ldots, v_n \subset {\mathbb{R}^d}$, and the goal is to pick a subset $B\subseteq [n]$ of given vectors to maximize the minimum eigenvalue of the matrix $\sum_{i\in B} v_i v_i^{\top} $. Often, additional combinatorial constraints such as cardinality constraint $\left(|B|\leq k\right)$ or matroid constraint ($B$ is a basis of a matroid defined on $[n]$) must be satisfied by the chosen set of vectors. The minimum eigenvalue problem with matroid constraints models a wide variety of problems including the Santa Clause problem, the E-design problem, and the constructive Kadison-Singer problem. In this paper, we give a randomized algorithm that finds a set $B\subseteq [n]$ subject to any matroid constraint whose minimum eigenvalue is at least $(1-ε)$ times the optimum, with high probability. The running time of the algorithm is $O\left( n^{O(d\log(d)/ε^2)}\right)$. In particular, our results give a polynomial time asymptotic scheme when the dimension of the vectors is constant. Our algorithm uses a convex programming relaxation of the problem after guessing a rescaling which allows us to apply pipage rounding and matrix Chernoff inequalities to round to a good solution. The key new component is a structural lemma which enables us to "guess'' the appropriate rescaling, which could be of independent interest. Our approach generalizes the approximation guarantee to monotone, homogeneous functions and as such we can maximize $\det(\sum_{i\in B} v_i v_i^\top)^{1/d}$, or minimize any norm of the eigenvalues of the matrix $\left(\sum_{i\in B} v_i v_i^\top\right)^{-1} $, with the same running time under some mild assumptions. As a byproduct, we also get a simple algorithm for an algorithmic version of Kadison-Singer problem. △ Less

Submitted 25 January, 2024; originally announced January 2024.

Approximation Algorithms for the Weighted Nash Social Welfare via Convex and Non-Convex Programs

Authors: Adam Brown, Aditi Laddha, Madhusudhan Reddy Pittu, Mohit Singh

Abstract: In an instance of the weighted Nash Social Welfare problem, we are given a set of $m$ indivisible items, $\mathscr{G}$, and $n$ agents, $\mathscr{A}$, where each agent $i \in \mathscr{A}$ has a valuation $v_{ij}\geq 0$ for each item $j\in \mathscr{G}$. In addition, every agent $i$ has a non-negative weight $w_i$ such that the weights collectively sum up to $1$. The goal is to find an assignment… ▽ More In an instance of the weighted Nash Social Welfare problem, we are given a set of $m$ indivisible items, $\mathscr{G}$, and $n$ agents, $\mathscr{A}$, where each agent $i \in \mathscr{A}$ has a valuation $v_{ij}\geq 0$ for each item $j\in \mathscr{G}$. In addition, every agent $i$ has a non-negative weight $w_i$ such that the weights collectively sum up to $1$. The goal is to find an assignment $σ:\mathscr{G}\rightarrow \mathscr{A}$ that maximizes $\prod_{i\in \mathscr{A}} \left(\sum_{j\in σ^{-1}(i)} v_{ij}\right)^{w_i}$, the product of the weighted valuations of the players. When all the weights equal $\frac1n$, the problem reduces to the classical Nash Social Welfare problem, which has recently received much attention. In this work, we present a $5\cdot\exp\left(2\cdot D_{\text{KL}}(\mathbf{w}\, ||\, \frac{\vec{\mathbf{1}}}{n})\right) = 5\cdot\exp\left(2\log{n} + 2\sum_{i=1}^n w_i \log{w_i}\right)$-approximation algorithm for the weighted Nash Social Welfare problem, where $D_{\text{KL}}(\mathbf{w}\, ||\, \frac{\vec{\mathbf{1}}}{n})$ denotes the KL-divergence between the distribution induced by $\mathbf{w}$ and the uniform distribution on $[n]$. We show a novel connection between the convex programming relaxations for the unweighted variant of Nash Social Welfare presented in \cite{cole2017convex, anari2017nash}, and generalize the programs to two different mathematical programs for the weighted case. The first program is convex and is necessary for computational efficiency, while the second program is a non-convex relaxation that can be rounded efficiently. The approximation factor derives from the difference in the objective values of the convex and non-convex relaxation. △ Less

Submitted 5 January, 2024; originally announced January 2024.

Motion-Conditioned Image Animation for Video Editing

Authors: Wilson Yan, Andrew Brown, Pieter Abbeel, Rohit Girdhar, Samaneh Azadi

Abstract: We introduce MoCA, a Motion-Conditioned Image Animation approach for video editing. It leverages a simple decomposition of the video editing problem into image editing followed by motion-conditioned image animation. Furthermore, given the lack of robust evaluation datasets for video editing, we introduce a new benchmark that measures edit capability across a wide variety of tasks, such as object r… ▽ More We introduce MoCA, a Motion-Conditioned Image Animation approach for video editing. It leverages a simple decomposition of the video editing problem into image editing followed by motion-conditioned image animation. Furthermore, given the lack of robust evaluation datasets for video editing, we introduce a new benchmark that measures edit capability across a wide variety of tasks, such as object replacement, background changes, style changes, and motion edits. We present a comprehensive human evaluation of the latest video editing methods along with MoCA, on our proposed benchmark. MoCA establishes a new state-of-the-art, demonstrating greater human preference win-rate, and outperforming notable recent approaches including Dreamix (63%), MasaCtrl (75%), and Tune-A-Video (72%), with especially significant improvements for motion edits. △ Less

Submitted 30 November, 2023; originally announced November 2023.

Comments: Project page: https://facebookresearch.github.io/MoCA

Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning

Authors: Rohit Girdhar, Mannat Singh, Andrew Brown, Quentin Duval, Samaneh Azadi, Sai Saketh Rambhatla, Akbar Shah, Xi Yin, Devi Parikh, Ishan Misra

Abstract: We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image. We identify critical design decisions--adjusted noise schedules for diffusion, and multi-stage training that enable us to directly generate high quality and high resoluti… ▽ More We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image. We identify critical design decisions--adjusted noise schedules for diffusion, and multi-stage training that enable us to directly generate high quality and high resolution videos, without requiring a deep cascade of models as in prior work. In human evaluations, our generated videos are strongly preferred in quality compared to all prior work--81% vs. Google's Imagen Video, 90% vs. Nvidia's PYOCO, and 96% vs. Meta's Make-A-Video. Our model outperforms commercial solutions such as RunwayML's Gen2 and Pika Labs. Finally, our factorizing approach naturally lends itself to animating images based on a user's text prompt, where our generations are preferred 96% over prior work. △ Less

Submitted 2 August, 2024; v1 submitted 17 November, 2023; originally announced November 2023.

Comments: ECCV 2024. Project page: https://emu-video.metademolab.com

Preference-conditioned Pixel-based AI Agent For Game Testing

Authors: Sherif Abdelfattah, Adrian Brown, Pushi Zhang

Abstract: The game industry is challenged to cope with increasing growth in demand and game complexity while maintaining acceptable quality standards for released games. Classic approaches solely depending on human efforts for quality assurance and game testing do not scale effectively in terms of time and cost. Game-testing AI agents that learn by interaction with the environment have the potential to miti… ▽ More The game industry is challenged to cope with increasing growth in demand and game complexity while maintaining acceptable quality standards for released games. Classic approaches solely depending on human efforts for quality assurance and game testing do not scale effectively in terms of time and cost. Game-testing AI agents that learn by interaction with the environment have the potential to mitigate these challenges with good scalability properties on time and costs. However, most recent work in this direction depends on game state information for the agent's state representation, which limits generalization across different game scenarios. Moreover, game test engineers usually prefer exploring a game in a specific style, such as exploring the golden path. However, current game testing AI agents do not provide an explicit way to satisfy such a preference. This paper addresses these limitations by proposing an agent design that mainly depends on pixel-based state observations while exploring the environment conditioned on a user's preference specified by demonstration trajectories. In addition, we propose an imitation learning method that couples self-supervised and supervised learning objectives to enhance the quality of imitation behaviors. Our agent significantly outperforms state-of-the-art pixel-based game testing agents over exploration coverage and test execution quality when evaluated on a complex open-world environment resembling many aspects of real AAA games. △ Less

Submitted 10 November, 2023; v1 submitted 18 August, 2023; originally announced August 2023.

Comments: Accepted at the IEEE Conference on Games (CoG) 2023, Boston, MA, USA

Causal Video Summarizer for Video Exploration

Authors: Jia-Hong Huang, Chao-Han Huck Yang, Pin-Yu Chen, Andrew Brown, Marcel Worring

Abstract: Recently, video summarization has been proposed as a method to help video exploration. However, traditional video summarization models only generate a fixed video summary which is usually independent of user-specific needs and hence limits the effectiveness of video exploration. Multi-modal video summarization is one of the approaches utilized to address this issue. Multi-modal video summarization… ▽ More Recently, video summarization has been proposed as a method to help video exploration. However, traditional video summarization models only generate a fixed video summary which is usually independent of user-specific needs and hence limits the effectiveness of video exploration. Multi-modal video summarization is one of the approaches utilized to address this issue. Multi-modal video summarization has a video input and a text-based query input. Hence, effective modeling of the interaction between a video input and text-based query is essential to multi-modal video summarization. In this work, a new causality-based method named Causal Video Summarizer (CVS) is proposed to effectively capture the interactive information between the video and query to tackle the task of multi-modal video summarization. The proposed method consists of a probabilistic encoder and a probabilistic decoder. Based on the evaluation of the existing multi-modal video summarization dataset, experimental results show that the proposed approach is effective with the increase of +5.4% in accuracy and +4.92% increase of F 1- score, compared with the state-of-the-art method. △ Less

Submitted 4 July, 2023; originally announced July 2023.

Comments: This paper is accepted by IEEE International Conference on Multimedia and Expo (ICME), 2022