arXiv subjects

Jonathan Wang

Publications and source records attributed to Jonathan Wang.

At least 19 recordsLinked to original sources

arXiv2026

WavesFM: Hierarchical Representation Learning for Longitudinal Wearable Sensor Waveforms

Wearable sensors enable the continuous acquisition of high-resolution physiological waveforms, such as photoplethysmography and accelerometry, under free-living conditions. However, inferring health-related phenotypes from these signals presents significant challenges due to high sampling frequencies, multimodal dependencies, and extreme sequence lengths (e.g., weeks of recordings), compounded by a scarcity of ground-truth labels. To address these challenges, existing self-supervised learning (SSL) methodologies typically follow two paradigms: (1) learning rich morphological representations from short waveform segments while collapsing longitudinal dynamics through simple aggregation, or (2) modeling behavioral patterns from coarse, hand-crafted features (e.g. heart rate, step counts) spanning longer horizons but foregoing subtle, predictive signatures in raw waveforms. To bridge this gap, we propose WavesFM, a foundation model utilizing a two-stage SSL framework for longitudinal physiological data. Specifically, we decompose the learning problem into two stages: first, a segment-level encoder is pretrained to extract local embeddings from short waveforms; subsequently, a temporal encoder is trained to model the sequence of these embeddings across a multi-day horizon. This hierarchical approach overcomes the computational complexity of high-resolution, long-sequence data, allowing the overall model to capture both local signal semantics and the complex circadian and inter-day variations governing physiological dynamics. Pretrained on over 6.8M hours (N=324k individuals) of recordings for the first stage and 5.3M hours (N=10k) for the second stage, WavesFM demonstrates superior performance across 58 diverse tasks spanning demographics, lifestyle, health conditions, and medications.

cs.LG↗

arXiv2025

Smartphone monitoring of smiling as a behavioral proxy of well-being in everyday life

Subjective well-being is a cornerstone of individual and societal health, yet its scientific measurement has traditionally relied on self-report methods prone to recall bias and high participant burden. This has left a gap in our understanding of well-being as it is expressed in everyday life. We hypothesized that candid smiles captured during natural smartphone interactions could serve as a scalable, objective behavioral correlate of positive affect. To test this, we analyzed 405,448 video clips passively recorded from 233 consented participants over one week. Using a deep learning model to quantify smile intensity, we identified distinct diurnal and daily patterns. Daily patterns of smile intensity across the week showed strong correlation with national survey data on happiness (r=0.92), and diurnal rhythms documented close correspondence with established results from the day reconstruction method (r=0.80). Higher daily mean smile intensity was significantly associated with more physical activity (Beta coefficient = 0.043, 95% CI [0.001, 0.085]) and greater light exposure (Beta coefficient = 0.038, [0.013, 0.063]), whereas no significant effects were found for smartphone use. These findings suggest that passive smartphone sensing could serve as a powerful, ecologically valid methodology for studying the dynamics of affective behavior and open the door to understanding this behavior at a population scale.

cs.CV↗

arXiv2025

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

Search-augmented LLMs often struggle with complex reasoning tasks due to ineffective multi-hop retrieval and limited reasoning ability. We propose AceSearcher, a cooperative self-play framework that trains a single large language model (LLM) to alternate between two roles: a decomposer that breaks down complex queries and a solver that integrates retrieved contexts for answer generation. AceSearcher couples supervised fine-tuning on a diverse mixture of search, reasoning, and decomposition tasks with reinforcement fine-tuning optimized for final answer accuracy, eliminating the need for intermediate annotations. Extensive experiments on three reasoning-intensive tasks across 10 datasets show that AceSearcher outperforms state-of-the-art baselines, achieving an average exact match improvement of 7.6%. Remarkably, on document-level finance reasoning tasks, AceSearcher-32B matches the performance of the DeepSeek-V3 model using less than 5% of its parameters. Even at smaller scales (1.5B and 8B), AceSearcher often surpasses existing search-augmented LLMs with up to 9x more parameters, highlighting its exceptional efficiency and effectiveness in tackling complex reasoning tasks. Our code will be published at https://github.com/ritaranx/AceSearcher and https://huggingface.co/AceSearcher.

cs.CL↗

arXiv2025

A High-Throughput Platform to Bench Test Smartphone-Based Heart Rate Measurements Derived From Video

Smartphone-based heart rate (HR) monitoring apps using finger-over-camera photoplethysmography (PPG) face significant challenges in performance evaluation and device compatibility due to device variability and fragmentation. Manual testing is impractical, and standardized methods are lacking. This paper presents a novel, high-throughput bench-testing platform to address this critical need. We designed a system comprising a test rig capable of holding 12 smartphones for parallel testing, a method for generating synthetic PPG test videos with controllable HR and signal quality, and a host machine for coordinating video playback and data logging. The system achieved a mean absolute percentage error (MAPE) of 0.11% +/- 0.001% between input and measured HR, and a correlation coefficient of 0.92 +/- 0.008 between input and measured PPG signals using a clinically-validated smartphone-based HR app. Bench-testing results of 20 different smartphone models correctly classified all the devices as meeting the ANSI/CTA accuracy standards for HR monitors (MAPE <10%) when compared to a prospective clinical study with 80 participants, demonstrating high positive predictive value. This platform offers a scalable solution for pre-deployment testing of smartphone HR apps to improve app performance, ensure device compatibility, and advance the field of mobile health.

cs.CV↗

arXiv2025

Critical Anatomy-Preserving & Terrain-Augmenting Navigation (CAPTAiN): Application to Laminectomy Surgical Education

Surgical training remains a crucial milestone in modern medicine, with procedures such as laminectomy exemplifying the high risks involved. Laminectomy drilling requires precise manual control to mill bony tissue while preserving spinal segment integrity and avoiding breaches in the dura: the protective membrane surrounding the spinal cord. Despite unintended tears occurring in up to 11.3% of cases, no assistive tools are currently utilized to reduce this risk. Variability in patient anatomy further complicates learning for novice surgeons. This study introduces CAPTAiN, a critical anatomy-preserving and terrain-augmenting navigation system that provides layered, color-coded voxel guidance to enhance anatomical awareness during spinal drilling. CAPTAiN was evaluated against a standard non-navigated approach through 110 virtual laminectomies performed by 11 orthopedic residents and medical students. CAPTAiN significantly improved surgical completion rates of target anatomy (87.99% vs. 74.42%) and reduced cognitive load across multiple NASA-TLX domains. It also minimized performance gaps across experience levels, enabling novices to perform on par with advanced trainees. These findings highlight CAPTAiN's potential to optimize surgical execution and support skill development across experience levels. Beyond laminectomy, it demonstrates potential for broader applications across various surgical and drilling procedures, including those in neurosurgery, otolaryngology, and other medical fields.

cs.RO↗

arXiv2025

Passive Heart Rate Monitoring During Smartphone Use in Everyday Life

Resting heart rate (RHR) is an important biomarker of cardiovascular health and mortality, but tracking it longitudinally generally requires a wearable device, limiting its availability. We present PHRM, a deep learning system for passive heart rate (HR) and RHR measurements during everyday smartphone use, using facial video-based photoplethysmography. Our system was developed using 225,773 videos from 495 participants and validated on 185,970 videos from 205 participants in laboratory and free-living conditions, representing the largest validation study of its kind. Compared to reference electrocardiogram, PHRM achieved a mean absolute percentage error (MAPE) < 10% for HR measurements across three skin tone groups of light, medium and dark pigmentation; MAPE for each skin tone group was non-inferior versus the others. Daily RHR measured by PHRM had a mean absolute error < 5 bpm compared to a wearable HR tracker, and was associated with known risk factors. These results highlight the potential of smartphones to enable passive and equitable heart health monitoring.

q-bio.TO↗

arXiv2025

RLPP: A Residual Method for Zero-Shot Real-World Autonomous Racing on Scaled Platforms

Autonomous racing presents a complex environment requiring robust controllers capable of making rapid decisions under dynamic conditions. While traditional controllers based on tire models are reliable, they often demand extensive tuning or system identification. Reinforcement Learning (RL) methods offer significant potential due to their ability to learn directly from interaction, yet they typically suffer from the sim-to-real gap, where policies trained in simulation fail to perform effectively in the real world. In this paper, we propose RLPP, a residual RL framework that enhances a Pure Pursuit (PP) controller with an RL-based residual. This hybrid approach leverages the reliability and interpretability of PP while using RL to fine-tune the controller's performance in real-world scenarios. Extensive testing on the F1TENTH platform demonstrates that RLPP improves lap times of the baseline controllers by up to 6.37 %, closing the gap to the State-of-the-Art methods by more than 52 % and providing reliable performance in zero-shot real-world deployment, overcoming key challenges associated with the sim-to-real transfer and reducing the performance gap from simulation to reality by more than 8-fold when compared to the baseline RL controller. The RLPP framework is made available as an open-source tool, encouraging further exploration and advancement in autonomous racing research. The code is available at: www.github.com/forzaeth/rlpp.

cs.RO↗

arXiv2024

Self-Supervised Learning of Dynamic Planar Manipulation of Free-End Cables

Dynamic manipulation of free-end cables has applications for cable management in homes, warehouses and manufacturing plants. We present a supervised learning approach for dynamic manipulation of free-end cables, focusing on the problem of getting the cable endpoint to a designated target position, which may lie outside the reachable workspace of the robot end effector. We present a simulator, tune it to closely match experiments with physical cables, and then collect training data for learning dynamic cable manipulation. We evaluate with 3 cables and a physical UR5 robot. Results over 32x5 trials on 3 cables suggest that a physical UR5 robot can attain a median error distance ranging from 22% to 35% of the cable length among cables, outperforming an analytic baseline by 21% and a Gaussian Process baseline by 7% with lower interquartile range (IQR).

cs.RO↗

arXiv2024

Geometric Langlands duality for periods

We study conjectures of Ben-Zvi--Sakellaridis--Venkatesh that categorify the relationship between automorphic periods and $L$-functions in the context of the Geometric Langlands equivalence. We provide evidence for these conjectures in some low-rank examples, by using derived Fourier analysis and the theory of chiral algebras to categorify the Rankin-Selberg unfolding method.

math.NT↗

arXiv2023

Certifying Zero-Knowledge Circuits with Refinement Types

Zero-knowledge (ZK) proof systems have emerged as a promising solution for building security-sensitive applications. However, bugs in ZK applications are extremely difficult to detect and can allow a malicious party to silently exploit the system without leaving any observable trace. This paper presents Coda, a novel statically-typed language for building zero-knowledge applications. Critically, Coda makes it possible to formally specify and statically check properties of a ZK application through a rich refinement type system. One of the key challenges in formally verifying ZK applications is that they require reasoning about polynomial equations over large prime fields that go beyond the capabilities of automated theorem provers. Coda mitigates this challenge by generating a set of Coq lemmas that can be proven in an interactive manner with the help of a tactic library. We have used Coda to re-implement 79 arithmetic circuits from widely-used Circom libraries and applications. Our evaluation shows that Coda makes it possible to specify important and formally verify correctness properties of these circuits. Our evaluation also revealed 6 previously-unknown vulnerabilities in the original Circom projects.

cs.CR↗

arXiv2023

Physics-based parameterized neural ordinary differential equations: prediction of laser ignition in a rocket combustor

In this work, we present a novel physics-based data-driven framework for reduced-order modeling of laser ignition in a model rocket combustor based on parameterized neural ordinary differential equations (PNODE). Deep neural networks are embedded as functions of high-dimensional parameters of laser ignition to predict various terms in a 0D flow model including the heat source function, pre-exponential factors, and activation energy. Using the governing equations of a 0D flow model, our PNODE needs only a limited number of training samples and predicts trajectories of various quantities such as temperature, pressure, and mass fractions of species while satisfying physical constraints. We validate our physics-based PNODE on solution snapshots of high-fidelity Computational Fluid Dynamics (CFD) simulations of laser-induced ignition in a prototype rocket combustor. We compare the performance of our physics-based PNODE with that of kernel ridge regression and fully connected neural networks. Our results show that our physics-based PNODE provides solutions with lower mean absolute errors of average temperature over time, thus improving the prediction of successful laser ignition with high-dimensional parameters.

cs.LG↗

arXiv2022

Template bank for compact binary mergers in the fourth observing run of Advanced LIGO, Advanced Virgo, and KAGRA

Matched-filtering gravitational wave search pipelines identify gravitational wave signals by computing correlations, i.e., signal-to-noise ratios, between gravitational wave detector data and gravitational wave template waveforms. Intrinsic parameters, the component masses and spins, of the gravitational wave waveforms are often stored in "template banks", and the construction of a densely populated template bank is essential for some gravitational wave search pipelines. This paper presents a template bank that is currently being used by the GstLAL-based compact binary search pipeline in the fourth observing run of the LIGO, Virgo, and KAGRA collaboration, and was generated with a new binary tree approach of placing templates, {\fontfamily{qcr}\selectfont manifold}. The template bank contains $1.8 \times 10^6$ sets of template parameters covering plausible neutron star and black hole systems up to a total mass of $400$ $M_\odot$ with component masses between $1$-$200$ $M_\odot$ and mass ratios between $1$ and $20$ under the assumption that each component object's angular momentum is aligned with the orbital angular momentum. We validate the template bank generated with our new method, {\fontfamily{qcr}\selectfont manifold}, by comparing it with a template bank generated with the previously used stochastic template placement method. We show that both template banks have similar effectualness. The {\fontfamily{qcr}\selectfont GstLAL} search pipeline performs singular value decomposition (SVD) on the template banks to reduce the number of filters used. We describe a new grouping of waveforms that improves the computational efficiency of SVD by nearly $5$ times as compared to previously reported SVD sorting schemes.

gr-qc↗

arXiv2022

Feature Engineering and Classification Models for Partial Discharge in Power Transformers

To ensure reliability, power transformers are monitored for partial discharge (PD) events, which are symptoms of transformer failure. Since failures can have catastrophic cascading consequences, it is critical to preempt them as early as possible. Our goal is to classify PDs as corona, floating, particle, or void, to gain an understanding of the failure location. Using phase resolved PD signal data, we create a small set of features, which can be used to classify PDs with high accuracy. This set of features consists of the total magnitude, the maximum magnitude, and the length of the longest empty band. These features represent the entire signal and not just a single phase, so the feature set has a fixed size and is easily comprehensible. With both Random Forest and SVM classification methods, we attain a 99% classification accuracy, which is significantly higher than classification using phase based feature sets such as phase magnitude. Furthermore, we develop a stacking ensemble to combine several classification models, resulting in a superior model that outperforms existing methods in both accuracy and variance.

cs.LG↗

arXiv2022

A binary tree approach to template placement for searches for gravitational waves from compact binary mergers

We demonstrate a new geometric method for fast template placement for searches for gravitational waves from the inspiral, merger and ringdown of compact binaries. The method is based on a binary tree decomposition of the template bank parameter space into non-overlapping hypercubes. We use a numerical approximation of the signal overlap metric at the center of each hypercube to estimate the number of templates required to cover the hypercube and determine whether to further split the hypercube. As long as the expected number of templates in a given cube is greater than a given threshold, we split the cube along its longest edge according to the metric. When the expected number of templates in a given hypercube drops below this threshold, the splitting stops and a template is placed at the center of the hypercube. Using this method, we generate aligned-spin template banks covering the mass range suitable for a search of Advanced LIGO data. The aligned-spin bank required ~24 CPU-hours and produced 2 million templates. In general, we find that other methods, namely stochastic placement, produces a more strictly bounded loss in match between waveforms, with the same minimal match between waveforms requiring about twice as many templates with our proposed algorithm. Though we note that the average match is higher, which would lead to a higher detection efficiency. Our primary motivation is not to strictly minimize the number of templates with this algorithm, but rather to produce a bank with useful geometric properties in the physical parameter space coordinates. Such properties are useful for population modeling and parameter estimation.

gr-qc↗

arXiv2021

Planar Robot Casting with Real2Sim2Real Self-Supervised Learning

This paper introduces the task of {\em Planar Robot Casting (PRC)}: where one planar motion of a robot arm holding one end of a cable causes the other end to slide across the plane toward a desired target. PRC allows the cable to reach points beyond the robot workspace and has applications for cable management in homes, warehouses, and factories. To efficiently learn a PRC policy for a given cable, we propose Real2Sim2Real, a self-supervised framework that automatically collects physical trajectory examples to tune parameters of a dynamics simulator using Differential Evolution, generates many simulated examples, and then learns a policy using a weighted combination of simulated and physical data. We evaluate Real2Sim2Real with three simulators, Isaac Gym-segmented, Isaac Gym-hybrid, and PyBullet, two function approximators, Gaussian Processes and Neural Networks (NNs), and three cables with differing stiffness, torsion, and friction. Results with 240 physical trials suggest that the PRC policies can attain median error distance (as % of cable length) ranging from 8% to 14%, outperforming baselines and policies trained on only real or only simulated examples. Code, data, and videos are available at https://tinyurl.com/robotcast.

cs.RO↗

arXiv2021

Metric Assisted Stochastic Sampling (MASS) search for gravitational waves from binary black hole mergers

We present a novel gravitational wave detection algorithm that conducts a matched filter search stochastically across the compact binary parameter space rather than relying on a fixed bank of template waveforms. This technique is competitive with standard template-bank-driven pipelines in both computational cost and sensitivity. However, the complexity of the analysis is simpler allowing for easy configuration and horizontal scaling across heterogeneous grids of computers. To demonstrate the method we analyze approximately one month of public LIGO data from July 27 00:00 2017 UTC - Aug 25 22:00 2017 UTC and recover eight known confident gravitational wave candidates. We also inject simulated binary black hole (BBH) signals to demonstrate the sensitivity.

gr-qc↗

arXiv2020

Robots of the Lost Arc: Self-Supervised Learning to Dynamically Manipulate Fixed-Endpoint Cables

We explore how high-speed robot arm motions can dynamically manipulate cables to vault over obstacles, knock objects from pedestals, and weave between obstacles. In this paper, we propose a self-supervised learning framework that enables a UR5 robot to perform these three tasks. The framework finds a 3D apex point for the robot arm, which, together with a task-specific trajectory function, defines an arcing motion that dynamically manipulates the cable to perform tasks with varying obstacle and target locations. The trajectory function computes minimum-jerk motions that are constrained to remain within joint limits and to travel through the 3D apex point by repeatedly solving quadratic programs to find the shortest and fastest feasible motion. We experiment with 5 physical cables with different thickness and mass and compare performance against two baselines in which a human chooses the apex point. Results suggest that a baseline with a fixed apex across the three tasks achieves respective success rates of 51.7%, 36.7%, and 15.0%, and a baseline with human-specified, task-specific apex points achieves 66.7%, 56.7%, and 15.0% success rate respectively, while the robot using the learned apex point can achieve success rates of 81.7% in vaulting, 65.0% in knocking, and 60.0% in weaving. Code, data, and supplementary materials are available at https: //sites.google.com/berkeley.edu/dynrope/home.

cs.RO↗

arXiv2020

Intersection complexes and unramified $L$-factors

Let X be an affine spherical variety, possibly singular, and $L^+X$ its arc space. The intersection complex of $L^+X$, or rather of its finite-dimensional formal models, is conjectured to be related to special values of local unramified L-functions. Such relationships were previously established in Braverman-Finkelberg-Gaitsgory-Mirkovic for the affine closure of the quotient of a reductive group by the unipotent radical of a parabolic, and in Bouthier-Ngo-Sakellaridis for toric varieties and L-monoids. In this paper, we compute this intersection complex for the large class of those spherical G-varieties whose dual group is equal to the Langlands dual group of G, and the stalks of its nearby cycles on the horospherical degeneration of X. We formulate the answer in terms of a Kashiwara crystal, which conjecturally corresponds to a finite-dimensional representation of the dual group determined by the set of B-invariant valuations on X. We prove the latter conjecture in many cases. Under the sheaf-function dictionary, our calculations give a formula for the Plancherel density of the IC function of $L^+X$ as a ratio of local L-values for a large class of spherical varieties.

math.RT↗