arXiv subjects

Yu Feng

Publications and source records attributed to Yu Feng.

At least 145 records · Page 8Linked to original sources

arXiv2023

GaVe: A Webcam-Based Gaze Vending Interface Using One-Point Calibration

Even before the Covid-19 pandemic, beneficial use cases for hygienic, touchless human-machine interaction have been explored. Gaze input, i.e., information input via eye-movements of users, represents a promising method for contact-free interaction in human-machine systems. In this paper, we present the GazeVending interface (GaVe), which lets users control actions on a display with their eyes. The interface works on a regular webcam, available on most of today's laptops, and only requires a one-point calibration before use. GaVe is designed in a hierarchical structure, presenting broad item cluster to users first and subsequently guiding them through another selection round, which allows the presentation of a large number of items. Cluster/item selection in GaVe is based on the dwell time of fixations, i.e., the time duration that users look at a given Cluster/item. A user study (N=22) was conducted to test optimal dwell time thresholds and comfortable human-to-display distances. Users' perception of the system, as well as error rates and task completion time were registered. We found that all participants were able to use the system with a short time training, and showed good performance during system usage, selecting a target item within a group of 12 items in 6.76 seconds on average. Participants were able to quickly understand and know how to interact with the interface. We provide design guidelines for GaVe and discuss the potentials of the system.

cs.HC↗

arXiv2023

Generic Temporal Reasoning with Differential Analysis and Explanation

Temporal reasoning is the task of predicting temporal relations of event pairs. While temporal reasoning models can perform reasonably well on in-domain benchmarks, we have little idea of these systems' generalizability due to existing datasets' limitations. In this work, we introduce a novel task named TODAY that bridges this gap with temporal differential analysis, which as the name suggests, evaluates whether systems can correctly understand the effect of incremental changes. Specifically, TODAY introduces slight contextual changes for given event pairs, and systems are asked to tell how this subtle contextual change would affect relevant temporal relation distributions. To facilitate learning, TODAY also annotates human explanations. We show that existing models, including GPT-3.5, drop to random guessing on TODAY, suggesting that they heavily rely on spurious information rather than proper reasoning for temporal predictions. On the other hand, we show that TODAY's supervision style and explanation annotations can be used in joint learning, encouraging models to use more appropriate signals during training and thus outperform across several benchmarks. TODAY can also be used to train models to solicit incidental supervision from noisy sources such as GPT-3.5, thus moving us more toward the goal of generic temporal reasoning systems.

cs.CL↗

arXiv2023

AI-assisted super-resolution cosmological simulations III: Time evolution

In this work, we extend our recently developed super-resolution (SR) model for cosmological simulations to produce fully time consistent evolving representations of the particle phase-space distribution. We employ a style-based constrained generative adversarial network (Style-GAN) where the changing cosmic time is an input style parameter to the network. The matter power spectrum and halo mass function agree well with results from high-resolution N-body simulations over the full trained redshift range ($10 \le z \le 0$). Furthermore, we assess the temporal consistency of our SR model by constructing halo merger trees. We examine progenitors, descendants and mass growth along the tree branches. All statistical indicators demonstrate the ability of our SR model to generate satisfactory high-resolution simulations based on low-resolution inputs.

astro-ph.CO↗

arXiv2023

Spin Fluctuations in Sr$_{1.8}$La$_{0.2}$RuO$_4$

We use inelastic neutron scattering to study spin fluctuations in Sr$_{1.8}$La$_{0.2}$RuO$_4$, where Lanthanum doping triggers a Lifshitz transition by pushing the van Hove singularity in the $γ$ band to the Fermi energy. Strong spin fluctuations emerge at an incommensurate wave vector $\mathbf{Q}_{ic} = (0.3,0.3)$, corresponding to the nesting vector between $α$ and $β$ Fermi sheets. The incommensurate antiferromagnetic fluctuations shift toward $(0.25,0.25)$ with increasing energy up to ${\sim}110$ meV. By contrast, scatterings near the ferromagnetic wave vectors $\mathbf{Q} = (1,0)$ and $(1,1)$ remain featureless at all energies. This contradicts the weak-coupling perspective that suggests a sharp enhancement of ferromagnetic susceptibility due to the divergence of density of states in the associated $γ$ band. Our findings imply that ferromagnetic fluctuations in Sr$_2$RuO$_4$ and related materials do not fit into the weak-coupling paradigm, but instead are quasi-local fluctuations induced by Hund's coupling. This imposes significant constraints for the pairing mechanism involving spin fluctuations.

cond-mat.str-el↗

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

CamJ: Enabling System-Level Energy Modeling and Architectural Exploration for In-Sensor Visual Computing

CMOS Image Sensors (CIS) are fundamental to emerging visual computing applications. While conventional CIS are purely imaging devices for capturing images, increasingly CIS integrate processing capabilities such as Deep Neural Network (DNN). Computational CIS expand the architecture design space, but to date no comprehensive energy model exists. This paper proposes CamJ, a detailed energy modeling framework that provides a component-level energy breakdown for computational CIS and is validated against nine recent CIS chips. We use CamJ to demonstrate three use-cases that explore architectural trade-offs including computing in vs. off CIS, 2D vs. 3D-stacked CIS design, and analog vs. digital processing inside CIS. The code of CamJ is available at: https://github.com/horizon-research/CamJ

cs.AR↗

arXiv2023

Covariance matrices for variance-suppressed simulations

Cosmological $N$-body simulations provide numerical predictions of the structure of the Universe against which to compare data from ongoing and future surveys, but the growing volume of the Universe mapped by surveys requires correspondingly lower statistical uncertainties in simulations, usually achieved by increasing simulation sizes at the expense of computational power. It was recently proposed to reduce simulation variance without incurring additional computational costs by adopting fixed-amplitude initial conditions. This method has been demonstrated not to introduce bias in various statistics, including the two-point statistics of galaxy samples typically used for extracting cosmological parameters from galaxy redshift survey data, but requires us to revisit current methods for estimating covariance matrices of clustering statistics for simulations. In this work, we find that it is not trivial to construct covariance matrices analytically for fixed-amplitude simulations, but we demonstrate that EZmock (Effective Zel'dovich approximation mock catalogue), the most efficient method for constructing mock catalogues with accurate two- and three-point statistics, provides reasonable covariance matrix estimates for such simulations. We further examine how the variance suppression obtained by amplitude-fixing depends on three-point clustering, small-scale clustering, and galaxy bias, and propose intuitive explanations for the effects we observe based on the EZmock bias model.

astro-ph.CO↗

arXiv2023

Revisiting NLO QCD corrections to total inclusive J/psi and Upsilon photoproduction cross sections in lepton-proton collisions

We revisit inclusive J/psi and Upsilon photoproduction at lepton-hadron colliders, namely in the limit when the exchanged photon is quasi real. Our computation includes the next-to-leading-order (NLO) alpha_s corrections to the leading-order contributions in v. Similarly to the case of NLO charmonium-hadroproduction processes, the resulting cross sections obtained in the MS-bar factorisation scheme are sometimes found to be negative. We show that the scale-fixing criteria which we derived in a previous study of eta(c) production successfully solves this problem from the EicC all the way up to the FCC-eh energies. We then elaborate on how to study a scale uncertainty akin to that derived by scale variations when one fixes a scale. In turn, we investigate where both J/psi and Upsilon photoproduction could be used to improve our knowledge of gluon content of the proton at scales as low as a couple of GeV.

hep-ph↗

arXiv2022

pmwd: A Differentiable Cosmological Particle-Mesh $N$-body Library

The formation of the large-scale structure, the evolution and distribution of galaxies, quasars, and dark matter on cosmological scales, requires numerical simulations. Differentiable simulations provide gradients of the cosmological parameters, that can accelerate the extraction of physical information from statistical analyses of observational data. The deep learning revolution has brought not only myriad powerful neural networks, but also breakthroughs including automatic differentiation (AD) tools and computational accelerators like GPUs, facilitating forward modeling of the Universe with differentiable simulations. Because AD needs to save the whole forward evolution history to backpropagate gradients, current differentiable cosmological simulations are limited by memory. Using the adjoint method, with reverse time integration to reconstruct the evolution history, we develop a differentiable cosmological particle-mesh (PM) simulation library pmwd (particle-mesh with derivatives) with a low memory cost. Based on the powerful AD library JAX, pmwd is fully differentiable, and is highly performant on GPUs.

astro-ph.IM↗

arXiv2022

Dissipation enhancement of cellular flows in general advection diffusion equations

The main contribution of this paper is twofold: (1) Recently, Iyer, Xu, and Zlatoš studied the dissipation enhancement by cellular flows based on standard advection-diffusion equations via a stochastic method. We generalize their results to advective hyper-diffusion equations and advective nonlinear diffusion equations. (2) We prove there exist smooth incompressible flows that are relaxation enhancing to hyper-diffusion but not to standard diffusion.

math.AP↗

arXiv2022

Tumor boundary instability induced by nutrient consumption and supply

We investigate the tumor boundary instability induced by nutrient consumption and supply based on a Hele-Shaw model derived from taking the incompressible limit of a cell density model. We analyze the boundary stability/instability in two scenarios: 1) the front of the traveling wave; 2) the radially symmetric boundary. In each scenario, we investigate the boundary behaviors under two different nutrient supply regimes, in vitro, and in vivo. Our main conclusion is that for either scenario, the in vitro regime always stabilizes the tumor's boundary regardless of the nutrient consumption rate. However, boundary instability may occur when the tumor cells aggressively consume nutrients, and the nutrient supply is governed by the in vivo regime.

math.AP↗

arXiv2022

Dissipation enhancement for a degenerated parabolic equation

In this paper, we quantitatively consider the enhanced-dissipation effect of the advection term to the parabolic $p$-Laplacian equations. More precisely, we show the mixing property of flow for the passive scalar enhances the dissipation process of the $p$-Laplacian in the sense of $L^2$ decay, that is, the $L^2$ decay can be arbitrarily fast. The main ingredient of our argument is to understand the underlying iteration structure inherited from the parabolic $p$-Laplacian equations. This extends the dissipation enhancement result of the advection diffusion equation by Yuanyuan Feng and Gautam Iyer into a non-linear setting.

math.AP↗

arXiv2022

Hybrid Multimodal Fusion for Humor Detection

In this paper, we present our solution to the MuSe-Humor sub-challenge of the Multimodal Emotional Challenge (MuSe) 2022. The goal of the MuSe-Humor sub-challenge is to detect humor and calculate AUC from audiovisual recordings of German football Bundesliga press conferences. It is annotated for humor displayed by the coaches. For this sub-challenge, we first build a discriminant model using the transformer module and BiLSTM module, and then propose a hybrid fusion strategy to use the prediction results of each modality to improve the performance of the model. Our experiments demonstrate the effectiveness of our proposed model and hybrid fusion strategy on multimodal fusion, and the AUC of our proposed model on the test set is 0.8972.

cs.LG↗

arXiv2022

The BlueTides Mock Image Catalogue: Simulated observations of high-redshift galaxies and predictions for JWST imaging surveys

We present a mock image catalogue of ~100,000 MUV=-22.5 to -19.6 mag galaxies at z=7-12 from the BlueTides cosmological simulation. We create mock images of each galaxy with the James Webb (JWST), Hubble, Roman, and Euclid Space Telescopes, as well as Subaru, and VISTA, with a range of near- and mid-infrared filters. We perform photometry on the mock images to estimate the success of these instruments for detecting high-z galaxies. We predict that JWST will have unprecedented power in detecting high-z galaxies, with a 95% completeness limit at least 2.5 magnitudes fainter than VISTA and Subaru, 1.1 magnitudes fainter than Hubble, and 0.9 magnitudes fainter than Roman, for the same wavelength and exposure time. Focusing on JWST, we consider a range of exposure times and filters, and find that the NIRCam F356W and F277W filters will detect the faintest galaxies, with 95% completeness at m=27.4 mag in 10ks exposures. We also predict the number of high-z galaxies that will be discovered by upcoming JWST imaging surveys. We predict that the COSMOS-Web survey will detect ~1000 MUV<-20.1 mag galaxies at 6.5<z<7.5, by virtue of its large survey area. JADES-Medium will detect almost 100% of MUV<-20 mag galaxies at z<8.5 due to its significant depth, however with its smaller survey area it will detect only ~100 of these galaxies at 6.5<z<7.5. Cosmic variance results in a large range in the number of predicted galaxies each survey will detect, which is more evident in smaller surveys such as CEERS and the PEARLS NEP and GOODS-S fields.

astro-ph.GA↗

arXiv2022

Properties and Evolution of Dual and Offset AGN in the ASTRID Simulation at $z \sim 2$

We examine the dual (both BHs active) and offset (one BH active) AGN population (comprising $\sim$ 2000 pairs at $0.5\,\text{kpc}\lesssimΔr<30\,\text{kpc}$) at $z=2\sim3$ in the ASTRID simulation covering (360 cMpc)${^3}$. The dual (offset) AGN make up $3.0(2.2)\%$ of all AGN at $z=2$. The dual fraction is roughly constant while the offset fraction increases by a factor of ten from $z=4\sim2$. Compared with the full AGN population, duals are characterized by a low $M_\text{BH}/M_*$ ratio, a high specific star-formation rate (sSFR) of $\sim 1\,\text{Gyr}^{-1}$, and a high Eddington ratio ($\sim 0.05$, double that of single AGN). The dual AGN are formed in major galaxy mergers (typically involving $M_\text{halo}<10^{13}\,M_\odot$), with BHs that have similar masses. At small separations (when their host galaxies are in the late phase of the merger) duals become $2\sim8$ times brighter (albeit more obscured) than at larger separations. $80\%$ of these bright, close duals merge in the simulation within $\sim500\,\text{Myrs}$. Notably, the initially less-massive BH in duals frequently becomes the brighter AGN during the galaxy merger. In offset AGN, the active BH is typically $\gtrsim 10$ times more massive than its non-active counterpart and than most BHs in duals. Offsets are predominantly formed in minor galaxy mergers with the active BH residing in the center of massive halos ($ M_\text{ halo}\sim 10^{13-14}\,M_\odot$). In these deep potentials, gas stripping is common and the secondary quickly deactivates. The stripping also leads to inefficient orbital decay amongst offsets, which stall at $Δr\sim5\,\text{kpc}$ for a few hundred Myrs.

astro-ph.GA↗

arXiv2022

The DESI $N$-body Simulation Project -- II. Suppressing sample variance with fast simulations

Dark Energy Spectroscopic Instrument (DESI) will construct a large and precise three-dimensional map of our Universe. The survey effective volume reaches $\sim20\Gpchcube$. It is a great challenge to prepare high-resolution simulations with a much larger volume for validating the DESI analysis pipelines. \textsc{AbacusSummit} is a suite of high-resolution dark-matter-only simulations designed for this purpose, with $200\Gpchcube$ (10 times DESI volume) for the base cosmology. However, further efforts need to be done to provide a more precise analysis of the data and to cover also other cosmologies. Recently, the CARPool method was proposed to use paired accurate and approximate simulations to achieve high statistical precision with a limited number of high-resolution simulations. Relying on this technique, we propose to use fast quasi-$N$-body solvers combined with accurate simulations to produce accurate summary statistics. This enables us to obtain 100 times smaller variance than the expected DESI statistical variance at the scales we are interested in, e.g. $k < 0.3\hMpc$ for the halo power spectrum. In addition, it can significantly suppress the sample variance of the halo bispectrum. We further generalize the method for other cosmologies with only one realization in \textsc{AbacusSummit} suite to extend the effective volume $\sim 20$ times. In summary, our proposed strategy of combining high-fidelity simulations with fast approximate gravity solvers and a series of variance suppression techniques sets the path for a robust cosmological analysis of galaxy survey data.

astro-ph.CO↗

arXiv2022

Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models

Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions. This paper proposes a new embedding-based KBQA framework which particularly takes numerical reasoning into account. We present NumericalTransformer on top of NSM, a state-of-the-art embedding-based KBQA model, to create NT-NSM. To enable better training, we propose two pre-training tasks with explicit numerical-oriented loss functions on two generated training datasets and a template-based data augmentation method for enriching ordinal constrained QA dataset. Extensive experiments on KBQA benchmarks demonstrate that with the help of our training algorithm, NT-NSM is empowered with numerical reasoning skills and substantially outperforms the baselines in answering ordinal constrained questions.

cs.CL↗

arXiv2022

Crescent: Taming Memory Irregularities for Accelerating Deep Point Cloud Analytics

3D perception in point clouds is transforming the perception ability of future intelligent machines. Point cloud algorithms, however, are plagued by irregular memory accesses, leading to massive inefficiencies in the memory sub-system, which bottlenecks the overall efficiency. This paper proposes Crescent, an algorithm-hardware co-design system that tames the irregularities in deep point cloud analytics while achieving high accuracy. To that end, we introduce two approximation techniques, approximate neighbor search and selectively bank conflict elision, that "regularize" the DRAM and SRAM memory accesses. Doing so, however, necessarily introduces accuracy loss, which we mitigate by a new network training procedure that integrates approximation into the network training process. In essence, our training procedure trains models that are conditioned upon a specific approximate setting and, thus, retain a high accuracy. Experiments show that Crescent doubles the performance and halves the energy consumption compared to an optimized baseline accelerator with < 1% accuracy loss. The code of our paper is available at: https://github.com/horizon-research/crescent.

cs.AR↗