arXiv subjects

Yuting Wang

Publications and source records attributed to Yuting Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction Features

Modern search systems use a multi-stage architecture to deliver personalized results efficiently. Key stages include retrieval, pre-ranking, full ranking, and blending, which refine billions of items to top selections. The pre-ranking stage, vital for scoring and filtering hundreds of thousands of items down to a few thousand, typically relies on two tower models due to their computational efficiency, despite often lacking in capturing complex interactions. While query-item cross interaction features are paramount for full ranking, integrating them into pre-ranking models presents efficiency-related challenges. In this paper, we introduce InteractRank, a novel two tower pre-ranking model with robust cross interaction features used at Pinterest. By incorporating historical user engagement-based query-item interactions in the scoring function along with the two tower dot product, InteractRank significantly boosts pre-ranking performance with minimal latency and computation costs. In real-world A/B experiments at Pinterest, InteractRank improves the online engagement metric by 6.5% over a BM25 baseline and by 3.7% over a vanilla two tower baseline. We also highlight other components of InteractRank, like real-time user-sequence modeling, and analyze their contributions through offline ablation studies. The code for InteractRank is available at https://github.com/pinterest/atg-research/tree/main/InteractRank.

cs.IR↗

arXiv2025

FCC-ee positron source from conventional to crystal-based

The high-luminosity requirement in future lepton colliders imposes a need for a high-intensity positron source. In the conventional scheme, positron beams are obtained by the conversion of bremsstrahlung photons into electron-positron pairs through the interaction between a high-energy electron beam and a high-Z amorphous target. One method to enhance the number of produced positrons is by boosting the incident electron beam power. However, the maximum heat load and thermo-mechanical stresses bearable by the target severely limit the beam power of the incident electrons. To overcome these limitations, an innovative approach using lattice coherent effects in oriented crystals appears promising. This approach uses a single thick crystal that serves as a radiator and a converter. In this paper, we investigate the application of this scheme as an alternative to the conventional positron source at the Future Circular Collider (FCC-ee). Simulations were carried out from the positron production stage to the entrance of the damping ring to estimate the accepted positron yield. The results demonstrate the advantages of the crystal-based positron source: it requires thinner targets than the conventional scheme, resulting in a 14% reduction in the deposited power while achieving a 10% increase in accepted positron yield.

physics.acc-ph↗

arXiv2025

Low RCS High-Gain Broadband Substrate Integrated Waveguide Antenna Based on Elliptical Polarization Conversion Metasurface

Designed an elliptical polarization conversion metasurface (PCM) for Ka-band applications, alongside a high-gain substrate integrated waveguide (SIW) antenna. The PCM elements are integrated into the antenna design in a chessboard array configuration, with the goal of achieving effective reduction in the antenna's radar cross section (RCS). Both the PCM elements and antenna structure exhibit a simple design. The top layer of the metasurface (MS) elements employs an elliptical pattern symmetric along the diagonal, enabling efficient conversion of linearly polarized waves. The antenna component, on the other hand, consists of a broadband dipole antenna fed by SIW slot coupling. Verified through simulations, the polarization conversion bandwidth of this PCM unit reaches 80.38% where polarization conversion ratio (PCR) exceeds 90% (25.3-59.3GHz), demonstrating exceptional conversion performance. When the dipole antenna is combined with the PCM, its -10dB impedance bandwidth reaches to 15.09% (33.7-39.2GHz), with a maximum realized gain of 9.1dBi. Notably, the antenna loaded with the chessboard PCM structure effectively disperses the energy of scattered echoes around, significantly reducing the concentration of scattered energy in the direction of the incident wave, thereby achieving an effective reduction in RCS.

eess.SY↗

arXiv2024

Efficient Self-Supervised Video Hashing with Selective State Spaces

Self-supervised video hashing (SSVH) is a practical task in video indexing and retrieval. Although Transformers are predominant in SSVH for their impressive temporal modeling capabilities, they often suffer from computational and memory inefficiencies. Drawing inspiration from Mamba, an advanced state-space model, we explore its potential in SSVH to achieve a better balance between efficacy and efficiency. We introduce S5VH, a Mamba-based video hashing model with an improved self-supervised learning paradigm. Specifically, we design bidirectional Mamba layers for both the encoder and decoder, which are effective and efficient in capturing temporal relationships thanks to the data-dependent selective scanning mechanism with linear complexity. In our learning strategy, we transform global semantics in the feature space into semantically consistent and discriminative hash centers, followed by a center alignment loss as a global learning signal. Our self-local-global (SLG) paradigm significantly improves learning efficiency, leading to faster and better convergence. Extensive experiments demonstrate S5VH's improvements over state-of-the-art methods, superior transferability, and scalable advantages in inference efficiency. Code is available at https://github.com/gimpong/AAAI25-S5VH.

cs.CV↗

arXiv2024

Modelling the covariance matrix for the power spectra before and after the BAO reconstruction

The baryon acoustic oscillation (BAO) reconstruction plays a crucial role in cosmological analysis for spectroscopic galaxy surveys because it can make the density field effectively more linear and more Gaussian. The combination of the power spectra before and after the BAO reconstruction helps break degeneracies among parameters, then improve the constraints on cosmological parameters. It is therefore important to estimate the covariance matrix between pre- and post-reconstructed power spectra. In this work, we use perturbation theory to estimate the covariance matrix of the related power spectra multipoles, and check the accuracy of the derived covariance model using a large suite of dark matter halo catalogs at $z=0.5$. We find that the diagonal part of the auto covariance is well described by the Gaussian prediction, while the cross covariance deviates from the Gaussian prediction quickly when $k > 0.1\,h\,\mathrm{Mpc}^{-1}$. Additionally, we find the non-Gaussian effect in the non-diagonal part of the cross covariance is comparable to, or even stronger than the pre-reconstruction covariance. By adding the non-Gaussian contribution, we obtain good agreement between analytical and numerical covariance matrices in the non-diagonal part up to $k \simeq 0.15\,h\,\mathrm{Mpc}^{-1}$. The agreement in the diagonal part is also improved, but still under-predicts the correlation in the cross covariance block.

astro-ph.CO↗

arXiv2024

Extracting key information from spectroscopic galaxy surveys

We develop a novel method to extract key cosmological information, which is primarily carried by the baryon acoustic oscillations and redshift space distortions, from spectroscopic galaxy surveys based on a joint principal component analysis (PCA) and massive optimized parameter estimation and data compression (MOPED) algorithm. We apply this method to galaxy samples from BOSS DR12, and find that a PCA manipulation is effective at extracting the informative modes in the 2D correlation function, giving a tighter constraint on BAO and RSD parameters compared to that using the lowest three multipole moments by the traditional method; i.e. the Figure of Merit of BAO and RSD parameters is improved by $17\%$. We then perform a compression of the informative PC modes for BAO and RSD parameters using the MOPED scheme, reducing the dimension of the data vector to the number of interesting parameters, manifesting the joint PCA and MOPED as a powerful tool for clustering analysis with almost no loss of constraining power.

astro-ph.CO↗

arXiv2024

Detect Everything with Few Examples

Few-shot object detection aims at detecting novel categories given only a few example images. It is a basic skill for a robot to perform tasks in open environments. Recent methods focus on finetuning strategies, with complicated procedures that prohibit a wider application. In this paper, we introduce DE-ViT, a few-shot object detector without the need for finetuning. DE-ViT's novel architecture is based on a new region-propagation mechanism for localization. The propagated region masks are transformed into bounding boxes through a learnable spatial integral layer. Instead of training prototype classifiers, we propose to use prototypes to project ViT features into a subspace that is robust to overfitting on base classes. We evaluate DE-ViT on few-shot, and one-shot object detection benchmarks with Pascal VOC, COCO, and LVIS. DE-ViT establishes new state-of-the-art results on all benchmarks. Notably, for COCO, DE-ViT surpasses the few-shot SoTA by 15 mAP on 10-shot and 7.2 mAP on 30-shot and one-shot SoTA by 2.8 AP50. For LVIS, DE-ViT outperforms few-shot SoTA by 17 box APr. Further, we evaluate DE-ViT with a real robot by building a pick-and-place system for sorting novel objects based on example images. The videos of our robot demonstrations, the source code and the models of DE-ViT can be found at https://mlzxy.github.io/devit.

cs.CV↗

arXiv2024

Nodeless superconductivity and topological nodal states in molybdenum carbide

The orthorhombic molybdenum carbide superconductor with $T_c$ = 3.2 K was investigated by muon-spin rotation and relaxation ($μ$SR) measurements and by first-principle calculations. The low-temperature superfluid density, determined by transverse-field $μ$SR, suggests a fully-gapped superconducting state in Mo$_2$C, with a zero-temperature gap $Δ_0$ = 0.44 meV and a magnetic penetration depth $λ_0$ = 291 nm. The time-reversal symmetry is preserved in the superconducting state, as confirmed by the absence of an additional muon-spin relaxation in the zero-field $μ$SR spectra. Band-structure calculations indicate that the density of states at the Fermi level is dominated by the Mo $4d$-orbitals, which are marginally hybridized with the C $2p$-orbitals over a wide energy range. The symmetry analysis confirms that, in the absence of spin-orbit coupling (SOC), Mo$_2$C hosts twofold-degenerate nodal surfaces and fourfold-degenerate nodal lines. When considering SOC, the fourfold-degenerate nodal lines cross the Fermi level and contribute to the electronic properties. Our results suggest that, similarly to other phases of carbides, also the orthorhombic transition-metal carbides host topological nodal states and may be potential candidates for future studies of topological superconductivity.

cond-mat.supr-con↗

arXiv2024

FMI-TAL: Few-shot Multiple Instances Temporal Action Localization by Probability Distribution Learning and Interval Cluster Refinement

The present few-shot temporal action localization model can't handle the situation where videos contain multiple action instances. So the purpose of this paper is to achieve manifold action instances localization in a lengthy untrimmed query video using limited trimmed support videos. To address this challenging problem effectively, we proposed a novel solution involving a spatial-channel relation transformer with probability learning and cluster refinement. This method can accurately identify the start and end boundaries of actions in the query video, utilizing only a limited number of labeled videos. Our proposed method is adept at capturing both temporal and spatial contexts to effectively classify and precisely locate actions in videos, enabling a more comprehensive utilization of these crucial details. The selective cosine penalization algorithm is designed to suppress temporal boundaries that do not include action scene switches. The probability learning combined with the label generation algorithm alleviates the problem of action duration diversity and enhances the model's ability to handle fuzzy action boundaries. The interval cluster can help us get the final results with multiple instances situations in few-shot temporal action localization. Our model achieves competitive performance through meticulous experimentation utilizing the benchmark datasets ActivityNet1.3 and THUMOS14. Our code is readily available at https://github.com/ycwfs/FMI-TAL.

cs.CV↗

arXiv2024

Reinforcement Learning from Human Feedback for Lane Changing of Autonomous Vehicles in Mixed Traffic

The burgeoning field of autonomous driving necessitates the seamless integration of autonomous vehicles (AVs) with human-driven vehicles, calling for more predictable AV behavior and enhanced interaction with human drivers. Human-like driving, particularly during lane-changing maneuvers on highways, is a critical area of research due to its significant impact on safety and traffic flow. Traditional rule-based decision-making approaches often fail to encapsulate the nuanced boundaries of human behavior in diverse driving scenarios, while crafting reward functions for learning-based methods introduces its own set of complexities. This study investigates the application of Reinforcement Learning from Human Feedback (RLHF) to emulate human-like lane-changing decisions in AVs. An initial RL policy is pre-trained to ensure safe lane changes. Subsequently, this policy is employed to gather data, which is then annotated by humans to train a reward model that discerns lane changes aligning with human preferences. This human-informed reward model supersedes the original, guiding the refinement of the policy to reflect human-like preferences. The effectiveness of RLHF in producing human-like lane changes is demonstrated through the development and evaluation of conservative and aggressive lane-changing models within obstacle-rich environments and mixed autonomy traffic scenarios. The experimental outcomes underscore the potential of RLHF to diversify lane-changing behaviors in AVs, suggesting its viability for enhancing the integration of AVs into the fabric of human-driven traffic.

cs.CE↗

arXiv2024

Advanced AI Framework for Enhanced Detection and Assessment of Abdominal Trauma: Integrating 3D Segmentation with 2D CNN and RNN Models

Trauma is a significant cause of mortality and disability, particularly among individuals under forty. Traditional diagnostic methods for traumatic injuries, such as X-rays, CT scans, and MRI, are often time-consuming and dependent on medical expertise, which can delay critical interventions. This study explores the application of artificial intelligence (AI) and machine learning (ML) to improve the speed and accuracy of abdominal trauma diagnosis. We developed an advanced AI-based model combining 3D segmentation, 2D Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) to enhance diagnostic performance. Our model processes abdominal CT scans to provide real-time, precise assessments, thereby improving clinical decision-making and patient outcomes. Comprehensive experiments demonstrated that our approach significantly outperforms traditional diagnostic methods, as evidenced by rigorous evaluation metrics. This research sets a new benchmark for automated trauma detection, leveraging the strengths of AI and ML to revolutionize trauma care.

eess.IV↗

arXiv2024

The Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey: Cosmological Implications from two Decades of Spectroscopic Surveys at the Apache Point observatory

We present the cosmological implications from final measurements of clustering using galaxies, quasars, and Ly$α$ forests from the completed Sloan Digital Sky Survey (SDSS) lineage of experiments in large-scale structure. These experiments, composed of data from SDSS, SDSS-II, BOSS, and eBOSS, offer independent measurements of baryon acoustic oscillation (BAO) measurements of angular-diameter distances and Hubble distances relative to the sound horizon, $r_d$, from eight different samples and six measurements of the growth rate parameter, $fσ_8$, from redshift-space distortions (RSD). This composite sample is the most constraining of its kind and allows us to perform a comprehensive assessment of the cosmological model after two decades of dedicated spectroscopic observation. We show that the BAO data alone are able to rule out dark-energy-free models at more than eight standard deviations in an extension to the flat, $Λ$CDM model that allows for curvature. When combined with Planck Cosmic Microwave Background (CMB) measurements of temperature and polarization the BAO data provide nearly an order of magnitude improvement on curvature constraints. The RSD measurements indicate a growth rate that is consistent with predictions from Planck primary data and with General Relativity. When combining the results of SDSS BAO and RSD with external data, all multiple-parameter extensions remain consistent with a $Λ$CDM model. Regardless of cosmological model, the precision on $Ω_Λ$, $H_0$, and $σ_8$, remains at roughly 1\%, showing changes of less than 0.6\% in the central values between models. The inverse distance ladder measurement under a o$w_0w_a$CDM yields $H_0= 68.20 \pm 0.81 \, \rm km\, s^{-1} Mpc^{-1}$, remaining in tension with several direct determination methods. (abridged)

astro-ph.CO↗

arXiv2024

GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval

Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments. Due to the lack of moment annotations, the uncertainty lying in clip modeling and text-clip correspondence leads to major challenges. Despite the great progress, existing solutions either sacrifice efficiency or efficacy to capture varying and uncertain video moments. What's worse, few methods have paid attention to the text-clip matching pattern under such uncertainty, exposing the risk of semantic collapse. To address these issues, we present GMMFormer v2, an uncertainty-aware framework for PRVR. For clip modeling, we improve a strong baseline GMMFormer with a novel temporal consolidation module upon multi-scale contextual features, which maintains efficiency and improves the perception for varying moments. To achieve uncertainty-aware text-clip matching, we upgrade the query diverse loss in GMMFormer to facilitate fine-grained uniformity and propose a novel optimal matching loss for fine-grained text-clip alignment. Their collaboration alleviates the semantic collapse phenomenon and neatly promotes accurate correspondence between texts and moments. We conduct extensive experiments and ablation studies on three PRVR benchmarks, demonstrating remarkable improvement of GMMFormer v2 compared to the past SOTA competitor and the versatility of uncertainty-aware text-clip matching for PRVR. Code is available at \url{https://github.com/huangmozhi9527/GMMFormer_v2}.

cs.CV↗

arXiv2024

Extracting high-order cosmological information in galaxy surveys with power spectra

The reconstruction method was proposed more than a decade ago to boost the signal of baryonic acoustic oscillations measured in galaxy redshift surveys, which is one of key probes for dark energy. After moving the observed overdensities in galaxy surveys back to their initial position, the reconstructed density field is closer to a linear Gaussian field, with higher-order information moved back into the power spectrum. We find that by jointly analysing power spectra measured from the pre- and post-reconstructed galaxy samples, higher-order information beyond the $2$-point power spectrum can be efficiently extracted, which generally yields an information gain upon the analysis using the pre- or post-reconstructed galaxy sample alone. This opens a window to easily use higher-order information when constraining cosmological models.

astro-ph.CO↗

arXiv2024

Emulating power spectra for pre- and post-reconstructed galaxy samples

The small-scale linear information in galaxy samples typically lost during non-linear growth can be restored to a certain level by the density field reconstruction, which has been demonstrated for improving the precision of the baryon acoustic oscillations (BAO) measurements. As proposed in the literature, a joint analysis of the power spectrum before and after the reconstruction enables an efficient extraction of information carried by high-order statistics. However, the statistics of the post-reconstruction density field are difficult to model. In this work, we circumvent this issue by developing an accurate emulator for the pre-reconstructed, post-reconstructed, and cross power spectra ($P_{\rm pre}$, $P_{\rm post}$, $P_{\rm cross}$) up to $k=0.5~h~{\rm Mpc^{-1}}$ based on the \textsc{Dark Quest} N-body simulations. The accuracy of the emulator is at percent level, namely, the error of the emulated monopole and quadrupole of the power spectra is less than $1\%$ and $10\%$ of the ground truth, respectively. A fit to an example power spectra using the emulator shows that the constraints on cosmological parameters get largely improved using $P_{\rm pre}$+$P_{\rm post}$+$P_{\rm cross}$ with $k_{\rm max}=0.25~h~{\rm Mpc^{-1}}$, compared to that derived from $P_{\rm pre}$ alone, namely, the constraints on ($Ω_m$, $H_0$, $σ_8$) are tightened by $\sim41 \%-55\%$, and the uncertainties of the derived BAO and RSD parameters ($α_{\perp}$, $α_{||}$, $fσ_8$) shrink by $\sim 28\%-54\%$, respectively. This highlights the complementarity among $P_{\rm pre}$, $P_{\rm post}$ and $P_{\rm cross}$, which demonstrates the efficiency and practicability of a joint $P_{\rm pre}$, $P_{\rm post}$ and $P_{\rm cross}$ analysis for cosmological implications.

astro-ph.CO↗

arXiv2024

GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval

Given a text query, partially relevant video retrieval (PRVR) seeks to find untrimmed videos containing pertinent moments in a database. For PRVR, clip modeling is essential to capture the partial relationship between texts and videos. Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead. To solve the efficiency problem of PRVR methods, this paper proposes GMMFormer, a Gaussian-Mixture-Model based Transformer which models clip representations implicitly. During frame interactions, we incorporate Gaussian-Mixture-Model constraints to focus each frame on its adjacent frames instead of the whole video. Then generated representations will contain multi-scale clip information, achieving implicit clip modeling. In addition, PRVR methods ignore semantic differences between text queries relevant to the same video, leading to a sparse embedding space. We propose a query diverse loss to distinguish these text queries, making the embedding space more intensive and contain more semantic information. Extensive experiments on three large-scale video datasets (i.e., TVR, ActivityNet Captions, and Charades-STA) demonstrate the superiority and efficiency of GMMFormer. Code is available at \url{https://github.com/huangmozhi9527/GMMFormer}.

cs.CV↗

arXiv2023

Fully Composable and Adequate Verified Compilation with Direct Refinements between Open Modules (Technical Report)

Verified compilation of open modules (i.e., modules whose functionality depends on other modules) provides a foundation for end-to-end verification of modular programs ubiquitous in contemporary software. However, despite intensive investigation in this topic for decades, the proposed approaches are still difficult to use in practice as they rely on assumptions about the internal working of compilers which make it difficult for external users to apply the verification results. We propose an approach to verified compositional compilation without such assumptions in the setting of verifying compilation of heterogeneous modules written in first-order languages supporting global memory and pointers. Our approach is based on the memory model of CompCert and a new discovery that a Kripke relation with a notion of memory protection can serve as a uniform and composable semantic interface for the compiler passes. By absorbing the rely-guarantee conditions on memory evolution for all compiler passes into this Kripke Memory Relation and by piggybacking requirements on compiler optimizations onto it, we get compositional correctness theorems for realistic optimizing compilers as refinements that directly relate native semantics of open modules and that are ignorant of intermediate compilation processes. Such direct refinements support all the compositionality and adequacy properties essential for verified compilation of open modules. We have applied this approach to the full compilation chain of CompCert with its Clight source language and demonstrated that our compiler correctness theorem is open to composition and intuitive to use with reduced verification complexity through end-to-end verification of non-trivial heterogeneous modules that may freely invoke each other (e.g., mutually recursively).

cs.PL↗

arXiv2023

OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping

Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments. However, existing benchmarks tend to oversimplify the scene by solely focusing on lane perception tasks. Observing that human drivers rely on both lanes and traffic signals to operate their vehicles safely, we present OpenLane-V2, the first dataset on topology reasoning for traffic scene structure. The objective of the presented dataset is to advance research in understanding the structure of road scenes by examining the relationship between perceived entities, such as traffic elements and lanes. Leveraging existing datasets, OpenLane-V2 consists of 2,000 annotated road scenes that describe traffic elements and their correlation to the lanes. It comprises three primary sub-tasks, including the 3D lane detection inherited from OpenLane, accompanied by corresponding metrics to evaluate the model's performance. We evaluate various state-of-the-art methods, and present their quantitative and qualitative results on OpenLane-V2 to indicate future avenues for investigating topology reasoning in traffic scenes.

cs.CV↗