arXiv subjects

Ke Wang

Publications and source records attributed to Ke Wang.

At least 325 records · Page 18Linked to original sources

arXiv2024

End-to-End Autonomous Driving without Costly Modularization and 3D Manual Annotation

We propose UAD, a method for vision-based end-to-end autonomous driving (E2EAD), achieving the best open-loop evaluation performance in nuScenes, meanwhile showing robust closed-loop driving quality in CARLA. Our motivation stems from the observation that current E2EAD models still mimic the modular architecture in typical driving stacks, with carefully designed supervised perception and prediction subtasks to provide environment information for oriented planning. Although achieving groundbreaking progress, such design has certain drawbacks: 1) preceding subtasks require massive high-quality 3D annotations as supervision, posing a significant impediment to scaling the training data; 2) each submodule entails substantial computation overhead in both training and inference. To this end, we propose UAD, an E2EAD framework with an unsupervised proxy to address all these issues. Firstly, we design a novel Angular Perception Pretext to eliminate the annotation requirement. The pretext models the driving scene by predicting the angular-wise spatial objectness and temporal dynamics, without manual annotation. Secondly, a self-supervised training strategy, which learns the consistency of the predicted trajectories under different augment views, is proposed to enhance the planning robustness in steering scenarios. Our UAD achieves 38.7% relative improvements over UniAD on the average collision rate in nuScenes and surpasses VAD for 41.32 points on the driving score in CARLA's Town05 Long benchmark. Moreover, the proposed method only consumes 44.3% training resources of UniAD and runs 3.4 times faster in inference. Our innovative design not only for the first time demonstrates unarguable performance advantages over supervised counterparts, but also enjoys unprecedented efficiency in data, training, and inference. Code and models will be released at https://github.com/KargoBot_Research/UAD.

cs.CV↗

arXiv2024

Probing many-body Bell correlation depth with superconducting qubits

Quantum nonlocality describes a stronger form of quantum correlation than that of entanglement. It refutes Einstein's belief of local realism and is among the most distinctive and enigmatic features of quantum mechanics. It is a crucial resource for achieving quantum advantages in a variety of practical applications, ranging from cryptography and certified random number generation via self-testing to machine learning. Nevertheless, the detection of nonlocality, especially in quantum many-body systems, is notoriously challenging. Here, we report an experimental certification of genuine multipartite Bell correlations, which signal nonlocality in quantum many-body systems, up to 24 qubits with a fully programmable superconducting quantum processor. In particular, we employ energy as a Bell correlation witness and variationally decrease the energy of a many-body system across a hierarchy of thresholds, below which an increasing Bell correlation depth can be certified from experimental data. As an illustrating example, we variationally prepare the low-energy state of a two-dimensional honeycomb model with 73 qubits and certify its Bell correlations by measuring an energy that surpasses the corresponding classical bound with up to 48 standard deviations. In addition, we variationally prepare a sequence of low-energy states and certify their genuine multipartite Bell correlations up to 24 qubits via energies measured efficiently by parity oscillation and multiple quantum coherence techniques. Our results establish a viable approach for preparing and certifying multipartite Bell correlations, which provide not only a finer benchmark beyond entanglement for quantum devices, but also a valuable guide towards exploiting multipartite Bell correlation in a wide spectrum of practical applications.

quant-ph↗

arXiv2024

FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents

LLM-based agents have emerged as promising tools, which are crafted to fulfill complex tasks by iterative planning and action. However, these agents are susceptible to undesired planning hallucinations when lacking specific knowledge for expertise-intensive tasks. To address this, preliminary attempts are made to enhance planning reliability by incorporating external workflow-related knowledge. Despite the promise, such infused knowledge is mostly disorganized and diverse in formats, lacking rigorous formalization and comprehensive comparisons. Motivated by this, we formalize different formats of workflow knowledge and present FlowBench, the first benchmark for workflow-guided planning. FlowBench covers 51 different scenarios from 6 domains, with knowledge presented in diverse formats. To assess different LLMs on FlowBench, we design a multi-tiered evaluation framework. We evaluate the efficacy of workflow knowledge across multiple formats, and the results indicate that current LLM agents need considerable improvements for satisfactory planning. We hope that our challenging benchmark can pave the way for future agent planning research.

cs.CL↗

arXiv2024

Relative alignment between gas structures and magnetic field in Orion A at different scales using different molecular gas tracers

Context: Magnetic fields can play crucial roles in high-mass star formation. Nonetheless, the significance of magnetic fields at various scales and their relationship with gas structures is largely overlooked. Aims: Our goal is to examine the relationship between the magnetic field and molecular gas structures within the Orion A giant molecular cloud at different scales and density regimes. Methods: We assess the gas intensity structures and column densities in Orion A by utilizing $^{12}$CO, $^{13}$CO, and C$^{18}$O from Nobeyama observations. Through comparing Nobeyama observations with {\it{Planck}} polarization observations on large scales ($\sim0.6$ pc) and JCMT polarization observations on small scales ($\sim0.04$ pc), we investigate how the role of magnetic fields change with scale and density. Results: We find a similar trend from parallel to perpendicular alignment with increasing column densities in Orion A at both large and small spatial scales. Besides, when changing from low-density to high-density tracers, the relative orientation preference changes from random to perpendicular. The self-similar results at different scales indicate that magnetic fields are dynamically important in both cloud formation and filament formation. However, magnetic fields properties at small scales are relative complicated, and the interplay between magnetic field and star-forming activities needs to be discussed case-by-case.

astro-ph.GA↗

arXiv2024

StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation

Predicting the future occupancy states of the surrounding environment is a vital task for autonomous driving. However, current best-performing single-modality methods or multi-modality fusion perception methods are only able to predict uniform snapshots of future occupancy states and require strictly synchronized sensory data for sensor fusion. We propose a novel framework, StreamingFlow, to lift these strong limitations. StreamingFlow is a novel BEV occupancy predictor that ingests asynchronous multi-sensor data streams for fusion and performs streaming forecasting of the future occupancy map at any future timestamps. By integrating neural ordinary differential equations (N-ODE) into recurrent neural networks, StreamingFlow learns derivatives of BEV features over temporal horizons, updates the implicit sensor's BEV features as part of the fusion process, and propagates BEV states to the desired future time point. It shows good zero-shot generalization ability of prediction, reflected in the interpolation of the observed prediction time horizon and the reasonable inference of the unseen farther future period. Extensive experiments on two large-scale datasets, nuScenes and Lyft L5, demonstrate that StreamingFlow significantly outperforms previous vision-based, LiDAR-based methods, and shows superior performance compared to state-of-the-art fusion-based methods.

cs.CV↗

arXiv2024

PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Driving

Vision-centric occupancy networks, which represent the surrounding environment with uniform voxels with semantics, have become a new trend for safe driving of camera-only autonomous driving perception systems, as they are able to detect obstacles regardless of their shape and occlusion. Modern occupancy networks mainly focus on reconstructing visible voxels from object surfaces with voxel-wise semantic prediction. Usually, they suffer from inconsistent predictions of one object and mixed predictions for adjacent objects. These confusions may harm the safety of downstream planning modules. To this end, we investigate panoptic segmentation on 3D voxel scenarios and propose an instance-aware occupancy network, PanoSSC. We predict foreground objects and backgrounds separately and merge both in post-processing. For foreground instance grouping, we propose a novel 3D instance mask decoder that can efficiently extract individual objects. we unify geometric reconstruction, 3D semantic segmentation, and 3D instance segmentation into PanoSSC framework and propose new metrics for evaluating panoptic voxels. Extensive experiments show that our method achieves competitive results on SemanticKITTI semantic scene completion benchmark.

cs.CV↗

arXiv2024

Data Caching for Enterprise-Grade Petabyte-Scale OLAP

With the exponential growth of data and evolving use cases, petabyte-scale OLAP data platforms are increasingly adopting a model that decouples compute from storage. This shift, evident in organizations like Uber and Meta, introduces operational challenges including massive, read-heavy I/O traffic with potential throttling, as well as skewed and fragmented data access patterns. Addressing these challenges, this paper introduces the Alluxio local (edge) cache, a highly effective architectural optimization tailored for such environments. This embeddable cache, optimized for petabyte-scale data analytics, leverages local SSD resources to alleviate network I/O and API call pressures, significantly improving data transfer efficiency. Integrated with OLAP systems like Presto and storage services like HDFS, the Alluxio local cache has demonstrated its effectiveness in handling large-scale, enterprise-grade workloads over three years of deployment at Uber and Meta. We share insights and operational experiences in implementing these optimizations, providing valuable perspectives on managing modern, massive-scale OLAP workloads.

cs.DC↗

arXiv2024

Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review

Grid-centric perception is a crucial field for mobile robot perception and navigation. Nonetheless, grid-centric perception is less prevalent than object-centric perception as autonomous vehicles need to accurately perceive highly dynamic, large-scale traffic scenarios and the complexity and computational costs of grid-centric perception are high. In recent years, the rapid development of deep learning techniques and hardware provides fresh insights into the evolution of grid-centric perception. The fundamental difference between grid-centric and object-centric pipeline lies in that grid-centric perception follows a geometry-first paradigm which is more robust to the open-world driving scenarios with endless long-tailed semantically-unknown obstacles. Recent researches demonstrate the great advantages of grid-centric perception, such as comprehensive fine-grained environmental representation, greater robustness to occlusion and irregular shaped objects, better ground estimation, and safer planning policies. There is also a growing trend that the capacity of occupancy networks are greatly expanded to 4D scene perception and prediction and latest techniques are highly related to new research topics such as 4D occupancy forecasting, generative AI and world models in the field of autonomous driving. Given the lack of current surveys for this rapidly expanding field, we present a hierarchically-structured review of grid-centric perception for autonomous vehicles. We organize previous and current knowledge of occupancy grid techniques along the main vein from 2D BEV grids to 3D occupancy to 4D occupancy forecasting. We additionally summarize label-efficient occupancy learning and the role of grid-centric perception in driving systems. Lastly, we present a summary of the current research trend and provide future outlooks.

cs.CV↗

arXiv2024

Efficient Optimal Control of Open Quantum Systems

The optimal control problem for open quantum systems can be formulated as a time-dependent Lindbladian that is parameterized by a number of time-dependent control variables. Given an observable and an initial state, the goal is to tune the control variables so that the expected value of some observable with respect to the final state is maximized. In this paper, we present algorithms for solving this optimal control problem efficiently, i.e., having a poly-logarithmic dependency on the system dimension, which is exponentially faster than best-known classical algorithms. Our algorithms are hybrid, consisting of both quantum and classical components. The quantum procedure simulates time-dependent Lindblad evolution that drives the initial state to the final state, and it also provides access to the gradients of the objective function via quantum gradient estimation. The classical procedure uses the gradient information to update the control variables. At the technical level, we provide the first (to the best of our knowledge) simulation algorithm for time-dependent Lindbladians with an $\ell_1$-norm dependence. As an alternative, we also present a simulation algorithm in the interaction picture to improve the algorithm for the cases where the time-independent component of a Lindbladian dominates the time-dependent part. On the classical side, we heavily adapt the state-of-the-art classical optimization analysis to interface with the quantum part of our algorithms. Both the quantum simulation techniques and the classical optimization analyses might be of independent interest.

quant-ph↗

arXiv2024

Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels

Label noise is a pervasive problem in deep learning that often compromises the generalization performance of trained models. Recently, leveraging privileged information (PI) -- information available only during training but not at test time -- has emerged as an effective approach to mitigate this issue. Yet, existing PI-based methods have failed to consistently outperform their no-PI counterparts in terms of preventing overfitting to label noise. To address this deficiency, we introduce Pi-DUAL, an architecture designed to harness PI to distinguish clean from wrong labels. Pi-DUAL decomposes the output logits into a prediction term, based on conventional input features, and a noise-fitting term influenced solely by PI. A gating mechanism steered by PI adaptively shifts focus between these terms, allowing the model to implicitly separate the learning paths of clean and wrong labels. Empirically, Pi-DUAL achieves significant performance improvements on key PI benchmarks (e.g., +6.8% on ImageNet-PI), establishing a new state-of-the-art test set accuracy. Additionally, Pi-DUAL is a potent method for identifying noisy samples post-training, outperforming other strong methods at this task. Overall, Pi-DUAL is a simple, scalable and practical approach for mitigating the effects of label noise in a variety of real-world scenarios with PI.

cs.LG↗

arXiv2024

Influence of mid-infrared Galactic bubble on surroundings: A case study on IRAS 16489-4431

We studied the influence of a massive star on a mid-infrared bubble and its surrounding gas in the IRAS\,16489-4431 star-forming region using multi-wavelength data. The {\it Spitzer} mid-infrared band images revealed the shocked nature of the bubble. Analyses showed that the bubble is developed by a massive star owing to its strong radiation pressure. Evidence of collected material along the edge of the bubble was noted by the cold gas tracer line observed using Atacama Millimeter/submillimeter Array (ALMA). The presence of dense dust cores with bi-polar outflows and young stellar objects toward the collected material is suggestive of active star formation possibly influenced by the expansion of the radiation driven bubble.

astro-ph.GA↗

arXiv2024

The Milky Way Atlas for Linear Filaments

Filamentary structure is important for the ISM and star formation. Galactic distribution of filaments may regulate the star formation rate in the Milky Way. However, interstellar filaments are intrinsically complex, making it difficult to study quantitatively. Here, we focus on linear filaments, the simplest morphology that can be treated as building blocks of any filamentary structure. We present the first catalog of 42 ``straight-line'' filaments across the full Galactic plane, identified by clustering of far-IR Herschel HiGAL clumps in position-position-velocity space. We use molecular line cubes to investigate the dynamics along the filaments; compare the filaments with Galactic spiral arms; and compare ambient magnetic fields with the filaments' orientation. The selected filaments show extreme linearity ($>$10), aspect ratio (7-48), and velocity coherence over a length of 3-40 pc (mostly $>$10 pc). About 1/3 of them are associated with spiral arms, but only one is located in arm center, a.k.a. ``bones'' of the Milky Way. A few of them extend perpendicular to the Galactic plane, and none is located in the Central Molecular Zone (CMZ) near the Galactic center. Along the filaments, prevalent periodic oscillation (both in velocity and density) is consistent with gas flows channeled by the filaments and feeding the clumps which harbor diverse star formation activities. No correlation is found between the filament orientations with Planck measured global magnetic field lines. This work highlights some of the fundamental properties of molecular filaments and provides a golden sample for follow-up studies on star formation, ISM structure, and Milky Way structure.

astro-ph.GA↗

arXiv2024

High-Coherence Kerr-cat qubit in 2D architecture

The Kerr-cat qubit is a bosonic qubit in which multi-photon Schrodinger cat states are stabilized by applying a two-photon drive to an oscillator with a Kerr nonlinearity. The suppressed bit-flip rate with increasing cat size makes this qubit a promising candidate to implement quantum error correction codes tailored for noise-biased qubits. However, achieving strong light-matter interactions necessary for stabilizing and controlling this qubit has traditionally required strong microwave drives that heat the qubit and degrade its performance. In contrast, increasing the coupling to the drive port removes the need for strong drives at the expense of large Purcell decay. By integrating an effective band-block filter on-chip, we overcome this trade-off and realize a Kerr-cat qubit in a scalable 2D superconducting circuit with high coherence. This filter provides 30 dB of isolation at the qubit frequency with negligible attenuation at the frequencies required for stabilization and readout. We experimentally demonstrate quantum non-demolition readout fidelity of 99.6% for a cat with 8 photons. Also, to have high-fidelity universal control over this qubit, we combine fast Rabi oscillations with a new demonstration of the X(90) gate through phase modulation of the stabilization drive. Finally, the lifetime in this architecture is examined as a function of the cat size of up to 10 photons in the oscillator achieving a bit-flip time higher than 1 ms and only a linear decrease in the phase-flip time, in good agreement with the theoretical analysis of the circuit. Our qubit shows promise as a building block for fault-tolerant quantum processors with a small footprint.

quant-ph↗

arXiv2024

Localizing Task Information for Improved Model Merging and Compression

Model merging and task arithmetic have emerged as promising scalable approaches to merge multiple single-task checkpoints to one multi-task model, but their applicability is reduced by significant performance loss. Previous works have linked these drops to interference in the weight space and erasure of important task-specific features. Instead, in this work we show that the information required to solve each task is still preserved after merging as different tasks mostly use non-overlapping sets of weights. We propose TALL-masks, a method to identify these task supports given a collection of task vectors and show that one can retrieve >99% of the single task accuracy by applying our masks to the multi-task vector, effectively compressing the individual checkpoints. We study the statistics of intersections among constructed masks and reveal the existence of selfish and catastrophic weights, i.e., parameters that are important exclusively to one task and irrelevant to all tasks but detrimental to multi-task fusion. For this reason, we propose Consensus Merging, an algorithm that eliminates such weights and improves the general performance of existing model merging approaches. Our experiments in vision and NLP benchmarks with up to 20 tasks, show that Consensus Merging consistently improves existing approaches. Furthermore, our proposed compression scheme reduces storage from 57Gb to 8.2Gb while retaining 99.7% of original performance.

cs.LG↗

arXiv2024

A Survey on Hallucination in Large Vision-Language Models

Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. However, ``hallucination'', or more specifically, the misalignment between factual visual content and corresponding textual generation, poses a significant challenge of utilizing LVLMs. In this comprehensive survey, we dissect LVLM-related hallucinations in an attempt to establish an overview and facilitate future mitigation. Our scrutiny starts with a clarification of the concept of hallucinations in LVLMs, presenting a variety of hallucination symptoms and highlighting the unique challenges inherent in LVLM hallucinations. Subsequently, we outline the benchmarks and methodologies tailored specifically for evaluating hallucinations unique to LVLMs. Additionally, we delve into an investigation of the root causes of these hallucinations, encompassing insights from the training data and model components. We also critically review existing methods for mitigating hallucinations. The open questions and future directions pertaining to hallucinations within LVLMs are discussed to conclude this survey.

cs.CV↗

arXiv2024

Universal non-Hermitian flow in one-dimensional PT-symmetric quantum criticalities

The critical point of a topological phase transition is described by a conformal field theory (CFT), where the finite-size corrections to the ground state energy are uniquely related to its central charge. We study the finite-size scaling of the energy of non-Hermitian Su-Schrieffer-Heeger (SSH) model with parity and time-reversal symmetry ($\mathcal{PT}$) symmetry. We find that under open boundary condition (OBC), the energy scaling $E(L)\sim c/L$ reveals a negative central charge $c=-2$ at the non-Hermitian critical point, indicative of a non-unitary CFT. Furthermore, we discover a universal scaling function capturing the flow of a system from Dirac CFT with $c=1$ to a non-unitary CFT with $c=-2$. The scaling function demonstrates distinct behaviors at topologically non-trivial and trivial sides of critical points. Notably, within the realm of topological criticality, the scaling function exhibits an universal rise-dip-rise pattern, manifesting a characteristic singularity inherent in the non-Hermitian topological critical points. The analytic expression of the scaling function has been derived and is in good agreement with the numerical results.

cond-mat.stat-mech↗

arXiv2024

Image of Kerr-de Sitter black holes illuminated by equatorial thin accretion disks

To explore the influence of the cosmological constant on black hole images, we have developed a comprehensive analytical method for simulating images of Kerr-de Sitter black holes illuminated by equatorial thin accretion disks. Through the application of explicit equations, we simulate images of Kerr-de Sitter black holes illuminated by both prograde and retrograde accretion disks, examining the impact of the cosmological constant on their characteristic curves, relative sizes, and observed intensities. Our findings reveal that, in comparison to Kerr black holes, the cosmological constant not only diminishes the relative size of a black hole but also amplifies its luminosity. Moreover, an observer's relative position in the universe ($r_0/r_C$) can influence both the relative size and luminosity of a black hole, where $r_0$ is the distance from the observer to the black hole, $r_C$ is the cosmological horizon determined by the value of the cosmological constant $Λ$.

gr-qc↗

arXiv2024

Graph Neural Network Approach to Semantic Type Detection in Tables

This study addresses the challenge of detecting semantic column types in relational tables, a key task in many real-world applications. While language models like BERT have improved prediction accuracy, their token input constraints limit the simultaneous processing of intra-table and inter-table information. We propose a novel approach using Graph Neural Networks (GNNs) to model intra-table dependencies, allowing language models to focus on inter-table information. Our proposed method not only outperforms existing state-of-the-art algorithms but also offers novel insights into the utility and functionality of various GNN types for semantic type detection. The code is available at https://github.com/hoseinzadeehsan/GAIT

cs.LG↗