arXiv subjects

Kai Xu

Publications and source records attributed to Kai Xu.

At least 199 records · Page 11Linked to original sources

arXiv2024

Relighting Scenes with Object Insertions in Neural Radiance Fields

The insertion of objects into a scene and relighting are commonly utilized applications in augmented reality (AR). Previous methods focused on inserting virtual objects using CAD models or real objects from single-view images, resulting in highly limited AR application scenarios. We propose a novel NeRF-based pipeline for inserting object NeRFs into scene NeRFs, enabling novel view synthesis and realistic relighting, supporting physical interactions like casting shadows onto each other, from two sets of images depicting the object and scene. The lighting environment is in a hybrid representation of Spherical Harmonics and Spherical Gaussians, representing both high- and low-frequency lighting components very well, and supporting non-Lambertian surfaces. Specifically, we leverage the benefits of volume rendering and introduce an innovative approach for efficient shadow rendering by comparing the depth maps between the camera view and the light source view and generating vivid soft shadows. The proposed method achieves realistic relighting effects in extensive experimental evaluations.

cs.CV↗

arXiv2024

Quantum Compiling with Reinforcement Learning on a Superconducting Processor

To effectively implement quantum algorithms on noisy intermediate-scale quantum (NISQ) processors is a central task in modern quantum technology. NISQ processors feature tens to a few hundreds of noisy qubits with limited coherence times and gate operations with errors, so NISQ algorithms naturally require employing circuits of short lengths via quantum compilation. Here, we develop a reinforcement learning (RL)-based quantum compiler for a superconducting processor and demonstrate its capability of discovering novel and hardware-amenable circuits with short lengths. We show that for the three-qubit quantum Fourier transformation, a compiled circuit using only seven CZ gates with unity circuit fidelity can be achieved. The compiler is also able to find optimal circuits under device topological constraints, with lengths considerably shorter than those by the conventional method. Our study exemplifies the codesign of the software with hardware for efficient quantum compilation, offering valuable insights for the advancement of RL-based compilers.

quant-ph↗

arXiv2024

Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions

Recently proposed reward-conditioned policies (RCPs) offer an appealing alternative in reinforcement learning. Compared with policy gradient methods, policy learning in RCPs is simpler since it is based on supervised learning, and unlike value-based methods, it does not require optimization in the action space to take actions. However, for multi-armed bandit (MAB) problems, we find that RCPs are slower to converge and have inferior expected rewards at convergence, compared with classic methods such as the upper confidence bound and Thompson sampling. In this work, we show that the performance of RCPs can be enhanced by constructing policies through the marginalization of rewards using normalized weight functions, whose sum or integral equal $1$, although the function values may be negative. We refer to this technique as generalized marginalization, whose advantage is that negative weights for policies conditioned on low rewards can make the resulting policies more distinct from them. Strategies to perform generalized marginalization in MAB with discrete action spaces are studied. Through simulations, we demonstrate that the proposed technique improves RCPs and makes them competitive with classic methods, showing superior performance on challenging MABs with large action spaces and sparse reward signals.

cs.LG↗

arXiv2024

SSR-2D: Semantic 3D Scene Reconstruction from 2D Images

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any 3D annotations. The key idea of our approach is to design a trainable model that employs both incomplete 3D reconstructions and their corresponding source RGB-D images, fusing cross-domain features into volumetric embeddings to predict complete 3D geometry, color, and semantics with only 2D labeling which can be either manual or machine-generated. Our key technical innovation is to leverage differentiable rendering of color and semantics to bridge 2D observations and unknown 3D space, using the observed RGB images and 2D semantics as supervision, respectively. We additionally develop a learning pipeline and corresponding method to enable learning from imperfect predicted 2D labels, which could be additionally acquired by synthesizing in an augmented set of virtual training views complementing the original real captures, enabling more efficient self-supervision loop for semantics. As a result, our end-to-end trainable solution jointly addresses geometry completion, colorization, and semantic mapping from limited RGB-D images, without relying on any 3D ground-truth information. Our method achieves the state-of-the-art performance of semantic scene completion on two large-scale benchmark datasets MatterPort3D and ScanNet, surpasses baselines even with costly 3D annotations in predicting both geometry and semantics. To our knowledge, our method is also the first 2D-driven method addressing completion and semantic segmentation of real-world 3D scans simultaneously.

cs.CV↗

arXiv2024

LAB: Large-Scale Alignment for ChatBots

This work introduces LAB (Large-scale Alignment for chatBots), a novel methodology designed to overcome the scalability challenges in the instruction-tuning phase of large language model (LLM) training. Leveraging a taxonomy-guided synthetic data generation process and a multi-phase tuning framework, LAB significantly reduces reliance on expensive human annotations and proprietary models like GPT-4. We demonstrate that LAB-trained models can achieve competitive performance across several benchmarks compared to models trained with traditional human-annotated or GPT-4 generated synthetic data. Thus offering a scalable, cost-effective solution for enhancing LLM capabilities and instruction-following behaviors without the drawbacks of catastrophic forgetting, marking a step forward in the efficient training of LLMs for a wide range of applications.

cs.CL↗

arXiv2024

Tunable coupling of a quantum phononic resonator to a transmon qubit with flip-chip architecture

A hybrid system with tunable coupling between phonons and qubits shows great potential for advancing quantum information processing. In this work, we demonstrate strong and tunable coupling between a surface acoustic wave (SAW) resonator and a transmon qubit based on galvanic-contact flip-chip technique. The coupling strength varies from $2π\times$7.0 MHz to -$2π\times$20.6 MHz, which is extracted from different vacuum Rabi oscillation frequencies. The phonon-induced ac Stark shift of the qubit at different coupling strengths is also shown. Our approach offers a good experimental platform for exploring quantum acoustics and hybrid systems.

quant-ph↗

arXiv2024

MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval

State-of-the-art video-text retrieval (VTR) methods typically involve fully fine-tuning a pre-trained model (e.g. CLIP) on specific datasets. However, this can result in significant storage costs in practical applications as a separate model per task must be stored. To address this issue, we present our pioneering work that enables parameter-efficient VTR using a pre-trained model, with only a small number of tunable parameters during training. Towards this goal, we propose a new method dubbed Multimodal Video Adapter (MV-Adapter) for efficiently transferring the knowledge in the pre-trained CLIP from image-text to video-text. Specifically, MV-Adapter utilizes bottleneck structures in both video and text branches, along with two novel components. The first is a Temporal Adaptation Module that is incorporated in the video branch to introduce global and local temporal contexts. We also train weights calibrations to adjust to dynamic variations across frames. The second is Cross Modality Tying that generates weights for video/text branches through sharing cross modality factors, for better aligning between modalities. Thanks to above innovations, MV-Adapter can achieve comparable or better performance than standard full fine-tuning with negligible parameters overhead. Notably, MV-Adapter consistently outperforms various competing methods in V2T/T2V tasks with large margins on five widely used VTR benchmarks (MSR-VTT, MSVD, LSMDC, DiDemo, and ActivityNet).

cs.CV↗

arXiv2024

Surface Reconstruction from Point Clouds via Grid-based Intersection Prediction

Surface reconstruction from point clouds is a crucial task in the fields of computer vision and computer graphics. SDF-based methods excel at reconstructing smooth meshes with minimal error and artefacts but struggle with representing open surfaces. On the other hand, UDF-based methods can effectively represent open surfaces but often introduce noise, leading to artefacts in the mesh. In this work, we propose a novel approach that directly predicts the intersection points between line segment of point pairs and implicit surfaces. To achieve it, we propose two modules named Relative Intersection Module and Sign Module respectively with the feature of point pair as input. To preserve the continuity of the surface, we also integrate symmetry into the two modules, which means the position of predicted intersection will not change even if the input order of the point pair changes. This method not only preserves the ability to represent open surfaces but also eliminates most artefacts on the mesh. Our approach demonstrates state-of-the-art performance on three datasets: ShapeNet, MGN, and ScanNet. The code will be made available upon acceptance.

cs.CV↗

arXiv2024

Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes

Multi-instance point cloud registration estimates the poses of multiple instances of a model point cloud in a scene point cloud. Extracting accurate point correspondence is to the center of the problem. Existing approaches usually treat the scene point cloud as a whole, overlooking the separation of instances. Therefore, point features could be easily polluted by other points from the background or different instances, leading to inaccurate correspondences oblivious to separate instances, especially in cluttered scenes. In this work, we propose MIRETR, Multi-Instance REgistration TRansformer, a coarse-to-fine approach to the extraction of instance-aware correspondences. At the coarse level, it jointly learns instance-aware superpoint features and predicts per-instance masks. With instance masks, the influence from outside of the instance being concerned is minimized, such that highly reliable superpoint correspondences can be extracted. The superpoint correspondences are then extended to instance candidates at the fine level according to the instance masks. At last, an efficient candidate selection and refinement algorithm is devised to obtain the final registrations. Extensive experiments on three public benchmarks demonstrate the efficacy of our approach. In particular, MIRETR outperforms the state of the arts by 16.6 points on F1 score on the challenging ROBI benchmark. Code and models are available at https://github.com/zhiyuanYU134/MIRETR.

cs.CV↗

arXiv2024

Black Hole Entropy for M-theory on the Quintic Threefold via F-theoretic Strings

Microscopic black hole entropy calculations in string theory usually proceeds through identifying them as wrapped strings in one higher dimension. For M-theory on elliptic Calabi-Yau threefolds this proceeds via its relation to F-theory in one higher dimension. Here we show how this method can be extended to M-theory on non-elliptic Calabi-Yau threefolds such as the quintic via conifold transition to elliptic threefolds. This leads to the computation of the black hole entropy through elliptic genera of the strings. However the Cardy formula for the computation of the black hole entropy of these strings fails because the relevant momentum excitations on the string are much smaller than the central charge of the strings. We show how the black hole attractor entropy formula leads to predicting corrections to the Cardy formula in this regime.

hep-th↗

arXiv2024

Experimental verification of the steering ellipsoid zoo via two-qubit states

Quantum steering ellipsoid visualizes the set of all qubit states that can be steered by measuring on another correlated qubit in the Bloch picture. Together with local reduced states, it provides a faithful geometric characterization of the underlying two-qubit state so that almost all nonclassical state features can be reflected in its geometric properties. Consequently, the various types of quantum ellipsoids with different geometric properties form an ellipsoid zoo, which, in this work, is experimentally verified via measurements on many polarization-path photonic states. By generating two-qubit states with high fidelity, the corresponding ellipsoids are constructed to certify the presence of entanglement, one-way Einstein-Podolsky-Rosen steering, discord, and steering incompleteness. It is also experimentally verified that the steering ellipsoid can be reconstructed from using the twelve vertices of the icosahedron as measurement directions. Our results aid progress in applying the quantum steering ellipsoid to reveal nonclassical features of the multi-qubit system.

quant-ph↗

arXiv2024

PrompTHis: Visualizing the Process and Influence of Prompt Editing during Text-to-Image Creation

Generative text-to-image models, which allow users to create appealing images through a text prompt, have seen a dramatic increase in popularity in recent years. However, most users have a limited understanding of how such models work and it often requires many trials and errors to achieve satisfactory results. The prompt history contains a wealth of information that could provide users with insights into what have been explored and how the prompt changes impact the output image, yet little research attention has been paid to the visual analysis of such process to support users. We propose the Image Variant Graph, a novel visual representation designed to support comparing prompt-image pairs and exploring the editing history. The Image Variant Graph models prompt differences as edges between corresponding images and presents the distances between images through projection. Based on the graph, we developed the PrompTHis system through co-design with artists. Besides Image Variant Graph, PrompTHis also incorporates a detailed prompt-image history and a navigation mini-map. Based on the review and analysis of the prompting history, users can better understand the impact of prompt changes and have a more effective control of image generation. A quantitative user study with eleven amateur participants and qualitative interviews with five professionals and one amateur user were conducted to evaluate the effectiveness of PrompTHis. The results demonstrate PrompTHis can help users review the prompt history, make sense of the model, and plan their creative process.

cs.HC↗

arXiv2024

Synchronized Dual-arm Rearrangement via Cooperative mTSP

Synchronized dual-arm rearrangement is widely studied as a common scenario in industrial applications. It often faces scalability challenges due to the computational complexity of robotic arm rearrangement and the high-dimensional nature of dual-arm planning. To address these challenges, we formulated the problem as cooperative mTSP, a variant of mTSP where agents share cooperative costs, and utilized reinforcement learning for its solution. Our approach involved representing rearrangement tasks using a task state graph that captured spatial relationships and a cooperative cost matrix that provided details about action costs. Taking these representations as observations, we designed an attention-based network to effectively combine them and provide rational task scheduling. Furthermore, a cost predictor is also introduced to directly evaluate actions during both training and planning, significantly expediting the planning process. Our experimental results demonstrate that our approach outperforms existing methods in terms of both performance and planning efficiency.

cs.RO↗

arXiv2024

Reducing multivariate independence testing to two bivariate means comparisons

Testing for independence between two random vectors is a fundamental problem in statistics. It is observed from empirical studies that many existing omnibus consistent tests may not work well for some strongly nonmonotonic and nonlinear relationships. To explore the reasons behind this issue, we novelly transform the multivariate independence testing problem equivalently into checking the equality of two bivariate means. An important observation we made is that the power loss is mainly due to cancellation of positive and negative terms in dependence metrics, making them very close to zero. Motivated by this observation, we propose a class of consistent metrics with a positive integer $γ$ that exactly characterize independence. Theoretically, we show that the metrics with even and infinity $γ$ can effectively avoid the cancellation, and have high powers under the alternatives that two mean differences offset each other. Since we target at a wide range of dependence scenarios in practice, we further suggest to combine the p-values of test statistics with different $γ$'s through the Fisher's method. We illustrate the advantages of our proposed tests through extensive numerical studies.

stat.ME↗

arXiv2024

High-order topological pumping on a superconducting quantum processor

High-order topological phases of matter refer to the systems of $n$-dimensional bulk with the topology of $m$-th order, exhibiting $(n-m)$-dimensional boundary modes and can be characterized by topological pumping. Here, we experimentally demonstrate two types of second-order topological pumps, forming four 0-dimensional corner localized states on a 4$\times$4 square lattice array of 16 superconducting qubits. The initial ground state of the system for half-filling, as a product of four identical entangled 4-qubit states, is prepared using an adiabatic scheme. During the pumping procedure, we adiabatically modulate the superlattice Bose-Hubbard Hamiltonian by precisely controlling both the hopping strengths and on-site potentials. At the half pumping period, the system evolves to a corner-localized state in a quadrupole configuration. The robustness of the second-order topological pump is also investigated by introducing different on-site disorder. Our work studies the topological properties of high-order topological phases from the dynamical transport picture using superconducting qubits, which would inspire further research on high-order topological phases.

quant-ph↗

arXiv2024

Learning Dual-arm Object Rearrangement for Cartesian Robots

This work focuses on the dual-arm object rearrangement problem abstracted from a realistic industrial scenario of Cartesian robots. The goal of this problem is to transfer all the objects from sources to targets with the minimum total completion time. To achieve the goal, the core idea is to develop an effective object-to-arm task assignment strategy for minimizing the cumulative task execution time and maximizing the dual-arm cooperation efficiency. One of the difficulties in the task assignment is the scalability problem. As the number of objects increases, the computation time of traditional offline-search-based methods grows strongly for computational complexity. Encouraged by the adaptability of reinforcement learning (RL) in long-sequence task decisions, we propose an online task assignment decision method based on RL, and the computation time of our method only increases linearly with the number of objects. Further, we design an attention-based network to model the dependencies between the input states during the whole task execution process to help find the most reasonable object-to-arm correspondence in each task assignment round. In the experimental part, we adapt some search-based methods to this specific setting and compare our method with them. Experimental result shows that our approach achieves outperformance over search-based methods in total execution time and computational efficiency, and also verifies the generalization of our method to different numbers of objects. In addition, we show the effectiveness of our method deployed on the real robot in the supplementary video.

cs.RO↗

arXiv2024

Conversational Crowdsensing: A Parallel Intelligence Powered Novel Sensing Approach

The transition from CPS-based Industry 4.0 to CPSS-based Industry 5.0 brings new requirements and opportunities to current sensing approaches, especially in light of recent progress in Chatbots and Large Language Models (LLMs). Therefore, the advancement of parallel intelligence-powered Crowdsensing Intelligence (CSI) is witnessed, which is currently advancing towards linguistic intelligence. In this paper, we propose a novel sensing paradigm, namely conversational crowdsensing, for Industry 5.0. It can alleviate workload and professional requirements of individuals and promote the organization and operation of diverse workforce, thereby facilitating faster response and wider popularization of crowdsensing systems. Specifically, we design the architecture of conversational crowdsensing to effectively organize three types of participants (biological, robotic, and digital) from diverse communities. Through three levels of effective conversation (i.e., inter-human, human-AI, and inter-AI), complex interactions and service functionalities of different workers can be achieved to accomplish various tasks across three sensing phases (i.e., requesting, scheduling, and executing). Moreover, we explore the foundational technologies for realizing conversational crowdsensing, encompassing LLM-based multi-agent systems, scenarios engineering and conversational human-AI cooperation. Finally, we present potential industrial applications of conversational crowdsensing and discuss its implications. We envision that conversations in natural language will become the primary communication channel during crowdsensing process, enabling richer information exchange and cooperative problem-solving among humans, robots, and AI.

cs.AI↗

arXiv2024

GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding

Speculative decoding is a relatively new decoding framework that leverages small and efficient draft models to reduce the latency of LLMs. In this study, we introduce GliDe and CaPE, two low-hassle modifications to vanilla speculative decoding to further improve the decoding speed of a frozen LLM. Specifically, GliDe is a modified draft model architecture that reuses the cached keys and values from the target LLM, while CaPE is a proposal expansion method that uses the draft model's confidence scores to help select additional candidate tokens for verification. Extensive experiments on different benchmarks demonstrate that our proposed GliDe draft model significantly reduces the expected decoding latency. Additional evaluation using walltime reveals that GliDe can accelerate Vicuna models up to 2.17x and further extend the improvement to 2.61x with CaPE. We will release our code, data, and the trained draft models.

cs.CL↗