Searcharxiv⌕ Search

arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 613 records · Page 34Linked to original sources
arXiv2024

Filtering one-way Einstein-Podolsky-Rosen steering

Einstein-Podolsky-Rosen (EPR) steering, a fundamental concept of quantum nonlocality, describes one observer's capability to remotely affect another distant observer's state by local measurements. Unlike quantum entanglement and Bell nonlocality, both associated with the symmetric quantum correlation, EPR steering depicts the unique asymmetric property of quantum nonlocality. With the local filter operation in which some system components are discarded, quantum nonlocality can be distilled to enhance the nonlocal correlation, and even the hidden nonlocality can be activated. However, asymmetric quantum nonlocality in the filter operation still lacks a well-rounded investigation, especially considering the discarded parts where quantum nonlocal correlations may still exist with probabilities. Here, in both theory and experiment, we investigate the effect of reusing the discarded particles from local filter. We observe all configurations of EPR steering simultaneously and other intriguing evolution of asymmetric quantum nonlocality, such as reversing the direction of one-way EPR steering. This work provides a perspective to answer "What is the essential role of utilizing quantum steering as a resource?", and demonstrates a practical toolbox for manipulating asymmetric quantum systems with significant potential applications in quantum information tasks.

quant-ph↗
arXiv2023

Set Prediction Guided by Semantic Concepts for Diverse Video Captioning

Diverse video captioning aims to generate a set of sentences to describe the given video in various aspects. Mainstream methods are trained with independent pairs of a video and a caption from its ground-truth set without exploiting the intra-set relationship, resulting in low diversity of generated captions. Different from them, we formulate diverse captioning into a semantic-concept-guided set prediction (SCG-SP) problem by fitting the predicted caption set to the ground-truth set, where the set-level relationship is fully captured. Specifically, our set prediction consists of two synergistic tasks, i.e., caption generation and an auxiliary task of concept combination prediction providing extra semantic supervision. Each caption in the set is attached to a concept combination indicating the primary semantic content of the caption and facilitating element alignment in set prediction. Furthermore, we apply a diversity regularization term on concepts to encourage the model to generate semantically diverse captions with various concept combinations. These two tasks share multiple semantics-specific encodings as input, which are obtained by iterative interaction between visual features and conceptual queries. The correspondence between the generated captions and specific concept combinations further guarantees the interpretability of our model. Extensive experiments on benchmark datasets show that the proposed SCG-SP achieves state-of-the-art (SOTA) performance under both relevance and diversity metrics.

cs.CV↗
arXiv2023

DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution

Recent research on deep convolutional neural networks (CNNs) has provided a significant performance boost on efficient super-resolution (SR) tasks by trading off the performance and applicability. However, most existing methods focus on subtracting feature processing consumption to reduce the parameters and calculations without refining the immediate features, which leads to inadequate information in the restoration. In this paper, we propose a lightweight network termed DDistill-SR, which significantly improves the SR quality by capturing and reusing more helpful information in a static-dynamic feature distillation manner. Specifically, we propose a plug-in reparameterized dynamic unit (RDU) to promote the performance and inference cost trade-off. During the training phase, the RDU learns to linearly combine multiple reparameterizable blocks by analyzing varied input statistics to enhance layer-level representation. In the inference phase, the RDU is equally converted to simple dynamic convolutions that explicitly capture robust dynamic and static feature maps. Then, the information distillation block is constructed by several RDUs to enforce hierarchical refinement and selective fusion of spatial context information. Furthermore, we propose a dynamic distillation fusion (DDF) module to enable dynamic signals aggregation and communication between hierarchical modules to further improve performance. Empirical results show that our DDistill-SR outperforms the baselines and achieves state-of-the-art results on most super-resolution domains with much fewer parameters and less computational overhead. We have released the code of DDistill-SR at https://github.com/icandle/DDistill-SR.

eess.IV↗
arXiv2023

Object Attribute Matters in Visual Question Answering

Visual question answering is a multimodal task that requires the joint comprehension of visual and textual information. However, integrating visual and textual semantics solely through attention layers is insufficient to comprehensively understand and align information from both modalities. Intuitively, object attributes can naturally serve as a bridge to unify them, which has been overlooked in previous research. In this paper, we propose a novel VQA approach from the perspective of utilizing object attribute, aiming to achieve better object-level visual-language alignment and multimodal scene understanding. Specifically, we design an attribute fusion module and a contrastive knowledge distillation module. The attribute fusion module constructs a multimodal graph neural network to fuse attributes and visual features through message passing. The enhanced object-level visual features contribute to solving fine-grained problem like counting-question. The better object-level visual-language alignment aids in understanding multimodal scenes, thereby improving the model's robustness. Furthermore, to augment scene understanding and the out-of-distribution performance, the contrastive knowledge distillation module introduces a series of implicit knowledge. We distill knowledge into attributes through contrastive loss, which further strengthens the representation learning of attribute features and facilitates visual-linguistic alignment. Intensive experiments on six datasets, COCO-QA, VQAv2, VQA-CPv2, VQA-CPv1, VQAvs and TDIUC, show the superiority of the proposed method.

cs.CV↗
arXiv2023

The PMT System of the TRIDENT Pathfinder Experiment

Next generation neutrino telescopes are highly anticipated to boost the development of neutrino astronomy. A multi-cubic-kilometer neutrino telescope, TRopIcal DEep-sea Neutrino Telescope (TRIDENT), was proposed to be built in the South China Sea. The detector aims to achieve ~ 0.1 degree angular resolution for track-like events at energy above 100 TeV by using hybrid digital optical modules, opening new opportunities for neutrino astronomy. In order to measure the water optical properties and marine environment of the proposed TRIDENT site, a pathfinder experiment was conducted, in which a 100-meter-long string consisting of three optical modules was deployed at a depth of 3420 m to perform in-situ measurements. The central module emits light by housing LEDs, whereas the other two modules detect light with two independent and complementary systems: the PMT and the camera systems. By counting the number of detected photons and analyzing the photon arrival time distribution, the PMT system can measure the absorption and scattering lengths of sea water, which serve as the basic inputs for designing the neutrino telescope. In this paper, we present the design concept, calibration and performance of the PMT system in the pathfinder experiment.

hep-ex↗
arXiv2023

Quantum squeezing induced nonreciprocal phonon laser

Phonon lasers or coherent amplifications of mechanical oscillations have provided powerful tools for both fundamental studies of coherent acoustics and diverse applications ranging from ultrasensitive force sensing to phononic information processing. Here, we propose how to achieve directional phonon lasing with an optomechanical resonator coupled to a nonlinear optical resonator. We find that, by pumping the nonlinear resonator, directional optical squeezing can occur along the pump direction. As a result, we can achieve the directional mechanical gain by utilizing the directional optical squeezing, thus leading to nonreciprocal phonon lasing with a well-tunable directional power threshold. Our work shows a feasible way to build nonreciprocal phonon lasers with various nonlinear optical mediums, which are important for such a wide range of applications as directional acoustic amplifiers, invisible sound sensing or imaging, and one-way phononic networks.

physics.optics↗
arXiv2023

ECM-OPCC: Efficient Context Model for Octree-based Point Cloud Compression

Recently, deep learning methods have shown promising results in point cloud compression. For octree-based point cloud compression, previous works show that the information of ancestor nodes and sibling nodes are equally important for predicting current node. However, those works either adopt insufficient context or bring intolerable decoding complexity (e.g. >600s). To address this problem, we propose a sufficient yet efficient context model and design an efficient deep learning codec for point clouds. Specifically, we first propose a window-constrained multi-group coding strategy to exploit the autoregressive context while maintaining decoding efficiency. Then, we propose a dual transformer architecture to utilize the dependency of current node on its ancestors and siblings. We also propose a random-masking pre-train method to enhance our model. Experimental results show that our approach achieves state-of-the-art performance for both lossy and lossless point cloud compression. Moreover, our multi-group coding strategy saves 98% decoding time compared with previous octree-based compression method.

cs.CV↗
arXiv2023

Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models

While Multi-modal Language Models (MLMs) demonstrate impressive multimodal ability, they still struggle on providing factual and precise responses for tasks like visual question answering (VQA). In this paper, we address this challenge from the perspective of contextual information. We propose Causal Context Generation, Causal-CoG, which is a prompting strategy that engages contextual information to enhance precise VQA during inference. Specifically, we prompt MLMs to generate contexts, i.e, text description of an image, and engage the generated contexts for question answering. Moreover, we investigate the advantage of contexts on VQA from a causality perspective, introducing causality filtering to select samples for which contextual information is helpful. To show the effectiveness of Causal-CoG, we run extensive experiments on 10 multimodal benchmarks and show consistent improvements, e.g., +6.30% on POPE, +13.69% on Vizwiz and +6.43% on VQAv2 compared to direct decoding, surpassing existing methods. We hope Casual-CoG inspires explorations of context knowledge in multimodal models, and serves as a plug-and-play strategy for MLM decoding.

cs.AI↗
arXiv2023

Large Language Models for Intent-Driven Session Recommendations

Intent-aware session recommendation (ISR) is pivotal in discerning user intents within sessions for precise predictions. Traditional approaches, however, face limitations due to their presumption of a uniform number of intents across all sessions. This assumption overlooks the dynamic nature of user sessions, where the number and type of intentions can significantly vary. In addition, these methods typically operate in latent spaces, thus hinder the model's transparency.Addressing these challenges, we introduce a novel ISR approach, utilizing the advanced reasoning capabilities of large language models (LLMs). First, this approach begins by generating an initial prompt that guides LLMs to predict the next item in a session, based on the varied intents manifested in user sessions. Then, to refine this process, we introduce an innovative prompt optimization mechanism that iteratively self-reflects and adjusts prompts. Furthermore, our prompt selection module, built upon the LLMs' broad adaptability, swiftly selects the most optimized prompts across diverse domains. This new paradigm empowers LLMs to discern diverse user intents at a semantic level, leading to more accurate and interpretable session recommendations. Our extensive experiments on three real-world datasets demonstrate the effectiveness of our method, marking a significant advancement in ISR systems.

cs.CL↗
arXiv2023

Unified learning-based lossy and lossless JPEG recompression

JPEG is still the most widely used image compression algorithm. Most image compression algorithms only consider uncompressed original image, while ignoring a large number of already existing JPEG images. Recently, JPEG recompression approaches have been proposed to further reduce the size of JPEG files. However, those methods only consider JPEG lossless recompression, which is just a special case of the rate-distortion theorem. In this paper, we propose a unified lossly and lossless JPEG recompression framework, which consists of learned quantization table and Markovian hierarchical variational autoencoders. Experiments show that our method can achieve arbitrarily low distortion when the bitrate is close to the upper bound, namely the bitrate of the lossless compression model. To the best of our knowledge, this is the first learned method that bridges the gap between lossy and lossless recompression of JPEG images.

cs.CV↗
arXiv2023

Evaluating residual acceleration noise for TianQin gravitational waves observatory with an empirical magnetic field model

TianQin (TQ) project plans to deploy three satellites in space around the Earth to measure the displacement change of test masses caused by gravitational waves via laser interferometry. The requirement of the acceleration noise of the test mass is on the order of $10^{-15}~\,{\rm m}\,{\rm s}^{-2}\,{\rm Hz}^{-1/2}$ in the sensitive frequency range of TQ, %the extremely precise acceleration measurement requirements make it necessary to investigate acceleration noise due to space magnetic fields. which is so stringent that the acceleration noise caused by the interaction of the space magnetic field with the test mass needs to be investigated. In this work, by using the Tsyganenko model, a data-based empirical space magnetic field model, we obtain the magnetic field distribution around TQ's orbit spanning two solar cycles in 23 years from 1998 to 2020. With the obtained space magnetic field, we derive the distribution and amplitude spectral densities (ASDs) of the acceleration noise of TQ in 23 years. Our results reveal that the average values of the ratio of the acceleration noise cauesd by the space magnetic field to the requirements of TQ at 1 mHz ($R_{\rm 1mHz}$) and 6 mHz ($R_{\rm 6mHz}$) are 0.123$\pm$0.052 and 0.027$\pm$0.013, respectively. The occurence probabilities of $R_{\rm 1mHz}>0.2$ and $>0.3$ are only 7.9% and 1.2%, respectively, and $R_{\rm 6mHz}$ never exceeds 0.2.

astro-ph.IM↗
arXiv2023

Beamforming Design for Hybrid IRS-aided AF Relay Wireless Networks

In this paper, a hybrid IRS-aided amplify-and-forward (AF) relay wireless network is put forward, where the hybrid IRS is made up of passive and active elements. For maximum signal-to-noise ratio (SNR), a low-complexity method based on successive convex approximation and fractional programming (LC-SCA-FP) is proposed to jointly optimize the beamforming matrix at AF relay and the reflecting coefficient matrices at IRS. Simulation results verify that the rate achieved by the proposed LC-SCA-FP method surpass those of the benchmark schemes, namely the passive IRS-aided AF relay and only AF relay network.

cs.IT↗
arXiv2023

A Unified Framework for 3D Point Cloud Visual Grounding

Thanks to its precise spatial referencing, 3D point cloud visual grounding is essential for deep understanding and dynamic interaction in 3D environments, encompassing 3D Referring Expression Comprehension (3DREC) and Segmentation (3DRES). We argue that 3DREC and 3DRES should be unified in one framework, which is also a natural progression in the community. To explain, 3DREC help 3DRES locate the referent, while 3DRES also facilitate 3DREC via more fine-grained language-visual alignment. To achieve this, this paper takes the initiative step to integrate 3DREC and 3DRES into a unified framework, termed 3D Referring Transformer (3DRefTR). Its key idea is to build upon a mature 3DREC model and leverage ready query embeddings and visual tokens from the 3DREC model to construct a dedicated mask branch. Specially, we propose Superpoint Mask Branch, which serves a dual purpose: i) By harnessing on the inherent association between the superpoints and point cloud, it eliminates the heavy computational overhead on the high-resolution visual features for upsampling; ii) By leveraging the heterogeneous CPU-GPU parallelism, while the GPU is occupied generating visual and language tokens, the CPU concurrently produces superpoints, equivalently accomplishing the upsampling computation. This elaborate design enables 3DRefTR to achieve both well-performing 3DRES and 3DREC capacities with only a 6% additional latency compared to the original 3DREC model. Empirical evaluations affirm the superiority of 3DRefTR. Specifically, on the ScanRefer dataset, 3DRefTR surpasses the state-of-the-art 3DRES method by 12.43% in mIoU and improves upon the SOTA 3DREC method by 0.6% Acc@0.25IoU. The codes and models will be released soon.

cs.CV↗
arXiv2023

Trustworthy Recommender Systems

Recommender systems (RSs) aim to help users to effectively retrieve items of their interests from a large catalogue. For a quite long period of time, researchers and practitioners have been focusing on developing accurate RSs. Recent years have witnessed an increasing number of threats to RSs, coming from attacks, system and user generated noise, system bias. As a result, it has become clear that a strict focus on RS accuracy is limited and the research must consider other important factors, e.g., trustworthiness. For end users, a trustworthy RS (TRS) should not only be accurate, but also transparent, unbiased and fair as well as robust to noise or attacks. These observations actually led to a paradigm shift of the research on RSs: from accuracy-oriented RSs to TRSs. However, researchers lack a systematic overview and discussion of the literature in this novel and fast developing field of TRSs. To this end, in this paper, we provide an overview of TRSs, including a discussion of the motivation and basic concepts of TRSs, a presentation of the challenges in building TRSs, and a perspective on the future directions in this area. We also provide a novel conceptual framework to support the construction of TRSs.

cs.IR↗
arXiv2023

Interpretable Reinforcement Learning for Robotics and Continuous Control

Interpretability in machine learning is critical for the safe deployment of learned policies across legally-regulated and safety-critical domains. While gradient-based approaches in reinforcement learning have achieved tremendous success in learning policies for continuous control problems such as robotics and autonomous driving, the lack of interpretability is a fundamental barrier to adoption. We propose Interpretable Continuous Control Trees (ICCTs), a tree-based model that can be optimized via modern, gradient-based, reinforcement learning approaches to produce high-performing, interpretable policies. The key to our approach is a procedure for allowing direct optimization in a sparse decision-tree-like representation. We validate ICCTs against baselines across six domains, showing that ICCTs are capable of learning policies that parity or outperform baselines by up to 33% in autonomous driving scenarios while achieving a 300x-600x reduction in the number of parameters against deep learning baselines. We prove that ICCTs can serve as universal function approximators and display analytically that ICCTs can be verified in linear time. Furthermore, we deploy ICCTs in two realistic driving domains, based on interstate Highway-94 and 280 in the US. Finally, we verify ICCT's utility with end-users and find that ICCTs are rated easier to simulate, quicker to validate, and more interpretable than neural networks.

cs.RO↗
arXiv2023

Explainable History Distillation by Marked Temporal Point Process

Explainability of machine learning models is mandatory when researchers introduce these commonly believed black boxes to real-world tasks, especially high-stakes ones. In this paper, we build a machine learning system to automatically generate explanations of happened events from history by \gls{ca} based on the \acrfull{tpp}. Specifically, we propose a new task called \acrfull{ehd}. This task requires a model to distill as few events as possible from observed history. The target is that the event distribution conditioned on left events predicts the observed future noticeably worse. We then regard distilled events as the explanation for the future. To efficiently solve \acrshort{ehd}, we rewrite the task into a \gls{01ip} and directly estimate the solution to the program by a model called \acrfull{model}. This work fills the gap between our task and existing works, which only spot the difference between factual and counterfactual worlds after applying a predefined modification to the environment. Experiment results on Retweet and StackOverflow datasets prove that \acrshort{model} significantly outperforms other \acrshort{ehd} baselines and can reveal the rationale underpinning real-world processes.

cs.LG↗
arXiv2023

PepLand: a large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids

In recent years, the scientific community has become increasingly interested on peptides with non-canonical amino acids due to their superior stability and resistance to proteolytic degradation. These peptides present promising modifications to biological, pharmacological, and physiochemical attributes in both endogenous and engineered peptides. Notwithstanding their considerable advantages, the scientific community exhibits a conspicuous absence of an effective pre-trained model adept at distilling feature representations from such complex peptide sequences. We herein propose PepLand, a novel pre-training architecture for representation and property analysis of peptides spanning both canonical and non-canonical amino acids. In essence, PepLand leverages a comprehensive multi-view heterogeneous graph neural network tailored to unveil the subtle structural representations of peptides. Empirical validations underscore PepLand's effectiveness across an array of peptide property predictions, encompassing protein-protein interactions, permeability, solubility, and synthesizability. The rigorous evaluation confirms PepLand's unparalleled capability in capturing salient synthetic peptide features, thereby laying a robust foundation for transformative advances in peptide-centric research domains. We have made all the source code utilized in this study publicly accessible via GitHub at https://github.com/zhangruochi/pepland

q-bio.BM↗
arXiv2023

Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps

Autonomous driving has traditionally relied heavily on costly and labor-intensive High Definition (HD) maps, hindering scalability. In contrast, Standard Definition (SD) maps are more affordable and have worldwide coverage, offering a scalable alternative. In this work, we systematically explore the effect of SD maps for real-time lane-topology understanding. We propose a novel framework to integrate SD maps into online map prediction and propose a Transformer-based encoder, SD Map Encoder Representations from transFormers, to leverage priors in SD maps for the lane-topology prediction task. This enhancement consistently and significantly boosts (by up to 60%) lane detection and topology prediction on current state-of-the-art online map prediction methods without bells and whistles and can be immediately incorporated into any Transformer-based lane-topology method. Code is available at https://github.com/NVlabs/SMERF.

cs.CV↗