Searcharxiv⌕ Search

arXiv subjects

Wei Liang

Publications and source records attributed to Wei Liang.

At least 73 records · Page 4Linked to original sources
arXiv2024

An alkali-referenced vector spectrum analyzer for visible-light integrated photonics

Integrated photonics has reformed our information society by offering on-chip optical signal synthesis, processing and detection with reduced size, weight and power consumption. As such, it has been successfully established in the near-infrared (NIR) telecommunication bands. With the soaring demand in miniaturized systems for biosensing, quantum information and transportable atomic clocks, extensive endeavors have been stacked on translating integrated photonics into the visible spectrum, i.e. visible-light integrated photonics. Various innovative visible-light integrated devices have been demonstrated, such as lasers, frequency combs, and atom traps, highlighting the capacity and prospect to create chip-based optical atomic clocks that can make timing and frequency metrology ubiquitous. A pillar to the development of visible-light integrated photonics is characterization techniques featuring high frequency resolution and wide spectral coverage, which however remain elusive. Here, we demonstrate a vector spectrum analyzer (VSA) for visible-light integrated photonics, offering spectral bandwidth from 766 to 795 nm and frequency resolution of 415 kHz. The VSA is rooted on a widely chirping, high-power, narrow-linewidth, mode-hop-free laser around 780 nm, which is frequency-doubled from the near-infrared via an efficient, broadband CPLN waveguide. The VSA is further referenced to hyperfine structures of rubidium and potassium atoms, enabling 8.1 MHz frequency accuracy. We apply our VSA to showcase the characterization of loss, dispersion and phase response of passive integrated devices, as well as densely spaced spectra of mode-locked lasers. Combining operation in the NIR and visible spectra, our VSA allows characterization bandwidth exceeding an octave and can be an invaluable diagnostic tool for spectroscopy, nonlinear optical processing, imaging and quantum interfaces to atomic devices.

physics.optics↗
arXiv2024

Prompt-guided Precise Audio Editing with Diffusion Models

Audio editing involves the arbitrary manipulation of audio content through precise control. Although text-guided diffusion models have made significant advancements in text-to-audio generation, they still face challenges in finding a flexible and precise way to modify target events within an audio track. We present a novel approach, referred to as PPAE, which serves as a general module for diffusion models and enables precise audio editing. The editing is based on the input textual prompt only and is entirely training-free. We exploit the cross-attention maps of diffusion models to facilitate accurate local editing and employ a hierarchical local-global pipeline to ensure a smoother editing process. Experimental results highlight the effectiveness of our method in various editing tasks.

cs.SD↗
arXiv2024

Robust inference for the unification of confidence intervals in meta-analysis

Traditional meta-analysis assumes that the effect sizes estimated in individual studies follow a Gaussian distribution. However, this distributional assumption is not always satisfied in practice, leading to potentially biased results. In the situation when the number of studies, denoted as K, is large, the cumulative Gaussian approximation errors from each study could make the final estimation unreliable. In the situation when K is small, it is not realistic to assume the random-effect follows Gaussian distribution. In this paper, we present a novel empirical likelihood method for combining confidence intervals under the meta-analysis framework. This method is free of the Gaussian assumption in effect size estimates from individual studies and from the random-effects. We establish the large-sample properties of the non-parametric estimator, and introduce a criterion governing the relationship between the number of studies, K, and the sample size of each study, n_i. Our methodology supersedes conventional meta-analysis techniques in both theoretical robustness and computational efficiency. We assess the performance of our proposed methods using simulation studies, and apply our proposed methods to two examples.

stat.ME↗
arXiv2024

Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance

Despite significant advancements in text-to-motion synthesis, generating language-guided human motion within 3D environments poses substantial challenges. These challenges stem primarily from (i) the absence of powerful generative models capable of jointly modeling natural language, 3D scenes, and human motion, and (ii) the generative models' intensive data requirements contrasted with the scarcity of comprehensive, high-quality, language-scene-motion datasets. To tackle these issues, we introduce a novel two-stage framework that employs scene affordance as an intermediate representation, effectively linking 3D scene grounding and conditional motion generation. Our framework comprises an Affordance Diffusion Model (ADM) for predicting explicit affordance map and an Affordance-to-Motion Diffusion Model (AMDM) for generating plausible human motions. By leveraging scene affordance maps, our method overcomes the difficulty in generating human motion under multimodal condition signals, especially when training with limited data lacking extensive language-scene-motion pairs. Our extensive experiments demonstrate that our approach consistently outperforms all baselines on established benchmarks, including HumanML3D and HUMANISE. Additionally, we validate our model's exceptional generalization capabilities on a specially curated evaluation set featuring previously unseen descriptions and scenes.

cs.CV↗
arXiv2024

Let Storytelling Tell Vivid Stories: An Expressive and Fluent Multimodal Storyteller

Storytelling aims to generate reasonable and vivid narratives based on an ordered image stream. The fidelity to the image story theme and the divergence of story plots attract readers to keep reading. Previous works iteratively improved the alignment of multiple modalities but ultimately resulted in the generation of simplistic storylines for image streams. In this work, we propose a new pipeline, termed LLaMS, to generate multimodal human-level stories that are embodied in expressiveness and consistency. Specifically, by fully exploiting the commonsense knowledge within the LLM, we first employ a sequence data auto-enhancement strategy to enhance factual content expression and leverage a textual reasoning architecture for expressive story generation and prediction. Secondly, we propose SQ-Adatpter module for story illustration generation which can maintain sequence consistency. Numerical results are conducted through human evaluation to verify the superiority of proposed LLaMS. Evaluations show that LLaMS achieves state-of-the-art storytelling performance and 86% correlation and 100% consistency win rate as compared with previous SOTA methods. Furthermore, ablation experiments are conducted to verify the effectiveness of proposed sequence data enhancement and SQ-Adapter.

cs.CV↗
arXiv2024

Miniature narrow-linewidth 1 μm Laser

Self-injection locking scheme has the potential to narrow the linewidth of lasers in a compact setup. Here, we report a narrow linewidth laser source near 1 μm by self-injection locking scheme using a Fabry-Perot (FP) hollow resonator with a high-quality factor (Q>10^8). The measured fundamental linewidth of the laser is 41 Hz, and a coarse tuning range over 5.5 nm is achieved by changing the driving current of the laser source. Meanwhile, a fine-tuning range of 373 MHz is achieved without mode hops by changing the voltage applied to the PZT on the resonator. More importantly, benefiting from the low thermal refractive noise and low thermal expansion of the FP hollow resonator, the beat-note linewidth and the frequency Allan deviation are measured to be 510.3 Hz in and 10^-11 (1s averaging time), respectively, by using a fully stabilized frequency comb as reference. Such a high-performance laser is fully integrated with a palm-sized package (52.3 mL) for field-deployable applications.

physics.optics↗
arXiv2024

$a_0(1710)$-$f_0(1710)$ mixing effect in the $D_{s}^{+} \rightarrow K_S^{0} K_S^{0} π^{+}$ decay

With the measurements of the decay $D^+_s \rightarrow K^0_S K^0_S π^+$ by the BESIII Collaboration, we investigate this three-body weak decay via the chiral unitary approach for the final state interaction, where the resonances $S(980)$ and $S(1710)$ are dynamically reproduced with the interaction of eleven coupled channels, and the $W$-external and -internal emission mechanisms are considered at the quark level. Besides, we also take into account the contribution from the $P$-wave resonance $K^*(892)^+$ and make a combined fit of the $K^0_S K^0_S$ and $K^0_S π^+$ invariant mass spectra measured by the BESIII Collaboration. The fitted results show that the enhancement around 1.7 GeV in $K^0_S K^0_S$ mass spectrum is overlapped with two visible peaks, indicating the mixing signal originated from the resonances $a_0(1710)$ and $f_0(1710)$ due to their different poles (masses). Thus, the decay $D^+_s \rightarrow K^0_S K^0_S π^+$ is helpful to reveal their molecular nature with the mixing signal, which can be more precisely measured in the future.

hep-ph↗
arXiv2023

Language-driven All-in-one Adverse Weather Removal

All-in-one (AiO) frameworks restore various adverse weather degradations with a single set of networks jointly. To handle various weather conditions, an AiO framework is expected to adaptively learn weather-specific knowledge for different degradations and shared knowledge for common patterns. However, existing methods: 1) rely on extra supervision signals, which are usually unknown in real-world applications; 2) employ fixed network structures, which restrict the diversity of weather-specific knowledge. In this paper, we propose a Language-driven Restoration framework (LDR) to alleviate the aforementioned issues. First, we leverage the power of pre-trained vision-language (PVL) models to enrich the diversity of weather-specific knowledge by reasoning about the occurrence, type, and severity of degradation, generating description-based degradation priors. Then, with the guidance of degradation prior, we sparsely select restoration experts from a candidate list dynamically based on a Mixture-of-Experts (MoE) structure. This enables us to adaptively learn the weather-specific and shared knowledge to handle various weather conditions (e.g., unknown or mixed weather). Experiments on extensive restoration scenarios show our superior performance (see Fig. 1). The source code will be made available.

cs.CV↗
arXiv2023

Active Reasoning in an Open-World Environment

Recent advances in vision-language learning have achieved notable success on complete-information question-answering datasets through the integration of extensive world knowledge. Yet, most models operate passively, responding to questions based on pre-stored knowledge. In stark contrast, humans possess the ability to actively explore, accumulate, and reason using both newfound and existing information to tackle incomplete-information questions. In response to this gap, we introduce $Conan$, an interactive open-world environment devised for the assessment of active reasoning. $Conan$ facilitates active exploration and promotes multi-round abductive inference, reminiscent of rich, open-world settings like Minecraft. Diverging from previous works that lean primarily on single-round deduction via instruction following, $Conan$ compels agents to actively interact with their surroundings, amalgamating new evidence with prior knowledge to elucidate events from incomplete observations. Our analysis on $Conan$ underscores the shortcomings of contemporary state-of-the-art models in active exploration and understanding complex scenarios. Additionally, we explore Abduction from Deduction, where agents harness Bayesian rules to recast the challenge of abduction as a deductive process. Through $Conan$, we aim to galvanize advancements in active reasoning and set the stage for the next generation of artificial intelligence agents adept at dynamically engaging in environments.

cs.AI↗
arXiv2023

Interactive Visual Reasoning under Uncertainty

One of the fundamental cognitive abilities of humans is to quickly resolve uncertainty by generating hypotheses and testing them via active trials. Encountering a novel phenomenon accompanied by ambiguous cause-effect relationships, humans make hypotheses against data, conduct inferences from observation, test their theory via experimentation, and correct the proposition if inconsistency arises. These iterative processes persist until the underlying mechanism becomes clear. In this work, we devise the IVRE (pronounced as "ivory") environment for evaluating artificial agents' reasoning ability under uncertainty. IVRE is an interactive environment featuring rich scenarios centered around Blicket detection. Agents in IVRE are placed into environments with various ambiguous action-effect pairs and asked to determine each object's role. They are encouraged to propose effective and efficient experiments to validate their hypotheses based on observations and actively gather new information. The game ends when all uncertainties are resolved or the maximum number of trials is consumed. By evaluating modern artificial agents in IVRE, we notice a clear failure of today's learning methods compared to humans. Such inefficacy in interactive reasoning ability under uncertainty calls for future research in building human-like intelligence.

cs.AI↗
arXiv2023

Approximation Algorithm for Unrooted Prize-Collecting Forest with Multiple Components and Its Application on Prize-Collecting Sweep Coverage

In this paper, we introduce a polynomial-time 2-approximation algorithm for the Unrooted Prize-Collecting Forest with $K$ Components (URPCF$_K$) problem. URPCF$_K$ aims to find a forest with exactly $K$ connected components while minimizing both the forest's weight and the penalties incurred by unspanned vertices. Unlike the rooted version RPCF$_K$, where a 2-approximation algorithm exists, solving the unrooted version by guessing roots leads to exponential time complexity for non-constant $K$. To address this challenge, we propose a rootless growing and rootless pruning algorithm. We also apply this algorithm to improve the approximation ratio for the Prize-Collecting Min-Sensor Sweep Cover problem (PCMinSSC) from 8 to 5. Keywords: approximation algorithm, prize-collecting Steiner forest, sweep cover.

cs.DS↗
arXiv2023

DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation

VLN-CE is a recently released embodied task, where AI agents need to navigate a freely traversable environment to reach a distant target location, given language instructions. It poses great challenges due to the huge space of possible strategies. Driven by the belief that the ability to anticipate the consequences of future actions is crucial for the emergence of intelligent and interpretable planning behavior, we propose DREAMWALKER -- a world model based VLN-CE agent. The world model is built to summarize the visual, topological, and dynamic properties of the complicated continuous environment into a discrete, structured, and compact representation. DREAMWALKER can simulate and evaluate possible plans entirely in such internal abstract world, before executing costly actions. As opposed to existing model-free VLN-CE agents simply making greedy decisions in the real world, which easily results in shortsighted behaviors, DREAMWALKER is able to make strategic planning through large amounts of ``mental experiments.'' Moreover, the imagined future scenarios reflect our agent's intention, making its decision-making process more transparent. Extensive experiments and ablation studies on VLN-CE dataset confirm the effectiveness of the proposed approach and outline fruitful directions for future work.

cs.CV↗
arXiv2023

MEWL: Few-shot multimodal word learning with referential uncertainty

Without explicit feedback, humans can rapidly learn the meaning of words. Children can acquire a new word after just a few passive exposures, a process known as fast mapping. This word learning capability is believed to be the most fundamental building block of multimodal understanding and reasoning. Despite recent advancements in multimodal learning, a systematic and rigorous evaluation is still missing for human-like word learning in machines. To fill in this gap, we introduce the MachinE Word Learning (MEWL) benchmark to assess how machines learn word meaning in grounded visual scenes. MEWL covers human's core cognitive toolkits in word learning: cross-situational reasoning, bootstrapping, and pragmatic learning. Specifically, MEWL is a few-shot benchmark suite consisting of nine tasks for probing various word learning capabilities. These tasks are carefully designed to be aligned with the children's core abilities in word learning and echo the theories in the developmental literature. By evaluating multimodal and unimodal agents' performance with a comparative analysis of human performance, we notice a sharp divergence in human and machine word learning. We further discuss these differences between humans and machines and call for human-like few-shot word learning in machines.

cs.CL↗
arXiv2023

On the tightness of an SDP relaxation for homogeneous QCQP with three real or four complex homogeneous constraints

In this paper, we consider the problem of minimizing a general homogeneous quadratic function, subject to three real or four complex homogeneous quadratic inequality or equality constraints. For this problem, we present a sufficient and necessary test condition to detect whether its typical semidefinite programming (SDP) relaxation is tight or not. This test condition is easily verifiable, and is based on only an optimal solution pair of the SDP relaxation and its dual. When the tightness is confirmed, a global optimal solution of the original problem is found simultaneously in polynomial-time. Furthermore, as an application of the test condition, S-lemma and Yuan's lemma are generalized to three real and four complex quadratic forms first under certain exact conditions, which improves some classical results in literature. Finally, numerical experiments demonstrate the numerical effectiveness of the test condition.

math.OC↗
arXiv2023

Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding

Knowledge Graph Embedding (KGE) is a fundamental technique that extracts expressive representation from knowledge graph (KG) to facilitate diverse downstream tasks. The emerging federated KGE (FKGE) collaboratively trains from distributed KGs held among clients while avoiding exchanging clients' sensitive raw KGs, which can still suffer from privacy threats as evidenced in other federated model trainings (e.g., neural networks). However, quantifying and defending against such privacy threats remain unexplored for FKGE which possesses unique properties not shared by previously studied models. In this paper, we conduct the first holistic study of the privacy threat on FKGE from both attack and defense perspectives. For the attack, we quantify the privacy threat by proposing three new inference attacks, which reveal substantial privacy risk by successfully inferring the existence of the KG triple from victim clients. For the defense, we propose DP-Flames, a novel differentially private FKGE with private selection, which offers a better privacy-utility tradeoff by exploiting the entity-binding sparse gradient property of FKGE and comes with a tight privacy accountant by incorporating the state-of-the-art private selection technique. We further propose an adaptive privacy budget allocation policy to dynamically adjust defense magnitude across the training procedure. Comprehensive evaluations demonstrate that the proposed defense can successfully mitigate the privacy threat by effectively reducing the success rate of inference attacks from $83.1\%$ to $59.4\%$ on average with only a modest utility decrease.

cs.CR↗
arXiv2023

Light meson emissions of the selected charmonium-like states within compact tetraquark configurations

We adopt the quark pair creation model to investigate the light meson emissions of several charmonium-like states. The quark pair creation model is applied to the four-body systems, and we calculate the pion/kaon emissions of the $X(4700)$, $Z_c(4430)$, $Y(4230)$, $Y(4360)$, $Y(4390)$ and $Y(4660)$ within the compact tetraquark assumptions. It is found that the pion/kaon decay widths for the $X(4700)$ and $Z_c(4430)$ are relatively small, while the partial decay widths for the resonances $Y(4230)$, $Y(4360)$, $Y(4390)$ and $Y(4660)$ are significant. We expect that our exploration of these decay behaviors can provide useful information for future experimental searches and theoretical interpretations.

hep-ph↗
arXiv2023

Diffusion-based Generation, Optimization, and Planning in 3D Scenes

We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser provides a unified model for solving scene-conditioned generation, optimization, and planning. In contrast to prior works, SceneDiffuser is intrinsically scene-aware, physics-based, and goal-oriented. With an iterative sampling strategy, SceneDiffuser jointly formulates the scene-aware generation, physics-based optimization, and goal-oriented planning via a diffusion-based denoising process in a fully differentiable fashion. Such a design alleviates the discrepancies among different modules and the posterior collapse of previous scene-conditioned generative models. We evaluate SceneDiffuser with various 3D scene understanding tasks, including human pose and motion generation, dexterous grasp generation, path planning for 3D navigation, and motion planning for robot arms. The results show significant improvements compared with previous models, demonstrating the tremendous potential of SceneDiffuser for the broad community of 3D scene understanding.

cs.CV↗
arXiv2023

The state-of-the-art 3D anisotropic intracranial hemorrhage segmentation on non-contrast head CT: The INSTANCE challenge

Automatic intracranial hemorrhage segmentation in 3D non-contrast head CT (NCCT) scans is significant in clinical practice. Existing hemorrhage segmentation methods usually ignores the anisotropic nature of the NCCT, and are evaluated on different in-house datasets with distinct metrics, making it highly challenging to improve segmentation performance and perform objective comparisons among different methods. The INSTANCE 2022 was a grand challenge held in conjunction with the 2022 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). It is intended to resolve the above-mentioned problems and promote the development of both intracranial hemorrhage segmentation and anisotropic data processing. The INSTANCE released a training set of 100 cases with ground-truth and a validation set with 30 cases without ground-truth labels that were available to the participants. A held-out testing set with 70 cases is utilized for the final evaluation and ranking. The methods from different participants are ranked based on four metrics, including Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), Relative Volume Difference (RVD) and Normalized Surface Dice (NSD). A total of 13 teams submitted distinct solutions to resolve the challenges, making several baseline models, pre-processing strategies and anisotropic data processing techniques available to future researchers. The winner method achieved an average DSC of 0.6925, demonstrating a significant growth over our proposed baseline method. To the best of our knowledge, the proposed INSTANCE challenge releases the first intracranial hemorrhage segmentation benchmark, and is also the first challenge that intended to resolve the anisotropic problem in 3D medical image segmentation, which provides new alternatives in these research fields.

eess.IV↗