Search

Image captioning, which generates natural language descriptions of the visual information in an image, is a crucial task in vision-language research. Previous models have typically addressed this task by aligning the generative capabilities of machines with human intelligence through statistical fitting of existing datasets. While effective for normal images, they may struggle to accurately describe those where certain parts of the image are obscured or edited, unlike humans who excel in such cases. These weaknesses they exhibit, including hallucinations and limited interpretability, often hinder performance in scenarios with shifted association patterns. In this paper, we present a generic image captioning framework that employs causal inference to make existing models more capable of interventional tasks, and counterfactually explainable. Our approach includes two variants leveraging either total effect or natural direct effect. Integrating them into the training process enables models to handle counterfactual scenarios, increasing their generalizability. Extensive experiments on various datasets show that our method effectively reduces hallucinations and improves the model's faithfulness to images, demonstrating high portability across both small-scale and large-scale image-to-text models. The code is available at https://github.com/Aman-4-Real/See-or-Guess., Comment: Accepted by ACM MM 2024

Orbital angular momentums (OAMs) of light can be categorized into longitudinal OAM (L-OAM) and transverse OAM (T-OAM). Light carrying time-varying L-OAM, known as self-torqued light, was recently discovered during harmonic generation and has been extensively developed within the context of optical frequency combs (OFCs). Meanwhile, ultrafast bursts of optical pulses, analogous to OFCs, are sought for various light-matter interaction, spectroscopic and nonlinear applications. However, achieving transiently switchable T-OAM of light on request, namely spatiotemporal vortex pulse bursts, with independently controlled spatiotemporal profile of each comb tooth, remain unrealized thus far. In this work, the experimental generation of spatiotemporal vortex bursts featured with controllable time-dependent characteristics is reported. The resultant bursts comprised of spatiotemporal optical vortex comb teeth have picosecond timescale switchable T-OAMs with defined arrangement, manifesting as spatiotemporal torquing of light. We also show ultrafast control of T-OAM chirality, yielding pulse bursts with staggered azimuthal local momentum density, resembling K\'arm\'an vortex streets. This approach enables the tailoring of more intricate spatiotemporal wavepacket bursts, such as high-purity modes variation in both radial and azimuthal quantum numbers of spatiotemporal Laguerre-Gaussian wavepackets over time, which may facilitate a host of novel applications in ultrafast light-mater interactions, high-dimensional quantum entanglements, space-time photonic topologies as well as spatiotemporal metrology and photography.

Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many open-source LLMs have been released with technical reports, the lack of training details hinders further research and development. This paper presents the development of YuLan, a series of open-source LLMs with $12$ billion parameters. The base model of YuLan is pre-trained on approximately $1.7$T tokens derived from a diverse corpus, including massive English, Chinese, and multilingual texts. We design a three-stage pre-training method to enhance YuLan's overall capabilities. Subsequent phases of training incorporate instruction-tuning and human alignment, employing a substantial volume of high-quality synthesized data. To facilitate the learning of complex and long-tail knowledge, we devise a curriculum-learning framework throughout across these stages, which helps LLMs learn knowledge in an easy-to-hard manner. YuLan's training is finished on Jan, 2024 and has achieved performance on par with state-of-the-art LLMs across various English and Chinese benchmarks. This paper outlines a comprehensive technical roadmap for developing LLMs from scratch. Our model and codes are available at https://github.com/RUC-GSAI/YuLan-Chat.

Spatial representation learning (SRL) aims at learning general-purpose neural network representations from various types of spatial data (e.g., points, polylines, polygons, networks, images, etc.) in their native formats. Learning good spatial representations is a fundamental problem for various downstream applications such as species distribution modeling, weather forecasting, trajectory generation, geographic question answering, etc. Even though SRL has become the foundation of almost all geospatial artificial intelligence (GeoAI) research, we have not yet seen significant efforts to develop an extensive deep learning framework and benchmark to support SRL model development and evaluation. To fill this gap, we propose TorchSpatial, a learning framework and benchmark for location (point) encoding, which is one of the most fundamental data types of spatial representation learning. TorchSpatial contains three key components: 1) a unified location encoding framework that consolidates 15 commonly recognized location encoders, ensuring scalability and reproducibility of the implementations; 2) the LocBench benchmark tasks encompassing 7 geo-aware image classification and 4 geo-aware image regression datasets; 3) a comprehensive suite of evaluation metrics to quantify geo-aware models' overall performance as well as their geographic bias, with a novel Geo-Bias Score metric. Finally, we provide a detailed analysis and insights into the model performance and geographic bias of different location encoders. We believe TorchSpatial will foster future advancement of spatial representation learning and spatial fairness in GeoAI research. The TorchSpatial model framework, LocBench, and Geo-Bias Score evaluation framework are available at https://github.com/seai-lab/TorchSpatial., Comment: 9 pages, 2 figures. Submitted to NeurIPS 2024 Datasets and Benchmarks Track. Under review

The growing popularity of Large Language Models has sparked interest in context compression for Large Language Models (LLMs). However, the performance of previous methods degrades dramatically as compression ratios increase, sometimes even falling to the closed-book level. This decline can be attributed to the loss of key information during the compression process. Our preliminary study supports this hypothesis, emphasizing the significance of retaining key information to maintain model performance under high compression ratios. As a result, we introduce Query-Guided Compressor (QGC), which leverages queries to guide the context compression process, effectively preserving key information within the compressed context. Additionally, we employ a dynamic compression strategy. We validate the effectiveness of our proposed QGC on the Question Answering task, including NaturalQuestions, TriviaQA, and HotpotQA datasets. Experimental results show that QGC can consistently perform well even at high compression ratios, which also offers significant benefits in terms of inference cost and throughput., Comment: Accepted to ACL 2024

Patients diagnosed with metastatic breast cancer (mBC) typically undergo several radiographic assessments during their treatment. mBC often involves multiple metastatic lesions in different organs, it is imperative to accurately track and assess these lesions to gain a comprehensive understanding of the disease's response to treatment. Computerized analysis methods that rely on lesion-level tracking have often used manual matching of corresponding lesions, a time-consuming process that is prone to errors. This paper introduces an automated lesion correspondence algorithm designed to precisely track both targets' lesions and non-targets' lesions in longitudinal data. Here we demonstrate the applicability of our algorithm on the anonymized data from two Phase III trials. The dataset contains imaging data of patients for different follow-up timepoints and the radiologist annotations for the patients enrolled in the trials. Target and non-target lesions are annotated by either one or two groups of radiologists. To facilitate accurate tracking, we have developed a registration-assisted lesion correspondence algorithm. The algorithm employs a sequential two-step pipeline: (a) Firstly, an adaptive Hungarian algorithm is used to establish correspondence among lesions within a single volumetric image series which have been annotated by multiple radiologists at a specific timepoint. (b) Secondly, after establishing correspondence and assigning unique names to the lesions, three-dimensional rigid registration is applied to various image series at the same timepoint. Registration is followed by ongoing lesion correspondence based on the adaptive Hungarian algorithm and updating lesion names for accurate tracking. Validation of our automated lesion correspondence algorithm is performed through triaxial plots based on axial, sagittal, and coronal views, confirming its efficacy in matching lesions.

TorchSurv is a Python package that serves as a companion tool to perform deep survival modeling within the PyTorch environment. Unlike existing libraries that impose specific parametric forms, TorchSurv enables the use of custom PyTorch-based deep survival models. With its lightweight design, minimal input requirements, full PyTorch backend, and freedom from restrictive survival model parameterizations, TorchSurv facilitates efficient deep survival model implementation and is particularly beneficial for high-dimensional and complex input data scenarios., Comment: https://opensource.nibr.com/torchsurv/

Optical spatiotemporal vortices with transverse photon orbital angular momentum (OAM) have recently become a focal point of research. In this work we theoretically and experimentally investigate optical spatiotemporal vortices with radial and azimuthal quantum numbers, known as spatiotemporal Laguerre-Gaussian (STLG) wavepackets. These 3D wavepackets exhibit phase singularities and cylinder-shaped edge dislocations, resulting in a multi-ring topology in its spatiotemporal profile. Unlike conventional ST optical vortices, STLG wavepackets with non-zero p and l values carry a composite transverse OAM consisting of two directionally opposite components. We further demonstrate mode conversion between an STLG wavepacket and an ST Hermite-Gaussian wavepacket through the application of strong spatiotemporal astigmatism. The converted STHG wavepacket is de-coupled in intensity in space-time domain that can be utilized to implement the efficient and accurate recognition of ultrafast STLG wavepackets carried various p and l. This study may offer new insights into high-dimensional quantum information, photonic topology, and nonlinear optics, while promising potential applications in other wave phenomena such as acoustics and electron waves.

Spatiotemporal structured light has opened up new avenues for optics and photonics. Current spatiotemporal manipulation of light mostly relies on phase-only devices such as liquid crystal spatial light modulator to generate spatiotemporal optical fields with unique photonic properties. However, simultaneous manipulation of both amplitude and phase of the complex field for the spatiotemporal light is still lacking, limiting the diversity and richness of achievable photonic properties. In this work, a simple and versatile spatiotemporal holographic method that can arbitrarily sculpture the spatiotemporal light is presented. The capabilities of this simple yet powerful method are demonstrated through the generation of fundamental and higher-order spatiotemporal Bessel wavepacket, spatiotemporal crystal-like and quasi-crystal-like structures, and spatiotemporal flat-top wavepackets. Fully customizable spatiotemporal wavepackets will find broader application in investigating the dynamics of spatiotemporal fields and interactions between ultrafast spatiotemporal pulses and matters, unveiling previously hidden light-matter interactions and unlocking breakthroughs in photonics and beyond.

The advent of large language models (LLMs) has heightened interest in their potential for multimodal applications that integrate language and vision. This paper explores the capabilities of GPT-4V in the realms of geography, environmental science, agriculture, and urban planning by evaluating its performance across a variety of tasks. Data sources comprise satellite imagery, aerial photos, ground-level images, field images, and public datasets. The model is evaluated on a series of tasks including geo-localization, textual data extraction from maps, remote sensing image classification, visual question answering, crop type identification, disease/pest/weed recognition, chicken behavior analysis, agricultural object counting, urban planning knowledge question answering, and plan generation. The results indicate the potential of GPT-4V in geo-localization, land cover classification, visual question answering, and basic image understanding. However, there are limitations in several tasks requiring fine-grained recognition and precise counting. While zero-shot learning shows promise, performance varies across problem domains and image complexities. The work provides novel insights into GPT-4V's capabilities and limitations for real-world geospatial, environmental, agricultural, and urban planning challenges. Further research should focus on augmenting the model's knowledge and reasoning for specialized domains through expanded training. Overall, the analysis demonstrates foundational multimodal intelligence, highlighting the potential of multimodal foundation models (FMs) to advance interdisciplinary applications at the nexus of computer vision and language., Comment: 110 Pages; 61 Figures

Recent advances in artificial general intelligence (AGI), particularly large language models and creative image generation systems have demonstrated impressive capabilities on diverse tasks spanning the arts and humanities. However, the swift evolution of AGI has also raised critical questions about its responsible deployment in these culturally significant domains traditionally seen as profoundly human. This paper provides a comprehensive analysis of the applications and implications of AGI for text, graphics, audio, and video pertaining to arts and the humanities. We survey cutting-edge systems and their usage in areas ranging from poetry to history, marketing to film, and communication to classical art. We outline substantial concerns pertaining to factuality, toxicity, biases, and public safety in AGI systems, and propose mitigation strategies. The paper argues for multi-stakeholder collaboration to ensure AGI promotes creativity, knowledge, and cultural values without undermining truth or human dignity. Our timely contribution summarizes a rapidly developing field, highlighting promising directions while advocating for responsible progress centering on human flourishing. The analysis lays the groundwork for further research on aligning AGI's technological capacities with enduring social goods.

Nuclear magnetic resonance (NMR) has been a widely used tool in various scientific fields and practical applications, with quantum control emerging as a promising strategy for synergistic advancements. In this paper, we propose a novel approach that combines NMR and quantum state preparation techniques to control free induction decay (FID) signals in weakly coupled spin systems, specifically Trifluoroiodoethylene $C_2F_3I$. We investigate the FID signal of the three-spin system and compare the differences between the FID signals in the thermal state and the pseudo-pure state (PPS), where the latter is generated using quantum state preparation techniques. Our approach aims to demonstrate a single exponentially decaying FID in weakly coupled spins, in which oscillatory FID signals are often observed. We validate our findings through numerical simulations and experimental measurements, and justify the validity of the theory. Our method opens a door to advancing spin system research and extending the capabilities of NMR with current quantum technologies in various scientific and practical fields., Comment: 6 pages, 4 figures. Comments are welcome

In the past decade, Artificial Intelligence (AI) algorithms have made promising impacts to transform healthcare in all aspects. One application is to triage patients' radiological medical images based on the algorithm's binary outputs. Such AI-based prioritization software is known as computer-aided triage and notification (CADt). Their main benefit is to speed up radiological review of images with time-sensitive findings. However, as CADt devices become more common in clinical workflows, there is still a lack of quantitative methods to evaluate a device's effectiveness in saving patients' waiting times. In this paper, we present a mathematical framework based on queueing theory to calculate the average waiting time per patient image before and after a CADt device is used. We study four workflow models with multiple radiologists (servers) and priority classes for a range of AI diagnostic performance, radiologist's reading rates, and patient image (customer) arrival rates. Due to model complexity, an approximation method known as the Recursive Dimensionality Reduction technique is applied. We define a performance metric to measure the device's time-saving effectiveness. A software tool is developed to simulate clinical workflow of image review/interpretation, to verify theoretical results, and to provide confidence intervals of the performance metric we defined. It is shown quantitatively that a triage device is more effective in a busy, short-staffed setting, which is consistent with our clinical intuition and simulation results. Although this work is motivated by the need for evaluating CADt devices, the framework we present in this paper can be applied to any algorithm that prioritizes customers based on its binary outputs.

The explorations of physical degrees of freedom with infinite dimensionalities, such as orbital angular momentum and frequency of light, have profoundly reshaped the landscape of modern optics with representative photonic functional devices including optical vortex emitters and frequency combs. In nanophotonics, whispering gallery mode microresonators naturally support orbital angular momentum of light and have been demonstrated as on-chip emitters of monochromatic optical vortices. On the other hand, whispering gallery mode microresonators serve as a highly efficient nonlinear optical platform for producing light at different frequencies - i.e., microcombs. Here, we interlace the optical vortices and microcombs by demonstrating an optical vortex comb on an III-V integrated nonlinear microresonator. The angular-grating-dressed nonlinear microring simultaneously emits spatiotemporal light springs consisting of 50 orbital angular momentum modes that are each spectrally addressed to the frequency components (longitudinal whispering gallery modes) of the generated microcomb. We further experimentally generate optical pulses with time-varying orbital angular momenta by carefully introducing a specific intermodal phase relation to spatiotemporal light springs. This work may immediately boost the development of integrated nonlinear/quantum photonics for exploring fundamental optical physics and advancing photonic quantum technology., Comment: To appear in Nature Photonics

Achieving high energy resolution in spin systems is important for fundamental physics research and precision measurements, with alkali-noble-gas comagnetometers being among the best available sensors. We found a new relaxation mechanism in such devices, the gradient of the Fermi-contact-interaction field that dominates the relaxation of hyperpolarized nuclear spins. We report on precise control over spin distribution, demonstrating a tenfold increase of nuclear spin hyperpolarization and transverse coherence time with optimal hybrid optical pumping. Operating in the self-compensation regime, our $^{21}$Ne-Rb-K comagnetometer achieves an ultrahigh inertial rotation sensitivity of $3\times10^{-8}$\,rad/s/Hz$^{1/2}$ in the frequency range from 0.2 to 1.0 Hz, which is equivalent to the energy resolution of $3.1\times 10^{-23}$\,eV/Hz$^{1/2}$. We propose to use this comagnetometer to search for exotic spin-dependent interactions involving proton and neutron spins. The projected sensitivity surpasses the previous experimental and astrophysical limits by more than four orders of magnitude.

AI creation, such as poem or lyrics generation, has attracted increasing attention from both industry and academic communities, with many promising models proposed in the past few years. Existing methods usually estimate the outputs based on single and independent visual or textual information. However, in reality, humans usually make creations according to their experiences, which may involve different modalities and be sequentially correlated. To model such human capabilities, in this paper, we define and solve a novel AI creation problem based on human experiences. More specifically, we study how to generate texts based on sequential multi-modal information. Compared with the previous works, this task is much more difficult because the designed model has to well understand and adapt the semantics among different modalities and effectively convert them into the output in a sequential manner. To alleviate these difficulties, we firstly design a multi-channel sequence-to-sequence architecture equipped with a multi-modal attention network. For more effective optimization, we then propose a curriculum negative sampling strategy tailored for the sequential inputs. To benchmark this problem and demonstrate the effectiveness of our model, we manually labeled a new multi-modal experience dataset. With this dataset, we conduct extensive experiments by comparing our model with a series of representative baselines, where we can demonstrate significant improvements in our model based on both automatic and human-centered metrics. The code and data are available at: \url{https://github.com/Aman-4-Real/MMTG}., Comment: Accepted by ACM Multimedia 2022