Search

We introduce a decoder-decoder architecture, YOCO, for large language models, which only caches key-value pairs once. It consists of two components, i.e., a cross-decoder stacked upon a self-decoder. The self-decoder efficiently encodes global key-value (KV) caches that are reused by the cross-decoder via cross-attention. The overall model behaves like a decoder-only Transformer, although YOCO only caches once. The design substantially reduces GPU memory demands, yet retains global attention capability. Additionally, the computation flow enables prefilling to early exit without changing the final output, thereby significantly speeding up the prefill stage. Experimental results demonstrate that YOCO achieves favorable performance compared to Transformer in various settings of scaling up model size and number of training tokens. We also extend YOCO to 1M context length with near-perfect needle retrieval accuracy. The profiling results show that YOCO improves inference memory, prefill latency, and throughput by orders of magnitude across context lengths and model sizes. Code is available at https://aka.ms/YOCO.

This paper focuses on multi-agent stochastic differential games for jump-diffusion systems. On one hand, we study the multi-agent game for optimal investment in a jump-diffusion market. We derive constant Nash equilibria and provide sufficient conditions for their existence and uniqueness for exponential, power, and logarithmic utilities, respectively. On the other hand, we introduce a computational framework based on the actor-critic method in deep reinforcement learning to solve the stochastic control problem with jumps. We extend this algorithm to address the multi-agent game with jumps and utilize parallel computing to enhance computational efficiency. We present numerical examples of the Merton problem with jumps, linear quadratic regulators, and the optimal investment game under various settings to demonstrate the accuracy, efficiency, and robustness of the proposed method. In particular, neural network solutions numerically converge to the derived constant Nash equilibrium for the multi-agent game.

Clickbaits are surprising social posts or deceptive news headlines that attempt to lure users for more clicks, which have posted at unprecedented rates for more profit or commercial revenue. The spread of clickbait has significant negative impacts on the users, which brings users misleading or even click-jacking attacks. Different from fake news, the crucial problem in clickbait detection is determining whether the headline matches the corresponding content. Most existing methods compute the semantic similarity between the headlines and contents for detecting clickbait. However, due to significant differences in length and semantic features between headlines and contents, directly calculating semantic similarity is often difficult to summarize the relationship between them. To address this problem, we propose a prompt-tuning method for clickbait detection via text summarization in this paper, text summarization is introduced to summarize the contents, and clickbait detection is performed based on the similarity between the generated summary and the contents. Specifically, we first introduce a two-stage text summarization model to produce high-quality news summaries based on pre-trained language models, and then both the headlines and new generated summaries are incorporated as the inputs for prompt-tuning. Additionally, a variety of strategies are conducted to incorporate external knowledge for improving the performance of clickbait detection. The extensive experiments on well-known clickbait detection datasets demonstrate that our method achieved state-of-the-art performance.

This work shows details of an evaluation of an observational system comprising a CMOS detector, 60-cm telescope, and filter complement. The system's photometric precision and differential photometric precision, and extinction coefficients were assessed through observations of Supersky flat fields, open clusters, standard stars, and exoplanets. Photometry was precision achieved at the 0.02 mag level, while differential photometry of 0.004 mag precision. Extinction was found to be agreed with previous studies conducted at Xinglong Observatory. Ultimately, the results demonstrate this observing system is capable of precision scientific observations with CCD across the optical wavelengths.

The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder to generate semantic masks. Despite its effectiveness, prevailing methods within this paradigm encounter challenges, including overfitting on seen classes and small fragmentation in masks. To mitigate these issues, we propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information.Specifically, we leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Moreover, to circumvent noisy alignments from the vision part due to its redundant nature, we introduce route attention into self-attention for finding visual consensus, thereby enhancing semantic consistency within the same object. Equipped with a vision-language prompting strategy, our approach significantly boosts the generalization capacity of segmentation models for unseen classes. Experimental results underscore the effectiveness of our approach, showcasing mIoU gains of 4.5 on the PASCAL VOC 2012 and 3.6 on the COCO-Stuff 164k for unseen classes compared with the state-of-the-art methods.

With the rapid increase of observational, experimental and simulated data for stochastic systems, tremendous efforts have been devoted to identifying governing laws underlying the evolution of these systems. Despite the broad applications of non-Gaussian fluctuations in numerous physical phenomena, the data-driven approaches to extracting stochastic dynamics with L\'{e}vy noise are relatively few. In this work, we propose a Weak Collocation Regression (WCR) to explicitly reveal unknown stochastic dynamical systems, i.e., the Stochastic Differential Equation (SDE) with both $\alpha$-stable L\'{e}vy noise and Gaussian noise, from discrete aggregate data. This method utilizes the evolution equation of the probability distribution function, i.e., the Fokker-Planck (FP) equation. With the weak form of the FP equation, the WCR constructs a linear system of unknown parameters where all integrals are evaluated by Monte Carlo method with the observations. Then, the unknown parameters are obtained by a sparse linear regression. For a SDE with L\'{e}vy noise, the corresponding FP equation is a partial integro-differential equation (PIDE), which contains nonlocal terms, and is difficult to deal with. The weak form can avoid complicated multiple integrals. Our approach can simultaneously distinguish mixed noise types, even in multi-dimensional problems. Numerical experiments demonstrate that our method is accurate and computationally efficient., Comment: 19 pages, 5 figures, 10 tables

Vision-and-language navigation (VLN) asks an agent to follow a given language instruction to navigate through a real 3D environment. Despite significant advances, conventional VLN agents are trained typically under disturbance-free environments and may easily fail in real-world scenarios, since they are unaware of how to deal with various possible disturbances, such as sudden obstacles or human interruptions, which widely exist and may usually cause an unexpected route deviation. In this paper, we present a model-agnostic training paradigm, called Progressive Perturbation-aware Contrastive Learning (PROPER) to enhance the generalization ability of existing VLN agents, by requiring them to learn towards deviation-robust navigation. Specifically, a simple yet effective path perturbation scheme is introduced to implement the route deviation, with which the agent is required to still navigate successfully following the original instruction. Since directly enforcing the agent to learn perturbed trajectories may lead to inefficient training, a progressively perturbed trajectory augmentation strategy is designed, where the agent can self-adaptively learn to navigate under perturbation with the improvement of its navigation performance for each specific trajectory. For encouraging the agent to well capture the difference brought by perturbation, a perturbation-aware contrastive learning mechanism is further developed by contrasting perturbation-free trajectory encodings and perturbation-based counterparts. Extensive experiments on R2R show that PROPER can benefit multiple VLN baselines in perturbation-free scenarios. We further collect the perturbed path data to construct an introspection subset based on the R2R, called Path-Perturbed R2R (PP-R2R). The results on PP-R2R show unsatisfying robustness of popular VLN agents and the capability of PROPER in improving the navigation robustness., Comment: Accepted by TPAMI 2023

The existence of edge states is one of the most vital properties of topological insulators. Although tremendous success has been accomplished in describing and explaining edge states associated with PT symmetry breaking, little work has been done on PT symmetry preserving cases. Two-dimensional Schroedinger operators with super honeycomb lattice potentials always have double Dirac cones at the Gamma point - the zero momentum point on their energy bands due to C6 symmetry, PT symmetry, and the "folding" symmetry - caused by an additional translation symmetry. There are two topologically different ways to deform such a system by PT symmetry preserving but folding symmetry breaking perturbations. Interestingly, there exist two gapped edge states on the interface between such two kinds of perturbed materials. In this paper, we illustrate the existence of such PT preserving edge states rigorously for the first time. We use a domain wall modulated Schroedinger operator to model the phenomenon under small perturbations and rigorously prove the existence of two gapped edge states. We also provide a brief interpretation from the point of view of "topology" by the parities of degenerate bulk modes. Our work thoroughly explains the existence of "helical" like edge states in super honeycomb configurations and lays a foundation for the descriptions of topologies of such systems., Comment: 3 Figures

In this paper, we study the method to reconstruct dynamical systems from data without time labels. Data without time labels appear in many applications, such as molecular dynamics, single-cell RNA sequencing etc. Reconstruction of dynamical system from time sequence data has been studied extensively. However, these methods do not apply if time labels are unknown. Without time labels, sequence data becomes distribution data. Based on this observation, we propose to treat the data as samples from a probability distribution and try to reconstruct the underlying dynamical system by minimizing the distribution loss, sliced Wasserstein distance more specifically. Extensive experiment results demonstrate the effectiveness of the proposed method.

Large Language Models (LLMs) have demonstrated remarkable capabilities in important tasks such as natural language understanding, language generation, and complex reasoning and have the potential to make a substantial impact on our society. Such capabilities, however, come with the considerable resources they demand, highlighting the strong need to develop effective techniques for addressing their efficiency challenges.In this survey, we provide a systematic and comprehensive review of efficient LLMs research. We organize the literature in a taxonomy consisting of three main categories, covering distinct yet interconnected efficient LLMs topics from model-centric, data-centric, and framework-centric perspective, respectively. We have also created a GitHub repository where we compile the papers featured in this survey at https://github.com/AIoT-MLSys-Lab/Efficient-LLMs-Survey, and will actively maintain this repository and incorporate new research as it emerges. We hope our survey can serve as a valuable resource to help researchers and practitioners gain a systematic understanding of the research developments in efficient LLMs and inspire them to contribute to this important and exciting field., Comment: Version 3: Added more latest papers

We present a longitudinal multi-sensor dataset collected from honey bee colonies (Apis mellifera) with rich phenotypic measurements. Data were continuously collected between May-2020 and April-2021 from 53 hives located at two apiaries in Qu\'ebec, Canada. The sensor data included audio features, temperature, and relative humidity. The phenotypic measurements contained beehive population, number of brood cells (eggs, larva and pupa), Varroa destructor infestation levels, defensive and hygienic behaviors, honey yield, and winter mortality. Our study is amongst the first to provide a wide variety of phenotypic trait measurements annotated by apicultural science experts, which facilitate a broader scope of analysis. We first summarize the data collection procedure, sensor data pre-processing steps, and data composition. We then provide an overview of the phenotypic data distribution as well as a visualization of the sensor data patterns. Lastly, we showcase several hive monitoring applications based on sensor data analysis and machine learning, such as winter mortality prediction, hive population estimation, and the presence of an active and laying queen., Comment: Under review; project webpage: https://zhu00121.github.io/MSPB-webpage/

The long gamma-ray burst GRB 191221B has abundant observations in X-ray, optical and radio bands. In the literature, the observed optical light curve of GRB 191221B displays a plateau around 0.1-day, which is rather peculiar in gamma-ray bursts. Here we performed detailed analysis of the observational data from Swift/UVOT, VLT and LCO, obtained the light curve of the multi-band afterglow of GRB 191221B. By examining optical, ultraviolet, X-ray, and radio data for this event, we demonstrate that an on-axis two-component jet model can explain the observations. Our analysis suggests that the narrow component has an initial Lorentz factor of 400 and a jet opening half-angle of $1.4^{\circ}$, while the wide component has an initial Lorentz factor of 25 and a jet opening half-angle of $2.8^{\circ}$. The narrow jet dominates the early decay, whereas the wider jet causes the optical plateau and dominates late decay. According to this model, the reason for the absence of the X-ray plateau is due to the steeper spectral index of the wide component, resulting in a less significant flux contribution from the wide jet in the X-ray bands than in the optical bands. Moreover, we have explained the inconsistency in the decay indices of the UVOT and Rc-band data around 2000 seconds using reverse shock emission., Comment: 10 pages, 7 figures, Accepted by the Monthly Notices of the Royal Astronomical Society

Recently, there has been increased attention towards 3D imaging using single-pixel single-photon detection (also known as temporal data) due to its potential advantages in terms of cost and power efficiency. However, to eliminate the symmetry blur in the reconstructed images, a fixed background is required. This paper proposes a fusion-data-based 3D imaging method that utilizes a single-pixel single-photon detector and a millimeter-wave radar to capture temporal histograms of a scene from multiple perspectives. Subsequently, the 3D information can be reconstructed from the one-dimensional fusion temporal data by using Artificial Neural Network (ANN). Both the simulation and experimental results demonstrate that our fusion method effectively eliminates symmetry blur and improves the quality of the reconstructed images., Comment: Accepted by Chinese Optics Letters, and comments are welcome

Existing Civil Engineering structures have limited capability to adapt their configurations for new functions, non-stationary environments, or future reuse. Although origami principles provide capabilities of dense packaging and reconfiguration, existing origami systems have not achieved deployable metre-scale structures that can support large loads. Here, we established modular and uniformly thick origami-inspired structures that can deploy into metre-scale structures, adapt into different shapes, and carry remarkably large loads. This work first derives general conditions for degree-N origami vertices to be flat foldable, developable, and uniformly thick, and uses these conditions to create the proposed origami-inspired structures. We then show that these origami-inspired structures can utilize high modularity for rapid repair and adaptability of shapes and functions; can harness multi-path folding motions to reconfigure between storage and structural states; and can exploit uniform thickness to carry large loads. We believe concepts of modular and uniformly thick origami-inspired structures will challenge traditional practice in Civil Engineering by enabling large-scale, adaptable, deployable, and load-carrying structures, and offer broader applications in aerospace systems, space habitats, robotics, and more., Comment: Under review at Nature Communications

Existing deepfake speech detection systems lack generalizability to unseen attacks (i.e., samples generated by generative algorithms not seen during training). Recent studies have explored the use of universal speech representations to tackle this issue and have obtained inspiring results. These works, however, have focused on innovating downstream classifiers while leaving the representation itself untouched. In this study, we argue that characterizing the long-term temporal dynamics of these representations is crucial for generalizability and propose a new method to assess representation dynamics. Indeed, we show that different generative models generate similar representation dynamics patterns with our proposed method. Experiments on the ASVspoof 2019 and 2021 datasets validate the benefits of the proposed method to detect deepfakes from methods unseen during training, significantly improving on several benchmark methods., Comment: Submitted to ICASSP 2024

Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spatial and temporal information are important for video understanding. This suggests that the random masking strategy that is inherited from the image MAE is less effective for video MAE. This motivates the design of a novel masking algorithm that can more efficiently make use of video saliency. Specifically, we propose a motion-guided masking algorithm (MGM) which leverages motion vectors to guide the position of each mask over time. Crucially, these motion-based correspondences can be directly obtained from information stored in the compressed format of the video, which makes our method efficient and scalable. On two challenging large-scale video benchmarks (Kinetics-400 and Something-Something V2), we equip video MAE with our MGM and achieve up to +$1.3\%$ improvement compared to previous state-of-the-art methods. Additionally, our MGM achieves equivalent performance to previous video MAE using up to $66\%$ fewer training epochs. Lastly, we show that MGM generalizes better to downstream transfer learning and domain adaptation tasks on the UCF101, HMDB51, and Diving48 datasets, achieving up to +$4.9\%$ improvement compared to baseline methods., Comment: Accepted to ICCV 2023

Recently, semantic segmentation models trained with image-level text supervision have shown promising results in challenging open-world scenarios. However, these models still face difficulties in learning fine-grained semantic alignment at the pixel level and predicting accurate object masks. To address this issue, we propose MixReorg, a novel and straightforward pre-training paradigm for semantic segmentation that enhances a model's ability to reorganize patches mixed across images, exploring both local visual relevance and global semantic coherence. Our approach involves generating fine-grained patch-text pairs data by mixing image patches while preserving the correspondence between patches and text. The model is then trained to minimize the segmentation loss of the mixed images and the two contrastive losses of the original and restored features. With MixReorg as a mask learner, conventional text-supervised semantic segmentation models can achieve highly generalizable pixel-semantic alignment ability, which is crucial for open-world segmentation. After training with large-scale image-text data, MixReorg models can be applied directly to segment visual objects of arbitrary categories, without the need for further fine-tuning. Our proposed framework demonstrates strong performance on popular zero-shot semantic segmentation benchmarks, outperforming GroupViT by significant margins of 5.0%, 6.2%, 2.5%, and 3.4% mIoU on PASCAL VOC2012, PASCAL Context, MS COCO, and ADE20K, respectively.

The development of a microwave electrometer with inherent uncertainty approaching its ultimate limit carries both fundamental and technological significance. Recently, the Rydberg electrometer has garnered considerable attention due to its exceptional sensitivity, small-size, and broad tunability. This specific quantum sensor utilizes low-entropy laser beams to detect disturbances in atomic internal states, thereby circumventing the intrinsic thermal noise encountered by its classical counterparts. However, due to the thermal motion of atoms, the advanced Rydberg-atom microwave electrometer falls considerably short of the standard quantum limit by over three orders of magnitude. In this study, we utilize an optically thin medium with approximately 5.2e5 laser-cooled atoms to implement heterodyne detection. By mitigating a variety of noises and strategically optimizing the parameters of the Rydberg electrometer, our study achieves an electric-field sensitivity of 10.0 nV/cm/Hz^1/2 at a 100 Hz repetition rate, reaching a factor of 2.6 above the standard quantum limit and a minimum detectable field of 540 pV/cm. We also provide an in-depth analysis of noise mechanisms and determine optimal parameters to bolster the performance of Rydberg-atom sensors. Our work provides insights into the inherent capacities and limitations of Rydberg electrometers, while offering superior sensitivity for detecting weak microwave signals in numerous applications., Comment: 12 pages

Lexical simplification (LS) methods based on pretrained language models have made remarkable progress, generating potential substitutes for a complex word through analysis of its contextual surroundings. However, these methods require separate pretrained models for different languages and disregard the preservation of sentence meaning. In this paper, we propose a novel multilingual LS method via paraphrase generation, as paraphrases provide diversity in word selection while preserving the sentence's meaning. We regard paraphrasing as a zero-shot translation task within multilingual neural machine translation that supports hundreds of languages. After feeding the input sentence into the encoder of paraphrase modeling, we generate the substitutes based on a novel decoding strategy that concentrates solely on the lexical variations of the complex word. Experimental results demonstrate that our approach surpasses BERT-based methods and zero-shot GPT3-based method significantly on English, Spanish, and Portuguese.

Earth system forecasting has traditionally relied on complex physical models that are computationally expensive and require significant domain expertise. In the past decade, the unprecedented increase in spatiotemporal Earth observation data has enabled data-driven forecasting models using deep learning techniques. These models have shown promise for diverse Earth system forecasting tasks but either struggle with handling uncertainty or neglect domain-specific prior knowledge, resulting in averaging possible futures to blurred forecasts or generating physically implausible predictions. To address these limitations, we propose a two-stage pipeline for probabilistic spatiotemporal forecasting: 1) We develop PreDiff, a conditional latent diffusion model capable of probabilistic forecasts. 2) We incorporate an explicit knowledge alignment mechanism to align forecasts with domain-specific physical constraints. This is achieved by estimating the deviation from imposed constraints at each denoising step and adjusting the transition distribution accordingly. We conduct empirical studies on two datasets: N-body MNIST, a synthetic dataset with chaotic behavior, and SEVIR, a real-world precipitation nowcasting dataset. Specifically, we impose the law of conservation of energy in N-body MNIST and anticipated precipitation intensity in SEVIR. Experiments demonstrate the effectiveness of PreDiff in handling uncertainty, incorporating domain-specific prior knowledge, and generating forecasts that exhibit high operational utility., Comment: Published at NeurIPS 2023. Camera-ready version

In this paper, we propose a deep learning framework for solving high-dimensional partial integro-differential equations (PIDEs) based on the temporal difference learning. We introduce a set of Levy processes and construct a corresponding reinforcement learning model. To simulate the entire process, we use deep neural networks to represent the solutions and non-local terms of the equations. Subsequently, we train the networks using the temporal difference error, termination condition, and properties of the non-local terms as the loss function. The relative error of the method reaches O(10^{-3}) in 100-dimensional experiments and O(10^{-4}) in one-dimensional pure jump problems. Additionally, our method demonstrates the advantages of low computational cost and robustness, making it well-suited for addressing problems with different forms and intensities of jumps.

This paper introduces innovative benchmarks to evaluate Vision-Language Models (VLMs) in real-world zero-shot recognition tasks, focusing on the granularity and specificity of prompting text. We propose a unique evaluation protocol using adapted ImageNet and MS-COCO datasets to assess models' consistency in recognizing concepts at varying granularity levels and their sensitivity to the specificity of language inputs. Our extensive evaluation reveals that state-of-the-art VLMs, including contrastive models like CLIP, struggle with granularity and are sensitive to text specificity, impacting their effectiveness in open-world settings. This comprehensive study, a first in evaluating VLMs from these perspectives, provides valuable insights and tools for the community, highlighting the limitations and paving the way for enhanced models with better generalization in zero-shot recognition., Comment: Additional experiments

Clickbait, which aims to induce users with some surprising and even thrilling headlines for increasing click-through rates, permeates almost all online content publishers, such as news portals and social media. Recently, Large Language Models (LLMs) have emerged as a powerful instrument and achieved tremendous success in a series of NLP downstream tasks. However, it is not yet known whether LLMs can be served as a high-quality clickbait detection system. In this paper, we analyze the performance of LLMs in the few-shot and zero-shot scenarios on several English and Chinese benchmark datasets. Experimental results show that LLMs cannot achieve the best results compared to the state-of-the-art deep and fine-tuning PLMs methods. Different from human intuition, the experiments demonstrated that LLMs cannot make satisfied clickbait detection just by the headlines.

Entropy, since its first discovery by Ludwig Boltzmann in 1877, has been widely applied in diverse disciplines, including thermodynamics, continuum mechanics, mathematical analysis, machine learning, etc. In this paper, we propose a new method for solving the inverse XDE (ODE, PDE, SDE) problems by utilizing the entropy balance equation instead of the original differential equations. This distinguishing feature constitutes a major difference between our current method and other previous classical methods (e.g. SINDy). Despite concerns about the potential information loss during the compression procedure from the original XDEs to single entropy balance equation, various examples from MM reactions, Schlogl model and chemical Lorenz equations in the form of ODEs to nonlinear porous medium equation and Fokker-Planck equation with a double-well potential in the PDE form all well confirm the accuracy, robustness and reliability of our method, as well as its comparable performance with respect to SINDy., Comment: 18 pages, 3 tables, 5 figures