Search

The explosive arrival of OpenAI's ChatGPT has fueled the globalization of large language model (LLM), which consists of billions of pretrained parameters that embodies the aspects of syntax and semantics. HyperAccel introduces latency processing unit (LPU), a latency-optimized and highly scalable processor architecture for the acceleration of LLM inference. LPU perfectly balances the memory bandwidth and compute logic with streamlined dataflow to maximize performance and efficiency. LPU is equipped with expandable synchronization link (ESL) that hides data synchronization latency between multiple LPUs. HyperDex complements LPU as an intuitive software framework to run LLM applications. LPU achieves 1.25 ms/token and 20.9 ms/token for 1.3B and 66B model, respectively, which is 2.09x and 1.37x faster than the GPU. LPU, synthesized using Samsung 4nm process, has total area of 0.824 mm2 and power consumption of 284.31 mW. LPU-based servers achieve 1.33x and 1.32x energy efficiency over NVIDIA H100 and L4 servers, respectively.

Monocular 3D object detection is an important challenging task in autonomous driving. Existing methods mainly focus on performing 3D detection in ideal weather conditions, characterized by scenarios with clear and optimal visibility. However, the challenge of autonomous driving requires the ability to handle changes in weather conditions, such as foggy weather, not just clear weather. We introduce MonoWAD, a novel weather-robust monocular 3D object detector with a weather-adaptive diffusion model. It contains two components: (1) the weather codebook to memorize the knowledge of the clear weather and generate a weather-reference feature for any input, and (2) the weather-adaptive diffusion model to enhance the feature representation of the input feature by incorporating a weather-reference feature. This serves an attention role in indicating how much improvement is needed for the input feature according to the weather conditions. To achieve this goal, we introduce a weather-adaptive enhancement loss to enhance the feature representation under both clear and foggy weather conditions. Extensive experiments under various weather conditions demonstrate that MonoWAD achieves weather-robust monocular 3D object detection. The code and dataset are released at https://github.com/VisualAIKHU/MonoWAD., Comment: Accepted by ECCV 2024

Recent Audio-Visual Question Answering (AVQA) methods rely on complete visual and audio input to answer questions accurately. However, in real-world scenarios, issues such as device malfunctions and data transmission errors frequently result in missing audio or visual modality. In such cases, existing AVQA methods suffer significant performance degradation. In this paper, we propose a framework that ensures robust AVQA performance even when a modality is missing. First, we propose a Relation-aware Missing Modal (RMM) generator with Relation-aware Missing Modal Recalling (RMMR) loss to enhance the ability of the generator to recall missing modal information by understanding the relationships and context among the available modalities. Second, we design an Audio-Visual Relation-aware (AVR) diffusion model with Audio-Visual Enhancing (AVE) loss to further enhance audio-visual features by leveraging the relationships and shared cues between the audio-visual modalities. As a result, our method can provide accurate answers by effectively utilizing available information even when input modalities are missing. We believe our method holds potential applications not only in AVQA research but also in various multi-modal scenarios., Comment: Accepted at ECCV 2024

The privacy-preserving approaches to machine learning (ML) models have made substantial progress in recent years. However, it is still opaque in which circumstances and conditions the model becomes privacy-vulnerable, leading to a challenge for ML models to maintain both performance and privacy. In this paper, we first explore the disparity between member and non-member data in the representation of models under common training frameworks. We identify how the representation magnitude disparity correlates with privacy vulnerability and address how this correlation impacts privacy vulnerability. Based on the observations, we propose Saturn Ring Classifier Module (SRCM), a plug-in model-level solution to mitigate membership privacy leakage. Through a confined yet effective representation space, our approach ameliorates models' privacy vulnerability while maintaining generalizability. The code of this work can be found here: \url{https://github.com/JEKimLab/AIES2024_SRCM}, Comment: Accepted in the AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, 2024

With the rapid increase in the research, development, and application of neural networks in the current era, there is a proportional increase in the energy needed to train and use models. Crucially, this is accompanied by the increase in carbon emissions into the environment. A sustainable and socially beneficial approach to reducing the carbon footprint and rising energy demands associated with the modern age of AI/deep learning is the adaptive and continuous reuse of models with regard to changes in the environment of model deployment or variations/changes in the input data. In this paper, we propose PreIndex, a predictive index to estimate the environmental and compute resources associated with model retraining to distributional shifts in data. PreIndex can be used to estimate environmental costs such as carbon emissions and energy usage when retraining from current data distribution to new data distribution. It also correlates with and can be used to estimate other resource indicators associated with deep learning, such as epochs, gradient norm, and magnitude of model parameter change. PreIndex requires only one forward pass of the data, following which it provides a single concise value to estimate resources associated with retraining to the new distribution shifted data. We show that PreIndex can be reliably used across various datasets, model architectures, different types, and intensities of distribution shifts. Thus, PreIndex enables users to make informed decisions for retraining to different distribution shifts and determine the most cost-effective and sustainable option, allowing for the reuse of a model with a much smaller footprint in the environment. The code for this work is available here: https://github.com/JEKimLab/AIES2024PreIndex, Comment: Accepted in the AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society, 2024

Some van der Waals (vdW) materials exhibit ferroelectricity, making them promising for novel non-volatile memories (NVMs) such as ferroelectric diodes (FeDs). CuInP2S6 (CIPS) is a well-known vdW ferroelectric that has been integrated with graphene for memory devices. Here we demonstrate FeDs with self-rectifying, hysteretic current-voltage characteristics based on vertical heterostructures of 10-nm-thick CIPS and graphene. By using vdW indium-cobalt top electrodes and graphene bottom electrodes, we achieve high electroresistance (on- and off-state resistance ratios) of ~10^6, on-state rectification ratios of ~2500 for read/write voltages of 2 V/0.5 V and maximum output current densities of 100 A/cm^2. These metrics compare favourably with state-of-the-art FeDs. Piezoresponse force microscopy measurements show that stabilization of intermediate net polarization states in CIPS leads to stable multi-bit data retention at room temperature. The combination of two-terminal design, multi-bit memory, and low-power operation in CIPS-based FeDs is potentially interesting for compute-in-memory and neuromorphic computing applications., Comment: 17 Pages

Computation of spin-resummed observables in post-Minkowskian dynamics typically involve evaluation of Feynman integrals deformed by an exponential factor, where the exponent is a linear sum of the momenta being integrated. Such integrals can be viewed as tensor integral generating functions, which provide alternative approaches to tensor reduction of Feynman integrals. We develop a systematic method to evaluate tensor integral generating functions using conventional multiloop integration techniques. The spin-resummed aligned-spin eikonal at second post-Minkowskian order is considered as a phenomenologically relevant example where evaluation of tensor integral generating functions is necessary., Comment: 10 pages, 4 figures

Precise and prompt identification of road surface conditions enables vehicles to adjust their actions, like changing speed or using specific traction control techniques, to lower the chance of accidents and potential danger to drivers and pedestrians. However, most of the existing methods for detecting road surfaces solely rely on visual data, which may be insufficient in certain situations, such as when the roads are covered by debris, in low light conditions, or in the presence of fog. Therefore, we introduce a multimodal approach for the automated detection of road surface conditions by integrating audio and images. The robustness of the proposed method is tested on a diverse dataset collected under various environmental conditions and road surface types. Through extensive evaluation, we demonstrate the effectiveness and reliability of our multimodal approach in accurately identifying road surface conditions in real-time scenarios. Our findings highlight the potential of integrating auditory and visual cues for enhancing road safety and minimizing accident risks, Comment: 4 pages

Sign languages are multi-channel languages that communicate information through not just the hands (manual signals) but also facial expressions and upper body movements (non-manual signals). However, since automatic sign language translation is usually performed by generating a single sequence of glosses, researchers eschew non-manual and co-occurring manual signals in favor of a simplified list of manual glosses. This can lead to significant information loss and ambiguity. In this paper, we introduce a new task named multi-channel sign language translation (MCSLT) and present a novel metric, SignBLEU, designed to capture multiple signal channels. We validated SignBLEU on a system-level task using three sign language corpora with varied linguistic structures and transcription methodologies and examined its correlation with human judgment through two segment-level tasks. We found that SignBLEU consistently correlates better with human judgment than competing metrics. To facilitate further MCSLT research, we report benchmark scores for the three sign language corpora and release the source code for SignBLEU at https://github.com/eq4all-projects/SignBLEU., Comment: Published in LREC-Coling 2024

We study the (ambi-)twistor model for spinning particles interacting via electromagnetic field, as a toy model for studying classical dynamics of gravitating bodies including effects of both spins to all orders. We compute the momentum kick and spin kick up to one-loop order and show precisely how they are encoded in the classical eikonal. The all-orders-in-spin effects are encoded as a dynamical implementation of the Newman-Janis shift, and we find that the expansion in both spins can be resummed to simple expressions in special kinematic configurations, at least up to one-loop order. We confirm that the classical eikonal can be understood as the generator of canonical transformations that map the in-states of a scattering process to the out-states. We also remark that cut contributions for converting worldline propagators from time-symmetric to retarded amount to the iterated action of the leading eikonal at one-loop order., Comment: 74 pages, 15 figures; (v2) 76 pages, 15 figures; additional references; extended discussions on singularity structures of axial scattering eikonal

In this paper, we propose a predictive quantifier to estimate the retraining cost of a trained model in distribution shifts. The proposed Aggregated Representation Measure (ARM) quantifies the change in the model's representation from the old to new data distribution. It provides, before actually retraining the model, a single concise index of resources - epochs, energy, and carbon emissions - required for the retraining. This enables reuse of a model with a much lower cost than training a new model from scratch. The experimental results indicate that ARM reasonably predicts retraining costs for varying noise intensities and enables comparisons among multiple model architectures to determine the most cost-effective and sustainable option.

Membership inference attacks (MIAs) are currently considered one of the main privacy attack strategies, and their defense mechanisms have also been extensively explored. However, there is still a gap between the existing defense approaches and ideal models in performance and deployment costs. In particular, we observed that the privacy vulnerability of the model is closely correlated with the gap between the model's data-memorizing ability and generalization ability. To address this, we propose a new architecture-agnostic training paradigm called center-based relaxed learning (CRL), which is adaptive to any classification model and provides privacy preservation by sacrificing a minimal or no loss of model generalizability. We emphasize that CRL can better maintain the model's consistency between member and non-member data. Through extensive experiments on standard classification datasets, we empirically show that this approach exhibits comparable performance without requiring additional model capacity or data costs., Comment: Accepted in the Conference on Uncertainty in Artificial Intelligence (UAI) 2024, PMLR

When neural networks are confronted with unfamiliar data that deviate from their training set, this signifies a domain shift. While these networks output predictions on their inputs, they typically fail to account for their level of familiarity with these novel observations. This challenge becomes even more pronounced in resource-constrained settings, such as embedded systems or edge devices. To address such challenges, we aim to recalibrate a neural network's decision boundaries in relation to its cognizance of the data it observes, introducing an approach we coin as certainty distillation. While prevailing works navigate unsupervised domain adaptation (UDA) with the goal of curtailing model entropy, they unintentionally birth models that grapple with calibration inaccuracies - a dilemma we term the over-certainty phenomenon. In this paper, we probe the drawbacks of this traditional learning model. As a solution to the issue, we propose a UDA algorithm that not only augments accuracy but also assures model calibration, all while maintaining suitability for environments with limited computational resources.

In this study, we consider the infinitely many-armed bandit problems in a rested rotting setting, where the mean reward of an arm may decrease with each pull, while otherwise, it remains unchanged. We explore two scenarios regarding the rotting of rewards: one in which the cumulative amount of rotting is bounded by $V_T$, referred to as the slow-rotting case, and the other in which the cumulative number of rotting instances is bounded by $S_T$, referred to as the abrupt-rotting case. To address the challenge posed by rotting rewards, we introduce an algorithm that utilizes UCB with an adaptive sliding window, designed to manage the bias and variance trade-off arising due to rotting rewards. Our proposed algorithm achieves tight regret bounds for both slow and abrupt rotting scenarios. Lastly, we demonstrate the performance of our algorithm using numerical experiments.

In this research, we propose an innovative method to boost Knowledge Distillation efficiency without the need for resource-heavy teacher models. Knowledge Distillation trains a smaller ``student'' model with guidance from a larger ``teacher'' model, which is computationally costly. However, the main benefit comes from the soft labels provided by the teacher, helping the student grasp nuanced class similarities. In our work, we propose an efficient method for generating these soft labels, thereby eliminating the need for a large teacher model. We employ a compact autoencoder to extract essential features and calculate similarity scores between different classes. Afterward, we apply the softmax function to these similarity scores to obtain a soft probability vector. This vector serves as valuable guidance during the training of the student model. Our extensive experiments on various datasets, including CIFAR-100, Tiny Imagenet, and Fashion MNIST, demonstrate the superior resource efficiency of our approach compared to traditional knowledge distillation methods that rely on large teacher models. Importantly, our approach consistently achieves similar or even superior performance in terms of model accuracy. We also perform a comparative study with various techniques recently developed for knowledge distillation showing our approach achieves competitive performance with using significantly less resources. We also show that our approach can be easily added to any logit based knowledge distillation method. This research contributes to making knowledge distillation more accessible and cost-effective for practical applications, making it a promising avenue for improving the efficiency of model training. The code for this work is available at, https://github.com/JEKimLab/ReffAKD.

We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. HyperCLOVA X was trained on a balanced mix of Korean, English, and code data, followed by instruction-tuning with high-quality human-annotated datasets while abiding by strict safety guidelines reflecting our commitment to responsible AI. The model is evaluated across various benchmarks, including comprehensive reasoning, knowledge, commonsense, factuality, coding, math, chatting, instruction-following, and harmlessness, in both Korean and English. HyperCLOVA X exhibits strong reasoning capabilities in Korean backed by a deep understanding of the language and cultural nuances. Further analysis of the inherent bilingual nature and its extension to multilingualism highlights the model's cross-lingual proficiency and strong generalization ability to untargeted languages, including machine translation between several language pairs and cross-lingual inference tasks. We believe that HyperCLOVA X can provide helpful guidance for regions or countries in developing their sovereign LLMs., Comment: 44 pages; updated authors list and fixed author names

The goal of the multi-sound source localization task is to localize sound sources from the mixture individually. While recent multi-sound source localization methods have shown improved performance, they face challenges due to their reliance on prior information about the number of objects to be separated. In this paper, to overcome this limitation, we present a novel multi-sound source localization method that can perform localization without prior knowledge of the number of sound sources. To achieve this goal, we propose an iterative object identification (IOI) module, which can recognize sound-making objects in an iterative manner. After finding the regions of sound-making objects, we devise object similarity-aware clustering (OSC) loss to guide the IOI module to effectively combine regions of the same object but also distinguish between different objects and backgrounds. It enables our method to perform accurate localization of sound-making objects without any prior knowledge. Extensive experimental results on the MUSIC and VGGSound benchmarks show the significant performance improvements of the proposed method over the existing methods for both single and multi-source. Our code is available at: https://github.com/VisualAIKHU/NoPrior_MultiSSL, Comment: Accepted at CVPR 2024

Transfer learning is a de facto standard method for efficiently training machine learning models for data-scarce problems by adding and fine-tuning new classification layers to a model pre-trained on large datasets. Although numerous previous studies proposed to use homomorphic encryption to resolve the data privacy issue in transfer learning in the machine learning as a service setting, most of them only focused on encrypted inference. In this study, we present HETAL, an efficient Homomorphic Encryption based Transfer Learning algorithm, that protects the client's privacy in training tasks by encrypting the client data using the CKKS homomorphic encryption scheme. HETAL is the first practical scheme that strictly provides encrypted training, adopting validation-based early stopping and achieving the accuracy of nonencrypted training. We propose an efficient encrypted matrix multiplication algorithm, which is 1.8 to 323 times faster than prior methods, and a highly precise softmax approximation algorithm with increased coverage. The experimental results for five well-known benchmark datasets show total training times of 567-3442 seconds, which is less than an hour., Comment: ICML 2023, Appendix D includes some updates after official publication

Quadrupedal robots have played a crucial role in various environments, from structured environments to complex harsh terrains, thanks to their agile locomotion ability. However, these robots can easily lose their locomotion functionality if damaged by external accidents or internal malfunctions. In this paper, we propose a novel deep reinforcement learning framework to enable a quadrupedal robot to walk with impaired joints. The proposed framework consists of three components: 1) a random joint masking strategy for simulating impaired joint scenarios, 2) a joint state estimator to predict an implicit status of current joint condition based on past observation history, and 3) progressive curriculum learning to allow a single network to conduct both normal gait and various joint-impaired gaits. We verify that our framework enables the Unitree's Go1 robot to walk under various impaired joint conditions in real-world indoor and outdoor environments., Comment: Appear to ICRA 2024, Project page: https://sites.google.com/view/learning-impaired-joints-loco

We propose a cooperative training framework for deep neural network architectures that enables the runtime network depths to change to satisfy dynamic computing resource requirements. In our framework, the number of layers participating in computation can be chosen dynamically to meet performance-cost trade-offs at inference runtime. Our method trains two Teammate nets and a Leader net, and two sets of Teammate sub-networks with various depths through knowledge distillation. The Teammate nets derive sub-networks and transfer knowledge to them, and to each other, while the Leader net guides Teammate nets to ensure accuracy. The approach trains the framework atomically at once instead of individually training various sizes of models; in a sense, the various-sized networks are all trained at once, in a "package deal." The proposed framework is not tied to any specific architecture but can incorporate any existing models/architectures, therefore it can maintain stable results and is insensitive to the size of a dataset's feature map. Compared with other related approaches, it provides comparable accuracy to its full network while various sizes of models are available.

We utilize three point amplitudes with (spinning) particles of unequal mass and a graviton to capture the dynamics of absorption processes. We demonstrate that the construction can represent the spheroidal harmonics appearing in the Teukolsky equations. The absolute square of the ``Wilson coefficients'' in this effective description can be fixed by matching to the known absorptive cross-sections. As an application, we compute corrections to the gravitational Compton amplitude from the exchange of states corresponding to such absorption effects. In the super-extremal limit, the corrections generate the non-analytic $|a|$-dependent contribution of the Compton amplitude found in ref.\cite{Bautista:2022wjf}., Comment: 32 pages, 2 figures

The use of biometrics to authenticate users and control access to secure areas has become extremely popular in recent years, and biometric access control systems are frequently used by both governments and private corporations. However, these systems may represent risks to security when deployed without considering the possibility of biometric presentation attacks (also known as spoofing). Presentation attacks are a serious threat because they do not require significant time, expense, or skill to carry out while remaining effective against many biometric systems in use today. This research compares three different software-based methods for facial and iris presentation attack detection in images. The first method uses Inception-v3, a pre-trained deep Convolutional Neural Network (CNN) made by Google for the ImageNet challenge, which is retrained for this problem. The second uses a shallow CNN based on a modified Spoofnet architecture, which is trained normally. The third is a texture-based method using Local Binary Patterns (LBP). The datasets used are the ATVS-FIr dataset, which contains real and fake iris images, and the CASIA Face Anti-Spoofing Dataset, which contains real images as well as warped photos, cut photos, and video replay presentation attacks. We also present a third set of results, based on cropped versions of the CASIA images.

Soft robotics is a modern robotic paradigm for performing dexterous interactions with the surroundings via morphological flexibility. The desire for autonomous operation requires soft robots to be capable of proprioception and makes it necessary to devise a calibration process. These requirements can be greatly benefited by adopting numerical simulation for computational efficiency. However, the gap between the simulated and real domains limits the accurate, generalized application of the approach. Herein, we propose an unsupervised domain adaptation framework as a data-efficient, generalized alignment of these heterogeneous sensor domains. A dual cross-modal autoencoder was designed to match the sensor domains at a feature level without any extensive labeling process, facilitating the computationally efficient transferability to various tasks. As a proof-of-concept, the methodology was adopted to the famous soft robot design, a multigait soft robot, and two fundamental perception tasks for autonomous robot operation, involving high-fidelity shape estimation and collision detection. The resulting perception demonstrates the digital-twinned calibration process in both the simulated and real domains. The proposed design outperforms the existing prevalent benchmarks for both perception tasks. This unsupervised framework envisions a new approach to imparting embodied intelligence to soft robotic systems via blending simulation., Comment: 13 pages, 12 figures

The cubic perovskite SrFeO$_3$ was recently reported to host hedgehog- and skyrmion-lattice phases in a highly symmetric crystal structure which does not support the Dzyaloshinskii-Moriya interactions commonly invoked to explain such magnetic order. Hints of a complex magnetic phase diagram have also recently been found in powder samples of the single-layer Ruddlesden-Popper analog Sr$_2$FeO$_4$, so a reinvestigation of the bilayer material Sr$_3$Fe$_2$O$_7$, believed to be a simple helimagnet, is called for. Our magnetization and dilatometry studies reveal a rich magnetic phase diagram with at least 6 distinct magnetically ordered phases and strong similarities to that of SrFeO$_3$. In particular, at least one phase is apparently multiple-$\mathbf{q}$, and the $\mathbf{q}$s are not observed to vary among the phases. Since Sr$_3$Fe$_2$O$_7$ has only two possible orientations for its propagation vector, some of the phases are likely exotic multiple-$\mathbf{q}$ order, and it is possible to fully detwin all phases and more readily access their exotic physics., Comment: 14 pages, 13 figures

Large language models (LLMs) trained on massive corpora demonstrate impressive capabilities in a wide range of tasks. While there are ongoing efforts to adapt these models to languages beyond English, the attention given to their evaluation methodologies remains limited. Current multilingual benchmarks often rely on back translations or re-implementations of English tests, limiting their capacity to capture unique cultural and linguistic nuances. To bridge this gap for the Korean language, we introduce the HAE-RAE Bench, a dataset curated to challenge models lacking Korean cultural and contextual depth. The dataset encompasses six downstream tasks across four domains: vocabulary, history, general knowledge, and reading comprehension. Unlike traditional evaluation suites focused on token and sequence classification or mathematical and logical reasoning, the HAE-RAE Bench emphasizes a model's aptitude for recalling Korean-specific knowledge and cultural contexts. Comparative analysis with prior Korean benchmarks indicates that the HAE-RAE Bench presents a greater challenge to non-Korean models by disturbing abilities and knowledge learned from English being transferred., Comment: Accepted at LREC-COLING 2024

Continual learning aims to learn a model from a continuous stream of data, but it mainly assumes a fixed number of data and tasks with clear task boundaries. However, in real-world scenarios, the number of input data and tasks is constantly changing in a statistical way, not a static way. Although recently introduced incremental learning scenarios having blurry task boundaries somewhat address the above issues, they still do not fully reflect the statistical properties of real-world situations because of the fixed ratio of disjoint and blurry samples. In this paper, we propose a new Stochastic incremental Blurry task boundary scenario, called Si-Blurry, which reflects the stochastic properties of the real-world. We find that there are two major challenges in the Si-Blurry scenario: (1) inter- and intra-task forgettings and (2) class imbalance problem. To alleviate them, we introduce Mask and Visual Prompt tuning (MVP). In MVP, to address the inter- and intra-task forgetting issues, we propose a novel instance-wise logit masking and contrastive visual prompt tuning loss. Both of them help our model discern the classes to be learned in the current batch. It results in consolidating the previous knowledge. In addition, to alleviate the class imbalance problem, we introduce a new gradient similarity-based focal loss and adaptive feature scaling to ease overfitting to the major classes and underfitting to the minor classes. Extensive experiments show that our proposed MVP significantly outperforms the existing state-of-the-art methods in our challenging Si-Blurry scenario.

The objective of the sound source localization task is to enable machines to detect the location of sound-making objects within a visual scene. While the audio modality provides spatial cues to locate the sound source, existing approaches only use audio as an auxiliary role to compare spatial regions of the visual modality. Humans, on the other hand, utilize both audio and visual modalities as spatial cues to locate sound sources. In this paper, we propose an audio-visual spatial integration network that integrates spatial cues from both modalities to mimic human behavior when detecting sound-making objects. Additionally, we introduce a recursive attention network to mimic human behavior of iterative focusing on objects, resulting in more accurate attention regions. To effectively encode spatial information from both modalities, we propose audio-visual pair matching loss and spatial region alignment loss. By utilizing the spatial cues of audio-visual modalities and recursively focusing objects, our method can perform more robust sound source localization. Comprehensive experimental results on the Flickr SoundNet and VGG-Sound Source datasets demonstrate the superiority of our proposed method over existing approaches. Our code is available at: https://github.com/VisualAIKHU/SIRA-SSL, Comment: Camera-Ready, ACM MM 2023

Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like image editing with fine-grained control). Many of such applications need to be run on resource-constraint edge devices, like mobile phones. In this work, we aim to make SAM mobile-friendly by replacing the heavyweight image encoder with a lightweight one. A naive way to train such a new SAM as in the original SAM paper leads to unsatisfactory performance, especially when limited training sources are available. We find that this is mainly caused by the coupled optimization of the image encoder and mask decoder, motivated by which we propose decoupled distillation. Concretely, we distill the knowledge from the heavy image encoder (ViT-H in the original SAM) to a lightweight image encoder, which can be automatically compatible with the mask decoder in the original SAM. The training can be completed on a single GPU within less than one day, and the resulting lightweight SAM is termed MobileSAM which is more than 60 times smaller yet performs on par with the original SAM. For inference speed, With a single GPU, MobileSAM runs around 10ms per image: 8ms on the image encoder and 4ms on the mask decoder. With superior performance, our MobileSAM is around 5 times faster than the concurrent FastSAM and 7 times smaller, making it more suitable for mobile applications. Moreover, we show that MobileSAM can run relatively smoothly on CPU. The code for our project is provided at \href{https://github.com/ChaoningZhang/MobileSAM}{\textcolor{red}{MobileSAM}}), with a demo showing that MobileSAM can run relatively smoothly on CPU., Comment: First work to make SAM lightweight for mobile applications

Open Information Extraction (OIE) aims to extract factual relational tuples from open-domain sentences. Downstream tasks use the extracted OIE tuples as facts, without examining the certainty of these facts. However, uncertainty/speculation is a common linguistic phenomenon. Existing studies on speculation detection are defined at sentence level, but even if a sentence is determined to be speculative, not all tuples extracted from it may be speculative. In this paper, we propose to study speculations in OIE and aim to determine whether an extracted tuple is speculative. We formally define the research problem of tuple-level speculation detection and conduct a detailed data analysis on the LSOIE dataset which contains labels for speculative tuples. Lastly, we propose a baseline model OIE-Spec for this new research task.

Open Information Extraction (OIE) aims to extract relational tuples from open-domain sentences. Existing OIE systems split a sentence into tokens and recognize token spans as tuple relations and arguments. We instead propose Sentence as Chunk sequence (SaC) and recognize chunk spans as tuple relations and arguments. We argue that SaC has better quantitative and qualitative properties for OIE than sentence as token sequence, and evaluate four choices of chunks (i.e., CoNLL chunks, simple phrases, NP chunks, and spans from SpanOIE) against gold OIE tuples. Accordingly, we propose a simple BERT-based model for sentence chunking, and propose Chunk-OIE for tuple extraction on top of SaC. Chunk-OIE achieves state-of-the-art results on multiple OIE datasets, showing that SaC benefits OIE task.

OpenAI has recently released GPT-4 (a.k.a. ChatGPT plus), which is demonstrated to be one small step for generative AI (GAI), but one giant leap for artificial general intelligence (AGI). Since its official release in November 2022, ChatGPT has quickly attracted numerous users with extensive media coverage. Such unprecedented attention has also motivated numerous researchers to investigate ChatGPT from various aspects. According to Google scholar, there are more than 500 articles with ChatGPT in their titles or mentioning it in their abstracts. Considering this, a review is urgently needed, and our work fills this gap. Overall, this work is the first to survey ChatGPT with a comprehensive review of its underlying technology, applications, and challenges. Moreover, we present an outlook on how ChatGPT might evolve to realize general-purpose AIGC (a.k.a. AI-generated content), which will be a significant milestone for the development of AGI., Comment: A Survey on ChatGPT and GPT-4, 29 pages. Feedback is appreciated (chaoningzhang1990@gmail.com)

The spin supplementary conditions are constraints on spin degrees of freedom in classical relativity which restricts physical degrees of freedom to rotations. It is argued that the equivalent constraints in quantum field theory are the projection conditions on polarisation tensors, which remove timelike/longitudinal polarisations from the physical spectrum. The claim is supported by three examples of massive spinning particles coupled to electromagnetism: Dirac and Proca fields in quantum field theory, and $\mathcal{N} = 1$ worldline QFT for classical worldline theory. This suggests a resolution to the apparent discrepancy between effective field theory description of massive higher-spin fields~\cite{Bern:2020buy,Bern:2022kto} and post-Newtonian effective field theory of spinning classical particles~\cite{Levi:2015msa}, where the former admits more unfixed parameters compared to the latter; the additional parameters are fixed by projection conditions and therefore are not tunable parameters., Comment: version accepted to JHEP; title modified; footnote 1 on spin tensor definitions with boost-subtraction added; appendix D on classical EOM derivation from WQFT added; references added; 27 pages

Open Information Extraction (OpenIE) aims to extract relational tuples from open-domain sentences. Traditional rule-based or statistical models have been developed based on syntactic structures of sentences, identified by syntactic parsers. However, previous neural OpenIE models under-explore the useful syntactic information. In this paper, we model both constituency and dependency trees into word-level graphs, and enable neural OpenIE to learn from the syntactic structures. To better fuse heterogeneous information from both graphs, we adopt multi-view learning to capture multiple relationships from them. Finally, the finetuned constituency and dependency representations are aggregated with sentential semantic representations for tuple generation. Experiments show that both constituency and dependency information, and the multi-view learning are effective., Comment: To appear in EMNLP 2022