Search

Sign language translation (SLT) aims to convert continuous sign language videos into textual sentences. As a typical multi-modal task, there exists an inherent modality gap between sign language videos and spoken language text, which makes the cross-modal alignment between visual and textual modalities crucial. However, previous studies tend to rely on an intermediate sign gloss representation to help alleviate the cross-modal problem thereby neglecting the alignment across modalities that may lead to compromised results. To address this issue, we propose a novel framework based on Conditional Variational autoencoder for SLT (CV-SLT) that facilitates direct and sufficient cross-modal alignment between sign language videos and spoken language text. Specifically, our CV-SLT consists of two paths with two Kullback-Leibler (KL) divergences to regularize the outputs of the encoder and decoder, respectively. In the prior path, the model solely relies on visual information to predict the target text; whereas in the posterior path, it simultaneously encodes visual information and textual knowledge to reconstruct the target text. The first KL divergence optimizes the conditional variational autoencoder and regularizes the encoder outputs, while the second KL divergence performs a self-distillation from the posterior path to the prior path, ensuring the consistency of decoder outputs. We further enhance the integration of textual information to the posterior path by employing a shared Attention Residual Gaussian Distribution (ARGD), which considers the textual information in the posterior path as a residual component relative to the prior path. Extensive experiments conducted on public datasets (PHOENIX14T and CSL-daily) demonstrate the effectiveness of our framework, achieving new state-of-the-art results while significantly alleviating the cross-modal representation discrepancy., Comment: Accepted as conference paper by AAAI24. The code and models are available at https://github.com/rzhao-zhsq/CV-SLT

In recent years, the rapid advancement and impressive capabilities of Large Language Models (LLMs) have been evident across various domains. This paper explores the application, implications, and potential of LLMs in building energy efficiency and decarbonization studies. The wide-ranging capabilities of LLMs are examined in the context of the building energy field, including intelligent control systems, code generation, data infrastructure, knowledge extraction, and education. Despite the promising potential of LLMs, challenges including complex and expensive computation, data privacy, security and copyright, complexity in fine-tuned LLMs, and self-consistency are discussed. The paper concludes with a call for future research focused on the enhancement of LLMs for domain-specific tasks, multi-modal LLMs, and collaborative research between AI and energy experts.

Free-hand sketches are appealing for humans as a universal tool to depict the visual world. Humans can recognize varied sketches of a category easily by identifying the concurrence and layout of the intrinsic semantic components of the category, since humans draw free-hand sketches based a common consensus that which types of semantic components constitute each sketch category. For example, an airplane should at least have a fuselage and wings. Based on this analysis, a semantic component-level memory module is constructed and embedded in the proposed structured sketch recognition network in this paper. The memory keys representing semantic components of each sketch category can be self-learned and enhance the recognition network's explainability. Our proposed networks can deal with different situations of sketch recognition, i.e., with or without semantic components labels of strokes. Experiments on the SPG and SketchIME datasets demonstrate the memory module's flexibility and the recognition network's explainability. The code and data are available at https://github.com/GuangmingZhu/SketchESC., Comment: The paper has been accepted by AAAI2024

World's first 1.3 GHz cryomodule containing eight 9-cell superconducting radio-frequency (RF) cavities treated by medium-temperature furnace baking (mid-T bake) was developed, assembled and tested at IHEP for the Dalian Advanced Light Source (DALS) and CEPC R&D. The 9-cell cavities in the cryomodule achieved an unprecedented highest average Q0 of 3.8E10 at 16 MV/m and 3.6E10 at 21 MV/m in the horizontal test. The cryomodule can operate stably up to a total CW RF voltage greater than 191 MV, with an average cavity CW accelerating gradient of more than 23 MV/m. The results significantly exceed the specifications of CEPC, DALS and the other high repetition rate free electron laser facilities (LCLS-II, LCLS-II-HE, SHINE, S3FEL). There is evidence that the mid-T bake cavity may not require fast cool-down or long processing time in the cryomodule. This paper reviews the cryomodule performance and discusses some important issues in cryomodule assembly and testing., Comment: 5 pages, 6 figures

With the recent surge in the use of touchscreen devices, free-hand sketching has emerged as a promising modality for human-computer interaction. While previous research has focused on tasks such as recognition, retrieval, and generation of familiar everyday objects, this study aims to create a Sketch Input Method Editor (SketchIME) specifically designed for a professional C4I system. Within this system, sketches are utilized as low-fidelity prototypes for recommending standardized symbols in the creation of comprehensive situation maps. This paper also presents a systematic dataset comprising 374 specialized sketch types, and proposes a simultaneous recognition and segmentation architecture with multilevel supervision between recognition and segmentation to improve performance and enhance interpretability. By incorporating few-shot domain adaptation and class-incremental learning, the network's ability to adapt to new users and extend to new task-specific classes is significantly enhanced. Results from experiments conducted on both the proposed dataset and the SPG dataset illustrate the superior performance of the proposed architecture. Our dataset and code are publicly available at https://github.com/GuangmingZhu/SketchIME., Comment: The paper has been accepted by ACM Multimedia 2023

The high-frequency bump, characterized by a frequency exceeding ~30 Hz, represents a seldom-explored time-variability feature in the power density spectrum (PDS) of black-hole X-ray binaries. In the 2002, 2004, 2007 and 2010 outbursts of GX 339-4, the bump has been occasionally observed in conjunction with type-C quasi-periodic oscillations (QPOs). We systematically study the properties of the bump during these four outbursts observed by Rossi X-ray Timing Explorer (RXTE) in the 2-60 keV bands and detect the bump in 39 observations. While the frequencies of the type-C QPOs are in the range of ~0.1-9 Hz, the root-mean-square (rms) amplitude of the bump shows an evolution in the hardness ratio versus the type-C QPO frequency plot. By comparing the rms amplitude of the bump with the corona temperature and simultaneous radio jet flux of the source, as previously studied in GRS 1915+105, we establish that in the hard state of GX 339-4, the bump is always strong, with the measurements of the rms amplitude in the range of 4-10%. At the same time, the corona temperature is high and the radio flux is low. These findings indicate that, using the bump as a proxy, the majority of the accretion energy is directed towards the hot corona rather than being channeled into the radio jet. We discuss this phenomenon in terms of an inefficient energy transfer mechanism between the corona and jet in GX 339-4., Comment: 11 pages, 5 figures, accepted for publication in MNRAS

Urban Building Energy Modeling (UBEM) is a critical tool to provide quantitative analysis on building decarbonization, sustainability, building-to-grid integration, and renewable energy applications on city, regional, and national scales. Researchers usually use open data as inputs to build and calibrate UBEM. However, open data are from thousands of sources covering various perspectives of weather, building characteristics, etc. Besides, a lack of semantic features of open data further increases the engineering effort to process information to be directly used for UBEM as inputs. In this paper, we first reviewed open data types used for UBEM and developed a taxonomy to categorize open data. Based on that, we further developed a semantic data schema for each open data category to maintain data consistency and improve model automation for UBEM. In a case study, we use three popular open data to show how they can be automatically processed based on the proposed schematic data structure using large language models. The accurate results generated by large language models indicate the machine-readability and human-interpretability of the developed semantic data schema.

The proposed Circular Electron Positron Collider (CEPC) imposes new challenges for the vertex detector in terms of pixel size and material budget. A Monolithic Active Pixel Sensor (MAPS) prototype called TaichuPix, based on a column drain readout architecture, has been developed to address the need for high spatial resolution. In order to evaluate the performance of the TaichuPix-3 chips, a beam test was carried out at DESY II TB21 in December 2022. Meanwhile, the Data Acquisition (DAQ) for a muti-plane configuration was tested during the beam test. This work presents the characterization of the TaichuPix-3 chips with two different processes, including cluster size, spatial resolution, and detection efficiency. The analysis results indicate the spatial resolution better than 5 $\mu m$ and the detection efficiency exceeds 99.5 % for both TaichuPix-3 chips with the two different processes.

Data sparsity and cold-start problems are persistent challenges in recommendation systems. Cross-domain recommendation (CDR) is a promising solution that utilizes knowledge from the source domain to improve the recommendation performance in the target domain. Previous CDR approaches have mainly followed the Embedding and Mapping (EMCDR) framework, which involves learning a mapping function to facilitate knowledge transfer. However, these approaches necessitate re-engineering and re-training the network structure to incorporate transferrable knowledge, which can be computationally expensive and may result in catastrophic forgetting of the original knowledge. In this paper, we present a scalable and efficient paradigm to address data sparsity and cold-start issues in CDR, named CDR-Adapter, by decoupling the original recommendation model from the mapping function, without requiring re-engineering the network structure. Specifically, CDR-Adapter is a novel plug-and-play module that employs adapter modules to align feature representations, allowing for flexible knowledge transfer across different domains and efficient fine-tuning with minimal training costs. We conducted extensive experiments on the benchmark dataset, which demonstrated the effectiveness of our approach over several state-of-the-art CDR approaches., Comment: 8 pages, 4 figures, 5 tables, Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval Workshop on eCommerce

Deep learning accelerators address the computational demands of Deep Neural Networks (DNNs), departing from the traditional Von Neumann execution model. They leverage specialized hardware to align with the application domain's structure. Compilers for these accelerators face distinct challenges compared to those for general-purpose processors. These challenges include exposing and managing more micro-architectural features, handling software-managed scratch pads for on-chip storage, explicitly managing data movement, and matching DNN layers with varying hardware capabilities. These complexities necessitate a new approach to compiler design, as traditional compilers mainly focused on generating fine-grained instruction sequences while abstracting micro-architecture details. This paper introduces the Architecture Covenant Graph (ACG), an abstract representation of an architectural structure's components and their programmable capabilities. By enabling the compiler to work with the ACG, it allows for adaptable compilation workflows when making changes to accelerator design, reducing the need for a complete compiler redevelopment. Codelets, which express DNN operation functionality and evolve into execution mappings on the ACG, are key to this process. The Covenant compiler efficiently targets diverse deep learning accelerators, achieving 93.8% performance compared to state-of-the-art, hand-tuned DNN layer implementations when compiling 14 DNN layers from various models on two different architectures.

Algorithmic reproducibility measures the deviation in outputs of machine learning algorithms upon minor changes in the training process. Previous work suggests that first-order methods would need to trade-off convergence rate (gradient complexity) for better reproducibility. In this work, we challenge this perception and demonstrate that both optimal reproducibility and near-optimal convergence guarantees can be achieved for smooth convex minimization and smooth convex-concave minimax problems under various error-prone oracle settings. Particularly, given the inexact initialization oracle, our regularization-based algorithms achieve the best of both worlds - optimal reproducibility and near-optimal gradient complexity - for minimization and minimax optimization. With the inexact gradient oracle, the near-optimal guarantees also hold for minimax optimization. Additionally, with the stochastic gradient oracle, we show that stochastic gradient descent ascent is optimal in terms of both reproducibility and gradient complexity. We believe our results contribute to an enhanced understanding of the reproducibility-convergence trade-off in the context of convex optimization., Comment: NeurIPS 2023 Spotlight

In single-cloud storage, ciphertext-policy attribute-based encryption (CP-ABE) allows one to encrypt any data under an access structure to a cloud server, specifying what attributes are required to decrypt. In multi-cloud storage, a secret sharing scheme (SSS) allows one to split any data into multiple shares, one to a single server, and specify which subset of the servers are able to recover the data. It is an interesting problem to remove some attributes/servers but still enable the remaining attributes/servers in every authorized set to recover the data. The problem is related to the contraction problem of access structures for SSSs. In this paper, we propose a method that can efficiently transform a given SSS for an access structure to SSSs for contractions of the access structure. We show its applications in solving the attribute removal problem in the CP-ABE based single-cloud storage and the data relocating problem in multi-cloud storage. Our method results in solutions that require either less server storage or even no additional server storage., Comment: IEEE Transactions on Services Computing

Neural Radiance Fields (NeRF) is a novel implicit 3D reconstruction method that shows immense potential and has been gaining increasing attention. It enables the reconstruction of 3D scenes solely from a set of photographs. However, its real-time rendering capability, especially for interactive real-time rendering of large-scale scenes, still has significant limitations. To address these challenges, in this paper, we propose a novel neural rendering system called UE4-NeRF, specifically designed for real-time rendering of large-scale scenes. We partitioned each large scene into different sub-NeRFs. In order to represent the partitioned independent scene, we initialize polygonal meshes by constructing multiple regular octahedra within the scene and the vertices of the polygonal faces are continuously optimized during the training process. Drawing inspiration from Level of Detail (LOD) techniques, we trained meshes of varying levels of detail for different observation levels. Our approach combines with the rasterization pipeline in Unreal Engine 4 (UE4), achieving real-time rendering of large-scale scenes at 4K resolution with a frame rate of up to 43 FPS. Rendering within UE4 also facilitates scene editing in subsequent stages. Furthermore, through experiments, we have demonstrated that our method achieves rendering quality comparable to state-of-the-art approaches. Project page: https://jamchaos.github.io/UE4-NeRF/., Comment: Accepted by NeurIPS2023

The widespread practice of fine-tuning large language models (LLMs) on domain-specific data faces two major challenges in memory and privacy. First, as the size of LLMs continues to grow, the memory demands of gradient-based training methods via backpropagation become prohibitively high. Second, given the tendency of LLMs to memorize training data, it is important to protect potentially sensitive information in the fine-tuning data from being regurgitated. Zeroth-order methods, which rely solely on forward passes, substantially reduce memory consumption during training. However, directly combining them with standard differentially private gradient descent suffers more as model size grows. To bridge this gap, we introduce DPZero, a novel private zeroth-order algorithm with nearly dimension-independent rates. The memory efficiency of DPZero is demonstrated in privately fine-tuning RoBERTa and OPT on several downstream tasks. Our code is available at https://github.com/Liang137/DPZero., Comment: ICML 2024

We present a detailed analysis of the spectral and timing characteristics of a 7-Hz type-A quasi-periodic oscillation (QPO) detected in NICER observations of the black hole X-ray binary MAXI J1348-630 during its high-soft state. The QPO is broad and weak, with an integrated fractional rms amplitude of 0.9 per cent in the 0.5-10 keV band. Thanks to the large effective area of NICER, combined with the high flux of the source and a relatively long accumulative exposure time, we construct the first rms and phase-lag spectra for a type-A QPO. Our analysis reveals that the fractional rms amplitude of the QPO increases with energy from below 1 per cent at 1 keV to 3 per cent at 6 keV. The shape of the QPO spectrum is similar to that of the Comptonised component, suggesting that the Comptonised region is driving the variability. The phase lags at the QPO frequency are always soft taking the lowest energy as reference. By jointly fitting the time-averaged spectrum of the source and the rms and phase-lag spectra of the QPO with the time-dependent Comptonisation model vkompthdk, we find that the radiative properties of the type-A QPO can be explained by a vertically extended Comptonised region with a size of 2300 km., Comment: 7 pages, 5 figures, accepted for publication in MNRAS

Neural video codecs have recently become competitive with standard codecs such as HEVC in the low-delay setting. However, most neural codecs are large floating-point networks that use pixel-dense warping operations for temporal modeling, making them too computationally expensive for deployment on mobile devices. Recent work has demonstrated that running a neural decoder in real time on mobile is feasible, but shows this only for 720p RGB video. This work presents the first neural video codec that decodes 1080p YUV420 video in real time on a mobile device. Our codec relies on two major contributions. First, we design an efficient codec that uses a block-based motion compensation algorithm available on the warping core of the mobile accelerator, and we show how to quantize this model to integer precision. Second, we implement a fast decoder pipeline that concurrently runs neural network components on the neural signal processor, parallel entropy coding on the mobile GPU, and warping on the warping core. Our codec outperforms the previous on-device codec by a large margin with up to 48% BD-rate savings, while reducing the MAC count on the receiver side by $10 \times$. We perform a careful ablation to demonstrate the effect of the introduced motion compensation scheme, and ablate the effect of model quantization., Comment: Matches version published at WACV 2024

The launch of ${\it JWST}$ opens a new window for studying the connection between metal-line absorbers and galaxies at the end of the Epoch of Reionization (EoR). Previous studies have detected absorber-galaxy pairs in limited quantities through ground-based observations. To enhance our understanding of the relationship between absorbers and their host galaxies at $z>5$, we utilized the NIRCam Wide Field Slitless Spectroscopy (WFSS) to search for absorber-associated galaxies by detecting their rest-frame optical emission lines (e.g., [OIII] + H$\beta$). We report the discovery of a MgII-associated galaxy at $z=5.428$ using data from the ${\it JWST}$ ASPIRE program. The MgII absorber is detected on the spectrum of quasar J0305--3150 with a rest-frame equivalent width of 0.74$\mathring{A}$. The associated galaxy has an [OIII] luminosity of $10^{42.5}\ {\rm erg\ s^{-1}}$ with an impact parameter of 24.9 proper kiloparsecs (pkpc). The joint ${\it HST}$-${\it JWST}$ spectral energy distribution (SED) implies a stellar mass and star-formation rate of ${\rm M_* \approx 10^{8.8}}$ ${\rm M_{\odot}}$, ${\rm SFR}\approx 10\ {\rm M_{\odot}\ yr^{-1}}$. Its [OIII] equivalent width and stellar mass are typical of [OIII] emitters at this redshift. Furthermore, connecting the outflow starting time to the SED-derived stellar age, the outflow velocity of this galaxy is $\sim300\ {\rm km\ s^{-1}}$, consistent with theoretical expectations. We identified six additional [OIII] emitters with impact parameters of up to $\sim300$ pkpc at similar redshifts ($|dv|<1000\ {\rm km\ s^{-1}}$). The observed number is consistent with that in cosmological simulations. This pilot study suggests that systematically investigating the absorber-galaxy connection within the ASPIRE program will provide insights into the metal-enrichment history in the early universe., Comment: Accepted for publication in ApJL. Main text 8 pages, 4 figures. For more information of the JWST ASPIRE program please check https://aspire-quasar.github.io/index.html

Reconstruction of tracks of charged particles with high precision is very crucial for HEP experiments to achieve their physics goals. As the tracking detector of BESIII experiment, the BESIII drift chamber has suffered from aging effects resulting in degraded tracking performance after operation for about 15 years. To preserve and enhance the tracking performance of BESIII, one of the proposals is to add one layer of thin CMOS pixel sensor in cylindrical shape based on the state-of-the-art stitching technology, between the beam pipe and the drift chamber. The improvement of tracking performance of BESIII with such an additional pixel detector compared to that with only the existing drift chamber is studied using the modern common tracking software ACTS, which provides a set of detector-agnostic and highly performant tracking algorithms that have demonstrated promising performance for a few high energy physics and nuclear physics experiments.

Existing approaches to automatic data transformation are insufficient to meet the requirements in many real-world scenarios, such as the building sector. First, there is no convenient interface for domain experts to provide domain knowledge easily. Second, they require significant training data collection overheads. Third, the accuracy suffers from complicated schema changes. To bridge this gap, we present a novel approach that leverages the unique capabilities of large language models (LLMs) in coding, complex reasoning, and zero-shot learning to generate SQL code that transforms the source datasets into the target datasets. We demonstrate the viability of this approach by designing an LLM-based framework, termed SQLMorpher, which comprises a prompt generator that integrates the initial prompt with optional domain knowledge and historical patterns in external databases. It also implements an iterative prompt optimization mechanism that automatically improves the prompt based on flaw detection. The key contributions of this work include (1) pioneering an end-to-end LLM-based solution for data transformation, (2) developing a benchmark dataset of 105 real-world building energy data transformation problems, and (3) conducting an extensive empirical evaluation where our approach achieved 96% accuracy in all 105 problems. SQLMorpher demonstrates the effectiveness of utilizing LLMs in complex, domain-specific challenges, highlighting the potential of their potential to drive sustainable solutions., Comment: 10 pages, 7 figures

In this paper, we introduce a simple and efficient approach for the general reduction of one-loop integrals. Our method employs the introduction of an auxiliary vector and the identification of the tensor structure as an auxiliary propagator. This key insight allows us to express a wide range of one-loop integrals, encompassing both tensor structures and higher poles, in the Baikov representation. By establishing an integral-by-parts (IBP) relation, we derive a recursive formula that systematically solves the one-loop reduction problem, even in the presence of various degenerate cases. Our proposed strategy is characterized by its simplicity and effectiveness, offering a significant advancement in the field of one-loop calculations., Comment: 28 pages, an ancillary file

Click-through rate (CTR) prediction is a crucial issue in recommendation systems. There has been an emergence of various public CTR datasets. However, existing datasets primarily suffer from the following limitations. Firstly, users generally click different types of items from multiple scenarios, and modeling from multiple scenarios can provide a more comprehensive understanding of users. Existing datasets only include data for the same type of items from a single scenario. Secondly, multi-modal features are essential in multi-scenario prediction as they address the issue of inconsistent ID encoding between different scenarios. The existing datasets are based on ID features and lack multi-modal features. Third, a large-scale dataset can provide a more reliable evaluation of models, fully reflecting the performance differences between models. The scale of existing datasets is around 100 million, which is relatively small compared to the real-world CTR prediction. To address these limitations, we propose AntM$^{2}$C, a Multi-Scenario Multi-Modal CTR dataset based on industrial data from Alipay. Specifically, AntM$^{2}$C provides the following advantages: 1) It covers CTR data of 5 different types of items, providing insights into the preferences of users for different items, including advertisements, vouchers, mini-programs, contents, and videos. 2) Apart from ID-based features, AntM$^{2}$C also provides 2 multi-modal features, raw text and image features, which can effectively establish connections between items with different IDs. 3) AntM$^{2}$C provides 1 billion CTR data with 200 features, including 200 million users and 6 million items. It is currently the largest-scale CTR dataset available. Based on AntM$^{2}$C, we construct several typical CTR tasks and provide comparisons with baseline methods. The dataset homepage is available at https://www.atecup.cn/home.

Recently, more and more research has focused on using Graph Neural Networks (GNN) to solve the Graph Similarity Computation problem (GSC), i.e., computing the Graph Edit Distance (GED) between two graphs. These methods treat GSC as an end-to-end learnable task, and the core of their architecture is the feature fusion modules to interact with the features of two graphs. Existing methods consider that graph-level embedding is difficult to capture the differences in local small structures between two graphs, and thus perform fine-grained feature fusion on node-level embedding can improve the accuracy, but leads to greater time and memory consumption in the training and inference phases. However, this paper proposes a novel graph-level fusion module Different Attention (DiffAtt), and demonstrates that graph-level fusion embeddings can substantially outperform these complex node-level fusion embeddings. We posit that the relative difference structure of the two graphs plays an important role in calculating their GED values. To this end, DiffAtt uses the difference between two graph-level embeddings as an attentional mechanism to capture the graph structural difference of the two graphs. Based on DiffAtt, a new GSC method, named Graph Edit Distance Learning via Different Attention (REDRAFT), is proposed, and experimental results demonstrate that REDRAFT achieves state-of-the-art performance in 23 out of 25 metrics in five benchmark datasets. Especially on MSE, it respectively outperforms the second best by 19.9%, 48.8%, 29.1%, 31.6%, and 2.2%. Moreover, we propose a quantitative test Remaining Subgraph Alignment Test (RESAT) to verify that among all graph-level fusion modules, the fusion embedding generated by DiffAtt can best capture the structural differences between two graphs.

While current visual captioning models have achieved impressive performance, they often assume that the image is well-captured and provides a complete view of the scene. In real-world scenarios, however, a single image may not offer a good viewpoint, hindering fine-grained scene understanding. To overcome this limitation, we propose a novel task called Embodied Captioning, which equips visual captioning models with navigation capabilities, enabling them to actively explore the scene and reduce visual ambiguity from suboptimal viewpoints. Specifically, starting at a random viewpoint, an agent must navigate the environment to gather information from different viewpoints and generate a comprehensive paragraph describing all objects in the scene. To support this task, we build the ET-Cap dataset with Kubric simulator, consisting of 10K 3D scenes with cluttered objects and three annotated paragraphs per scene. We propose a Cascade Embodied Captioning model (CaBOT), which comprises of a navigator and a captioner, to tackle this task. The navigator predicts which actions to take in the environment, while the captioner generates a paragraph description based on the whole navigation trajectory. Extensive experiments demonstrate that our model outperforms other carefully designed baselines. Our dataset, codes and models are available at https://aim3-ruc.github.io/ExploreAndTell., Comment: 12 pages; 10 figures; ICCV 2023

Robust pedestrian trajectory forecasting is crucial to developing safe autonomous vehicles. Although previous works have studied adversarial robustness in the context of trajectory forecasting, some significant issues remain unaddressed. In this work, we try to tackle these crucial problems. Firstly, the previous definitions of robustness in trajectory prediction are ambiguous. We thus provide formal definitions for two kinds of robustness, namely label robustness and pure robustness. Secondly, as previous works fail to consider robustness about all points in a disturbance interval, we utilise a probably approximately correct (PAC) framework for robustness verification. Additionally, this framework can not only identify potential counterexamples, but also provides interpretable analyses of the original methods. Our approach is applied using a prototype tool named TrajPAC. With TrajPAC, we evaluate the robustness of four state-of-the-art trajectory prediction models -- Trajectron++, MemoNet, AgentFormer, and MID -- on trajectories from five scenes of the ETH/UCY dataset and scenes of the Stanford Drone Dataset. Using our framework, we also experimentally study various factors that could influence robustness performance., Comment: ICCV 2023 version

Large language models (LLMs) have demonstrated impressive capabilities across various NLP tasks. Additionally, LLMs are also highly valuable in supporting software engineering tasks, particularly in the field of code generation. Automatic code generation is a process of automatically generating source code or executable code based on given specifications or requirements, improving developer productivity. In this study, we perform a systematic empirical assessment to the quality of code generation using ChatGPT. We leverage 728 algorithm problems in five languages (i.e., C, C++, Java, Python, and JavaScript) and 18 CWEs with 54 code scenarios for the code generation task. Our evaluation encompasses a comprehensive analysis of code snippets generated by ChatGPT, focusing on three critical aspects: correctness, complexity, and security. We also specifically investigate ChatGPT's ability to engage in multi-round fixing process (i.e., ChatGPT's dialog ability) of facilitating code generation. By delving into the generated code and examining the experimental results, this work provides valuable insights into the performance of ChatGPT in tackling code generation tasks over the three critical aspects. Overall, our findings uncover potential issues and limitations that arise in the ChatGPT-based code generation and lay the groundwork for improving AI and LLM-based code generation techniques.