Search

Naturalistic driving action localization task aims to recognize and comprehend human behaviors and actions from video data captured during real-world driving scenarios. Previous studies have shown great action localization performance by applying a recognition model followed by probability-based post-processing. Nevertheless, the probabilities provided by the recognition model frequently contain confused information causing challenge for post-processing. In this work, we adopt an action recognition model based on self-supervise learning to detect distracted activities and give potential action probabilities. Subsequently, a constraint ensemble strategy takes advantages of multi-camera views to provide robust predictions. Finally, we introduce a conditional post-processing operation to locate distracted behaviours and action temporal boundaries precisely. Experimenting on test set A2, our method obtains the sixth position on the public leaderboard of track 3 of the 2024 AI City Challenge., Comment: Computer Vision and Pattern Recognition Workshop 2024

Training robot policies in simulation is becoming increasingly popular; nevertheless, a precise, reliable, and easy-to-use tactile simulator for contact-rich manipulation tasks is still missing. To close this gap, we develop TacEx -- a modular tactile simulation framework. We embed a state-of-the-art soft-body simulator for contacts named GIPC and vision-based tactile simulators Taxim and FOTS into Isaac Sim to achieve robust and plausible simulation of the visuotactile sensor GelSight Mini. We implement several Isaac Lab environments for Reinforcement Learning (RL) leveraging our TacEx simulation, including object pushing, lifting, and pole balancing. We validate that the simulation is stable and that the high-dimensional observations, such as the gel deformation and the RGB images from the GelSight camera, can be used for training. The code, videos, and additional results will be released online https://sites.google.com/view/tacex., Comment: 11 pages, accepted at "CoRL Workshop on Learning Robot Fine and Dexterous Manipulation: Perception and Control"

In recent years, motion planning for urban self-driving cars (SDV) has become a popular problem due to its complex interaction of road components. To tackle this, many methods have relied on large-scale, human-sampled data processed through Imitation learning (IL). Although effective, IL alone cannot adequately handle safety and reliability concerns. Combining IL with Reinforcement learning (RL) by adding KL divergence between RL and IL policy to the RL loss can alleviate IL's weakness but suffer from over-conservation caused by covariate shift of IL. To address this limitation, we introduce a method that combines IL with RL using an implicit entropy-KL control that offers a simple way to reduce the over-conservation characteristic. In particular, we validate different challenging simulated urban scenarios from the unseen dataset, indicating that although IL can perform well in imitation tasks, our proposed method significantly improves robustness (over 17\% reduction in failures) and generates human-like driving behavior., Comment: submitted to IEEE Open Journal of Intelligent Transportation Systems

Scanning probe microscopy (SPM) is a powerful technique for mapping nanoscale surface properties through tip-sample interactions. Thermal scanning-probe lithography (tSPL) is an advanced SPM variant that uses a silicon tip on a heated cantilever to sculpt and measure polymer films with nanometer precision. The surfaces produced by tSPL-smooth topographic landscapes-allow mathematically defined contours to be fabricated on the nanoscale, enabling sophisticated functionalities for photonic, electronic, chemical, and biological technologies. Evaluating the physical effects of a landscape requires fitting arbitrary mathematical functions to SPM datasets, however, this capability does not exist in standard analysis programs. Here, we provide an open-source software package (FunFit) to fit analytical functions to SPM data and develop a fabrication and characterization protocol based on this analysis. We demonstrate the benefit of this approach by patterning periodic and quasiperiodic landscapes in a polymer resist with tSPL, which we transfer to hexagonal boron nitride (hBN) flakes with high fidelity via reactive-ion etching. The topographic landscapes in polymers and hBN are measured with tSPL and atomic force microscopy (AFM), respectively. Within the FunFit program, the datasets are corrected for artefacts, fit with analytical functions, and compared, providing critical feedback on the fabrication procedure. Beyond application to tSPL, this protocol can improve analysis, reproducibility, and process development for a broad range of SPM experiments. The protocol can be performed within a working day by an inexperienced user, where fabrication and characterization take a few hours and software analysis takes a few minutes.

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

We generalize previous diameter estimates and local non-vanishing of volumes for Kaehler metrics to the case of big cohomology classes. In our proof, among other things, we will prove a uniform diameter estimate for a family of smooth Kaehler metrics only involving an integrability condition. We also have to use fine stability properties of complex Monge-Ampere equations with prescribed singularities., Comment: 28 pages, minor changes, comments welcome

Statutory law retrieval is a typical problem in legal language processing, that has various practical applications in law engineering. Modern deep learning-based retrieval methods have achieved significant results for this problem. However, retrieval systems relying on semantic and lexical correlations often exhibit limitations, particularly when handling queries that involve real-life scenarios, or use the vocabulary that is not specific to the legal domain. In this work, we focus on overcoming this weaknesses by utilizing the logical reasoning capabilities of large language models (LLMs) to identify relevant legal terms and facts related to the situation mentioned in the query. The proposed retrieval system integrates additional information from the term--based expansion and query reformulation to improve the retrieval accuracy. The experiments on COLIEE 2022 and COLIEE 2023 datasets show that extra knowledge from LLMs helps to improve the retrieval result of both lexical and semantic ranking models. The final ensemble retrieval system outperformed the highest results among all participating teams in the COLIEE 2022 and 2023 competitions., Comment: Presented at NeLaMKRR@KR, 2024 (arXiv:2410.05339)

Service robots that work alongside humans in a shared environment need a navigation system that takes into account not only physical safety but also social norms for mutual cooperation. In this paper, we introduce a motion planning system that includes human states such as positions and velocities and their personal space for social-aware navigation. The system first extracts human positions from the LiDAR and the RGB-D camera. It then uses the Kalman filter to fuse that information for human state estimation. An asymmetric Gaussian function is then employed to model human personal space based on their states. This model is used as the input to the dynamic window approach algorithm to generate trajectories for the robot. Experiments show that the robot is able to navigate alongside humans in a dynamic environment while respecting their physical and psychological comfort., Comment: In Proceedings of 2024, the 7th International Conference on Control, Robotics and Informatics (ICCRI 2024)

Fairness in artificial intelligence and machine learning (AI/ML) models is becoming critically important, especially as decisions made by these systems impact diverse groups. In education, a vital sector for all countries, the widespread application of AI/ML systems raises specific concerns regarding fairness. Current research predominantly focuses on fairness for individual sensitive features, which limits the comprehensiveness of fairness assessments. This paper introduces FAIREDU, a novel and effective method designed to improve fairness across multiple sensitive features. Through extensive experiments, we evaluate FAIREDU effectiveness in enhancing fairness without compromising model performance. The results demonstrate that FAIREDU addresses intersectionality across features such as gender, race, age, and other sensitive features, outperforming state-of-the-art methods with minimal effect on model accuracy. The paper also explores potential future research directions to enhance further the method robustness and applicability to various machine-learning models and datasets.

In personalized Federated Learning (pFL), high data heterogeneity can cause significant gradient divergence across devices, adversely affecting the learning process. This divergence, especially when gradients from different users form an obtuse angle during aggregation, can negate progress, leading to severe weight and gradient update degradation. To address this issue, we introduce a new approach to pFL design, namely Federated Learning with Layer-wise Aggregation via Gradient Analysis (FedLAG), utilizing the concept of gradient conflict at the layer level. Specifically, when layer-wise gradients of different clients form acute angles, those gradients align in the same direction, enabling updates across different clients toward identifying client-invariant features. Conversely, when layer-wise gradient pairs make create obtuse angles, the layers tend to focus on client-specific tasks. In hindsights, FedLAG assigns layers for personalization based on the extent of layer-wise gradient conflicts. Specifically, layers with gradient conflicts are excluded from the global aggregation process. The theoretical evaluation demonstrates that when integrated into other pFL baselines, FedLAG enhances pFL performance by a certain margin. Therefore, our proposed method achieves superior convergence behavior compared with other baselines. Extensive experiments show that our FedLAG outperforms several state-of-the-art methods and can be easily incorporated with many existing methods to further enhance performance.

The research on audio clue-based target speaker extraction (TSE) has mostly focused on modeling the mixture and reference speech, achieving high performance in English due to the availability of large datasets. However, less attention has been given to the consistent properties of human speech across languages. To bridge this gap, we introduce WHYV (Wanna Hear Your Voice), which addresses the challenge of transferring TSE models from one language to another without fine-tuning. In this work, we proposed a gating mechanism that be able to modify specific frequencies based on the speaker's acoustic features. The model achieves an SI-SDR of 17.3544 on clean English speech and 13.2032 on clean speech mixed with Wham! noise, outperforming all other models in its ability to adapt to different languages., Comment: Submitted to ICASSP 2025

Recent advances in neural topic models have concentrated on two primary directions: the integration of the inference network (encoder) with a pre-trained language model (PLM) and the modeling of the relationship between words and topics in the generative model (decoder). However, the use of large PLMs significantly increases inference costs, making them less practical for situations requiring low inference times. Furthermore, it is crucial to simultaneously model the relationships between topics and words as well as the interrelationships among topics themselves. In this work, we propose a novel framework called NeuroMax (Neural Topic Model with Maximizing Mutual Information with Pretrained Language Model and Group Topic Regularization) to address these challenges. NeuroMax maximizes the mutual information between the topic representation obtained from the encoder in neural topic models and the representation derived from the PLM. Additionally, NeuroMax employs optimal transport to learn the relationships between topics by analyzing how information is transported among them. Experimental results indicate that NeuroMax reduces inference time, generates more coherent topics and topic groups, and produces more representative document embeddings, thereby enhancing performance on downstream tasks., Comment: Findings of EMNLP 2024

We study the existence of bounded asymptotic mild solutions to evolution equations of the form $u'(t)=Au(t)+f(t), t\ge 0$ in a Banach space $\X$, where $A$ generates an (analytic) $C_0$-semigroup and $f$ is bounded. We find spectral conditions on $A$ and $f$ for the existence and uniqueness of asymptotic mild solutions with the same "profile" as that of $f$. In the resonance case, a sufficient condition of Massera type theorem is found for the existence of bounded solutions with the same profile as $f$. The obtained results are stated in terms of spectral properties of $A$ and $f$, and they are analogs of classical results of Katznelson-Tzafriri and Massera for the evolution equations on the half line. Applications from PDE are given.

This paper extends the recently developed framework of multilinear kernel regression and imputation via manifold learning (MultiL-KRIM) to impute time-varying edge flows in a graph. MultiL-KRIM uses simplicial-complex arguments and Hodge Laplacians to incorporate the graph topology, and exploits manifold-learning arguments to identify latent geometries within features which are modeled as a point-cloud around a smooth manifold embedded in a reproducing kernel Hilbert space (RKHS). Following the concept of tangent spaces to smooth manifolds, linear approximating patches are used to add a collaborative-filtering flavor to the point-cloud approximations. Together with matrix factorizations, MultiL-KRIM effects dimensionality reduction, and enables efficient computations, without any training data or additional information. Numerical tests on real-network time-varying edge flows demonstrate noticeable improvements of MultiL-KRIM over several state-of-the-art schemes.

Large Language Models (LLMs) have recently advanced many applications on software engineering tasks, particularly the potential for code generation. Among contemporary challenges, code generated by LLMs often suffers from inaccuracies and hallucinations, requiring external inputs to correct. One recent strategy to fix these issues is to refine the code generated from LLMs using the input from the model itself (self-augmented). In this work, we proposed a novel method, namely CoT-SelfEvolve. CoT-SelfEvolve iteratively and automatically refines code through a self-correcting process, guided by a chain of thought constructed from real-world programming problem feedback. Focusing on data science code, including Python libraries such as NumPy and Pandas, our evaluations on the DS-1000 dataset demonstrate that CoT-SelfEvolve significantly outperforms existing models in solving complex problems. The framework shows substantial improvements in both initial code generation and subsequent iterations, with the model's accuracy increasing significantly with each additional iteration. This highlights the effectiveness of using chain-of-thought prompting to address complexities revealed by program executor traceback error messages. We also discuss how CoT-SelfEvolve can be integrated into continuous software engineering environments, providing a practical solution for improving LLM-based code generation.

Accurate prediction of 3D semantic occupancy from 2D visual images is vital in enabling autonomous agents to comprehend their surroundings for planning and navigation. State-of-the-art methods typically employ fully supervised approaches, necessitating a huge labeled dataset acquired through expensive LiDAR sensors and meticulous voxel-wise labeling by human annotators. The resource-intensive nature of this annotating process significantly hampers the application and scalability of these methods. We introduce a novel semi-supervised framework to alleviate the dependency on densely annotated data. Our approach leverages 2D foundation models to generate essential 3D scene geometric and semantic cues, facilitating a more efficient training process. Our framework exhibits notable properties: (1) Generalizability, applicable to various 3D semantic scene completion approaches, including 2D-3D lifting and 3D-2D transformer methods. (2) Effectiveness, as demonstrated through experiments on SemanticKITTI and NYUv2, wherein our method achieves up to 85% of the fully-supervised performance using only 10% labeled data. This approach not only reduces the cost and labor associated with data annotation but also demonstrates the potential for broader adoption in camera-based systems for 3D semantic occupancy prediction.

Comics are an effective method for sequential data-driven storytelling, especially for dynamic graphs -- graphs whose vertices and edges change over time. However, manually creating such comics is currently time-consuming, complex, and error-prone. In this paper, we propose DG Comics, a novel comic authoring tool for dynamic graphs that allows users to semi-automatically build and annotate comics. The tool uses a newly developed hierarchical clustering algorithm to segment consecutive snapshots of dynamic graphs while preserving their chronological order. It also presents rich information on both individuals and communities extracted from dynamic graphs in multiple views, where users can explore dynamic graphs and choose what to tell in comics. For evaluation, we provide an example and report the results of a user study and an expert review., Comment: To appear in IEEE Transactions on Visualization and Computer Graphics

We consider a sequential task and motion planning (tamp) setting in which a robot is assigned continuous-space rearrangement-style tasks one-at-a-time in an environment that persists between each. Lacking advance knowledge of future tasks, existing (myopic) planning strategies unwittingly introduce side effects that impede completion of subsequent tasks: e.g., by blocking future access or manipulation. We present anticipatory task and motion planning, in which estimates of expected future cost from a learned model inform selection of plans generated by a model-based tamp planner so as to avoid such side effects, choosing configurations of the environment that both complete the task and minimize overall cost. Simulated multi-task deployments in navigation-among-movable-obstacles and cabinet-loading domains yield improvements of 32.7% and 16.7% average per-task cost respectively. When given time in advance to prepare the environment, our learning-augmented planning approach yields improvements of 83.1% and 22.3%. Both showcase the value of our approach. Finally, we also demonstrate anticipatory tamp on a real-world Fetch mobile manipulator.

In this paper, we consider a change-point problem for a centered, stationary and $m$-dependent multivariate random field. Under the distribution free assumption, a change-point test using CUSUM statistic is proposed to detect anomalies within a multidimensional random field, controlling the false positive rate as well as the Family-Wise Error in the multiple hypotheses testing context.

In this paper, we propose a fast method for crack detection in 3D computed tomography (CT) images. Our approach combines the Maximal Hessian Entry filter and a Deep-First Search algorithm-based technique to strike a balance between computational complexity and accuracy. Experimental results demonstrate the effectiveness of our approach in detecting the crack structure with predefined misclassification probability.

3D meshes are one of the main components of Virtual Reality applications. However, many network and computational resources are required to process 3D meshes in real-time. A potential solution to this challenge is to dynamically adapt the Level of Detail (LoD) of a 3D mesh based on the object's position and the user's viewpoint. In this paper, we conduct a subjective study to investigate users' quality perception of 3D meshes with dynamic Level of Detail in a Virtual Reality environment. The subjective experiment is carried out with five 3D meshes of different characteristics, four Levels of Detail, and four distance settings. The results of the experiment show that the impact of the dynamic level of detail depends on both the position of the 3D object in the virtual world and the number of vertices of the original mesh. In addition, we present a quality model that can accurately predict the MOS score of a LoD version of a 3D mesh from the number of vertices and the distance from the viewpoint., Comment: Acceped to ICIP 2024

Excessive caregiver workload in hospital nurses has been implicated in poorer patient care and increased worker burnout. Measurement of this workload in the Intensive Care Unit (ICU) is often done using the Nursing Activities Score (NAS), but this is usually recorded manually and sporadically. Previous work has made use of Ambient Intelligence (AmI) by using computer vision to passively derive caregiver-patient interaction times to monitor staff workload. In this letter, we propose using a Multiscale Vision Transformer (MViT) to passively predict the NAS from low-resolution thermal videos recorded in an ICU. 458 videos were obtained from an ICU in Melbourne, Australia and used to train a MViTv2 model using an indirect prediction and a direct prediction method. The indirect method predicted 1 of 8 potentially identifiable NAS activities from the video before inferring the NAS. The direct method predicted the NAS score immediately from the video. The indirect method yielded an average 5-fold accuracy of 57.21%, an area under the receiver operating characteristic curve (ROC AUC) of 0.865, a F1 score of 0.570 and a mean squared error (MSE) of 28.16. The direct method yielded a MSE of 18.16. We also showed that the MViTv2 outperforms similar models such as R(2+1)D and ResNet50-LSTM under identical settings. This study shows the feasibility of using a MViTv2 to passively predict the NAS in an ICU and monitor staff workload automatically. Our results above also show an increased accuracy in predicting NAS directly versus predicting NAS indirectly. We hope that our study can provide a direction for future work and further improve the accuracy of passive NAS monitoring., Comment: 4 pages, 1 figure

Federated Learning (FL) is a promising paradigm that offers significant advancements in privacy-preserving, decentralized machine learning by enabling collaborative training of models across distributed devices without centralizing data. However, the practical deployment of FL systems faces a significant bottleneck: the communication overhead caused by frequently exchanging large model updates between numerous devices and a central server. This communication inefficiency can hinder training speed, model performance, and the overall feasibility of real-world FL applications. In this survey, we investigate various strategies and advancements made in communication-efficient FL, highlighting their impact and potential to overcome the communication challenges inherent in FL systems. Specifically, we define measures for communication efficiency, analyze sources of communication inefficiency in FL systems, and provide a taxonomy and comprehensive review of state-of-the-art communication-efficient FL methods. Additionally, we discuss promising future research directions for enhancing the communication efficiency of FL systems. By addressing the communication bottleneck, FL can be effectively applied and enable scalable and practical deployment across diverse applications that require privacy-preserving, decentralized machine learning, such as IoT, healthcare, or finance.

In this paper we study the well-posedness of the evolution equation of the form $u'(t)=Au(t)+Cu(t)$, $t\ge 0$, where $A$ is the generator of a $C_0$- semigroup and $C$ is a (possibly unbounded) linear operator in a Banach space $\mathbb{X}$. We prove that if $A$ generates a $C_0$-semigroup $\left (T_A(t)\right )_{t \geq 0}$ with $\|T(t)\| \le Me^{\omega t}$ in a Banach space $\mathbb{X}$ and $C$ is a linear operator in $\mathbb{X}$ such that $D(A)\subset D(C)$ and $\| CR(\mu ,A)\| \le K/(\mu -\omega)$ for each $\mu>\omega$, then, the above-mentioned evolution equation is well-posed, that is, $A+C$ generates a $C_0$-semigroup $\left (T_{A+C}(t)\right )_{t \geq 0}$ satisfying $\| T_{A+C}(t)\| \le Me^{(\omega +MK)t}$. Our approach is to use the Hille-Yosida Theorem. Discussions on the persistence of asymptotic behavior of the perturbed equations such as the roughness of exponential dichotomy are also given. The obtained results seem to be new., Comment: 12 pages

We study higher complex Sobolev spaces and their corresponding functional capacities. In particular, we prove the Moser-Trudinger inequality for these spaces and discuss some relationships between these spaces and the complex Monge-Amp\`{e}re equation.

The NaI:Tl crystals were early investigated and used for wide application fields due to high light yield and crystal growth advantages. So far, the absolute light yields of NaI:Tl crystal have typically been known to be 40 ph/keV. However, it varies widely, far from the theoretical estimation. Since the high light yield and better sensitivity of NaI:Tl crystal is important for low mass dark matter search. Therefore, it is necessary to use high light NaI:Tl crystal, and absolute light yield should be measured with accuracy. In this work, we use the single photoelectron technique for measuring the absolute light yield of 35 NaI:Tl crystals with various sizes from different vendors. There are several high-quality crystals from the COSINE-100 experiment and commercial companies in these crystals. The theoretical estimation and GEANT4 optical simulation have been studied to investigate the PMT optics. Results show the essential role of this correction in avoiding overrated light yield values. The SPE technique using different PMT was compared to the photodiode and avalanche photodiode methods. A 10% systematic error was obtained. Our results show the excellent absolute light yield of NaI:Tl, at 59.4 +- 5.9 ph/keV, while the theoretical predicted light yield is around 70 ph/keV. The evaluation with NaI:Tl crystals in the COSINE-100 experiment has been performed. The six crystals in the COSINE-100 experiment have a high light yield. Based on our results, the light loss of encapsulation needs to be improved, especially for the big-size crystals., Comment: 14 pages, 16 figures

Human Activity Recognition (HAR) is a well-studied field with research dating back to the 1980s. Over time, HAR technologies have evolved significantly from manual feature extraction, rule-based algorithms, and simple machine learning models to powerful deep learning models, from one sensor type to a diverse array of sensing modalities. The scope has also expanded from recognising a limited set of activities to encompassing a larger variety of both simple and complex activities. However, there still exist many challenges that hinder advancement in complex activity recognition using modern deep learning methods. In this paper, we comprehensively systematise factors leading to inaccuracy in complex HAR, such as data variety and model capacity. Among many sensor types, we give more attention to wearable and camera due to their prevalence. Through this Systematisation of Knowledge (SoK) paper, readers can gain a solid understanding of the development history and existing challenges of HAR, different categorisations of activities, obstacles in deep learning-based complex HAR that impact accuracy, and potential research directions.

In this paper, we study the torsion subgroup, which is denoted by ${\rm TK}_1(E)$, of the Whitehead group $E^*/[E^*,E^*]$ of a graded division algebra $E$ which is finite dimensional over its center. In particular, we provide formulas for ${\rm TK}_1(E)$ in some special cases such as when $E$ is unramified, totally ramified or semiramified. Using the formulas, we are able to compute the group ${\rm TK}_1(D)$ of a valued division ring $D$, which is finite dimensional over a henselian center.

This paper proposes a new control algorithm for human-robot co-transportation based on a robot manipulator equipped with a mobile base and a robotic arm. The primary focus is to adapt to human uncertainties through the robot's whole-body kinematics and pose optimization. We introduce an augmented Model Predictive Control (MPC) formulation that explicitly models human uncertainties and contains extra variables than regular MPC to optimize the pose of the robotic arm. The core of our methodology involves a two-step iterative design: At each planning horizon, we select the best pose of the robotic arm (joint angle combination) from a candidate set, aiming to achieve the lowest estimated control cost. This selection is based on solving an uncertainty-aware Discrete Algebraic Ricatti Equation (DARE), which also informs the optimal control inputs for both the mobile base and the robotic arm. To validate the effectiveness of the proposed approach, we provide theoretical derivation for the uncertainty-aware DARE and perform simulated and hardware experiments using a Fetch robot under varying conditions, including different trajectories and noise levels. The results reveal that our proposed approach outperforms baseline algorithms., Comment: 8 pages, 6 figures

Our work addresses limitations seen in previous approaches for object-centric editing problems, such as unrealistic results due to shape discrepancies and limited control in object replacement or insertion. To this end, we introduce FlexEdit, a flexible and controllable editing framework for objects where we iteratively adjust latents at each denoising step using our FlexEdit block. Initially, we optimize latents at test time to align with specified object constraints. Then, our framework employs an adaptive mask, automatically extracted during denoising, to protect the background while seamlessly blending new content into the target image. We demonstrate the versatility of FlexEdit in various object editing tasks and curate an evaluation test suite with samples from both real and synthetic images, along with novel evaluation metrics designed for object-centric editing. We conduct extensive experiments on different editing scenarios, demonstrating the superiority of our editing framework over recent advanced text-guided image editing methods. Our project page is published at https://flex-edit.github.io/., Comment: Our project page: https://flex-edit.github.io/

Large language models with billions of parameters, such as GPT-3.5, GPT-4, and LLaMA, are increasingly prevalent. Numerous studies have explored effective prompting techniques to harness the power of these LLMs for various research problems. Retrieval, specifically in the legal data domain, poses a challenging task for the direct application of Prompting techniques due to the large number and substantial length of legal articles. This research focuses on maximizing the potential of prompting by placing it as the final phase of the retrieval system, preceded by the support of two phases: BM25 Pre-ranking and BERT-based Re-ranking. Experiments on the COLIEE 2023 dataset demonstrate that integrating prompting techniques on LLMs into the retrieval system significantly improves retrieval accuracy. However, error analysis reveals several existing issues in the retrieval system that still need resolution., Comment: JURISIN 2024

This study presents a method for deep neural network nonlinear model predictive control (DNN-MPC) to reduce computational complexity, and we show its practical utility through its application in optimizing the energy management of hybrid electric vehicles (HEVs). For optimal power management of HEVs, we first design the online NMPC to collect the data set, and the deep neural network is trained to approximate the NMPC solutions. We assess the effectiveness of our approach by conducting comparative simulations with rule and online NMPC-based power management strategies for HEV, evaluating both fuel consumption and computational complexity. Lastly, we verify the real-time feasibility of our approach through process-in-the-loop (PIL) testing. The test results demonstrate that the proposed method closely approximates the NMPC performance while substantially reducing the computational burden., Comment: 6 pages, 10 figures, 3 tables, 2024 ACC conference (accepted)

In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio. The family includes two new models: (1) an updated Gemini 1.5 Pro, which exceeds the February version on the great majority of capabilities and benchmarks; (2) Gemini 1.5 Flash, a more lightweight variant designed for efficiency with minimal regression in quality. Gemini 1.5 models achieve near-perfect recall on long-context retrieval tasks across modalities, improve the state-of-the-art in long-document QA, long-video QA and long-context ASR, and match or surpass Gemini 1.0 Ultra's state-of-the-art performance across a broad set of benchmarks. Studying the limits of Gemini 1.5's long-context ability, we find continued improvement in next-token prediction and near-perfect retrieval (>99%) up to at least 10M tokens, a generational leap over existing models such as Claude 3.0 (200k) and GPT-4 Turbo (128k). Finally, we highlight real-world use cases, such as Gemini 1.5 collaborating with professionals on completing their tasks achieving 26 to 75% time savings across 10 different job categories, as well as surprising new capabilities of large language models at the frontier; when given a grammar manual for Kalamang, a language with fewer than 200 speakers worldwide, the model learns to translate English to Kalamang at a similar level to a person who learned from the same content.

Recent advancements in large language models (LLMs) have underscored their importance in the evolution of artificial intelligence. However, despite extensive pretraining on multilingual datasets, available open-sourced LLMs exhibit limited effectiveness in processing Vietnamese. The challenge is exacerbated by the absence of systematic benchmark datasets and metrics tailored for Vietnamese LLM evaluation. To mitigate these issues, we have finetuned LLMs specifically for Vietnamese and developed a comprehensive evaluation framework encompassing 10 common tasks and 31 metrics. Our evaluation results reveal that the fine-tuned LLMs exhibit enhanced comprehension and generative capabilities in Vietnamese. Moreover, our analysis indicates that models with more parameters can introduce more biases and uncalibrated outputs and the key factor influencing LLM performance is the quality of the training or fine-tuning datasets. These insights underscore the significance of meticulous fine-tuning with high-quality datasets in enhancing LLM performance., Comment: 51 pages

This paper presents our contributions towards advancing the state of Vietnamese language understanding and generation through the development and dissemination of open datasets and pre-trained models for Vietnamese Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs).