Search

Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the versatility of masked prediction, it remains unclear how to balance the learning of skills at different levels of complexity. To address this, we propose CurrMask, a curriculum masking pretraining paradigm for sequential decision making. Motivated by how humans learn by organizing knowledge in a curriculum, CurrMask adjusts its masking scheme during pretraining for learning versatile skills. Through extensive experiments, we show that CurrMask exhibits superior zero-shot performance on skill prompting tasks, goal-conditioned planning tasks, and competitive finetuning performance on offline RL tasks. Additionally, our analysis of training dynamics reveals that CurrMask gradually acquires skills of varying complexity by dynamically adjusting its masking scheme., Comment: NeurIPS 2024 poster, 21 pages, 8 figures

A novel theoretical model for bubble dynamics is established that simultaneously accounts for the liquid compressibility, phase transition, oscillation, migration, ambient flow field, etc. The bubble dynamics equations are presented in a unified and concise mathematical form with clear physical meanings and extensibility. The bubble oscillation equation can be simplified to the Keller-Miksis equation by neglecting the effects of phase transition and bubble migration. The present theoretical model effectively captures the experimental results for bubbles generated in free fields, near free surfaces, adjacent to rigid walls, and in the vicinity of other bubbles. Based on the present theory, we explore the effect of the bubble content by changing the vapor proportion inside the cavitation bubble for an initial high-pressure bubble. It is found that the energy loss of the bubble shows a consistent increase with increasing Mach number and initial vapor proportion. However, the radiated pressure peak by the bubble at the collapse stage increases with the decreasing Mach number and increasing vapor proportion. The energy analyses of the bubble reveal that the presence of vapor inside the bubble not only directly contributes to the energy loss of the bubble through phase transition but also intensifies the bubble collapse, which leads to greater radiation of energy into the surrounding flow field due to the fluid compressibility.

Urban intersections, filled with a diverse mix of vehicles from small cars to large semi-trailers, present a persistent challenge for traffic control and management. This reality drives our investigation into how robot vehicles (RVs) can transform such heterogeneous traffic flow, particularly at unsignalized intersections where traditional control methods often falter during power failures and emergencies. Using reinforcement learning (RL) and real-world traffic data, we study heterogeneous mixed traffic across complex intersections under gradual automation by varying RV penetration from 10% to 90%. The results are compelling: average waiting times decrease by up to 86% and 91% compared to signalized and unsignalized intersections, respectively. Additionally, we uncover a "rarity advantage," where less frequent vehicles, such as trucks, benefit the most from RV coordination (by up to 87%). RVs' presence also leads to lower CO2 emissions and fuel consumption compared to managing traffic via traffic lights. Moreover, space headways decrease across all vehicle types as RV rate increases, indicating better road space utilization.

Learned image compression have attracted considerable interests in recent years. It typically comprises an analysis transform, a synthesis transform, quantization and an entropy coding model. The analysis transform and synthesis transform are used to encode an image to latent feature and decode the quantized feature to reconstruct the image, and can be regarded as coupled transforms. However, the analysis transform and synthesis transform are designed independently in the existing methods, making them unreliable in high-quality image compression. Inspired by the invertible neural networks in generative modeling, invertible modules are used to construct the coupled analysis and synthesis transforms. Considering the noise introduced in the feature quantization invalidates the invertible process, this paper proposes an Approximately Invertible Neural Network (A-INN) framework for learned image compression. It formulates the rate-distortion optimization in lossy image compression when using INN with quantization, which differentiates from using INN for generative modelling. Generally speaking, A-INN can be used as the theoretical foundation for any INN based lossy compression method. Based on this formulation, A-INN with a progressive denoising module (PDM) is developed to effectively reduce the quantization noise in the decoding. Moreover, a Cascaded Feature Recovery Module (CFRM) is designed to learn high-dimensional feature recovery from low-dimensional ones to further reduce the noise in feature channel compression. In addition, a Frequency-enhanced Decomposition and Synthesis Module (FDSM) is developed by explicitly enhancing the high-frequency components in an image to address the loss of high-frequency information inherent in neural network based image compression. Extensive experiments demonstrate that the proposed A-INN outperforms the existing learned image compression methods.

Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but they have also been observed to magnify societal biases, particularly those related to gender. In response to this issue, several benchmarks have been proposed to assess gender bias in LLMs. However, these benchmarks often lack practical flexibility or inadvertently introduce biases. To address these shortcomings, we introduce GenderCARE, a comprehensive framework that encompasses innovative Criteria, bias Assessment, Reduction techniques, and Evaluation metrics for quantifying and mitigating gender bias in LLMs. To begin, we establish pioneering criteria for gender equality benchmarks, spanning dimensions such as inclusivity, diversity, explainability, objectivity, robustness, and realisticity. Guided by these criteria, we construct GenderPair, a novel pair-based benchmark designed to assess gender bias in LLMs comprehensively. Our benchmark provides standardized and realistic evaluations, including previously overlooked gender groups such as transgender and non-binary individuals. Furthermore, we develop effective debiasing techniques that incorporate counterfactual data augmentation and specialized fine-tuning strategies to reduce gender bias in LLMs without compromising their overall performance. Extensive experiments demonstrate a significant reduction in various gender bias benchmarks, with reductions peaking at over 90% and averaging above 35% across 17 different LLMs. Importantly, these reductions come with minimal variability in mainstream language tasks, remaining below 2%. By offering a realistic assessment and tailored reduction of gender biases, we hope that our GenderCARE can represent a significant step towards achieving fairness and equity in LLMs. More details are available at https://github.com/kstanghere/GenderCARE-ccs24.

With the rapid development of industry, the vibration control of flexible structures and underactuated systems has been increasingly gaining attention. Input shaping technology enables stable performance for high-speed motion in industrial motion systems. However, existing input shapers generally suffer from the ineffective control performance due to the neglect of observation errors. To address this critical issue, this paper proposes an Extended Kalman Filter-incorporated Residual Neural Network-based input Shaping (ERS) model for vibration control. Its main ideas are two-fold: a) adopting an extended Kalman filter to address a vertical flexible beam's model errors; and b) adopting a residual neural network to cascade with the extended Kalman filter for eliminating the remaining observation errors. Detailed experiments on a real dataset collected from a vertical flexible beam demonstrate that the proposed ERS model has achieved significant vibration control performance over several state-of-the-art models.

Within the context of intelligent manufacturing, industrial robots have a pivotal function. Nonetheless, extended operational periods cause a decline in their absolute positioning accuracy, preventing them from meeting high precision. To address this issue, this paper presents a novel robot algorithm that combines an adaptive and momental bound algorithm with decoupled weight decay (AdaModW), which has three-fold ideas: a) adopting an adaptive moment estimation (Adam) algorithm to achieve a high convergence rate, b) introducing a hyperparameter into the Adam algorithm to define the length of memory, effectively addressing the issue of the abnormal learning rate, and c) interpolating a weight decay coefficient to improve its generalization. Numerous experiments on an HRS-JR680 industrial robot show that the presented algorithm significantly outperforms state-of-the-art algorithms in robot calibration performance. Thus, in light of its reliability, this algorithm provides an efficient way to address robot calibration concerns.

Creating crystal bilayers twisted with respect to each other would lead to large periodic supercell structures, which can support a wide range of novel electron correlated phenomena, where the full understanding is still under debate. Here, we propose a new scheme to realize a nonlinearity-induced dynamical self-organized twisted-bilayer lattice in an atomic Bose-Einstein condensate (BEC). The key idea here is to utilize the nonlinear effect from the intrinsic atomic interactions to couple different layers and induce a dynamical self-organized supercell structure, dramatically distinct from the conventional wisdom to achieve the static twisted-bilayer lattices. To illustrate that, we study the dynamics of a two-component BEC and show that the nonlinear interaction effect naturally emerged in the Gross-Pitaevskii equation of interacting bosonic ultracold atoms can dynamically induce both periodic (commensurable) and aperiodic (incommensurable) moir\'{e} structures. One of the interesting moir\'{e} phenomena, i.e., the flat-band physics, is shown through investigating the dynamics of the wave packet of BEC. Our proposal can be implemented using available state-of-the-art experimental techniques and reveal a profound connection between the nonlinearity and twistronics in cold atom quantum simulators., Comment: 6 pages, 5 figures

We theoretically demonstrate a spontaneous spin superconductor (SC) state in ABCA-stacked tetralayer graphene, under sequential effects of electron-electron (e-e) and electron-hole (e-h) interactions. First of all, we examine the ferromagnetic (FM) exchange instability and phase diagram of the system induced by the long-range e-e interaction. At non- or low-doping levels, the interaction trends to stabilize a FM phase with the coexisting electron and hole carriers. Superior to bilayer and trilayer systems, tetralayer graphene has a larger FM phase region and spin splitting, making it more advantageous to realize the spin SC state. Subsequently, we prove that the FM phase becomes unstable when attractive e-h interaction is considered. As a consequence, the spin SC state can be spontaneously formed at low temperature, where spin-triplet exciton pairs act as the equivalent of Cooper pairs. We further develop a consistent BCS-type theory for the spin SC state in ABCA-stacked graphene. The predicted spin superconducting gap can reach about $7.0$ meV, with a critical temperature of about 45 K for non-doping system. At last, we demonstrated a spin-current Josephson effect in the ABCA-stacked graphene spin SC heterojunction. Our findings enrich the prospective spin SC candidate materials, illuminating more possibilities for achieving non-dissipative super-spintronics., Comment: 15 pages,7 figures

The non-Hermitian skin effect (NHSE), an anomalous localization behavior of the bulk states, is an inherently non-Hermitian phenomenon, which can not find a counterpart in Hermitian systems. However, the fragility of NHSE has been revealed recently, such as the boundary sensitivity, and it stimulates a lot of studies on discussing the fate of that. Here we present a theorem which shows that the combined spatial reflection symmetry can be considered as a criterion in one-dimensional non-Hermitian systems to determine whether the NHSE can exist or not. Distinct from previous studies, our proposed criterion only relies on analyzing the symmetry of the system, freeing out other requirements, such as the information of the energy spectrum. Furthermore, by taking the non-Hermitian Kitaev chain as an example, we verify our theorem through both a mathematical proof via the non-Bloch band theory and the exact diagonalization numerical studies. Our results reveal a profound connection between the symmetry and the fate of NHSE., Comment: 7 pages, 2 figures, including Supplementary Material

The non-Bloch topology leads to the emergence of various counter-intuitive phenomena in non-Hermitian systems under the open boundary condition (OBC), which can not find a counterpart in Hermitian systems. However, in the non-Hermitian system without chiral symmetry, being ubiquitous in nature, exploring its non-Bloch topology has so far eluded experimental effort. Here by introducing the concept of non-chiral non-Bloch invariants, we theoretically predict and experimentally identify the non-Bloch topological phase diagram of a one-dimensional (1D) non-Hermitian system without chiral symmetry in discrete-time non-unitary quantum walks of single photons. Interestingly, we find that such topological invariants not only can distinguish topologically distinct gapped phases, but also faithfully capture the corresponding gap closing in open-boundary spectrum at the phase boundary. Different topological regions are experimentally identified by measuring the featured discontinuities of the higher moments of the walker's displacement, which amazingly match excellently with our defined non-Bloch invariants. Our work provides a useful platform to study the interplay among topology, symmetries and the non-Hermiticity., Comment: 10 pages, 5 figures, including Supplementary Material

The scarcity of large-scale 3D-text paired data poses a great challenge on open vocabulary 3D scene understanding, and hence it is popular to leverage internet-scale 2D data and transfer their open vocabulary capabilities to 3D models through knowledge distillation. However, the existing distillation-based 3D scene understanding approaches rely on the representation capacity of 2D models, disregarding the exploration of geometric priors and inherent representational advantages offered by 3D data. In this paper, we propose an effective approach, namely Geometry Guided Self-Distillation (GGSD), to learn superior 3D representations from 2D pre-trained models. Specifically, we first design a geometry guided distillation module to distill knowledge from 2D models, and then leverage the 3D geometric priors to alleviate the inherent noise in 2D models and enhance the representation learning process. Due to the advantages of 3D representation, the performance of the distilled 3D student model can significantly surpass that of the 2D teacher model. This motivates us to further leverage the representation advantages of 3D data through self-distillation. As a result, our proposed GGSD approach outperforms the existing open vocabulary 3D scene understanding methods by a large margin, as demonstrated by our experiments on both indoor and outdoor benchmark datasets.

Screen content (SC) differs from natural scene (NS) with unique characteristics such as noise-free, repetitive patterns, and high contrast. Aiming at addressing the inadequacies of current learned image compression (LIC) methods for SC, we propose an improved two-stage octave convolutional residual blocks (IToRB) for high and low-frequency feature extraction and a cascaded two-stage multi-scale residual blocks (CTMSRB) for improved multi-scale learning and nonlinearity in SC. Additionally, we employ a window-based attention module (WAM) to capture pixel correlations, especially for high contrast regions in the image. We also construct a diverse SC image compression dataset (SDU-SCICD2K) for training, including text, charts, graphics, animation, movie, game and mixture of SC images and NS images. Experimental results show our method, more suited for SC than NS data, outperforms existing LIC methods in rate-distortion performance on SC images. The code is publicly available at https://github.com/SunshineSki/OMR Net.git., Comment: 7 figures, 2 tables

In point cloud geometry compression, context models usually use the one-hot encoding of node occupancy as the label, and the cross-entropy between the one-hot encoding and the probability distribution predicted by the context model as the loss function. However, this approach has two main weaknesses. First, the differences between contexts of different nodes are not significant, making it difficult for the context model to accurately predict the probability distribution of node occupancy. Second, as the one-hot encoding is not the actual probability distribution of node occupancy, the cross-entropy loss function is inaccurate. To address these problems, we propose a general structure that can enhance existing context models. We introduce the context feature residuals into the context model to amplify the differences between contexts. We also add a multi-layer perception branch, that uses the mean squared error between its output and node occupancy as a loss function to provide accurate gradients in backpropagation. We validate our method by showing that it can improve the performance of an octree-based model (OctAttention) and a voxel-based model (VoxelDNN) on the object point cloud datasets MPEG 8i and MVUB, as well as the LiDAR point cloud dataset SemanticKITTI., Comment: 11 pages, 8 figures

Integrating low-light image enhancement techniques, in which diffusion-based AI-generated content (AIGC) models are promising, is necessary to enhance nighttime teleoperation. Remarkably, the AIGC model is computation-intensive, thus necessitating the allocation of AIGC tasks to edge servers with ample computational resources. Given the distinct cost of the AIGC model trained with varying-sized datasets and AIGC tasks possessing disparate demand, it is imperative to formulate a differential pricing strategy to optimize the utility of teleoperators and edge servers concurrently. Nonetheless, the pricing strategy formulation is under information asymmetry, i.e., the demand (e.g., the difficulty level of AIGC tasks and their distribution) of AIGC tasks is hidden information to edge servers. Additionally, manually assessing the difficulty level of AIGC tasks is tedious and unnecessary for teleoperators. To this end, we devise a framework of AIGC task allocation assisted by the Vision Language Model (VLM)-empowered contract theory, which includes two components: VLM-empowered difficulty assessment and contract theory-assisted AIGC task allocation. The first component enables automatic and accurate AIGC task difficulty assessment. The second component is capable of formulating the pricing strategy for edge servers under information asymmetry, thereby optimizing the utility of both edge servers and teleoperators. The simulation results demonstrated that our proposed framework can improve the average utility of teleoperators and edge servers by 10.88~12.43% and 1.4~2.17%, respectively. Code and data are available at https://github.com/ZiJun0819/VLM-Contract-Theory., Comment: 11 pages, 10 figures

The detection of moving infrared dim-small targets has been a challenging and prevalent research topic. The current state-of-the-art methods are mainly based on ConvLSTM to aggregate information from adjacent frames to facilitate the detection of the current frame. However, these methods implicitly utilize motion information only in the training stage and fail to explicitly explore motion compensation, resulting in poor performance in the case of a video sequence including large motion. In this paper, we propose a Deformable Feature Alignment and Refinement (DFAR) method based on deformable convolution to explicitly use motion context in both the training and inference stages. Specifically, a Temporal Deformable Alignment (TDA) module based on the designed Dilated Convolution Attention Fusion (DCAF) block is developed to explicitly align the adjacent frames with the current frame at the feature level. Then, the feature refinement module adaptively fuses the aligned features and further aggregates useful spatio-temporal information by means of the proposed Attention-guided Deformable Fusion (AGDF) block. In addition, to improve the alignment of adjacent frames with the current frame, we extend the traditional loss function by introducing a new motion compensation loss. Extensive experimental results demonstrate that the proposed DFAR method achieves the state-of-the-art performance on two benchmark datasets including DAUB and IRDST.

Self-propelled micromotors can efficiently convert ambient energy into mechanical motion, which is of great interest for its potential biomedical applications in delivering therapeutics noninvasively. However, navigating these micromotors through biological barriers remains a significant challenge as most micromotors do not provide sufficient disruption forces in in-vivo conditions. In this study, we employed focused scanning laser from conventional confocal microscope to manipulate carbon microbottle based microswimmers. With the increasing of the laser power, the microswimmers' motions translates from autonomous to directional, and finally the high power laser induced the microswimmer explosions, which effectively deliveres microbottle fragments through the cell membrane. It is revealed that photothermally-induced cavitation bubbles enable the propulsion of microbottles in liquids, where the motion direction can be precisely regulated by the scanning orientation of the laser. Furthermore, the membrane penetration ability of the microbottles promised potential applications in drug delivery and cellular injections. As microbottles navigate toward cells, we strategically increase the laser power to trigger their explosion. By loading microswimmers with transfection genes, cytoplasmic transfection can be realized, which is demonstrated by successful gene transfection of GPF in cells. Our findings open new possibilities for cell injection and gene transfection using micromotors., Comment: 30 pages, 6 figures

We introduce a novel framework of combinatorial multi-armed bandits (CMAB) with multivariant and probabilistically triggering arms (CMAB-MT), where the outcome of each arm is a $d$-dimensional multivariant random variable and the feedback follows a general arm triggering process. Compared with existing CMAB works, CMAB-MT not only enhances the modeling power but also allows improved results by leveraging distinct statistical properties for multivariant random variables. For CMAB-MT, we propose a general 1-norm multivariant and triggering probability-modulated smoothness condition, and an optimistic CUCB-MT algorithm built upon this condition. Our framework can include many important problems as applications, such as episodic reinforcement learning (RL) and probabilistic maximum coverage for goods distribution, all of which meet the above smoothness condition and achieve matching or improved regret bounds compared to existing works. Through our new framework, we build the first connection between the episodic RL and CMAB literature, by offering a new angle to solve the episodic RL through the lens of CMAB, which may encourage more interactions between these two important directions.

Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought (CoT) prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious mistakes and contradictions, raising doubts about their ability to robustly process and utilize generated rationales. In this work, we investigate CoT reasoning in LLMs through the lens of internal representations, focusing on how these representations are influenced by generated rationales. Our preliminary analysis reveals that while generated rationales improve answer accuracy, inconsistencies emerge between the model's internal representations in middle layers and those in final layers, potentially undermining the reliability of their reasoning processes. To address this, we propose internal consistency as a measure of the model's confidence by examining the agreement of latent predictions decoded from intermediate layers. Extensive empirical studies across different models and datasets demonstrate that internal consistency effectively distinguishes between correct and incorrect reasoning paths. Motivated by this, we propose a new approach to calibrate CoT reasoning by up-weighting reasoning paths with high internal consistency, resulting in a significant boost in reasoning performance. Further analysis uncovers distinct patterns in attention and feed-forward modules across layers, providing insights into the emergence of internal inconsistency. In summary, our results demonstrate the potential of using internal representations for self-evaluation of LLMs.

Recommender models play a vital role in various industrial scenarios, while often faced with the catastrophic forgetting problem caused by the fast shifting data distribution. To alleviate this problem, a common approach is to reuse knowledge from the historical data. However, preserving the vast and fast-accumulating data is hard, which causes dramatic storage overhead. Memorizing old data through a parametric knowledge base is then proposed, which compresses the vast amount of raw data into model parameters. Despite the flexibility, how to improve the memorization and generalization capabilities of the parametric knowledge base and suit the flexible information need of each instance are challenging. In this paper, we propose FINED to Feed INstance-wise information need with Essential and Disentangled parametric knowledge from past data for recommendation enhancement. Concretely, we train a knowledge extractor that extracts knowledge patterns of arbitrary order from past data and a knowledge encoder that memorizes the arbitrary order patterns, which serves as the retrieval key generator and memory network respectively in the following knowledge reusing phase. The whole process is regularized by the proposed two constraints, which improve the capabilities of the parametric knowledge base without increasing the size of it. The essential principle helps to compress the input into representative vectors that capture the task-relevant information and filter out the noisy information. The disentanglement principle reduces the redundancy of stored information and pushes the knowledge base to focus on capturing the disentangled invariant patterns. These two rules together promote rational compression of information for robust and generalized knowledge representations. Extensive experiments on two datasets justify the effectiveness of the proposed method.

Chain-of-Thought (CoT) has been a widely adopted prompting method, eliciting impressive reasoning abilities of Large Language Models (LLMs). Inspired by the sequential thought structure of CoT, a number of Chain-of-X (CoX) methods have been developed to address various challenges across diverse domains and tasks involving LLMs. In this paper, we provide a comprehensive survey of Chain-of-X methods for LLMs in different contexts. Specifically, we categorize them by taxonomies of nodes, i.e., the X in CoX, and application tasks. We also discuss the findings and implications of existing CoX methods, as well as potential future directions. Our survey aims to serve as a detailed and up-to-date resource for researchers seeking to apply the idea of CoT to broader scenarios.

Eliminating image blur produced by various kinds of motion has been a challenging problem. Dominant approaches rely heavily on model capacity to remove blurring by reconstructing residual from blurry observation in feature space. These practices not only prevent the capture of spatially variable motion in the real world but also ignore the tailored handling of various motions in image space. In this paper, we propose a novel real-world deblurring filtering model called the Motion-adaptive Separable Collaborative (MISC) Filter. In particular, we use a motion estimation network to capture motion information from neighborhoods, thereby adaptively estimating spatially-variant motion flow, mask, kernels, weights, and offsets to obtain the MISC Filter. The MISC Filter first aligns the motion-induced blurring patterns to the motion middle along the predicted flow direction, and then collaboratively filters the aligned image through the predicted kernels, weights, and offsets to generate the output. This design can handle more generalized and complex motion in a spatially differentiated manner. Furthermore, we analyze the relationships between the motion estimation network and the residual reconstruction network. Extensive experiments on four widely used benchmarks demonstrate that our method provides an effective solution for real-world motion blur removal and achieves state-of-the-art performance. Code is available at https://github.com/ChengxuLiu/MISCFilter, Comment: CVPR 2024

Axion insulators possess a quantized axion field $\theta=\pi$ protected by combined lattice and time-reversal symmetry, holding great potential for device applications in layertronics and quantum computing. Here, we propose a high-spin axion insulator (HSAI) defined in large spin-$s$ representation, which maintains the same inherent symmetry but possesses a notable axion field $\theta=(s+1/2)^2\pi$. Such distinct axion field is confirmed independently by the direct calculation of the axion term using hybrid Wannier functions, layer-resolved Chern numbers, as well as the topological magneto-electric effect. We show that the guaranteed gapless quasi-particle excitation is absent at the boundary of the HSAI despite its integer surface Chern number, hinting an unusual quantum anomaly violating the conventional bulk-boundary correspondence. Furthermore, we ascertain that the axion field $\theta$ can be precisely tuned through an external magnetic field, enabling the manipulation of bonded transport properties. The HSAI proposed here can be experimentally verified in ultra-cold atoms by the quantized non-reciprocal conductance or topological magnetoelectric response. Our work enriches the understanding of axion insulators in condensed matter physics, paving the way for future device applications., Comment: To appear in Nature Communications

Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which limits their effectiveness in addressing various types of hallucinations exhibited in LLM outputs. To our best knowledge, in this paper we propose the first active learning framework to alleviate LLM hallucinations, reducing costly human annotations of hallucination needed. By measuring fine-grained hallucinations from errors in semantic frame, discourse and content verifiability in text summarization, we propose HAllucination Diversity-Aware Sampling (HADAS) to select diverse hallucinations for annotations in active learning for LLM finetuning. Extensive experiments on three datasets and different backbone models demonstrate advantages of our method in effectively and efficiently mitigating LLM hallucinations., Comment: Accepted to NAACL 2024

Human-driven vehicles (HVs) exhibit complex and diverse behaviors. Accurately modeling such behavior is crucial for validating Robot Vehicles (RVs) in simulation and realizing the potential of mixed traffic control. However, existing approaches like parameterized models and data-driven techniques struggle to capture the full complexity and diversity. To address this, in this work, we introduce CARL, a hybrid approach that combines imitation learning for close proximity car-following and probabilistic sampling for larger headways. We also propose two classes of RL-based RVs: a safety RV focused on maximizing safety and an efficiency RV focused on maximizing efficiency. Our experiments show that the safety RV increases Time-to-Collision above the critical 4-second threshold and reduces Deceleration Rate to Avoid a Crash by up to 80%, while the efficiency RV achieves improvements in throughput of up to 49%. These results demonstrate the effectiveness of CARL in enhancing both safety and efficiency in mixed traffic., Comment: Accepted to IEEE CYBER 2024

The speed-precision trade-off is a critical problem for visual object tracking which usually requires low latency and deployment on constrained resources. Existing solutions for efficient tracking mainly focus on adopting light-weight backbones or modules, which nevertheless come at the cost of a sacrifice in precision. In this paper, inspired by dynamic network routing, we propose DyTrack, a dynamic transformer framework for efficient tracking. Real-world tracking scenarios exhibit diverse levels of complexity. We argue that a simple network is sufficient for easy frames in video sequences, while more computation could be assigned to difficult ones. DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget. Thus, it can achieve higher performance with the same running speed. We formulate instance-specific tracking as a sequential decision problem and attach terminating branches to intermediate layers of the entire model. Especially, to fully utilize the computations, we introduce the feature recycling mechanism to reuse the outputs of predecessors. Furthermore, a target-aware self-distillation strategy is designed to enhance the discriminating capabilities of early predictions by effectively mimicking the representation pattern of the deep model. Extensive experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model. For instance, DyTrack obtains 64.9% AUC on LaSOT with a speed of 256 fps.

Time-jerk optimal trajectory planning is crucial in advancing robotic arms' performance in dynamic tasks. Traditional methods rely on solving complex nonlinear programming problems, bringing significant delays in generating optimized trajectories. In this paper, we propose a two-stage approach to accelerate time-jerk optimal trajectory planning. Firstly, we introduce a dual-encoder based transformer model to establish a good preliminary trajectory. This trajectory is subsequently refined through sequential quadratic programming to improve its optimality and robustness. Our approach outperforms the state-of-the-art by up to 79.72\% in reducing trajectory planning time. Compared with existing methods, our method shrinks the optimality gap with the objective function value decreasing by up to 29.9\%., Comment: 6 pages, 7 figures, conference

Electric vertical-takeoff and landing (eVTOL) aircraft, recognized for their maneuverability and flexibility, offer a promising alternative to our transportation system. However, the operational effectiveness of these aircraft faces many challenges, such as the delicate balance between energy and time efficiency, stemming from unpredictable environmental factors, including wind fields. Mathematical modeling-based approaches have been adopted to plan aircraft flight path in urban wind fields with the goal to save energy and time costs. While effective, they are limited in adapting to dynamic and complex environments. To optimize energy and time efficiency in eVTOL's flight through dynamic wind fields, we introduce a novel path planning method leveraging deep reinforcement learning. We assess our method with extensive experiments, comparing it to Dijkstra's algorithm -- the theoretically optimal approach for determining shortest paths in a weighted graph, where weights represent either energy or time cost. The results show that our method achieves a graceful balance between energy and time efficiency, closely resembling the theoretically optimal values for both objectives.

Industrial managements, including quality control, cost and safety optimization, etc., heavily rely on high quality industrial human action recognitions (IHARs) which were hard to be implemented in large-scale industrial scenes due to their high costs and poor real-time performance. In this paper, we proposed a large-scale foundation model(LSFM)-based IHAR method, wherein various LSFMs and lightweight methods were jointly used, for the first time, to fulfill low-cost dataset establishment and real-time IHARs. Comprehensive tests on in-situ large-scale industrial manufacturing lines elucidated that the proposed method realized great reduction on employment costs, superior real-time performance, and satisfactory accuracy and generalization capabilities, indicating its great potential as a backbone IHAR method, especially for large-scale industrial applications.

Web-based applications such as chatbots, search engines and news recommendations continue to grow in scale and complexity with the recent surge in the adoption of LLMs. Online model selection has thus garnered increasing attention due to the need to choose the best model among a diverse set while balancing task reward and exploration cost. Organizations faces decisions like whether to employ a costly API-based LLM or a locally finetuned small LLM, weighing cost against performance. Traditional selection methods often evaluate every candidate model before choosing one, which are becoming impractical given the rising costs of training and finetuning LLMs. Moreover, it is undesirable to allocate excessive resources towards exploring poor-performing models. While some recent works leverage online bandit algorithm to manage such exploration-exploitation trade-off in model selection, they tend to overlook the increasing-then-converging trend in model performances as the model is iteratively finetuned, leading to less accurate predictions and suboptimal model selections. In this paper, we propose a time-increasing bandit algorithm TI-UCB, which effectively predicts the increase of model performances due to finetuning and efficiently balances exploration and exploitation in model selection. To further capture the converging points of models, we develop a change detection mechanism by comparing consecutive increase predictions. We theoretically prove that our algorithm achieves a logarithmic regret upper bound in a typical increasing bandit setting, which implies a fast convergence rate. The advantage of our method is also empirically validated through extensive experiments on classification model selection and online selection of LLMs. Our results highlight the importance of utilizing increasing-then-converging pattern for more efficient and economic model selection in the deployment of LLMs., Comment: Accepted by WWW'24 (Oral)

Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising serious concerns on network robustness. Although adversarial training (AT), in responding to malevolent AEs, was recognized as an effective approach to improve robustness, it was challenging to overcome generalization decline of networks caused by the AT. In this paper, in order to reserve high generalization while improving robustness, we proposed a dynamic perturbation-adaptive adversarial training (DPAAT) method, which placed AT in a dynamic learning environment to generate adaptive data-level perturbations and provided a dynamically updated criterion by loss information collections to handle the disadvantage of fixed perturbation sizes in conventional AT methods and the dependence on external transference. Comprehensive testing on dermatology HAM10000 dataset showed that the DPAAT not only achieved better robustness improvement and generalization preservation but also significantly enhanced mean average precision and interpretability on various CNNs, indicating its great potential as a generic adversarial training method on the MIC., Comment: 9 pages, 4 figures, 2 tables

Under-display camera (UDC) systems are the foundation of full-screen display devices in which the lens mounts under the display. The pixel array of light-emitting diodes used for display diffracts and attenuates incident light, causing various degradations as the light intensity changes. Unlike general video restoration which recovers video by treating different degradation factors equally, video restoration for UDC systems is more challenging that concerns removing diverse degradation over time while preserving temporal consistency. In this paper, we introduce a novel video restoration network, called D$^2$RNet, specifically designed for UDC systems. It employs a set of Decoupling Attention Modules (DAM) that effectively separate the various video degradation factors. More specifically, a soft mask generation function is proposed to formulate each frame into flare and haze based on the diffraction arising from incident light of different intensities, followed by the proposed flare and haze removal components that leverage long- and short-term feature learning to handle the respective degradations. Such a design offers an targeted and effective solution to eliminating various types of degradation in UDC systems. We further extend our design into multi-scale to overcome the scale-changing of degradation that often occur in long-range videos. To demonstrate the superiority of D$^2$RNet, we propose a large-scale UDC video benchmark by gathering HDR videos and generating realistically degraded videos using the point spread function measured by a commercial UDC system. Extensive quantitative and qualitative evaluations demonstrate the superiority of D$^2$RNet compared to other state-of-the-art video restoration and UDC image restoration methods. Code is available at https://github.com/ChengxuLiu/DDRNet.git, Comment: AAAI 2024

Despite the recent advances in unified image segmentation (IS), developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them across consecutive frames, while prompt-guided VS tasks require re-identifying the target with visual/text prompts throughout the entire video, making it hard to handle the different tasks with the same architecture. We make an attempt to address these issues and present a novel unified VS architecture, namely UniVS, by using prompts as queries. UniVS averages the prompt features of the target from previous frames as its initial query to explicitly decode masks, and introduces a target-wise prompt cross-attention layer in the mask decoder to integrate prompt features in the memory pool. By taking the predicted masks of entities from previous frames as their visual prompts, UniVS converts different VS tasks into prompt-guided target segmentation, eliminating the heuristic inter-frame matching process. Our framework not only unifies the different VS tasks but also naturally achieves universal training and testing, ensuring robust performance across different scenarios. UniVS shows a commendable balance between performance and universality on 10 challenging VS benchmarks, covering video instance, semantic, panoptic, object, and referring segmentation tasks. Code can be found at \url{https://github.com/MinghanLi/UniVS}., Comment: 21 pages, 11 figures, 10 tabels, CVPR2024

The ever-expanding scale of integrated circuits has brought about a significant rise in the design risks associated with radiation-resistant integrated circuit chips. Traditional single-particle experimental methods, with their iterative design approach, are increasingly ill-suited for the challenges posed by large-scale integrated circuits. In response, this article introduces a novel sensitivity-aware single-particle radiation effects simulation framework tailored for System-on-Chip platforms. Based on SVM algorithm we have implemented fast finding and classification of sensitive circuit nodes. Additionally, the methodology automates soft error analysis across the entire software stack. The study includes practical experiments focusing on RISC-V architecture, encompassing core components, buses, and memory systems. It culminates in the establishment of databases for Single Event Upsets (SEU) and Single Event Transients (SET), showcasing the practical efficacy of the proposed methodology in addressing radiation-induced challenges at the scale of contemporary integrated circuits. Experimental results have shown up to 12.78X speed-up on the basis of achieving 94.58% accuracy., Comment: Accepted to the 61th ACM/IEEE Design Automation conference (DAC 2024)

Artificial intelligence has been around for a while, but suddenly it has received more attention than ever before. Thanks to innovations from companies like Google, Microsoft, Meta, and other major brands in technology. OpenAI, though, has triggered the button with its ground-breaking invention ChatGPT. ChatGPT is a Large Language Model (LLM) based on Transformer architecture that has the ability to generate human-like responses in a conversational context. It uses deep learning algorithms to generate natural language responses to input text. Its large number of parameters, contextual generation, and open-domain training make it a versatile and effective tool for a wide range of applications, from chatbots to customer service to language translation. It has the potential to revolutionize various industries and transform the way we interact with technology. However, the use of ChatGPT has also raised several concerns, including ethical, social, and employment challenges, which must be carefully considered to ensure the responsible use of this technology. The article provides an overview of ChatGPT, delving into its architecture and training process. It highlights the potential impacts of ChatGPT on the society. In this paper, we suggest some approaches involving technology, regulation, education, and ethics in an effort to maximize ChatGPT's benefits while minimizing its negative impacts. This study is expected to contribute to a greater understanding of ChatGPT and aid in predicting the potential changes it may bring about., Comment: 13 Pages

Data-driven predictive control promises model-free wave-dampening strategies for Connected and Autonomous Vehicles (CAVs) in mixed traffic flow. However, its performance relies on data quality, which suffers from unknown noise and disturbances. This paper introduces a Robust Data-EnablEd Predictive Leading Cruise Control (RDeeP-LCC) method based on reachability analysis, aiming to achieve safe and optimal CAV control under bounded process noise and external disturbances. Precisely, the matrix zonotope set technique and Willems' Fundamental Lemma are employed to derive the over-approximated system dynamics directly from data, and a data-driven feedback control technique is utilized to obtain an additional feedback input for stability. We decouple the mixed platoon into an error system and a nominal system, where the error system provides data-driven reachability sets for the enhanced safety constraints in the nominal system. Finally, a data-driven predictive control framework is formulated in a tube-based control manner for robustness guarantees. Nonlinear simulations with noise-corrupted data demonstrate that the proposed method outperforms baseline methods in mitigating traffic waves., Comment: 8 pages, 4 figures

Deep neural networks were significantly vulnerable to adversarial examples manipulated by malicious tiny perturbations. Although most conventional adversarial attacks ensured the visual imperceptibility between adversarial examples and corresponding raw images by minimizing their geometric distance, these constraints on geometric distance led to limited attack transferability, inferior visual quality, and human-imperceptible interpretability. In this paper, we proposed a supervised semantic-transformation generative model to generate adversarial examples with real and legitimate semantics, wherein an unrestricted adversarial manifold containing continuous semantic variations was constructed for the first time to realize a legitimate transition from non-adversarial examples to adversarial ones. Comprehensive experiments on MNIST and industrial defect datasets showed that our adversarial examples not only exhibited better visual quality but also achieved superior attack transferability and more effective explanations for model vulnerabilities, indicating their great potential as generic adversarial examples. The code and pre-trained models were available at https://github.com/shuaili1027/MAELS.git., Comment: 12 pages, 6 figures

Unsupervised skeleton based action recognition has achieved remarkable progress recently. Existing unsupervised learning methods suffer from severe overfitting problem, and thus small networks are used, significantly reducing the representation capability. To address this problem, the overfitting mechanism behind the unsupervised learning for skeleton based action recognition is first investigated. It is observed that the skeleton is already a relatively high-level and low-dimension feature, but not in the same manifold as the features for action recognition. Simply applying the existing unsupervised learning method may tend to produce features that discriminate the different samples instead of action classes, resulting in the overfitting problem. To solve this problem, this paper presents an Unsupervised spatial-temporal Feature Enrichment and Fidelity Preservation framework (U-FEFP) to generate rich distributed features that contain all the information of the skeleton sequence. A spatial-temporal feature transformation subnetwork is developed using spatial-temporal graph convolutional network and graph convolutional gate recurrent unit network as the basic feature extraction network. The unsupervised Bootstrap Your Own Latent based learning is used to generate rich distributed features and the unsupervised pretext task based learning is used to preserve the information of the skeleton sequence. The two unsupervised learning ways are collaborated as U-FEFP to produce robust and discriminative representations. Experimental results on three widely used benchmarks, namely NTU-RGB+D-60, NTU-RGB+D-120 and PKU-MMD dataset, demonstrate that the proposed U-FEFP achieves the best performance compared with the state-of-the-art unsupervised learning methods. t-SNE illustrations further validate that U-FEFP can learn more discriminative features for unsupervised skeleton based action recognition.