Search

Numerous studies have assessed the proficiency of AI systems, particularly large language models (LLMs), in facilitating everyday tasks such as email writing, question answering, and creative content generation. However, researchers face unique challenges and opportunities in leveraging LLMs for their own work, such as brainstorming research ideas, designing experiments, and writing or reviewing papers. In this study, we introduce AAAR-1.0, a benchmark dataset designed to evaluate LLM performance in three fundamental, expertise-intensive research tasks: (i) EquationInference, assessing the correctness of equations based on the contextual information in paper submissions; (ii) ExperimentDesign, designing experiments to validate research ideas and solutions; (iii) PaperWeakness, identifying weaknesses in paper submissions; and (iv) REVIEWCRITIQUE, identifying each segment in human reviews is deficient or not. AAAR-1.0 differs from prior benchmarks in two key ways: first, it is explicitly research-oriented, with tasks requiring deep domain expertise; second, it is researcher-oriented, mirroring the primary activities that researchers engage in on a daily basis. An evaluation of both open-source and proprietary LLMs reveals their potential as well as limitations in conducting sophisticated research tasks. We will keep iterating AAAR-1.0 to new versions., Comment: Project Webpage: https://renzelou.github.io/AAAR-1.0/

Federated learning (FL) enables decentralized model training while preserving privacy. Recently, integrating Foundation Models (FMs) into FL has boosted performance but also introduced a novel backdoor attack mechanism. Attackers can exploit the FM's capabilities to embed backdoors into synthetic data generated by FMs used for model fusion, subsequently infecting all client models through knowledge sharing without involvement in the long-lasting FL process. These novel attacks render existing FL backdoor defenses ineffective, as they primarily detect anomalies among client updates, which may appear uniformly malicious under this attack. Our work proposes a novel data-free defense strategy by constraining abnormal activations in the hidden feature space during model aggregation on the server. The activation constraints, optimized using synthetic data alongside FL training, mitigate the attack while barely affecting model performance, as the parameters remain untouched. Extensive experiments demonstrate its effectiveness against both novel and classic backdoor attacks, outperforming existing defenses while maintaining model performance.

This study extended noncanonical warm inflation to the nonminimal derivative coupling scenario. The fundamental equations, including the evolution equations and the slow roll equations of this new framework, were derived. The enlarged damping term, which encompasses both gravitationally enhanced friction and thermal damping, resulted in a well overdamped inflationary process, ensuring that the slow roll approximations can be satisfactorily satisfied. A linear stability analysis corroborated the viability of this approach, yielding significantly relaxed slow roll conditions within the context of noncanonical warm inflation with nonminimal derivative coupling. Subsequently, the density fluctuations in this new framework were analyzed, leading to approximately analytic results for the power spectrum, spectral index, and related quantities. Both the energy scale at horizon crossing and the tensor-to-scalar ratio decreased considerably because of the effects of thermal damping and nonminimal derivative coupling. The upper bound for field excursion remained safely sub-Planckian in this inflationary scenario. Thus we reached a successful and meaningful model to broad the scope of warm inflation., Comment: 18 pages, 0 figures

Recently, camera pose, as a user-friendly and physics-related condition, has been introduced into text-to-video diffusion model for camera control. However, existing methods simply inject camera conditions through a side input. These approaches neglect the inherent physical knowledge of camera pose, resulting in imprecise camera control, inconsistencies, and also poor interpretability. In this paper, we emphasize the necessity of integrating explicit physical constraints into model design. Epipolar attention is proposed for modeling all cross-frame relationships from a novel perspective of noised condition. This ensures that features are aggregated from corresponding epipolar lines in all noised frames, overcoming the limitations of current attention mechanisms in tracking displaced features across frames, especially when features move significantly with the camera and become obscured by noise. Additionally, we introduce register tokens to handle cases without intersections between frames, commonly caused by rapid camera movements, dynamic objects, or occlusions. To support image-to-video, we propose the multiple guidance scale to allow for precise control for image, text, and camera, respectively. Furthermore, we establish a more robust and reproducible evaluation pipeline to solve the inaccuracy and instability of existing camera control measurement. We achieve a 25.5% improvement in camera controllability on RealEstate10K while maintaining strong generalization to out-of-domain images. Only 24GB and 12GB are required for training and inference, respectively. We plan to release checkpoints, along with training and evaluation codes. Dynamic videos are best viewed at https://zgctroy.github.io/CamI2V.

The growing interest in embodied intelligence has brought ego-centric perspectives to contemporary research. One significant challenge within this realm is the accurate localization and tracking of objects in ego-centric videos, primarily due to the substantial variability in viewing angles. Addressing this issue, this paper introduces a novel zero-shot approach for the 3D reconstruction and tracking of all objects from the ego-centric video. We present Ego3DT, a novel framework that initially identifies and extracts detection and segmentation information of objects within the ego environment. Utilizing information from adjacent video frames, Ego3DT dynamically constructs a 3D scene of the ego view using a pre-trained 3D scene reconstruction model. Additionally, we have innovated a dynamic hierarchical association mechanism for creating stable 3D tracking trajectories of objects in ego-centric videos. Moreover, the efficacy of our approach is corroborated by extensive experiments on two newly compiled datasets, with 1.04x - 2.90x in HOTA, showcasing the robustness and accuracy of our method in diverse ego-centric scenarios., Comment: Accepted by ACM Multimedia 2024

Manufacturing quality audits are pivotal for ensuring high product standards in mass production environments. Traditional auditing processes, however, are labor-intensive and reliant on human expertise, posing challenges in maintaining transparency, accountability, and continuous improvement across complex global supply chains. To address these challenges, we propose a smart audit system empowered by large language models (LLMs). Our approach introduces three innovations: a dynamic risk assessment model that streamlines audit procedures and optimizes resource allocation; a manufacturing compliance copilot that enhances data processing, retrieval, and evaluation for a self-evolving manufacturing knowledge base; and a Re-act framework commonality analysis agent that provides real-time, customized analysis to empower engineers with insights for supplier improvement. These enhancements elevate audit efficiency and effectiveness, with testing scenarios demonstrating an improvement of over 24%.

Quantum secret sharing (QSS) enables a dealer to securely distribute keys to multiple players. Device-independent (DI) QSS can resist all possible attacks from practical imperfect devices and provide QSS the highest level of security in theory. However, DI QSS requires high-performance devices, especially for low-noise channels, which is a big challenge for its experimental demonstration. We propose a DI QSS protocol with the advanced random key generation basis strategy, which combines the random key generation basis with the noise preprocessing and postselection strategies. We develop the methods to simplify Eve's conditional entropy bound and numerically simulate the key generation rate in an acceptable time. Our DI QSS protocol has some advantages. First, it can increase the noise tolerance threshold from initial 7.147% to 9.231% (29.16% growth), and reduce the global detection efficiency threshold from 96.32% to 93.41%. The maximal distance between any two users increases to 1.43 km, which is about 5.5 times of the initial value. Second, by randomly selecting two basis combinations to generate the key, our DI QSS protocol can reduce the entanglement resource consumption. Our protocol has potential for DI QSS's experimental demonstration and application in the future., Comment: 16 pages, 6 figures, 1 table

Multi-object tracking (MOT) emerges as a pivotal and highly promising branch in the field of computer vision. Classical closed-vocabulary MOT (CV-MOT) methods aim to track objects of predefined categories. Recently, some open-vocabulary MOT (OV-MOT) methods have successfully addressed the problem of tracking unknown categories. However, we found that the CV-MOT and OV-MOT methods each struggle to excel in the tasks of the other. In this paper, we present a unified framework, Associate Everything Detected (AED), that simultaneously tackles CV-MOT and OV-MOT by integrating with any off-the-shelf detector and supports unknown categories. Different from existing tracking-by-detection MOT methods, AED gets rid of prior knowledge (e.g. motion cues) and relies solely on highly robust feature learning to handle complex trajectories in OV-MOT tasks while keeping excellent performance in CV-MOT tasks. Specifically, we model the association task as a similarity decoding problem and propose a sim-decoder with an association-centric learning mechanism. The sim-decoder calculates similarities in three aspects: spatial, temporal, and cross-clip. Subsequently, association-centric learning leverages these threefold similarities to ensure that the extracted features are appropriate for continuous tracking and robust enough to generalize to unknown categories. Compared with existing powerful OV-MOT and CV-MOT methods, AED achieves superior performance on TAO, SportsMOT, and DanceTrack without any prior knowledge. Our code is available at https://github.com/balabooooo/AED.

Multimodal Emotion Recognition (MER) aims to automatically identify and understand human emotional states by integrating information from various modalities. However, the scarcity of annotated multimodal data significantly hinders the advancement of this research field. This paper presents our solution for the MER-SEMI sub-challenge of MER 2024. First, to better adapt acoustic modality features for the MER task, we experimentally evaluate the contributions of different layers of the pre-trained speech model HuBERT in emotion recognition. Based on these observations, we perform Parameter-Efficient Fine-Tuning (PEFT) on the layers identified as most effective for emotion recognition tasks, thereby achieving optimal adaptation for emotion recognition with a minimal number of learnable parameters. Second, leveraging the strengths of the acoustic modality, we propose a feature alignment pre-training method. This approach uses large-scale unlabeled data to train a visual encoder, thereby promoting the semantic alignment of visual features within the acoustic feature space. Finally, using the adapted acoustic features, aligned visual features, and lexical features, we employ an attention mechanism for feature fusion. On the MER2024-SEMI test set, the proposed method achieves a weighted F1 score of 88.90%, ranking fourth among all participating teams, validating the effectiveness of our approach.

Single-frame infrared small target (SIRST) detection poses a significant challenge due to the requirement to discern minute targets amidst complex infrared background clutter. Recently, deep learning approaches have shown promising results in this domain. However, these methods heavily rely on extensive manual annotations, which are particularly cumbersome and resource-intensive for infrared small targets owing to their minute sizes. To address this limitation, we introduce a Hybrid Mask Generation (HMG) approach that recovers high-quality masks for each target from only a single-point label for network training. Specifically, our HMG approach consists of a handcrafted Points-to-Mask Generation strategy coupled with a pseudo mask updating strategy to recover and refine pseudo masks from point labels. The Points-to-Mask Generation strategy divides two distinct stages: Points-to-Box conversion, where individual point labels are transformed into bounding boxes, and subsequently, Box-to-Mask prediction, where these bounding boxes are elaborated into precise masks. The mask updating strategy integrates the complementary strengths of handcrafted and deep-learning algorithms to iteratively refine the initial pseudo masks. Experimental results across three datasets demonstrate that our method outperforms the existing methods for infrared small target detection with single-point supervision., Comment: 9 pages, 5 figures

Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of video diffusion models (VDMs) to combine concepts and generate motions. To restore these abilities, some methods use additional video similar to the prompt to fine-tune or guide the model. This requires frequent changes of guiding videos and even re-tuning of the model when generating different motions, which is very inconvenient for users. In this paper, we propose CustomCrafter, a novel framework that preserves the model's motion generation and conceptual combination abilities without additional video and fine-tuning to recovery. For preserving conceptual combination ability, we design a plug-and-play module to update few parameters in VDMs, enhancing the model's ability to capture the appearance details and the ability of concept combinations for new subjects. For motion generation, we observed that VDMs tend to restore the motion of video in the early stage of denoising, while focusing on the recovery of subject details in the later stage. Therefore, we propose Dynamic Weighted Video Sampling Strategy. Using the pluggability of our subject learning modules, we reduce the impact of this module on motion generation in the early stage of denoising, preserving the ability to generate motion of VDMs. In the later stage of denoising, we restore this module to repair the appearance details of the specified subject, thereby ensuring the fidelity of the subject's appearance. Experimental results show that our method has a significant improvement compared to previous methods., Comment: project page: https://customcrafter.github.io/

Few-shot learning (FSL) aims to recognize new concepts using a limited number of visual samples. Existing approaches attempt to incorporate semantic information into the limited visual data for category understanding. However, these methods often enrich class-level feature representations with abstract category names, failing to capture the nuanced features essential for effective generalization. To address this issue, we propose a novel framework for FSL, which incorporates both the abstract class semantics and the concrete class entities extracted from Large Language Models (LLMs), to enhance the representation of the class prototypes. Specifically, our framework composes a Semantic-guided Visual Pattern Extraction (SVPE) module and a Prototype-Calibration (PC) module, where the SVPE meticulously extracts semantic-aware visual patterns across diverse scales, while the PC module seamlessly integrates these patterns to refine the visual prototype, enhancing its representativeness. Extensive experiments on four few-shot classification benchmarks and the BSCD-FSL cross-domain benchmarks showcase remarkable advancements over the current state-of-the-art methods. Notably, for the challenging one-shot setting, our approach, utilizing the ResNet-12 backbone, achieves an impressive average improvement of 1.95% over the second-best competitor., Comment: 9 pages, 7 figures

In the past two decades, the exploration of quantumness within Schwarzschild spacetime has garnered significant interest, particularly regarding the Hawking radiation's impact on quantum correlations and quantum coherence. Building on this foundation, we investigate how Hawking radiation influences maximal steered coherence (MSC)-a crucial measure for gauging the ability to generate coherence through steering. We find that as the Hawking temperature increases, the physically accessible MSC degrade while the unaccessible MSC increase. This observation is attributed to a redistribution of the initial quantum correlations, previously acknowledged by inertial observers, across all bipartite modes. In particular, we find that in limit case that the Hawking temperature tends to infinity, the accessible MSC equals to 1/\sqrt{2} of its initial value, and the unaccessible MSC also equals to the same value. Our findings illuminate the intricate dynamics of quantum information in the vicinity of black holes, suggesting that Hawking radiation plays a pivotal role in reshaping the landscape of quantum coherence and entanglement in curved spacetime. This study not only advances our theoretical understanding of black hole thermodynamics but also opens new avenues for investigating the interface between quantum mechanics and general relativity., Comment: 4 pages, 1 figure

We construct a decoupled, first-order, fully discrete, and unconditionally energy stable scheme for the Cahn-Hilliard-Navier-Stokes equations. The scheme is divided into two main parts. The first part involves the calculation of the Cahn-Hilliard equations, and the other part is calculating the Navier-Stokes equations subsequently by utilizing the phase field and chemical potential values obtained from the above step. Specifically, the velocity in the Cahn-Hilliard equation is discretized explicitly at the discrete time level, which enables the computation of the Cahn-Hilliard equations is fully decoupled from that of Navier-Stokes equations. Furthermore, the pressure-correction projection method, in conjunction with the scalar auxiliary variable approach not only enables the discrete scheme to satisfy unconditional energy stability, but also allows the convective term in the Navier-Stokes equations to be treated explicitly. We subsequently prove that the time semi-discrete scheme is unconditionally stable and analyze the optimal error estimates for the fully discrete scheme. Finally, several numerical experiments validate the theoretical results., Comment: 3 figures, 2 tables

Semiparametric statistics play a pivotal role in a wide range of domains, including but not limited to missing data, causal inference, and transfer learning, to name a few. In many settings, semiparametric theory leads to (nearly) statistically optimal procedures that yet involve numerically solving Fredholm integral equations of the second kind. Traditional numerical methods, such as polynomial or spline approximations, are difficult to scale to multi-dimensional problems. Alternatively, statisticians may choose to approximate the original integral equations by ones with closed-form solutions, resulting in computationally more efficient, but statistically suboptimal or even incorrect procedures. To bridge this gap, we propose a novel framework by formulating the semiparametric estimation problem as a bi-level optimization problem; and then we develop a scalable algorithm called Deep Neural-Nets Assisted Semiparametric Estimation (DNA-SE) by leveraging the universal approximation property of Deep Neural-Nets (DNN) to streamline semiparametric procedures. Through extensive numerical experiments and a real data analysis, we demonstrate the numerical and statistical advantages of $\dnase$ over traditional methods. To the best of our knowledge, we are the first to bring DNN into semiparametric statistics as a numerical solver of integral equations in our proposed general framework., Comment: semiparametric statistics, missing data, causal inference, Fredholm integral equations of the second kind, bi-level optimization, deep learning, AI for science

In a recent study, we found that publicly BCCD and BCD datasets have significant issues such as labeling errors, insufficient sample size, and poor data quality. To address these problems, we performed sample deletion, re-labeling, and integration of these two datasets. Additionally, we introduced the PBC and Raabin-WBC datasets, and ultimately created a high-quality, sample-balanced new dataset, which we named TXL-PBC. The dataset contains 1008 training sets, 288 validation sets, and 144 test sets. Firstly, The dataset underwent strict manual annotation, automatic annotation with YOLOv8n model, and manual audit steps to ensure the accuracy and consistency of annotations. Secondly, we addresses the blood cell mislabeling problem of the original datasets. The distribution of label boundary box areas and the number of labels are better than the BCCD and BCD datasets. Moreover, we used the YOLOv8n model to train these three datasets, the performance of the TXL-PBC dataset surpass the original two datasets. Finally, we employed YOLOv5n, YOLOv5s, YOLOv5l, YOLOv8s, YOLOv8m detection models as the baseline models for TXL-PBC. This study not only enhances the quality of the blood cell dataset but also supports researchers in improving models for blood cell target detection. We published our freely accessible TXL-PBC dataset at https://github.com/lugan113/TXL-PBC\_Dataset.

Gait recognition, which aims at identifying individuals by their walking patterns, has achieved great success based on silhouette. The binary silhouette sequence encodes the walking pattern within the sparse boundary representation. Therefore, most pixels in the silhouette are under-sensitive to the walking pattern since the sparse boundary lacks dense spatial-temporal information, which is suitable to be represented with dense texture. To enhance the sensitivity to the walking pattern while maintaining the robustness of recognition, we present a Complementary Learning with neural Architecture Search (CLASH) framework, consisting of walking pattern sensitive gait descriptor named dense spatial-temporal field (DSTF) and neural architecture search based complementary learning (NCL). Specifically, DSTF transforms the representation from the sparse binary boundary into the dense distance-based texture, which is sensitive to the walking pattern at the pixel level. Further, NCL presents a task-specific search space for complementary learning, which mutually complements the sensitivity of DSTF and the robustness of the silhouette to represent the walking pattern effectively. Extensive experiments demonstrate the effectiveness of the proposed methods under both in-the-lab and in-the-wild scenarios. On CASIA-B, we achieve rank-1 accuracy of 98.8%, 96.5%, and 89.3% under three conditions. On OU-MVLP, we achieve rank-1 accuracy of 91.9%. Under the latest in-the-wild datasets, we outperform the latest silhouette-based methods by 16.3% and 19.7% on Gait3D and GREW, respectively.

In text-to-video (T2V) generation, significant attention has been directed toward its development, yet unifying discrete and continuous grounding conditions in T2V generation remains under-explored. This paper proposes a Grounded text-to-Video generation framework, termed GVDIFF. First, we inject the grounding condition into the self-attention through an uncertainty-based representation to explicitly guide the focus of the network. Second, we introduce a spatial-temporal grounding layer that connects the grounding condition with target objects and enables the model with the grounded generation capacity in the spatial-temporal domain. Third, our dynamic gate network adaptively skips the redundant grounding process to selectively extract grounding information and semantics while improving efficiency. We extensively evaluate the grounded generation capacity of GVDIFF and demonstrate its versatility in applications, including long-range video generation, sequential prompts, and object-specific editing.

The Mixture-of-Experts (MoE) has gained increasing attention in studying Large Vision-Language Models (LVLMs). It uses a sparse model to replace the dense model, achieving comparable performance while activating fewer parameters during inference, thus significantly reducing the inference cost. Existing MoE methods in LVLMs encourage different experts to handle different tokens, and they usually employ a router to predict the routing of each token. However, the predictions are based solely on sample features and do not truly reveal the optimization directions of tokens. This may lead to severe optimization interference between different tokens assigned to an expert. To address this problem, this paper proposes a novel method based on token-level gradient analysis, i.e., Solving Token Gradient Conflict (STGC). Specifically, we first use token-level gradients to identify conflicting tokens in experts. After that, we add a specialized loss tailored to eliminate conflicts among tokens within each expert. Our method can serve as a plug-in for diverse Large Vision-Language Models, and extensive experimental results demonstrate its effectiveness. The code will be publicly available at https://github.com/longrongyang/STGC.

Large Language Models (LLMs) have stunningly advanced the field of machine translation, though their effectiveness within the financial domain remains largely underexplored. To probe this issue, we constructed a fine-grained Chinese-English parallel corpus of financial news called FFN. We acquired financial news articles spanning between January 1st, 2014, to December 31, 2023, from mainstream media websites such as CNN, FOX, and China Daily. The dataset consists of 1,013 main text and 809 titles, all of which have been manually corrected. We measured the translation quality of two LLMs -- ChatGPT and ERNIE-bot, utilizing BLEU, TER and chrF scores as the evaluation metrics. For comparison, we also trained an OpenNMT model based on our dataset. We detail problems of LLMs and provide in-depth analysis, intending to stimulate further research and solutions in this largely uncharted territory. Our research underlines the need to optimize LLMs within the specific field of financial translation to ensure accuracy and quality., Comment: a simplified version of this paper is accepted by International Conference on Asian Language Processing 2024

Referring Expression Comprehension (REC) aims to localize the target objects specified by free-form natural language descriptions in images. While state-of-the-art methods achieve impressive performance, they perform a dense perception of images, which incorporates redundant visual regions unrelated to linguistic queries, leading to additional computational overhead. This inspires us to explore a question: can we eliminate linguistic-irrelevant redundant visual regions to improve the efficiency of the model? Existing relevant methods primarily focus on fundamental visual tasks, with limited exploration in vision-language fields. To address this, we propose a coarse-to-fine iterative perception framework, called ScanFormer. It can iteratively exploit the image scale pyramid to extract linguistic-relevant visual patches from top to bottom. In each iteration, irrelevant patches are discarded by our designed informativeness prediction. Furthermore, we propose a patch selection strategy for discarded patches to accelerate inference. Experiments on widely used datasets, namely RefCOCO, RefCOCO+, RefCOCOg, and ReferItGame, verify the effectiveness of our method, which can strike a balance between accuracy and efficiency., Comment: Accepted by CVPR2024

This paper represents a neat yet effective framework, named SemanticMIM, to integrate the advantages of masked image modeling (MIM) and contrastive learning (CL) for general visual representation. We conduct a thorough comparative analysis between CL and MIM, revealing that their complementary advantages fundamentally stem from two distinct phases, i.e., compression and reconstruction. Specifically, SemanticMIM leverages a proxy architecture that customizes interaction between image and mask tokens, bridging these two phases to achieve general visual representation with the property of abundant semantic and positional awareness. Through extensive qualitative and quantitative evaluations, we demonstrate that SemanticMIM effectively amalgamates the benefits of CL and MIM, leading to significant enhancement of performance and feature linear separability. SemanticMIM also offers notable interpretability through attention response visualization. Codes are available at https://github.com/yyk-wew/SemanticMIM.

In this short note, we show that one cannot differentiate between reciprocal Dunford--Pettis sets and V$^*$-sets in a Banach lattice. That is, for a bounded subset $K$ of a Banach lattice $E$, $K$ is a V$^*$-set if and only if $K$ is a reciprocal Dunford--Pettis set, or equivalently, if and only if every disjoint sequence in the solid hull of $K$ is weakly null (i.e. $K$ is disjointly weakly compact)., Comment: 4 pages

Vision-based roadside 3D object detection has attracted rising attention in autonomous driving domain, since it encompasses inherent advantages in reducing blind spots and expanding perception range. While previous work mainly focuses on accurately estimating depth or height for 2D-to-3D mapping, ignoring the position approximation error in the voxel pooling process. Inspired by this insight, we propose a novel voxel pooling strategy to reduce such error, dubbed BEVSpread. Specifically, instead of bringing the image features contained in a frustum point to a single BEV grid, BEVSpread considers each frustum point as a source and spreads the image features to the surrounding BEV grids with adaptive weights. To achieve superior propagation performance, a specific weight function is designed to dynamically control the decay speed of the weights according to distance and depth. Aided by customized CUDA parallel acceleration, BEVSpread achieves comparable inference time as the original voxel pooling. Extensive experiments on two large-scale roadside benchmarks demonstrate that, as a plug-in, BEVSpread can significantly improve the performance of existing frustum-based BEV methods by a large margin of (1.12, 5.26, 3.01) AP in vehicle, pedestrian and cyclist.

Backdoor attacks present significant threats to Large Language Models (LLMs), particularly with the rise of third-party services that offer API integration and prompt engineering. Untrustworthy third parties can plant backdoors into LLMs and pose risks to users by embedding malicious instructions into user queries. The backdoor-compromised LLM will generate malicious output when and input is embedded with a specific trigger predetermined by an attacker. Traditional defense strategies, which primarily involve model parameter fine-tuning and gradient calculation, are inadequate for LLMs due to their extensive computational and clean data requirements. In this paper, we propose a novel solution, Chain-of-Scrutiny (CoS), to address these challenges. Backdoor attacks fundamentally create a shortcut from the trigger to the target output, thus lack reasoning support. Accordingly, CoS guides the LLMs to generate detailed reasoning steps for the input, then scrutinizes the reasoning process to ensure consistency with the final answer. Any inconsistency may indicate an attack. CoS only requires black-box access to LLM, offering a practical defense, particularly for API-accessible LLMs. It is user-friendly, enabling users to conduct the defense themselves. Driven by natural language, the entire defense process is transparent to users. We validate the effectiveness of CoS through extensive experiments across various tasks and LLMs. Additionally, experiments results shows CoS proves more beneficial for more powerful LLMs.

City scene generation has gained significant attention in autonomous driving, smart city development, and traffic simulation. It helps enhance infrastructure planning and monitoring solutions. Existing methods have employed a two-stage process involving city layout generation, typically using Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), or Transformers, followed by neural rendering. These techniques often exhibit limited diversity and noticeable artifacts in the rendered city scenes. The rendered scenes lack variety, resembling the training images, resulting in monotonous styles. Additionally, these methods lack planning capabilities, leading to less realistic generated scenes. In this paper, we introduce CityCraft, an innovative framework designed to enhance both the diversity and quality of urban scene generation. Our approach integrates three key stages: initially, a diffusion transformer (DiT) model is deployed to generate diverse and controllable 2D city layouts. Subsequently, a Large Language Model(LLM) is utilized to strategically make land-use plans within these layouts based on user prompts and language guidelines. Based on the generated layout and city plan, we utilize the asset retrieval module and Blender for precise asset placement and scene construction. Furthermore, we contribute two new datasets to the field: 1)CityCraft-OSM dataset including 2D semantic layouts of urban areas, corresponding satellite images, and detailed annotations. 2) CityCraft-Buildings dataset, featuring thousands of diverse, high-quality 3D building assets. CityCraft achieves state-of-the-art performance in generating realistic 3D cities., Comment: 20 pages, 9 figures

Measurement-device-independent quantum secret sharing (MDI-QSS) can eliminate all the security loopholes associated with imperfect measurement devices and greatly enhance QS's security under practical experimental condition. MDI-QSS requires each communication user to send single photon to the measurement party for the coincident measurement. However, the unsynchronization of the transmitted photons greatly limits MDI-QSS's practical performance.In the paper, we propose a high-efficient quantum memory (QM)-assisted MDI-QSS protocol, which employs the QM-assisted synchronization of three heralded single-photon sources to efficiently generate three simultaneous single-photon states. The QM constructed with all-optical, polarization-insensitive storage loop has superior performance in terms of bandwidth, storage efficiency, and noise resistance, and is feasible under current experiment conditions. Combining with the decoy-state method, we perform the numerical simulation of the secure key rate in the symmetric model without considering the finite-size effect. The simulation results show that our QM-assisted MDI-QSS protocol exhibit largely improved secure key rate and maximal photon transmission distance compared with all existing MDI-QSS protocols without QM. Our protocol provides a promising way for implementing the high-efficient long-distance MDI-QSS in the near future., Comment: 11 pages, 6 figures

Multimodal large language models (MLLMs) enhance the capabilities of standard large language models by integrating and processing data from multiple modalities, including text, vision, audio, video, and 3D environments. Data plays a pivotal role in the development and refinement of these models. In this survey, we comprehensively review the literature on MLLMs from a data-centric perspective. Specifically, we explore methods for preparing multimodal data during the pretraining and adaptation phases of MLLMs. Additionally, we analyze the evaluation methods for the datasets and review the benchmarks for evaluating MLLMs. Our survey also outlines potential future research directions. This work aims to provide researchers with a detailed understanding of the data-driven aspects of MLLMs, fostering further exploration and innovation in this field.

Due to the large-scale image size and object variations, current CNN-based and Transformer-based approaches for remote sensing image semantic segmentation are suboptimal for capturing the long-range dependency or limited to the complex computational complexity. In this paper, we propose CM-UNet, comprising a CNN-based encoder for extracting local image features and a Mamba-based decoder for aggregating and integrating global information, facilitating efficient semantic segmentation of remote sensing images. Specifically, a CSMamba block is introduced to build the core segmentation decoder, which employs channel and spatial attention as the gate activation condition of the vanilla Mamba to enhance the feature interaction and global-local information fusion. Moreover, to further refine the output features from the CNN encoder, a Multi-Scale Attention Aggregation (MSAA) module is employed to merge the different scale features. By integrating the CSMamba block and MSAA module, CM-UNet effectively captures the long-range dependencies and multi-scale global contextual information of large-scale remote-sensing images. Experimental results obtained on three benchmarks indicate that the proposed CM-UNet outperforms existing methods in various performance metrics. The codes are available at https://github.com/XiaoBuL/CM-UNet., Comment: 5 pages, 6 figures

The virtualization of Radio Access Networks (vRAN) is well on its way to become a reality, driven by its advantages such as flexibility and cost-effectiveness. However, virtualization comes at a high price - virtual Base Stations (vBSs) sharing the same computing platform incur a significant computing overhead due to in extremis consumption of shared cache memory resources. Consequently, vRAN suffers from increased energy consumption, which fuels the already high operational costs in 5G networks. This paper investigates cache memory allocation mechanisms' effectiveness in reducing total energy consumption. Using an experimental vRAN platform, we profile the energy consumption and CPU utilization of vBS as a function of the network state (e.g., traffic demand, modulation scheme). Then, we address the high dimensionality of the problem by decomposing it per vBS, which is possible thanks to the Last-Level Cache (LLC) isolation implemented in our system. Based on this, we train a vBS digital twin, which allows us to train offline a classifier, avoiding the performance degradation of the system during training. Our results show that our approach performs very closely to an offline optimal oracle, outperforming standard approaches used in today's deployments.

Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long videos, the computational complexity and memory costs associated with long-term temporal connections are significantly increased, posing additional challenges.Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose MovieChat to overcome these challenges. We lift pre-trained multi-modal large language models for understanding long videos without incorporating additional trainable temporal modules, employing a zero-shot approach. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video, 2K temporal grounding labels, and 14K manual annotations for validation of the effectiveness of our method. The code along with the dataset can be accessed via the following https://github.com/rese1f/MovieChat.

Face recognition systems are frequently subjected to a variety of physical and digital attacks of different types. Previous methods have achieved satisfactory performance in scenarios that address physical attacks and digital attacks, respectively. However, few methods are considered to integrate a model that simultaneously addresses both physical and digital attacks, implying the necessity to develop and maintain multiple models. To jointly detect physical and digital attacks within a single model, we propose an innovative approach that can adapt to any network architecture. Our approach mainly contains two types of data augmentation, which we call Simulated Physical Spoofing Clues augmentation (SPSC) and Simulated Digital Spoofing Clues augmentation (SDSC). SPSC and SDSC augment live samples into simulated attack samples by simulating spoofing clues of physical and digital attacks, respectively, which significantly improve the capability of the model to detect "unseen" attack types. Extensive experiments show that SPSC and SDSC can achieve state-of-the-art generalization in Protocols 2.1 and 2.2 of the UniAttackData dataset, respectively. Our method won first place in "Unified Physical-Digital Face Attack Detection" of the 5th Face Anti-spoofing Challenge@CVPR2024. Our final submission obtains 3.75% APCER, 0.93% BPCER, and 2.34% ACER, respectively. Our code is available at https://github.com/Xianhua-He/cvpr2024-face-anti-spoofing-challenge., Comment: 10 pages with 6 figures, Accepted by CVPRW 2024

Device-independent (DI) quantum secret sharing (QSS) can relax the security assumptions about the devices' internal workings and provide QSS the highest level of security in theory. The original DI QSS protocol proved its correctness and completeness under a causal independence assumption regarding measurement devices. However, there has been a lack of DI QSS's performance characterization in practical communication situations, which impedes its experimental demonstration and application in the future. Here, we propose a three-partite DI QSS protocol with noise preprocessing and postselection strategies and develop the numerical methods to implement its performance characterization in practical communication situations. The adoption of the noise preprocessing and postselection can reduce DI QSS's global detection efficiency threshold from 96.32% to 94.30% and increase the noise threshold from 7.148% to 8.072%. Our DI QSS protocol has two advantages. First, it is a DI QSS protocol with performance characterization in practical communication situations. Second, the adoption of noise preprocessing and postselection can effectively relax its experimental requirement and enhance the noise resistance. Our DI QSS protocol has potential for future experimental demonstration and application., Comment: 14 pages, 7 figures

Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains.However, it remains a challenging task due to the inherent spherical distortion and geometry characteristics, resulting in low-quality content generation.In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges, for better generating high-quality and precisely controllable spherical panoramic images.For the spherical distortion characteristic, we embed the semantics of the distorted object with text encoding, then explicitly construct the relationship with text-object correspondence to better use the pre-trained knowledge of the planar images.Meanwhile, we employ a deformable technique to mitigate the semantic deviation in latent space caused by spherical distortion.For the spherical geometry characteristic, in virtue of spherical rotation invariance, we improve the data diversity and optimization objectives in the training process, enabling the model to better learn the spherical geometry characteristic.Furthermore, we enhance the denoising process of the diffusion model, enabling it to effectively use the learned geometric characteristic to ensure the boundary continuity of the generated images.With these specific techniques, experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average., Comment: Accepted by AAAI2024