Search

Comprehensive evaluation of Multimodal Large Language Models (MLLMs) has recently garnered widespread attention in the research community. However, we observe that existing benchmarks present several common barriers that make it difficult to measure the significant challenges that models face in the real world, including: 1) small data scale leads to a large performance variance; 2) reliance on model-based annotations results in restricted data quality; 3) insufficient task difficulty, especially caused by the limited image resolution. To tackle these issues, we introduce MME-RealWorld. Specifically, we collect more than $300$K images from public datasets and the Internet, filtering $13,366$ high-quality images for annotation. This involves the efforts of professional $25$ annotators and $7$ experts in MLLMs, contributing to $29,429$ question-answer pairs that cover $43$ subtasks across $5$ real-world scenarios, extremely challenging even for humans. As far as we know, MME-RealWorld is the largest manually annotated benchmark to date, featuring the highest resolution and a targeted focus on real-world applications. We further conduct a thorough evaluation involving $28$ prominent MLLMs, such as GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet. Our results show that even the most advanced models struggle with our benchmarks, where none of them reach $60\%$ accuracy. The challenges of perceiving high-resolution images and understanding complex real-world scenarios remain urgent issues to be addressed. The data and evaluation code are released at https://mme-realworld.github.io/ ., Comment: Project Page: $\href{https://mme-realworld.github.io/}{\text{https://mme-realworld.github.io/}}$

Embodied learning for object-centric robotic manipulation is a rapidly developing and challenging area in embodied AI. It is crucial for advancing next-generation intelligent robots and has garnered significant interest recently. Unlike data-driven machine learning methods, embodied learning focuses on robot learning through physical interaction with the environment and perceptual feedback, making it especially suitable for robotic manipulation. In this paper, we provide a comprehensive survey of the latest advancements in this field and categorize the existing work into three main branches: 1) Embodied perceptual learning, which aims to predict object pose and affordance through various data representations; 2) Embodied policy learning, which focuses on generating optimal robotic decisions using methods such as reinforcement learning and imitation learning; 3) Embodied task-oriented learning, designed to optimize the robot's performance based on the characteristics of different tasks in object grasping and manipulation. In addition, we offer an overview and discussion of public datasets, evaluation metrics, representative applications, current challenges, and potential future research directions. A project associated with this survey has been established at https://github.com/RayYoh/OCRM_survey.

The operation of upcoming ultra-high-energy cosmic-ray, gamma-ray, and neutrino radio-detection experiments, like the Giant Radio Array for Neutrino Detection (GRAND), poses significant computational challenges involving the production of numerous simulations of particle showers and their detection, and a high data throughput. GRANDlib is an open-source software tool designed to meet these challenges. Its primary goal is to perform end-to-end simulations of the detector operation, from the interaction of ultra-high-energy particles, through -- by interfacing with external air-shower simulations -- the ensuing particle shower development and its radio emission, to its detection by antenna arrays and its processing by data-acquisition systems. Additionally, GRANDlib manages the visualization, storage, and retrieval of experimental and simulated data. We present an overview of GRANDlib to serve as the basis of future GRAND analyses., Comment: 11 pages, 9 figures, plus appendices

The equation of state (EOS) serves as a cornerstone in elucidating the properties of quantum many-body systems. A recent highlight along this research line consists of the derivation of the nonuniversal Lee-Huang-Yang (LHY) EOS for an ultracold quantum bosonic gas with finite-range interatomic interactions using one-loop effective path-integral field theory. The purpose of this work is to extend Salasnich's pioneering work to uncover beyond-LHY corrections to the EOS by employing the Cornwall-Jackiw-Tomboulis (CJT) effective field theory, leveraging its two-loop approximation. In this end, we expand Salasnich's remarkable findings of EOS to the next leading order characterized by $\left(\rho a_{\text{s}}^{3}\right)^{2}$, with $\rho$ and $a_{\text{s}}$ being the density and the $s$-wave scattering length. Notably, we derive analytical expressions for quantum depletion and chemical potential, representing the next-to-LHY corrections to nonuniversal EOS induced by finite-range effects. Moreover, we propose an experimental protocol of observing the nonuniversal next-to-LHY corrections to the EOS by calculating fractional frequency shifts in the breathing modes. The nonuniversal beyond-LHY EOS in this work paves the way of using LHY effects in quantum simulation experiments and for investigations beyond the LHY regime., Comment: 14 pages,2 figures

Large-scale magnetic fields are observed off the midplanes of disk galaxies, indicating that they harbour magnetised halos. These halos are crucial to studies of galaxy evolution, galactic-scale outflows, and feedback from star formation activity. Identifying the magnetised halo of the Milky Way is challenging because of the potential contamination from foreground emission arising in local spiral arms. Additionally, it is unclear how our magnetic halo is influenced by recently revealed large-scale structures such as the X-ray emitting eROSITA Bubbles, which, according to previous simulations, might be transient structures powered by the Galactic Center or the Galaxy's star-forming ring. Here we report the identification of several kpc-scale magnetised structures based on their polarized radio emission and their gamma-ray counterparts, which can be interpreted as the radiation of relativistic electrons. These non-thermal structures extend far above and below the Galactic plane and are spatially coincident with the thermal X-ray emission from the eROSITA Bubbles. The morphological consistency of these structures suggests a common origin, which can be sustained by Galactic outflows driven by the active star-forming regions located at 3-5 kpc from the Galactic Centre. These results reveal how X-ray-emitting and magnetised halos of spiral galaxies can be related to intense star formation activities and suggest that the X-shaped coherent magnetic structures observed in their halos can stem from galaxy outflows., Comment: Initially submitted on March 2nd, 2024

Rota-Baxter operators on various structures have found important applications in diverse areas, from renormalization of quantum field theory to Yang-Baxter equations. Relative Rota-Baxter operators on Lie algebras are closely related to pre-Lie algebras and post-Lie algebras. Some of their group counterparts have been introduced to study post-groups, skew left braces and set-theoretic solutions of Yang-Baxter equations, but searching suitable notions of relative Rota-Baxter operators on groups with weight zero and pre-groups has been challenging and has been the focus of recent studies, by provisionally imposing an abelian condition. Arising from the works of Balinsky-Novikov and Gelfand-Dorfman, Novikov algebras and their constructions from differential commutative algebras have led to broad applications. Finding their suitable counterparts for groups and Lie algebras has also attracted quite much recent attention. This paper uses one-sided-inverse pairs of maps to give a perturbative approach to a general notion of relative Rota-Baxter operators and differential operators on a group and a Lie algebra with limit-weight. With the extra condition of limit-abelianess on the group or Lie algebra, we give an interpretation of relative Rota-Baxter and differential operators with weight zero. These operators motivate us to define pre-groups and Novikov groups respectively as the induced structures. The tangent maps of these operators are shown to give Rota-Baxter and differential operators with weight zero on Lie algebras. The tangent spaces of the pre-Lie and Novikov Lie groups are pre-Lie algebras and Novikov Lie algebras, fulfilling the expected property. Furthermore, limit-weight relative Rota-Baxter operators on groups give rise to skew left braces and then set-theoretic solutions of the Yang-Baxter equation., Comment: 29 pages. Comments welcome

Traditional partial differential equations with constant coefficients often struggle to capture abrupt changes in real-world phenomena, leading to the development of variable coefficient PDEs and Markovian switching models. Recently, research has introduced the concept of PDEs with Markov switching models, established their well-posedness and presented numerical methods. However, there has been limited discussion on parameter estimation for the jump coefficients in these models. This paper addresses this gap by focusing on parameter inference for the wave equation with Markovian switching. We propose a Bayesian statistical framework using discrete sparse Bayesian learning to establish its convergence and a uniform error bound. Our method requires fewer assumptions and enables independent parameter inference for each segment by allowing different underlying structures for the parameter estimation problem within each segmented time interval. The effectiveness of our approach is demonstrated through three numerical cases, which involve noisy spatiotemporal data from different wave equations with Markovian switching. The results show strong performance in parameter estimation for variable coefficient PDEs.

This paper introduces Multi-Garment Customized Model Generation, a unified framework based on Latent Diffusion Models (LDMs) aimed at addressing the unexplored task of synthesizing images with free combinations of multiple pieces of clothing. The method focuses on generating customized models wearing various targeted outfits according to different text prompts. The primary challenge lies in maintaining the natural appearance of the dressed model while preserving the complex textures of each piece of clothing, ensuring that the information from different garments does not interfere with each other. To tackle these challenges, we first developed a garment encoder, which is a trainable UNet copy with shared weights, capable of extracting detailed features of garments in parallel. Secondly, our framework supports the conditional generation of multiple garments through decoupled multi-garment feature fusion, allowing multiple clothing features to be injected into the backbone network, significantly alleviating conflicts between garment information. Additionally, the proposed garment encoder is a plug-and-play module that can be combined with other extension modules such as IP-Adapter and ControlNet, enhancing the diversity and controllability of the generated models. Extensive experiments demonstrate the superiority of our approach over existing alternatives, opening up new avenues for the task of generating images with multiple-piece clothing combinations

We propose two novel models in the framework of $f(Q)$ gravity to explain our accelerated universe, namely the exponential $f(Q)_{EXP}$ model and the hyperbolic tangent $f(Q)_{HT}$ model. The current cosmological electromagnetic observations including the cosmic microwave background anisotropies (CMB), the baryon acoustic oscillations(BAO), the type Ia supernovae (SN) and the direct measurements of H(z), combined with the simulated gravitational-wave data are used to constrain the $f(Q)$ models. We find that the Hubble tension can be significantly alleviated to $1.40\sigma$ level in the $f(Q)_{EXP}$ model. The fitting $\chi^2$ of the $f(Q)_{HT}$ model is $9.75\sigma$ poorer than that of the $f(Q)_{EXP}$ model, implying the $f(Q)_{HT}$ model would be excluded by future gravitational-wave observation., Comment: 10 pages, 4 figures

Elementary, but very useful lemma due to Biernacki and Krzy\.{z} (1955) asserts that the ratio of two power series inherits monotonicity from that of the sequence of ratios of their corresponding coefficients. Over the last two decades it has been realized that, under some additional assumptions, similar claims hold for more general series ratios as well as for unimodality in place of monotonicity. This paper continues this line of research: we consider ratios of general functional series and integral transforms and furnish natural sufficient conditions for preservation of unimodality by such ratios. Numerous series and integral transforms appearing in applications satisfy our sufficient conditions, including Dirichlet, factorial and inverse factorial series, Laplace, Mellin and generalized Stieltjes transforms, among many others. Finally, we illustrate our general results by exhibiting certain statements on monotonicity patterns for ratios of some special functions. The key role in our considerations is played by the notion of sign regularity., Comment: 17 pages, no figures

Self-supervised learning (SSL) has recently attracted significant attention in the field of recommender systems. Contrastive learning (CL) stands out as a major SSL paradigm due to its robust ability to generate self-supervised signals. Mainstream graph contrastive learning (GCL)-based methods typically implement CL by creating contrastive views through various data augmentation techniques. Despite these methods are effective, we argue that there still exist several challenges: i) Data augmentation (e.g., discarding edges or adding noise) necessitates additional graph convolution (GCN) or modeling operations, which are highly time-consuming and potentially harm the embedding quality. ii) Existing CL-based methods use traditional CL objectives to capture self-supervised signals. However, few studies have explored obtaining CL objectives from more perspectives and have attempted to fuse the varying signals from these CL objectives to enhance recommendation performance. To overcome these challenges, we propose a High-Order Fusion Graph Contrastive Learning (HFGCL) framework for recommendation. Specifically, we discards the data augmentations and instead high-order information from GCN process to create contrastive views. Additionally, to integrate self-supervised signals from various CL objectives, we propose an advanced CL objective. By ensuring that positive pairs are distanced from negative samples derived from both contrastive views, we effectively fuse self-supervised signals from distinct CL objectives, thereby enhancing the mutual information between positive pairs. Experimental results on three public datasets demonstrate the superior effectiveness of HFGCL compared to the state-of-the-art baselines.

This article addresses the problem of testing the conditional independence of two generic random vectors $X$ and $Y$ given a third random vector $Z$, which plays an important role in statistical and machine learning applications. We propose a new non-parametric testing procedure that avoids explicitly estimating any conditional distributions but instead requires sampling from the two marginal conditional distributions of $X$ given $Z$ and $Y$ given $Z$. We further propose using a generative neural network (GNN) framework to sample from these approximated marginal conditional distributions, which tends to mitigate the curse of dimensionality due to its adaptivity to any low-dimensional structures and smoothness underlying the data. Theoretically, our test statistic is shown to enjoy a doubly robust property against GNN approximation errors, meaning that the test statistic retains all desirable properties of the oracle test statistic utilizing the true marginal conditional distributions, as long as the product of the two approximation errors decays to zero faster than the parametric rate. Asymptotic properties of our statistic and the consistency of a bootstrap procedure are derived under both null and local alternatives. Extensive numerical experiments and real data analysis illustrate the effectiveness and broad applicability of our proposed test.

Contrastive Learning (CL)-based recommender systems have gained prominence in the context of Heterogeneous Graph (HG) due to their capacity to enhance the consistency of representations across different views. However, existing frameworks often neglect the fact that user-item interactions within HG are governed by diverse latent intents (e.g., brand preferences or demographic characteristics of item audiences), which are pivotal in capturing fine-grained relations. The exploration of these underlying intents, particularly through the lens of meta-paths in HGs, presents us with two principal challenges: i) How to integrate CL with intents; ii) How to mitigate noise from meta-path-driven intents. To address these challenges, we propose an innovative framework termed Intent-guided Heterogeneous Graph Contrastive Learning (IHGCL), which designed to enhance CL-based recommendation by capturing the intents contained within meta-paths. Specifically, the IHGCL framework includes: i) a meta-path-based Dual Contrastive Learning (DCL) approach to effectively integrate intents into the recommendation, constructing intent-intent contrast and intent-interaction contrast; ii) a Bottlenecked AutoEncoder (BAE) that combines mask propagation with the information bottleneck principle to significantly reduce noise perturbations introduced by meta-paths. Empirical evaluations conducted across six distinct datasets demonstrate the superior performance of our IHGCL framework relative to conventional baseline methods. Our model implementation is available at https://github.com/wangyu0627/IHGCL., Comment: 14pages, 11figures

Localization and delocalization are historic topics central to quantum and condensed matter physics. We discover a new delocalization mechanism attributed to a residue imaginary (part of) velocity $\operatorname{Im}(v)$, feasible for ground states or low-temperature states of non-Hermitian quantum systems under periodic boundary conditions. Interestingly, a disorder field contributing to $\operatorname{Im}(v)$ may allow strong-disorder-limit delocalization when $\operatorname{Im}(v)$ prevails over the Anderson localization. We demonstrate such delocalization with correlation and entanglement behaviors, as well as its many-body nature and generalizability to finite temperatures and interactions. Thus, the nontrivial physics of $\operatorname{Im}(v)$ significantly enriches our understanding of delocalization and breeds useful applications, e.g., in quantum adiabatic processes.

A family of subsets $\mathcal{F}$ is intersecting if $A \cap B \neq \emptyset$ for any $A, B \in \mathcal{F}$. In this paper, we show that for given integers $k > d \ge 2$ and $n \ge 2k+2d-3$, and any intersecting family $\mathcal{F}$ of $k$-subsets of $\{1, \cdots, n\}$, there exists a $d$-subset of $[n]$ contained in at most $\binom{n-d-1}{k-d-1}$ subsets of $\mathcal{F}$. This result, proved using spectral graph theory, gives a $d$-degree generalization of the celebrated Erd\H{o}s-Ko-Rado Theorem, improving a theorem of Kupavskii.

Deep & Cross Network and its derivative models have become an important paradigm for click-through rate (CTR) prediction due to their effective balance between computational cost and performance. However, these models face four major limitations: (1) the performance of existing explicit feature interaction methods is often weaker than that of implicit deep neural network (DNN), undermining their necessity; (2) many models fail to adaptively filter noise while increasing the order of feature interactions; (3) the fusion methods of most models cannot provide suitable supervision signals for their different sub-networks; (4) while most models claim to capture high-order feature interactions, they often do so implicitly and non-interpretably through DNN, which limits the trustworthiness of the model's predictions. To address the identified limitations, this paper proposes the next generation deep cross network: Deep Cross Network v3 (DCNv3), along with its two sub-networks: Linear Cross Network (LCN) and Exponential Cross Network (ECN) for CTR prediction. DCNv3 ensures interpretability in feature interaction modeling while linearly and exponentially increasing the order of feature interactions to achieve genuine Deep Crossing rather than just Deep & Cross. Additionally, we employ a Self-Mask operation to filter noise and reduce the number of parameters in the Cross Network by half. In the fusion layer, we use a simple yet effective multi-loss trade-off and calculation method, called Tri-BCE, to provide appropriate supervision signals. Comprehensive experiments on six datasets demonstrate the effectiveness, efficiency, and interpretability of DCNv3. The code, running logs, and detailed hyperparameter configurations are available at: https://github.com/salmon1802/DCNv3.

Offline reinforcement learning (RL) is an effective tool for real-world recommender systems with its capacity to model the dynamic interest of users and its interactive nature. Most existing offline RL recommender systems focus on model-based RL through learning a world model from offline data and building the recommendation policy by interacting with this model. Although these methods have made progress in the recommendation performance, the effectiveness of model-based offline RL methods is often constrained by the accuracy of the estimation of the reward model and the model uncertainties, primarily due to the extreme discrepancy between offline logged data and real-world data in user interactions with online platforms. To fill this gap, a more accurate reward model and uncertainty estimation are needed for the model-based RL methods. In this paper, a novel model-based Reward Shaping in Offline Reinforcement Learning for Recommender Systems, ROLeR, is proposed for reward and uncertainty estimation in recommendation systems. Specifically, a non-parametric reward shaping method is designed to refine the reward model. In addition, a flexible and more representative uncertainty penalty is designed to fit the needs of recommendation systems. Extensive experiments conducted on four benchmark datasets showcase that ROLeR achieves state-of-the-art performance compared with existing baselines. The source code can be downloaded at https://github.com/ArronDZhang/ROLeR., Comment: CIKM 2024

Recent years have witnessed increasing research attention towards pedestrian detection by taking the advantages of different sensor modalities (e.g. RGB, IR, Depth, LiDAR and Event). However, designing a unified generalist model that can effectively process diverse sensor modalities remains a challenge. This paper introduces MMPedestron, a novel generalist model for multimodal perception. Unlike previous specialist models that only process one or a pair of specific modality inputs, MMPedestron is able to process multiple modal inputs and their dynamic combinations. The proposed approach comprises a unified encoder for modal representation and fusion and a general head for pedestrian detection. We introduce two extra learnable tokens, i.e. MAA and MAF, for adaptive multi-modal feature fusion. In addition, we construct the MMPD dataset, the first large-scale benchmark for multi-modal pedestrian detection. This benchmark incorporates existing public datasets and a newly collected dataset called EventPed, covering a wide range of sensor modalities including RGB, IR, Depth, LiDAR, and Event data. With multi-modal joint training, our model achieves state-of-the-art performance on a wide range of pedestrian detection benchmarks, surpassing leading models tailored for specific sensor modality. For example, it achieves 71.1 AP on COCO-Persons and 72.6 AP on LLVIP. Notably, our model achieves comparable performance to the InternImage-H model on CrowdHuman with 30x smaller parameters. Codes and data are available at https://github.com/BubblyYi/MMPedestron., Comment: Accepted to ECCV'2024

This paper introduces Lite-SAM, an efficient end-to-end solution for the SegEvery task designed to reduce computational costs and redundancy. Lite-SAM is composed of four main components: a streamlined CNN-Transformer hybrid encoder (LiteViT), an automated prompt proposal network (AutoPPN), a traditional prompt encoder, and a mask decoder. All these components are integrated within the SAM framework. Our LiteViT, a high-performance lightweight backbone network, has only 1.16M parameters, which is a 23% reduction compared to the lightest existing backbone network Shufflenet. We also introduce AutoPPN, an innovative end-to-end method for prompt boxes and points generation. This is an improvement over traditional grid search sampling methods, and its unique design allows for easy integration into any SAM series algorithm, extending its usability. we have thoroughly benchmarked Lite-SAM across a plethora of both public and private datasets. The evaluation encompassed a broad spectrum of universal metrics, including the number of parameters, SegEvery execution time, and accuracy. The findings reveal that Lite-SAM, operating with a lean 4.2M parameters, significantly outpaces its counterparts, demonstrating performance improvements of 43x, 31x, 20x, 21x, and 1.6x over SAM, MobileSAM, Edge-SAM, EfficientViT-SAM, and MobileSAM-v2 respectively, all the while maintaining competitive accuracy. This underscores Lite-SAM's prowess in achieving an optimal equilibrium between performance and precision, thereby setting a new state-of-the-art(SOTA) benchmark in the domain., Comment: ECCV 2024 Accepted

In this paper, we consider the problem of prototype-based vision-language reasoning problem. We observe that existing methods encounter three major challenges: 1) escalating resource demands and prolonging training times, 2) contending with excessive learnable parameters, and 3) fine-tuning based only on a single modality. These challenges will hinder their capability to adapt Vision-Language Models (VLMs) to downstream tasks. Motivated by this critical observation, we propose a novel method called NODE-Adapter, which utilizes Neural Ordinary Differential Equations for better vision-language reasoning. To fully leverage both visual and textual modalities and estimate class prototypes more effectively and accurately, we divide our method into two stages: cross-modal prototype construction and cross-modal prototype optimization using neural ordinary differential equations. Specifically, we exploit VLM to encode hand-crafted prompts into textual features and few-shot support images into visual features. Then, we estimate the textual prototype and visual prototype by averaging the textual features and visual features, respectively, and adaptively combine the textual prototype and visual prototype to construct the cross-modal prototype. To alleviate the prototype bias, we then model the prototype optimization process as an initial value problem with Neural ODEs to estimate the continuous gradient flow. Our extensive experimental results, which cover few-shot classification, domain generalization, and visual reasoning on human-object interaction, demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches.

Recent studies empirically indicate that language models (LMs) encode rich world knowledge beyond mere semantics, attracting significant attention across various fields. However, in the recommendation domain, it remains uncertain whether LMs implicitly encode user preference information. Contrary to the prevailing understanding that LMs and traditional recommender models learn two distinct representation spaces due to a huge gap in language and behavior modeling objectives, this work rethinks such understanding and explores extracting a recommendation space directly from the language representation space. Surprisingly, our findings demonstrate that item representations, when linearly mapped from advanced LM representations, yield superior recommendation performance. This outcome suggests the homomorphism between the language representation space and an effective recommendation space, implying that collaborative signals may indeed be encoded within advanced LMs. Motivated by these findings, we propose a simple yet effective collaborative filtering (CF) model named AlphaRec, which utilizes language representations of item textual metadata (e.g., titles) instead of traditional ID-based embeddings. Specifically, AlphaRec is comprised of three main components: a multilayer perceptron (MLP), graph convolution, and contrastive learning (CL) loss function, making it extremely easy to implement and train. Our empirical results show that AlphaRec outperforms leading ID-based CF models on multiple datasets, marking the first instance of such a recommender with text embeddings achieving this level of performance. Moreover, AlphaRec introduces a new language-representation-based CF paradigm with several desirable advantages: being easy to implement, lightweight, rapid convergence, superior zero-shot recommendation abilities in new domains, and being aware of user intention., Comment: Codes are available at https://github.com/LehengTHU/AlphaRec

Quantum digital signatures (QDS), which utilize correlated bit strings among sender and recipients, guarantee the authenticity, integrity and non-repudiation of classical messages based on quantum laws. Continuous-variable (CV) quantum protocol with heterodyne and homodyne measurement has obvious advantages of low-cost implementation and easy wavelength division multiplexing. However, security analyses in previous researches are limited to the proof against collective attacks in finite-size scenarios. Moreover, existing multi-bit CV QDS schemes have primarily focused on adapting single-bit protocols for simplicity of security proof, often sacrificing signature efficiency. Here, we introduce a CV QDS protocol designed to withstand general coherent attacks through the use of a cutting-edge fidelity test function, while achieving high signature efficiency by employing a refined one-time universal hashing signing technique. Our protocol is proved to be robust against finite-size effects and excess noise in quantum channels. In simulation, results demonstrate a significant reduction of over 6 orders of magnitude in signature length for a megabit message signing task compared to existing CV QDS protocols and this advantage expands as the message size grows. Our work offers a solution with enhanced security and efficiency, paving the way for large-scale deployment of CV QDS in future quantum networks., Comment: 18 pages, 8 figures

In this paper, we propose Conceptual Codebook Learning (CoCoLe), a novel fine-tuning method for vision-language models (VLMs) to address the challenge of improving the generalization capability of VLMs while fine-tuning them on downstream tasks in a few-shot setting. We recognize that visual concepts, such as textures, shapes, and colors are naturally transferable across domains and play a crucial role in generalization tasks. Motivated by this interesting finding, we learn a conceptual codebook consisting of visual concepts as keys and conceptual prompts as values, which serves as a link between the image encoder's outputs and the text encoder's inputs. Specifically, for a given image, we leverage the codebook to identify the most relevant conceptual prompts associated with the class embeddings to perform the classification. Additionally, we incorporate a handcrafted concept cache as a regularization to alleviate the overfitting issues in low-shot scenarios. We observe that this conceptual codebook learning method is able to achieve enhanced alignment between visual and linguistic modalities. Extensive experimental results demonstrate that our CoCoLe method remarkably outperforms the existing state-of-the-art methods across various evaluation settings, including base-to-new generalization, cross-dataset evaluation, and domain generalization tasks. Detailed ablation studies further confirm the efficacy of each component in CoCoLe., Comment: Accepted by ECCV 2024

The classical Serrin's overdetermined theorem states that a $C^2$ bounded domain, which admits a function with constant Laplacian that satisfies both constant Dirichlet and Neumann boundary conditions, must necessarily be a ball. While extensions of this theorem to non-smooth domains have been explored since the 1990s, the applicability of Serrin's theorem to Lipschitz domains remained unresolved. This paper answers this open question affirmatively. Actually, our approach shows that the result holds for domains that are sets of finite perimeter with a uniform upper bound on the density, and it also allows for slit discontinuities., Comment: 17 Pages

In this paper, we analyze the spectral energy distributions (SEDs) of 17 powerful (with a spin-down luminosity greater than $10^{35}$ erg s$^{-1}$) young (with an age less than 15000 yrs) pulsar wind nebulae (PWNe) using a simple time-independent one-zone emission model. Our aim is to investigate correlations between model parameters and the ages of the corresponding PWNe, thereby revealing the evolution of high-energy electron distributions within PWNe. Our findings are as follows: (1) The electron distributions in PWNe can be characterized by a double power-law with a superexponential cutoff; (2) As PWNe evolve, the high-energy end of the electron distribution spectrum becomes harder with the index decreasing from approximately 3.5 to 2.5, while the low-energy end spectrum index remains constant near 1.5; (3) There is no apparent correlation between the break energy or cutoff energy and the age of PWNe. (4) The average magnetic field within PWNe decreases with age, leading to a positive correlation between the energy loss timescale of electrons at the break energy or the high-energy cutoff, and the age of the PWN. (5) The total electron energy within PWNe remains constant near $2 \times 10^{48}$ erg, while the total magnetic energy decreases with age., Comment: 19 pages, 20 figures, 1 table accepted for publication in RAA

We investigate the coupling effects of the two-phase interface, viscosity ratio, and density ratio of the dispersed phase to the continuous phase on the flow statistics in two-phase Taylor-Couette turbulence at a system Reynolds number of 6000 and a system Weber number of 10 using interface-resolved three-dimensional direct numerical simulations with the volume-of-fluid method. Our study focuses on four different scenarios: neutral droplets, low-viscosity droplets, light droplets, and low-viscosity light droplets. We find that neutral droplets and low-viscosity droplets primarily contribute to drag enhancement through the two-phase interface, while light droplets reduce the system's drag by explicitly reducing Reynolds stress due to the density dependence of Reynolds stress. Additionally, low-viscosity light droplets contribute to greater drag reduction by further reducing momentum transport near the inner cylinder and implicitly reducing Reynolds stress. While interfacial tension enhances turbulent kinetic energy (TKE) transport, drag enhancement is not strongly correlated with TKE transport for both neutral droplets and low-viscosity droplets. Light droplets primarily reduce the production term by diminishing Reynolds stress, whereas the density contrast between the phases boosts TKE transport near the inner wall. Therefore, the reduction in the dissipation rate is predominantly attributed to decreased turbulence production, causing drag reduction. For low-viscosity light droplets, the production term diminishes further, primarily due to their greater reduction in Reynolds stress, while reduced viscosity weakens the density difference's contribution to TKE transport near the inner cylinder, resulting in a more pronounced reduction in the dissipation rate and consequently stronger drag reduction. Our findings provide new insights into the turbulence modulation in two-phase flow.

Decays $B\to DP\ell^+\nu_\ell~(\ell=e,\mu,\tau)$ with the non-resonance, the charmed vector resonances, the charmed scalar resonances and the charmed tensor resonances are calculated by using the SU(3) flavor symmetry. Firstly, the decay amplitudes of different modes are related by the SU(3) flavor symmetry. Then, relevant experiential data are used to constrain nonperturbative coefficients in the non-resonant and various resonant $B\to DP\ell^+\nu_\ell$ decays. Finally, using the constrained nonperturbative coefficients, the branching ratios of not-yet-measured $B\to D^*P\ell^+\nu_\ell$ decays with the non-resonant and various charmed resonant contributions are predicted. Many branching ratios are predicted for the first time. We find that $B\to D\eta'\ell^+\nu_\ell, B_s\to D_s\eta'\ell^+\nu_\ell$ decays only receive the non-resonant contributions, $B\to D_sK\ell^+\nu_\ell$, $B_s\to DK\ell^+\nu_\ell$, $B\to D\eta\ell^+\nu_\ell$ and $B_s\to D_s\eta\ell^+\nu_\ell$ decays receive both non-resonant and charmed tensor resonant contributions, $B^+\to D^-\pi^+\ell^+\nu_\ell$ decays receive the non-resonant, the charmed scalar resonant and the charmed tensor resonant contributions, and other $B\to D\pi\ell^+\nu_\ell$ decays receive all four kinds of contributions. These results can be used to test the SU(3) flavor symmetry approach in the four-body semileptonic decays by the future LHCb and Belle-II experiments., Comment: 16 pages. arXiv admin note: text overlap with arXiv:2403.14929

Pulsations from the Crab pulsar have been detected by the MAGIC telescopes at energies up to 1.5 TeV, and the pulsed emission from the Vela pulsar was detected by H.E.S.S., reaching tens of TeV. These discoveries, along with the proposed additional emission due to inverse Compton scattering at TeV energies, lead us to consider suitable candidates for detection with current and future extensive air show (EAS) experiments at very-high-energy (VHE; 0.1 $-$ 100 TeV) ranges. Leveraging energy spectrum data from pulsars as observed by Fermi and Imaging Atmospheric Cherenkov Telescopes (IACTs) and considering the sensitivities of both LHAASO and SWGO, this study evaluates their detectability and estimates the time required for their significant detection. Our results indicate that LHAASO could detect the Crab's pulsed signal within six years, while SWGO might detect Vela's signal within one year. Observations of the most energetic Fermi pulsars with EAS experiments will provide insight into the nature of VHE pulsar emissions, helping to clarify the primary characteristics of VHE pulsars., Comment: 6 pages, 3 figures, 2 Tables and accepted for publication in MNRAS

Using $(27.12\pm 0.14)\times10^8$ $\psi(3686)$ decays and data samples of $e^+e^-$ collisions with $\sqrt{s}$ from 4.130 to 4.780~GeV collected with the BESIII detector, we report the first observation of the electromagnetic Dalitz transition $h_c\to e^+e^-\eta_c$ with a statistical significance of $5.4\sigma$. We measure the ratio of the branching fractions $\frac{\mathcal{B}(h_c\rightarrow e^+e^-\eta_c)}{\mathcal{B}(h_c\rightarrow \gamma \eta_c)}$ separately for the $h_c$ samples produced via $\psi(3686)\to\pi^0h_c$ and $e^+e^-\to\pi^+\pi^-h_c$. The average ratio is determined to be $(0.59\pm0.10(\text{stat.})\pm0.04(\text{syst.}))\%$, where the uncertainty includes both statistical and systematic components.

Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. This work is based on the following interesting finding: in transformer-based image classification, the class token at the first transformer encoder layer can be learned to capture the domain-specific characteristics of target samples during test-time adaptation. This learned token, when combined with input image patch embeddings, is able to gradually remove the domain-specific information from the feature representations of input samples during the transformer encoding process, thereby significantly improving the test-time adaptation performance of the source model across different domains. We refer to this class token as visual conditioning token (VCT). To successfully learn the VCT, we propose a bi-level learning approach to capture the long-term variations of domain-specific characteristics while accommodating local variations of instance-specific characteristics. Experimental results on the benchmark datasets demonstrate that our proposed bi-level visual conditioning token learning method is able to achieve significantly improved test-time adaptation performance by up to 1.9%.

Graphical User Interfaces (GUIs) are central to our interaction with digital devices. Recently, growing efforts have been made to build models for various GUI understanding tasks. However, these efforts largely overlook an important GUI-referring task: screen reading based on user-indicated points, which we name the Screen Point-and-Read (SPR) task. This task is predominantly handled by rigid accessible screen reading tools, in great need of new models driven by advancements in Multimodal Large Language Models (MLLMs). In this paper, we propose a Tree-of-Lens (ToL) agent, utilizing a novel ToL grounding mechanism, to address the SPR task. Based on the input point coordinate and the corresponding GUI screenshot, our ToL agent constructs a Hierarchical Layout Tree. Based on the tree, our ToL agent not only comprehends the content of the indicated area but also articulates the layout and spatial relationships between elements. Such layout information is crucial for accurately interpreting information on the screen, distinguishing our ToL agent from other screen reading tools. We also thoroughly evaluate the ToL agent against other baselines on a newly proposed SPR benchmark, which includes GUIs from mobile, web, and operating systems. Last but not least, we test the ToL agent on mobile GUI navigation tasks, demonstrating its utility in identifying incorrect actions along the path of agent execution trajectories. Code and data: screen-point-and-read.github.io

Image registration is essential for medical image applications where alignment of voxels across multiple images is needed for qualitative or quantitative analysis. With recent advancements in deep neural networks and parallel computing, deep learning-based medical image registration methods become competitive with their flexible modelling and fast inference capabilities. However, compared to traditional optimization-based registration methods, the speed advantage may come at the cost of registration performance at inference time. Besides, deep neural networks ideally demand large training datasets while optimization-based methods are training-free. To improve registration accuracy and data efficiency, we propose a novel image registration method, termed Recurrent Inference Image Registration (RIIR) network. RIIR is formulated as a meta-learning solver to the registration problem in an iterative manner. RIIR addresses the accuracy and data efficiency issues, by learning the update rule of optimization, with implicit regularization combined with explicit gradient input. We evaluated RIIR extensively on brain MRI and quantitative cardiac MRI datasets, in terms of both registration accuracy and training data efficiency. Our experiments showed that RIIR outperformed a range of deep learning-based methods, even with only $5\%$ of the training data, demonstrating high data efficiency. Key findings from our ablation studies highlighted the important added value of the hidden states introduced in the recurrent inference framework for meta-learning. Our proposed RIIR offers a highly data-efficient framework for deep learning-based medical image registration., Comment: Preprint

Quantitative $T_1$ mapping by MRI is an increasingly important tool for clinical assessment of cardiovascular diseases. The cardiac $T_1$ map is derived by fitting a known signal model to a series of baseline images, while the quality of this map can be deteriorated by involuntary respiratory and cardiac motion. To correct motion, a template image is often needed to register all baseline images, but the choice of template is nontrivial, leading to inconsistent performance sensitive to image contrast. In this work, we propose a novel deep-learning-based groupwise registration framework, which omits the need for a template, and registers all baseline images simultaneously. We design two groupwise losses for this registration framework: the first is a linear principal component analysis (PCA) loss that enforces alignment of baseline images irrespective of the intensity variation, and the second is an auxiliary relaxometry loss that enforces adherence of intensity profile to the signal model. We extensively evaluated our method, termed ``PCA-Relax'', and other baseline methods on an in-house cardiac MRI dataset including both pre- and post-contrast $T_1$ sequences. All methods were evaluated under three distinct training-and-evaluation strategies, namely, standard, one-shot, and test-time-adaptation. The proposed PCA-Relax showed further improved performance of registration and mapping over well-established baselines. The proposed groupwise framework is generic and can be adapted to applications involving multiple images., Comment: MICCAI 2024. Contents may slightly differ from the camera-ready version

The same real-life questions posed to different individuals may lead to different answers based on their unique situations. For instance, whether a student is eligible for a scholarship depends on eligibility conditions, such as major or degree required. ConditionalQA was proposed to evaluate models' capability of reading a document and answering eligibility questions, considering unmentioned conditions. However, it is limited to questions on single documents, neglecting harder cases that may require cross-document reasoning and optimization, for example, "What is the maximum number of scholarships attainable?" Such questions over multiple documents are not only more challenging due to more context having to understand, but also because the model has to (1) explore all possible combinations of unmentioned conditions and (2) understand the relationship between conditions across documents, to reason about the optimal outcome. To evaluate models' capability of answering such questions, we propose a new dataset MDCR, which can reflect real-world challenges and serve as a new test bed for complex conditional reasoning that requires optimization. We evaluate this dataset using the most recent LLMs and demonstrate their limitations in solving this task. We believe this dataset will facilitate future research in answering optimization questions with unknown conditions.

Large Language Models (LLMs) are increasingly employed in zero-shot documents ranking, yielding commendable results. However, several significant challenges still persist in LLMs for ranking: (1) LLMs are constrained by limited input length, precluding them from processing a large number of documents simultaneously; (2) The output document sequence is influenced by the input order of documents, resulting in inconsistent ranking outcomes; (3) Achieving a balance between cost and ranking performance is quite challenging. To tackle these issues, we introduce a novel documents ranking method called TourRank, which is inspired by the tournament mechanism. This approach alleviates the impact of LLM's limited input length through intelligent grouping, while the tournament-like points system ensures robust ranking, mitigating the influence of the document input sequence. We test TourRank with different LLMs on the TREC DL datasets and the BEIR benchmark. Experimental results show that TourRank achieves state-of-the-art performance at a reasonable cost.

Using the gauge-gravity duality, we investigate the fermionic correlation function in the D(-1)-D3 brane system which describes the instantonic plasma in holography. In this system, the charge of the D(-1) brane as the D-instanton gives the gluon condensate. To simplify the holographic setup, we first reduce briefly the ten-dimensional supergravity background produced by D(-1)-D3-branes to an equivalently five-dimensional background. Then using the standard method for computing the Green function in the AdS/CFT dictionary, we derive the equations for the fermionic correlation functions and solve them numerically with the infalling boundary condition. Our numerical results illustrate that the fermionic correlation function as spectral function includes two branches of the dispersion curves whose behavior is very close to the results obtained from the method of hard thermal loop. And the effective mass generated by the medium effect of fermion splits into two values due to the spin-dependent interactions induced by instantons. Therefore, this work in holography demonstrates the instantonic configuration is very influential to the fermionic plasmino in plasma., Comment: 19 pages, 5 figures

In recent years, accelerated extra-gradient methods have attracted much attention by researchers, for solving monotone inclusion problems. A limitation of most current accelerated extra-gradient methods lies in their direct utilization of the initial point, which can potentially decelerate numerical convergence rate. In this work, we present a new accelerated extra-gradient method, by utilizing the symplectic acceleration technique. We establish the inverse of quadratic convergence rate by employing the Lyapunov function technique. Also, we demonstrate a faster inverse of quadratic convergence rate alongside its weak convergence property under stronger assumptions. To improve practical efficiency, we introduce a line search technique for our symplectic extra-gradient method. Theoretically, we prove the convergence of the symplectic extra-gradient method with line search. Numerical tests show that this adaptation exhibits faster convergence rates in practice compared to several existing extra-gradient type methods., Comment: 37 pages, 7 figures, 1 table

In this work we try to search for signals generated by ultra-heavy dark matter at the Large High Altitude Air Shower Observatory (LHAASO) data. We look for possible gamma-ray by dark matter annihilation or decay from 16 dwarf spheroidal galaxies in the field of view of LHAASO. Dwarf spheroidal galaxies are among the most promising targets for indirect detection of dark matter which have low fluxes of astrophysical $\gamma$-ray background while large amount of dark matter. By analyzing more than 700 days observational data at LHAASO, no significant dark matter signal from 1 TeV to 1 EeV is detected. Accordingly we derive the most stringent constraints on the ultra-heavy dark matter annihilation cross-section up to EeV. The constraints on the lifetime of dark matter in decay mode are also derived., Comment: 17 pages, 12 figures, accepted by PRL

Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where the image consists of global and local branches, with the latter being the sliced image patches but resized to the same resolution as the former. This means that higher resolution requires more local patches, resulting in exorbitant computational expenses, and meanwhile, the dominance of local image tokens may diminish the global context. In this paper, we dive into the problems and propose a new framework as well as an elaborate optimization strategy. Specifically, we extract contextual information from the global view using a mixture of adapters, based on the observation that different adapters excel at different tasks. With regard to local patches, learnable query embeddings are introduced to reduce image tokens, the most important tokens accounting for the user question will be further selected by a similarity-based selector. Our empirical results demonstrate a `less is more' pattern, where \textit{utilizing fewer but more informative local image tokens leads to improved performance}. Besides, a significant challenge lies in the training strategy, as simultaneous end-to-end training of the global mining block and local compression block does not yield optimal results. We thus advocate for an alternating training way, ensuring balanced learning between global and local aspects. Finally, we also introduce a challenging dataset with high requirements for image detail, enhancing the training of the local compression layer. The proposed method, termed LMM with Sophisticated Tasks, Local image compression, and Mixture of global Experts (SliME), achieves leading performance across various benchmarks with only 2 million training data., Comment: Project page: https://github.com/yfzhang114/SliME

The inverse scattering transform for the defocusing-defocusing coupled Hirota equations with non-zero boundary conditions at infinity is thoroughly discussed. We delve into the analytical properties of the Jost eigenfunctions and scrutinize the characteristics of the scattering coefficients. To enhance our investigation of the fundamental eigenfunctions, we have derived additional auxiliary eigenfunctions with the help of the adjoint problem. Two symmetry conditions are studied to constrain the behavior of the eigenfunctions and scattering coefficients. Utilizing these symmetries, we precisely delineate the discrete spectrum and establish the associated symmetries of the scattering data. By framing the inverse problem within the context of the Riemann-Hilbert problem, we develop suitable jump conditions to express the eigenfunctions. Consequently, we deduce the pure soliton solutions from the defocusing-defocusing coupled Hirota equations, and the double-poles solutions are provided explicitly for the first time in this work.

For a convex set $K\subset \mathbb R^n$ and the associated anisotropic perimeter $P_K$, we establish that every $(\epsilon,\,r)$-minimizer for $P_K$ satisfies a local John property. Furthermore, we prove that a certain class of John domains, including $(\epsilon,\,r)$-minimizers close to $K$, admits a trace inequality. As a consequence, we provide a more concrete proof for a crucial step in the quantitative Wulff inequality, thereby complementing the seminal work of Figalli, Maggi, and Pratelli., Comment: 22 Pages

We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets (represented by Neural Radiance Fields) from text prompts. Unlike recent 3D generative models that rely on clean and well-aligned 3D data, limiting them to single or few-class generation, our model is directly trained on extensive noisy and unaligned `in-the-wild' 3D assets, mitigating the key challenge (i.e., data scarcity) in large-scale 3D generation. In particular, DIRECT-3D is a tri-plane diffusion model that integrates two innovations: 1) A novel learning framework where noisy data are filtered and aligned automatically during the training process. Specifically, after an initial warm-up phase using a small set of clean data, an iterative optimization is introduced in the diffusion process to explicitly estimate the 3D pose of objects and select beneficial data based on conditional density. 2) An efficient 3D representation that is achieved by disentangling object geometry and color features with two separate conditional diffusion models that are optimized hierarchically. Given a prompt input, our model generates high-quality, high-resolution, realistic, and complex 3D objects with accurate geometric details in seconds. We achieve state-of-the-art performance in both single-class generation and text-to-3D generation. We also demonstrate that DIRECT-3D can serve as a useful 3D geometric prior of objects, for example to alleviate the well-known Janus problem in 2D-lifting methods such as DreamFusion. The code and models are available for research purposes at: https://github.com/qihao067/direct3d., Comment: Accepted to CVPR 2024. Code: https://github.com/qihao067/direct3d Project page: https://direct-3d.github.io/

Multimodal large language models (MLLMs), initiated with a trained LLM, first align images with text and then fine-tune on multimodal mixed inputs. However, the MLLM catastrophically forgets the text-only instructions, which do not include images and can be addressed within the initial LLM. In this paper, we present Wings, a novel MLLM that excels in both text-only dialogues and multimodal comprehension. Analyzing MLLM attention in multimodal instructions reveals that text-only forgetting is related to the attention shifts from pre-image to post-image text. From that, we construct extra modules that act as the boosted learner to compensate for the attention shift. The complementary visual and textual learners, like "wings" on either side, are connected in parallel within each layer's attention block. Initially, image and text inputs are aligned with visual learners operating alongside the main attention, balancing focus on visual elements. Textual learners are later collaboratively integrated with attention-based routing to blend the outputs of the visual and textual learners. We design the Low-Rank Residual Attention (LoRRA) to guarantee high efficiency for learners. Our experimental results demonstrate that Wings outperforms equally-scaled MLLMs in both text-only and visual question-answering tasks. On a newly constructed Interleaved Image-Text (IIT) benchmark, Wings exhibits superior performance from text-only-rich to multimodal-rich question-answering tasks.

The potential for improvements brought by Large Language Models (LLMs) in Text-to-SQL systems is mostly assessed on monolingual English datasets. However, LLMs' performance for other languages remains vastly unexplored. In this work, we release the StatBot.Swiss dataset, the first bilingual benchmark for evaluating Text-to-SQL systems based on real-world applications. The StatBot.Swiss dataset contains 455 natural language/SQL-pairs over 35 big databases with varying level of complexity for both English and German. We evaluate the performance of state-of-the-art LLMs such as GPT-3.5-Turbo and mixtral-8x7b-instruct for the Text-to-SQL translation task using an in-context learning approach. Our experimental analysis illustrates that current LLMs struggle to generalize well in generating SQL queries on our novel bilingual dataset., Comment: This work is accepted at ACL Findings 2024

The long-tail distribution of real driving data poses challenges for training and testing autonomous vehicles (AV), where rare yet crucial safety-critical scenarios are infrequent. And virtual simulation offers a low-cost and efficient solution. This paper proposes a near-miss focused training framework for AV. Utilizing the driving scenario information provided by sensors in the simulator, we design novel reward functions, which enable background vehicles (BV) to generate near-miss scenarios and ensure gradients exist not only in collision-free scenes but also in collision scenarios. And then leveraging the Robust Adversarial Reinforcement Learning (RARL) framework for simultaneous training of AV and BV to gradually enhance AV and BV capabilities, as well as generating near-miss scenarios tailored to different levels of AV capabilities. Results from three testing strategies indicate that the proposed method generates scenarios closer to near-miss, thus enhancing the capabilities of both AVs and BVs throughout training.

This paper proposes a programmable multi-input buck-boost structure method, which can enhance the operation tolerance for the PV array under extremely harsh climatic conditions. The proposed structure based on a traditional two switches buck-boost converter can connect PV panels in parallel and cascade flexibly, and also enable the individual operation of each PV panel. The active switches can be programmed to change the connection structures as well as achieve the maximum power point track of PV panels simultaneously. The paper presents the programming method for an exemplified scalable structure converter for two PV panels. The simulation has been established in MATLAB/Simulink to validate the performance of the proposed converter in terms of multiplexing function, wide operating range of PV panels, and low switching stress., Comment: This work has been accepted by the conference proceedings of IPEMC 2024-ECCE Asia

Existing mainstream approaches follow the encoder-decoder paradigm for generating radiology reports. They focus on improving the network structure of encoders and decoders, which leads to two shortcomings: overlooking the modality gap and ignoring report content constraints. In this paper, we proposed Textual Inversion and Self-supervised Refinement (TISR) to address the above two issues. Specifically, textual inversion can project text and image into the same space by representing images as pseudo words to eliminate the cross-modeling gap. Subsequently, self-supervised refinement refines these pseudo words through contrastive loss computation between images and texts, enhancing the fidelity of generated reports to images. Notably, TISR is orthogonal to most existing methods, plug-and-play. We conduct experiments on two widely-used public datasets and achieve significant improvements on various baselines, which demonstrates the effectiveness and generalization of TISR. The code will be available soon., Comment: This paper has been early accepted by MICCAI 2024!

Multi-modal object detection in autonomous driving has achieved great breakthroughs due to the usage of fusing complementary information from different sensors. The calibration in fusion between sensors such as LiDAR and camera is always supposed to be precise in previous work. However, in reality, calibration matrices are fixed when the vehicles leave the factory, but vibration, bumps, and data lags may cause calibration bias. As the research on the calibration influence on fusion detection performance is relatively few, flexible calibration dependency multi-sensor detection method has always been attractive. In this paper, we conducted experiments on SOTA detection method EPNet++ and proved slight bias on calibration can reduce the performance seriously. We also proposed a re-calibration model based on semantic segmentation which can be combined with a detection algorithm to improve the performance and robustness of multi-modal calibration bias., Comment: 10 pages, 6 figures

To generate data from trained diffusion models, most inference algorithms, such as DDPM, DDIM, and other variants, rely on discretizing the reverse SDEs or their equivalent ODEs. In this paper, we view such approaches as decomposing the entire denoising diffusion process into several segments, each corresponding to a reverse transition kernel (RTK) sampling subproblem. Specifically, DDPM uses a Gaussian approximation for the RTK, resulting in low per-subproblem complexity but requiring a large number of segments (i.e., subproblems), which is conjectured to be inefficient. To address this, we develop a general RTK framework that enables a more balanced subproblem decomposition, resulting in $\tilde O(1)$ subproblems, each with strongly log-concave targets. We then propose leveraging two fast sampling algorithms, the Metropolis-Adjusted Langevin Algorithm (MALA) and Underdamped Langevin Dynamics (ULD), for solving these strongly log-concave subproblems. This gives rise to the RTK-MALA and RTK-ULD algorithms for diffusion inference. In theory, we further develop the convergence guarantees for RTK-MALA and RTK-ULD in total variation (TV) distance: RTK-ULD can achieve $\epsilon$ target error within $\tilde{\mathcal O}(d^{1/2}\epsilon^{-1})$ under mild conditions, and RTK-MALA enjoys a $\mathcal{O}(d^{2}\log(d/\epsilon))$ convergence rate under slightly stricter conditions. These theoretical results surpass the state-of-the-art convergence rates for diffusion inference and are well supported by numerical experiments., Comment: 68 pages, 2 figures

We study the efficacy of Small Language Models (SLMs) in facilitating application usage through natural language interactions. Our focus here is on a particular internal application used in Microsoft for cloud supply chain fulfilment. Our experiments show that small models can outperform much larger ones in terms of both accuracy and running time, even when fine-tuned on small datasets. Alongside these results, we also highlight SLM-based system design considerations.