Search

Mathematical reasoning presents a significant challenge to the cognitive capabilities of LLMs. Various methods have been proposed to enhance the mathematical ability of LLMs. However, few recognize the value of state transition for LLM reasoning. In this work, we define mathematical problem-solving as a process of transiting from an initial unsolved state to the final resolved state, and propose Kwai-STaR framework, which transforms LLMs into State-Transition Reasoners to improve their intuitive reasoning capabilities. Our approach comprises three main steps: (1) Define the state space tailored to the mathematical reasoning. (2) Generate state-transition data based on the state space. (3) Convert original LLMs into State-Transition Reasoners via a curricular training strategy. Our experiments validate the effectiveness of Kwai-STaR in enhancing mathematical reasoning: After training on the small-scale Kwai-STaR dataset, general LLMs, including Mistral-7B and LLaMA-3, achieve considerable performance gain on the GSM8K and GSM-Hard dataset. Additionally, the state transition-based design endows Kwai-STaR with remarkable training and inference efficiency. Further experiments are underway to establish the generality of Kwai-STaR., Comment: 6 pages, 2 figures

In this paper, we present \textbf{\textit{FasterCache}}, a novel training-free strategy designed to accelerate the inference of video diffusion models with high-quality generation. By analyzing existing cache-based methods, we observe that \textit{directly reusing adjacent-step features degrades video quality due to the loss of subtle variations}. We further perform a pioneering investigation of the acceleration potential of classifier-free guidance (CFG) and reveal significant redundancy between conditional and unconditional features within the same timestep. Capitalizing on these observations, we introduce FasterCache to substantially accelerate diffusion-based video generation. Our key contributions include a dynamic feature reuse strategy that preserves both feature distinction and temporal continuity, and CFG-Cache which optimizes the reuse of conditional and unconditional outputs to further enhance inference speed without compromising video quality. We empirically evaluate FasterCache on recent video diffusion models. Experimental results show that FasterCache can significantly accelerate video generation (\eg 1.67$\times$ speedup on Vchitect-2.0) while keeping video quality comparable to the baseline, and consistently outperform existing methods in both inference speed and video quality.

In recent years, there has been growing interest in the field of functional neural networks. They have been proposed and studied with the aim of approximating continuous functionals defined on sets of functions on Euclidean domains. In this paper, we consider functionals defined on sets of functions on spheres. The approximation ability of deep ReLU neural networks is investigated by novel spherical analysis using an encoder-decoder framework. An encoder comes up first to accommodate the infinite-dimensional nature of the domain of functionals. It utilizes spherical harmonics to help us extract the latent finite-dimensional information of functions, which in turn facilitates in the next step of approximation analysis using fully connected neural networks. Moreover, real-world objects are frequently sampled discretely and are often corrupted by noise. Therefore, encoders with discrete input and those with discrete and random noise input are constructed, respectively. The approximation rates with different encoder structures are provided therein.

The development of Artificial Intelligence (AI) Large Models has a great impact on the application development of automotive Intelligent cockpit. The fusion development of Intelligent Cockpit and Large Models has become a new growth point of user experience in the industry, which also creates problems for related scholars, practitioners and users in terms of their understanding and evaluation of the user experience and the capability characteristics of the Intelligent Cockpit Large Models (ICLM). This paper aims to analyse the current situation of Intelligent cockpit, large model and AI Agent, to reveal the key of application research focuses on the integration of Intelligent Cockpit and Large Models, and to put forward a necessary limitation for the subsequent development of an evaluation system for the capability of automotive ICLM and user experience. The evaluation system, P-CAFE, proposed in this paper mainly proposes five dimensions of perception, cognition, action, feedback and evolution as the first-level indicators from the domains of cognitive architecture, user experience, and capability characteristics of large models, and many second-level indicators to satisfy the current status of the application and research focuses are selected. After expert evaluation, the weights of the indicators were determined, and the indicator system of P-CAFE was established. Finally, a complete evaluation method was constructed based on Fuzzy Hierarchical Analysis. It will lay a solid foundation for the application and evaluation of the automotive ICLM, and provide a reference for the development and improvement of the future ICLM., Comment: 21pages, 5 figures

Context: With the waning of Moore's Law, the software industry is placing increasing importance on finding alternative solutions for continuous performance enhancement. The significance and research results of software performance optimization have been on the rise in recent years, especially with the advancement propelled by Large Language Models(LLMs). However, traditional strategies for rectifying performance flaws have shown significant limitations at the competitive code efficiency optimization level, and research on this topic is surprisingly scarce. Objective: This study aims to address the research gap in this domain, offering practical solutions to the various challenges encountered. Specifically, we have overcome the constraints of traditional performance error rectification strategies and developed a Language Model (LM) tailored for the competitive code efficiency optimization realm. Method: We introduced E-code, an advanced program synthesis LM. Inspired by the recent success of expert LMs, we designed an innovative structure called the Expert Encoder Group. This structure employs multiple expert encoders to extract features tailored for different input types. We assessed the performance of E-code against other leading models on a competitive dataset and conducted in-depth ablation experiments. Results: Upon systematic evaluation, E-code achieved a 54.98% improvement in code efficiency, significantly outperforming other advanced models. In the ablation experiments, we further validated the significance of the expert encoder group and other components within E-code. Conclusion: The research findings indicate that the expert encoder group can effectively handle various inputs in efficiency optimization tasks, significantly enhancing the model's performance.

Recent advancements in autonomous driving, augmented reality, robotics, and embodied intelligence have necessitated 3D perception algorithms. However, current 3D perception methods, particularly small models, struggle with processing logical reasoning, question-answering, and handling open scenario categories. On the other hand, generative multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks, due to weak spatial and local object perception, poor text-based geometric numerical output, and inability to handle camera focal variations. To address these challenges, we propose the following solutions: Spatial-Enhanced Local Feature Mining for better spatial feature extraction, 3D Query Token-Derived Info Decoding for precise geometric regression, and Geometry Projection-Based 3D Reasoning for handling camera focal length variations. We employ parameter-efficient fine-tuning for a pre-trained MLLM and develop LLMI3D, a powerful 3D perception MLLM. Additionally, we have constructed the IG3D dataset, which provides fine-grained descriptions and question-answer annotations. Extensive experiments demonstrate that our LLMI3D achieves state-of-the-art performance, significantly outperforming existing methods.

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Posters play a crucial role in marketing and advertising by enhancing visual communication and brand visibility, making significant contributions to industrial design. With the latest advancements in controllable T2I diffusion models, increasing research has focused on rendering text within synthesized images. Despite improvements in text rendering accuracy, the field of automatic poster generation remains underexplored. In this paper, we propose an automatic poster generation framework with text rendering capabilities leveraging LLMs, utilizing a triple-cross attention mechanism based on alignment learning. This framework aims to create precise poster text within a detailed contextual background. Additionally, the framework supports controllable fonts, adjustable image resolution, and the rendering of posters with descriptions and text in both English and Chinese.Furthermore, we introduce a high-resolution font dataset and a poster dataset with resolutions exceeding 1024 pixels. Our approach leverages the SDXL architecture. Extensive experiments validate our method's capability in generating poster images with complex and contextually rich backgrounds.Codes is available at https://github.com/OPPO-Mente-Lab/GlyphDraw2.

With the advancement of deep learning techniques, the performance of Automatic Program Repair(APR) techniques has reached a new level. Previous deep learning-based APR techniques essentially modified program sentences in the Autoregressive(AR) manner, which predicts future values based on past values. Due to the manner of word-by-word generation, the AR-based APR technique has a huge time delay. This negative consequence overshadows the widespread adoption of APR techniques in real-life software development. To address the issue, we aim to apply the Non-Autoregressive(NAR) method to the APR task, which can output target code in a parallel manner to avoid huge inference delays. To effectively adapt the NAR manner for the APR task, we in this paper propose NARRepair, the first customized NAR code generation model for the APR task. The NARRepair features three major novelties, including 1) using repair actions to alleviate the over-correction issue, 2) extracting dependency information from AST to alleviate the issue of lacking inter-word dependency information, 3) employing two-stage decoding to alleviate the issue of lacking contextual information. We evaluated NARRepair on three widely used datasets in the APR community, and the results show that our technique can significantly improve the inference speed while maintaining high repair accuracy.

Commit Message Generation (CMG) approaches aim to automatically generate commit messages based on given code diffs, which facilitate collaboration among developers and play a critical role in Open-Source Software (OSS). Very recently, Large Language Models (LLMs) have demonstrated extensive applicability in diverse code-related task. But few studies systematically explored their effectiveness using LLMs. This paper conducts the first comprehensive experiment to investigate how far we have been in applying LLM to generate high-quality commit messages. Motivated by a pilot analysis, we first clean the most widely-used CMG dataset following practitioners' criteria. Afterward, we re-evaluate diverse state-of-the-art CMG approaches and make comparisons with LLMs, demonstrating the superior performance of LLMs against state-of-the-art CMG approaches. Then, we further propose four manual metrics following the practice of OSS, including Accuracy, Integrity, Applicability, and Readability, and assess various LLMs accordingly. Results reveal that GPT-3.5 performs best overall, but different LLMs carry different advantages. To further boost LLMs' performance in the CMG task, we propose an Efficient Retrieval-based In-Context Learning (ICL) framework, namely ERICommiter, which leverages a two-step filtering to accelerate the retrieval efficiency and introduces semantic/lexical-based retrieval algorithm to construct the ICL examples. Extensive experiments demonstrate the substantial performance improvement of ERICommiter on various LLMs for code diffs of different programming languages. Meanwhile, ERICommiter also significantly reduces the retrieval time while keeping almost the same performance. Our research contributes to the understanding of LLMs' capabilities in the CMG field and provides valuable insights for practitioners seeking to leverage these tools in their workflows.

Skeleton Ground Truth (GT) is critical to the success of supervised skeleton extraction methods, especially with the popularity of deep learning techniques. Furthermore, we see skeleton GTs used not only for training skeleton detectors with Convolutional Neural Networks (CNN) but also for evaluating skeleton-related pruning and matching algorithms. However, most existing shape and image datasets suffer from the lack of skeleton GT and inconsistency of GT standards. As a result, it is difficult to evaluate and reproduce CNN-based skeleton detectors and algorithms on a fair basis. In this paper, we present a heuristic strategy for object skeleton GT extraction in binary shapes and natural images. Our strategy is built on an extended theory of diagnosticity hypothesis, which enables encoding human-in-the-loop GT extraction based on clues from the target's context, simplicity, and completeness. Using this strategy, we developed a tool, SkeView, to generate skeleton GT of 17 existing shape and image datasets. The GTs are then structurally evaluated with representative methods to build viable baselines for fair comparisons. Experiments demonstrate that GTs generated by our strategy yield promising quality with respect to standard consistency, and also provide a balance between simplicity and completeness., Comment: Accepted for publication in the International Journal of Computer Vision (IJCV)

Imaging polarimetry based on dielectric metasurface is well-known for its ultra-compactness and high integration. However, previous works suffer from low energy efficiency, limited restrictions on choice of target polarization states, or inability to focus light. Here, by inverse design, we numerically demonstrate a multi-foci metalens-based polarimetry that can simultaneously separate and focus the four free-chosen elliptical polarization states at the wavelength of 10.6 \mu m. Such a full-stokes polarimetry features an average absolute efficiency up to 54.63%, and an average relative error as low as 0.00137%. This spatial-multiplexing-free full stokes polarimetry exceeds the theoretical maximum efficiency of traditional polarization-filtering counterparts, and resolves the restriction faced by the orthogonal polarization-multiplexed method.

We developed a deep ensemble learning model with a radiomics spatial encoding execution for improved glioma segmentation accuracy using multi-parametric MRI (mp-MRI). This model was developed using 369 glioma patients with a 4-modality mp-MRI protocol: T1, contrast-enhanced T1 (T1-Ce), T2, and FLAIR. In each modality volume, a 3D sliding kernel was implemented across the brain to capture image heterogeneity: fifty-six radiomic features were extracted within the kernel, resulting in a 4th order tensor. Each radiomic feature can then be encoded as a 3D image volume, namely a radiomic feature map (RFM). PCA was employed for data dimension reduction and the first 4 PCs were selected. Four deep neural networks as sub-models following the U-Net architecture were trained for the segmenting of a region-of-interest (ROI): each sub-model utilizes the mp-MRI and 1 of the 4 PCs as a 5-channel input for a 2D execution. The 4 softmax probability results given by the U-net ensemble were superimposed and binarized by Otsu method as the segmentation result. Three ensemble models were trained to segment enhancing tumor (ET), tumor core (TC), and whole tumor (WT). The adopted radiomics spatial encoding execution enriches the image heterogeneity information that leads to the successful demonstration of the proposed deep ensemble model, which offers a new tool for mp-MRI based medical image segmentation.

Graphs have a superior ability to represent relational data, like chemical compounds, proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as input, has been applied to many tasks including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs heavily rely on hand-crafted features, such as substructures. But while these methods benefit from good interpretability, they often suffer from computational bottlenecks as they cannot skirt the graph isomorphism problem. Conversely, deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations. As a result, these deep graph learning methods have been responsible for many successes. Yet, there is no comprehensive survey that reviews graph-level learning starting with traditional learning and moving through to the deep learning approaches. This article fills this gap and frames the representative algorithms into a systematic taxonomy covering traditional learning, graph-level deep neural networks, graph-level graph neural networks, and graph pooling. To ensure a thoroughly comprehensive survey, the evolutions, interactions, and communications between methods from four different branches of development are also examined. This is followed by a brief review of the benchmark data sets, evaluation metrics, and common downstream applications. The survey concludes with a broad overview of 12 current and future directions in this booming field.

This work focuses on multi-target tracking in Video synthetic aperture radar. Specifically, we refer to tracking based on targets' shadows. Current methods have limited accuracy as they fail to consider shadows' characteristics and surroundings fully. Shades are low-scattering and varied, resulting in missed tracking. Surroundings can cause interferences, resulting in false tracking. To solve these, we propose a shadow-oriented multi-target tracking method (SOTrack). To avoid false tracking, a pre-processing module is proposed to enhance shadows from surroundings, thus reducing their interferences. To avoid missed tracking, a detection method based on deep learning is designed to thoroughly learn shadows' features, thus increasing the accurate estimation. And further, a recall module is designed to recall missed shadows. We conduct experiments on measured data. Results demonstrate that, compared with other methods, SOTrack achieves much higher performance in tracking accuracy-18.4%. And ablation study confirms the effectiveness of the proposed modules.

Metalenses, featuring ultra-compactness and CMOS compatibility, are limited by the compromise between the diameter, numerical aperture, and working waveband. To address this problem, we propose and numerically demonstrate a centimeter-scale metasurface-refractive hybrid metalens working in the band of 440 - 700 nm. Revisiting the general Snell law, we present the phase profile of a chromatic aberration correction metasurface that can apply to a plano-convex refractive lens of an arbitrary surface type. Simulated by our semi-vector method, the designed achromatic hybrid metalens achieves 81% chromatic aberration suppression and polarization insensitivity. Broadband imaging results of the hybrid metalens are further provided, verifying the achromatism of the designed hybrid metalens. It can find applications in camera lenses and other optical systems that need compact, high-performance lenses., Comment: 10 pages, 5 figures

The projection of planar MRI data onto a spherical surface is equivalent to a nonlinear image transformation that retains global anatomical information. By incorporating this image transformation process in our proposed spherical projection-based U-Net (SPU-Net) segmentation model design, multiple independent segmentation predictions can be obtained from a single MRI. The final segmentation is the average of all available results, and the variation can be visualized as a pixel-wise uncertainty map. An uncertainty score was introduced to evaluate and compare the performance of uncertainty measurements. The proposed SPU-Net model was implemented on the basis of 369 glioma patients with MP-MRI scans (T1, T1-Ce, T2, and FLAIR). Three SPU-Net models were trained to segment enhancing tumor (ET), tumor core (TC), and whole tumor (WT), respectively. The SPU-Net model was compared with (1) the classic U-Net model with test-time augmentation (TTA) and (2) linear scaling-based U-Net (LSU-Net) segmentation models in terms of both segmentation accuracy (Dice coefficient, sensitivity, specificity, and accuracy) and segmentation uncertainty (uncertainty map and uncertainty score). The developed SPU-Net model successfully achieved low uncertainty for correct segmentation predictions (e.g., tumor interior or healthy tissue interior) and high uncertainty for incorrect results (e.g., tumor boundaries). This model could allow the identification of missed tumor targets or segmentation errors in U-Net. Quantitatively, the SPU-Net model achieved the highest uncertainty scores for three segmentation targets (ET/TC/WT): 0.826/0.848/0.936, compared to 0.784/0.643/0.872 using the U-Net with TTA and 0.743/0.702/0.876 with the LSU-Net (scaling factor = 2). The SPU-Net also achieved statistically significantly higher Dice coefficients, underscoring the improved segmentation accuracy., Comment: 31 pages, 9 figures, 1 table