Search

Although Large Language Models (LLMs) achieve remarkable performance across various tasks, they often struggle with complex reasoning tasks, such as answering mathematical questions. Recent efforts to address this issue have primarily focused on leveraging mathematical datasets through supervised fine-tuning or self-improvement techniques. However, these methods often depend on high-quality datasets that are difficult to prepare, or they require substantial computational resources for fine-tuning. Inspired by findings that LLMs know how to produce the right answer but struggle to select the correct reasoning path, we propose a purely inference-based searching method -- MindStar (M*). This method formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths. We evaluate the M* framework on both the GSM8K and MATH datasets, comparing its performance with existing open and closed-source LLMs. Our results demonstrate that M* significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1, but with substantially reduced model size and computational costs.

CsV3Sb5, a notable compound within the kagome family, is renowned for its topological and superconducting properties, as well as its detection of local magnetic field and anomalous Hall effect in experiments. However, the origin of this local magnetic field is still veiled. In this study, we employ the first-principles calculations to investigate the atomic vibration in both the pristine and the charge-density-wave phases of CsV$_3$Sb$_5$. Our analysis reveals the presence of ``anomalous phonons" in these structures, these phonon induce the circular vibration of atoms, contributing to the phonon magnetic moments and subsequently to the observed the local magnetic fields. Additionally, we observe that lattice distortion in the charge-density-wave phase amplifies these circular vibrations, resulting in a stronger local magnetic field, particularly from the vanadium atoms. This investigation not only reveals the potential relation between lattice distortion and atomic polarization but also offers a novel idea to understand the origin of local magnetic moment in CsV3Sb5., Comment: 6 pages, 5 figures

The extraction of road network is essential for the generation of high-definition maps since it enables the precise localization of road landmarks and their interconnections. However, generating road network poses a significant challenge due to the conflicting underlying combination of Euclidean (e.g., road landmarks location) and non-Euclidean (e.g., road topological connectivity) structures. Existing methods struggle to merge the two types of data domains effectively, but few of them address it properly. Instead, our work establishes a unified representation of both types of data domain by projecting both Euclidean and non-Euclidean data into an integer series called RoadNet Sequence. Further than modeling an auto-regressive sequence-to-sequence Transformer model to understand RoadNet Sequence, we decouple the dependency of RoadNet Sequence into a mixture of auto-regressive and non-autoregressive dependency. Building on this, our proposed non-autoregressive sequence-to-sequence approach leverages non-autoregressive dependencies while fixing the gap towards auto-regressive dependencies, resulting in success on both efficiency and accuracy. We further identify two main bottlenecks in the current RoadNetTransformer on a non-overfitting split of the dataset: poor landmark detection limited by the BEV Encoder and error propagation to topology reasoning. Therefore, we propose Topology-Inherited Training to inherit better topology knowledge into RoadNetTransformer. Additionally, we collect SD-Maps from open-source map datasets and use this prior information to significantly improve landmark detection and reachability. Extensive experiments on nuScenes dataset demonstrate the superiority of RoadNet Sequence representation and the non-autoregressive approach compared to existing state-of-the-art alternatives., Comment: V1 is the ICCV 2023 conference version, and V2 is the extended version

Understanding road structures is crucial for autonomous driving. Intricate road structures are often depicted using lane graphs, which include centerline curves and connections forming a Directed Acyclic Graph (DAG). Accurate extraction of lane graphs relies on precisely estimating vertex and edge information within the DAG. Recent research highlights Transformer-based language models' impressive sequence prediction abilities, making them effective for learning graph representations when graph data are encoded as sequences. However, existing studies focus mainly on modeling vertices explicitly, leaving edge information simply embedded in the network. Consequently, these approaches fall short in the task of lane graph extraction. To address this, we introduce LaneGraph2Seq, a novel approach for lane graph extraction. It leverages a language model with vertex-edge encoding and connectivity enhancement. Our serialization strategy includes a vertex-centric depth-first traversal and a concise edge-based partition sequence. Additionally, we use classifier-free guidance combined with nucleus sampling to improve lane connectivity. We validate our method on prominent datasets, nuScenes and Argoverse 2, showcasing consistent and compelling results. Our LaneGraph2Seq approach demonstrates superior performance compared to state-of-the-art techniques in lane graph extraction., Comment: AAAI 2024

Visual bird's eye view (BEV) semantic segmentation helps autonomous vehicles understand the surrounding environment only from images, including static elements (e.g., roads) and dynamic elements (e.g., vehicles, pedestrians). However, the high cost of annotation procedures of full-supervised methods limits the capability of the visual BEV semantic segmentation, which usually needs HD maps, 3D object bounding boxes, and camera extrinsic matrixes. In this paper, we present a novel semi-supervised framework for visual BEV semantic segmentation to boost performance by exploiting unlabeled images during the training. A consistency loss that makes full use of unlabeled data is then proposed to constrain the model on not only semantic prediction but also the BEV feature. Furthermore, we propose a novel and effective data augmentation method named conjoint rotation which reasonably augments the dataset while maintaining the geometric relationship between the front-view images and the BEV semantic segmentation. Extensive experiments on the nuScenes and Argoverse datasets show that our semi-supervised framework can effectively improve prediction accuracy. To the best of our knowledge, this is the first work that explores improving visual BEV semantic segmentation performance using unlabeled data. The code is available at https://github.com/Junyu-Z/Semi-BEVseg, Comment: Accepted by ICRA2024

Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments. However, existing benchmarks tend to oversimplify the scene by solely focusing on lane perception tasks. Observing that human drivers rely on both lanes and traffic signals to operate their vehicles safely, we present OpenLane-V2, the first dataset on topology reasoning for traffic scene structure. The objective of the presented dataset is to advance research in understanding the structure of road scenes by examining the relationship between perceived entities, such as traffic elements and lanes. Leveraging existing datasets, OpenLane-V2 consists of 2,000 annotated road scenes that describe traffic elements and their correlation to the lanes. It comprises three primary sub-tasks, including the 3D lane detection inherited from OpenLane, accompanied by corresponding metrics to evaluate the model's performance. We evaluate various state-of-the-art methods, and present their quantitative and qualitative results on OpenLane-V2 to indicate future avenues for investigating topology reasoning in traffic scenes., Comment: Accepted by NeurIPS 2023 Track on Datasets and Benchmarks | OpenLane-V2 Dataset: https://github.com/OpenDriveLab/OpenLane-V2

The Mn-Bi-Te family displaying magnetism and non-trivial topological properties has received extensive attention. Here, we predict that the antiferromagnetic structure of Mn$_{3}$Bi$_{2}$Te$_{6}$ with three MnTe layers is energetically stable and the magnetic coupling strength of Mn-Mn is enhanced four times compared with that in the single MnTe layer of MnBi$_{2}$Te$_{4}$. The predicted N\'eel transition point is higher than 77 K, the liquid-nitrogen temperature. The topological properties show that with the variation of the MnTe layer from a single layer to three layers, the system transforms from a nontrivial topological phase to a trivial topological phase. Interestingly, the ferromagnetic state of Mn$_{3}$Bi$_{2}$Te$_{6}$ is a topological semimetal and it exhibits a topological transition from trivial to nontrivial induced by the magnetic transition. Our results enrich the Mn-Bi-Te family system, offer a new platform for studying topological phase transitions, and pave a new way to improve the working temperature of magnetically topological devices.

This paper investigates the bistability of curved compression ramp (CCR) flows. It reports that both separated and attached states can be stably established even for the same boundary conditions, revealing that the ultimate stable states of CCR flows also depend on the initial conditions and evolutionary history. Firstly, we design a thought experiment involving two establishment routes of CCR flows, constructing two distinct-different stable states, respectively. Subsequently, three-dimensional direct numerical simulations are meticulously performed to instantiate the thought experiment, verifying the existence of the bistable states. Finally, we compare the pressure, wall friction, and heat flux distributions under two stable states. As a canonical type of Shock wave-Boundary layer interactions, local CCR flows often appear on aircraft, hence the bistability will certainly bring noteworthy changes to the global aerothermodynamic characteristics, which supersonic/hypersonic flight has to deal with.

Patch-to-point matching has become a robust way of point cloud registration. However, previous patch-matching methods employ superpoints with poor localization precision as nodes, which may lead to ambiguous patch partitions. In this paper, we propose a HybridPoint-based network to find more robust and accurate correspondences. Firstly, we propose to use salient points with prominent local features as nodes to increase patch repeatability, and introduce some uniformly distributed points to complete the point cloud, thus constituting hybrid points. Hybrid points not only have better localization precision but also give a complete picture of the whole point cloud. Furthermore, based on the characteristic of hybrid points, we propose a dual-classes patch matching module, which leverages the matching results of salient points and filters the matching noise of non-salient points. Experiments show that our model achieves state-of-the-art performance on 3DMatch, 3DLoMatch, and KITTI odometry, especially with 93.0% Registration Recall on the 3DMatch dataset. Our code and models are available at https://github.com/liyih/HybridPoint., Comment: Accepted by IEEE International Conference on Multimedia and Expo (ICME), 2023