Search

Parameter-efficient transfer learning (PETL) has become a promising paradigm for adapting large-scale vision foundation models to downstream tasks. Typical methods primarily leverage the intrinsic low rank property to make decomposition, learning task-specific weights while compressing parameter size. However, such approaches predominantly manipulate within the original feature space utilizing a single-branch structure, which might be suboptimal for decoupling the learned representations and patterns. In this paper, we propose ALoRE, a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts using a multi-branch paradigm, disentangling the learned cognitive patterns during training. Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone via re-parameterization in a sequential manner, avoiding additional inference latency. We conduct extensive experiments on 24 image classification tasks using various backbone variants. Experimental results demonstrate that ALoRE outperforms the full fine-tuning strategy and other state-of-the-art PETL methods in terms of performance and parameter efficiency. For instance, ALoRE obtains 3.06% and 9.97% Top-1 accuracy improvement on average compared to full fine-tuning on the FGVC datasets and VTAB-1k benchmark by only updating 0.15M parameters., Comment: 23 pages, 7 figures

Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiority over continual SFT during this preference alignment stage. In this paper, we observe that the inherent value of multimodal RLHF lies in its negative supervision, the logit of the rejected responses. We thus propose a novel negative supervised finetuning (nSFT) approach that fully excavates these information resided. Our nSFT disentangles this negative supervision in RLHF paradigm, and continually aligns VLMs with a simple SFT loss. This is more memory efficient than multimodal RLHF where 2 (e.g., DPO) or 4 (e.g., PPO) large VLMs are strictly required. The effectiveness of nSFT is rigorously proved by comparing it with various multimodal RLHF approaches, across different dataset sources, base VLMs and evaluation metrics. Besides, fruitful of ablations are provided to support our hypothesis. We hope this paper will stimulate further research to properly align large vision language models.

Let $G$ be a graph and $k \geq 3$ an integer. A subset $D \subseteq V(G)$ is a $k$-clique (resp., cycle) isolating set of $G$ if $G-N[D]$ contains no $k$-clique (resp., cycle). In this paper, we prove that every connected graph with maximum degree at most $k$, except $k$-clique, can be partitioned into $k+1$ disjoint $k$-clique isolating sets, and that every connected claw-free subcubic graph, except 3-cycle, can be partitioned into four disjoint cycle isolating sets. As a consequence of the first result, every $k$-regular graph can be partitioned into $k+1$ disjoint $k$-clique isolating sets., Comment: 14 pages, 5 figures

Existing Large Multimodal Models (LMMs) struggle with mathematical geometric reasoning due to a lack of high-quality image-text paired data. Current geometric data generation approaches, which apply preset templates to generate geometric data or use Large Language Models (LLMs) to rephrase questions and answers (Q&A), unavoidably limit data accuracy and diversity. To synthesize higher-quality data, we propose a two-stage Reverse Chain-of-Thought (R-CoT) geometry problem generation pipeline. First, we introduce GeoChain to produce high-fidelity geometric images and corresponding descriptions highlighting relations among geometric elements. We then design a Reverse A&Q method that reasons step-by-step based on the descriptions and generates questions in reverse from the reasoning results. Experiments demonstrate that the proposed method brings significant and consistent improvements on multiple LMM baselines, achieving new performance records in the 2B, 7B, and 8B settings. Notably, R-CoT-8B significantly outperforms previous state-of-the-art open-source mathematical models by 16.6% on MathVista and 9.2% on GeoQA, while also surpassing the closed-source model GPT-4o by an average of 13% across both datasets. The code is available at https://github.com/dle666/R-CoT.

We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two crucial techniques. First, we present Multimodal LoRA (MM-LoRA), a module designed to enhance the decoder. Unlike traditional language-driven decoders, MM-LoRA consists of two parallel LoRAs -- one for vision and one for language -- each with its own parameters. This disentangled parameters design allows for more specialized learning in each modality and better integration of multimodal information. Second, we introduce the Query Ladder adapter (QLadder) to improve the visual encoder. QLadder employs a learnable ``\textit{ladder}'' structure to deeply aggregates the intermediate representations from the frozen pretrained visual encoder (e.g., CLIP image encoder). This enables the model to learn new and informative visual features, as well as remaining the powerful capabilities of the pretrained visual encoder. These techniques collectively enhance Arcana's visual perception power, enabling it to leverage improved visual information for more accurate and contextually relevant outputs across various multimodal scenarios. Extensive experiments and ablation studies demonstrate the effectiveness and generalization capability of our Arcana. The code and re-annotated data are available at \url{https://arcana-project-page.github.io}.

Multimodal Large Language Models (MLLMs) have shown promise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they heavily depend on high-quality data in the Supervised Fine-Tuning (SFT) phase. The existing approaches aim to curate high-quality data via GPT-4V, but they are not scalable due to the commercial nature of GPT-4V and the simplicity of the prompts used to instruct the model. To this end, we devised the FullAnno system, which is a data engine that can generate large-scale, high-quality, and fine-grained image annotations consisting of the category and position of objects, region descriptions, text information, as well as image dense captions. This engine is characterized by its cascade annotation process, which involves multiple expert models and employs rich prompts to instruct LLMs in generating dense image captions. We re-annotated the COCO and Visual Genome datasets using our FullAnno system, tripling the number of object annotations and increasing the length of the original image captions by a factor of 15. Experiments show that the regenerated annotation can significantly enhance the capabilities of LLaVA-v1.5 on several benchmarks. The re-annotated data are available at: https://arcana-project-page.github.io, Comment: 7 pages, 5 figures, 2 tables

Diffusion models have exhibited remarkable prowess in visual generalization. Building on this success, we introduce an instruction-based object addition pipeline, named Add-SD, which automatically inserts objects into realistic scenes with rational sizes and positions. Different from layout-conditioned methods, Add-SD is solely conditioned on simple text prompts rather than any other human-costly references like bounding boxes. Our work contributes in three aspects: proposing a dataset containing numerous instructed image pairs; fine-tuning a diffusion model for rational generation; and generating synthetic data to boost downstream tasks. The first aspect involves creating a RemovalDataset consisting of original-edited image pairs with textual instructions, where an object has been removed from the original image while maintaining strong pixel consistency in the background. These data pairs are then used for fine-tuning the Stable Diffusion (SD) model. Subsequently, the pretrained Add-SD model allows for the insertion of expected objects into an image with good rationale. Additionally, we generate synthetic instances for downstream task datasets at scale, particularly for tail classes, to alleviate the long-tailed problem. Downstream tasks benefit from the enriched dataset with enhanced diversity and rationale. Experiments on LVIS val demonstrate that Add-SD yields an improvement of 4.3 mAP on rare classes over the baseline. Code and models are available at https://github.com/ylingfeng/Add-SD.

Existing methods enhance open-vocabulary object detection by leveraging the robust open-vocabulary recognition capabilities of Vision-Language Models (VLMs), such as CLIP.However, two main challenges emerge:(1) A deficiency in concept representation, where the category names in CLIP's text space lack textual and visual knowledge.(2) An overfitting tendency towards base categories, with the open vocabulary knowledge biased towards base categories during the transfer from VLMs to detectors.To address these challenges, we propose the Language Model Instruction (LaMI) strategy, which leverages the relationships between visual concepts and applies them within a simple yet effective DETR-like detector, termed LaMI-DETR.LaMI utilizes GPT to construct visual concepts and employs T5 to investigate visual similarities across categories.These inter-category relationships refine concept representation and avoid overfitting to base categories.Comprehensive experiments validate our approach's superior performance over existing methods in the same rigorous setting without reliance on external training resources.LaMI-DETR achieves a rare box AP of 43.4 on OV-LVIS, surpassing the previous best by 7.8 rare box AP., Comment: ECCV2024

Open-vocabulary object detection focusing on detecting novel categories guided by natural language. In this report, we propose Open-Vocabulary Light-Weighted Detection Transformer (OVLW-DETR), a deployment friendly open-vocabulary detector with strong performance and low latency. Building upon OVLW-DETR, we provide an end-to-end training recipe that transferring knowledge from vision-language model (VLM) to object detector with simple alignment. We align detector with the text encoder from VLM by replacing the fixed classification layer weights in detector with the class-name embeddings extracted from the text encoder. Without additional fusing module, OVLW-DETR is flexible and deployment friendly, making it easier to implement and modulate. improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time open-vocabulary detectors on standard Zero-Shot LVIS benchmark. Source code and pre-trained models are available at [https://github.com/Atten4Vis/LW-DETR]., Comment: 4 pages

In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach leverages recent advanced techniques, such as training-effective techniques, e.g., improved loss and pretraining, and interleaved window and global attentions for reducing the ViT encoder complexity. We improve the ViT encoder by aggregating multi-level feature maps, and the intermediate and final feature maps in the ViT encoder, forming richer feature maps, and introduce window-major feature map organization for improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time detectors, e.g., YOLO and its variants, on COCO and other benchmark datasets. Code and models are available at (https://github.com/Atten4Vis/LW-DETR).

There has been a significant focus on real topological systems that enjoy space-time inversion symmetry (PT ) and lack spin-orbit coupling. While the theoretical classification of the real topology has been established, more progress has yet to be made in the materials realization of such real topological systems in three dimensions (3D). To address this crucial issue, by selecting the carbon-based material candidates as targets, we perform high-throughput computing to inspect the real topology in the phonon spectrums of the 3D carbon allotropes in the Samara Carbon Allotrope Database (SACADA). Among 1192 kinds of 3D carbon allotropes, we find 65 real topological systems with a phononic real Chern insulating (PRCI) state, 2 real topological systems with a phononic real nodal line (PRNL) state, 10 real topological systems with a phononic real Dirac point (PRDP) state, and 8 real topological systems with a phononic real triple-point pair (PRTPP) state. This extremely expands the material candidates with real topology, especially for the gapless topological phonons. We exhibit the PRCI, PRNL, PRTPP, and PRDP states of 27-SG. 166-pcu-h, 1081-SG. 194- 4 2T13-CA, 52-SG. 141-gis, and 132-SG. 191-3,4T157 as illustrative examples, and explore the second-order boundary mode, i.e., phononic hinge mode. Among the four examples, the materials 1081-SG. 194-42T13-CA and 52-SG. 141-gis are so ideal that the PRNL and PRTPP in them are well separated from other bands, and the phononic hinge mode can be clearly observed. This study aims to broaden the understanding of 3D topological phonons, and emphasizes the potential of 3D carbon allotropes as a valuable framework for exploring the fascinating physics related to phononic hinge modes and phononic real topology.

This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes. The task of this challenge is to super-resolve an input image with a magnification factor of x4 based on pairs of low and corresponding high-resolution images. The primary objective is to develop networks that optimize various aspects such as runtime, parameters, and FLOPs, while still maintaining a peak signal-to-noise ratio (PSNR) of approximately 26.90 dB on the DIV2K_LSDIR_valid dataset and 26.99 dB on the DIV2K_LSDIR_test dataset. In addition, this challenge has 4 tracks including the main track (overall performance), sub-track 1 (runtime), sub-track 2 (FLOPs), and sub-track 3 (parameters). In the main track, all three metrics (ie runtime, FLOPs, and parameter count) were considered. The ranking of the main track is calculated based on a weighted sum-up of the scores of all other sub-tracks. In sub-track 1, the practical runtime performance of the submissions was evaluated, and the corresponding score was used to determine the ranking. In sub-track 2, the number of FLOPs was considered. The score calculated based on the corresponding FLOPs was used to determine the ranking. In sub-track 3, the number of parameters was considered. The score calculated based on the corresponding parameters was used to determine the ranking. RLFN is set as the baseline for efficiency measurement. The challenge had 262 registered participants, and 34 teams made valid submissions. They gauge the state-of-the-art in efficient single-image super-resolution. To facilitate the reproducibility of the challenge and enable other researchers to build upon these findings, the code and the pre-trained model of validated solutions are made publicly available at https://github.com/Amazingren/NTIRE2024_ESR/., Comment: The report paper of NTIRE2024 Efficient Super-resolution, accepted by CVPRW2024

LiDAR-based 3D object detection plays an essential role in autonomous driving. Existing high-performing 3D object detectors usually build dense feature maps in the backbone network and prediction head. However, the computational costs introduced by the dense feature maps grow quadratically as the perception range increases, making these models hard to scale up to long-range detection. Some recent works have attempted to construct fully sparse detectors to solve this issue; nevertheless, the resulting models either rely on a complex multi-stage pipeline or exhibit inferior performance. In this work, we propose SAFDNet, a straightforward yet highly effective architecture, tailored for fully sparse 3D object detection. In SAFDNet, an adaptive feature diffusion strategy is designed to address the center feature missing problem. We conducted extensive experiments on Waymo Open, nuScenes, and Argoverse2 datasets. SAFDNet performed slightly better than the previous SOTA on the first two datasets but much better on the last dataset, which features long-range detection, verifying the efficacy of SAFDNet in scenarios where long-range detection is required. Notably, on Argoverse2, SAFDNet surpassed the previous best hybrid detector HEDNet by 2.6% mAP while being 2.1x faster, and yielded 2.1% mAP gains over the previous best sparse detector FSDv2 while being 1.3x faster. The code will be available at https://github.com/zhanggang001/HEDNet., Comment: Accepted by CVPR 2024 (Oral)

In autonomous driving, 3D occupancy prediction outputs voxel-wise status and semantic labels for more comprehensive understandings of 3D scenes compared with traditional perception tasks, such as 3D object detection and bird's-eye view (BEV) semantic segmentation. Recent researchers have extensively explored various aspects of this task, including view transformation techniques, ground-truth label generation, and elaborate network design, aiming to achieve superior performance. However, the inference speed, crucial for running on an autonomous vehicle, is neglected. To this end, a new method, dubbed FastOcc, is proposed. By carefully analyzing the network effect and latency from four parts, including the input image resolution, image backbone, view transformation, and occupancy prediction head, it is found that the occupancy prediction head holds considerable potential for accelerating the model while keeping its accuracy. Targeted at improving this component, the time-consuming 3D convolution network is replaced with a novel residual-like architecture, where features are mainly digested by a lightweight 2D BEV convolution network and compensated by integrating the 3D voxel features interpolated from the original image features. Experiments on the Occ3D-nuScenes benchmark demonstrate that our FastOcc achieves state-of-the-art results with a fast inference speed., Comment: Accepted by ICRA 2024

In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Anything Model (SAM) to utilize annotated reference images as prompts for segmentation, creating the VRP-SAM model. In essence, VRP-SAM can utilize annotated reference images to comprehend specific objects and perform segmentation of specific objects in target image. It is note that the VRP encoder can support a variety of annotation formats for reference images, including \textbf{point}, \textbf{box}, \textbf{scribble}, and \textbf{mask}. VRP-SAM achieves a breakthrough within the SAM framework by extending its versatility and applicability while preserving SAM's inherent strengths, thus enhancing user-friendliness. To enhance the generalization ability of VRP-SAM, the VRP encoder adopts a meta-learning strategy. To validate the effectiveness of VRP-SAM, we conducted extensive empirical studies on the Pascal and COCO datasets. Remarkably, VRP-SAM achieved state-of-the-art performance in visual reference segmentation with minimal learnable parameters. Furthermore, VRP-SAM demonstrates strong generalization capabilities, allowing it to perform segmentation of unseen objects and enabling cross-domain segmentation. The source code and models will be available at \url{https://github.com/syp2ysy/VRP-SAM}, Comment: Accepted by CVPR 2024; The camera-ready version

LiDAR panoptic segmentation facilitates an autonomous vehicle to comprehensively understand the surrounding objects and scenes and is required to run in real time. The recent proposal-free methods accelerate the algorithm, but their effectiveness and efficiency are still limited owing to the difficulty of modeling non-existent instance centers and the costly center-based clustering modules. To achieve accurate and real-time LiDAR panoptic segmentation, a novel center focusing network (CFNet) is introduced. Specifically, the center focusing feature encoding (CFFE) is proposed to explicitly understand the relationships between the original LiDAR points and virtual instance centers by shifting the LiDAR points and filling in the center points. Moreover, to leverage the redundantly detected centers, a fast center deduplication module (CDM) is proposed to select only one center for each instance. Experiments on the SemanticKITTI and nuScenes panoptic segmentation benchmarks demonstrate that our CFNet outperforms all existing methods by a large margin and is 1.6 times faster than the most efficient method. The code is available at https://github.com/GangZhang842/CFNet., Comment: Published in the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023)

Design and synthesis of novel two-dimensional (2D) materials that possess robust structural stability and unusual physical properties may open up enormous opportunities for device and engineering applications. Herein we propose a 2D sumanene lattice that be regarded as a derivative of the conventional Kagome lattice. Our tight-binding analysis demonstrates sumanene lattice contains two sets of Dirac cones and two sets of flat bands near the Fermi surface, distinctively different from the Kagome lattice. Using first-principles calculations, we theoretically suggest two possible routines for realization of stable 2D sumanene monolayers (named as a phase and b phase), and a-sumanene monolayer can be experimentally synthesized with chemical vapor deposition using C21H12 as a precursor. Small binding energies on Au(111) surface signify the possibility of their peel-off after grown on the noble metal substrate. Importantly, our GW plus Bethe-Salpeter equation calculations demonstrate both monolayers have moderate band gaps (1.94 eV for a) and ultrahigh carrier mobilities (3.4*104 cm2/Vs for a). In particular, a-sumanene monolayer possesses a strong exciton binding energy of 0.73 eV, suggesting potential applications in optics.

3D object detection in point clouds is important for autonomous driving systems. A primary challenge in 3D object detection stems from the sparse distribution of points within the 3D scene. Existing high-performance methods typically employ 3D sparse convolutional neural networks with small kernels to extract features. To reduce computational costs, these methods resort to submanifold sparse convolutions, which prevent the information exchange among spatially disconnected features. Some recent approaches have attempted to address this problem by introducing large-kernel convolutions or self-attention mechanisms, but they either achieve limited accuracy improvements or incur excessive computational costs. We propose HEDNet, a hierarchical encoder-decoder network for 3D object detection, which leverages encoder-decoder blocks to capture long-range dependencies among features in the spatial space, particularly for large and distant objects. We conducted extensive experiments on the Waymo Open and nuScenes datasets. HEDNet achieved superior detection accuracy on both datasets than previous state-of-the-art methods with competitive efficiency. The code is available at https://github.com/zhanggang001/HEDNet., Comment: Accepted by NeurIPS 2023

Let $C_k$ be the cycle of length $k$. For any graph $G$, a subset $D \subseteq V(G)$ is a $C_k$-isolating set of $G$ if the graph obtained from $G$ by deleting the closed neighbourhood of $D$ contains no $C_k$ as a subgraph. The $C_k$-isolation number of $G$, denoted by $\iota(G,C_k)$, is the cardinality of a smallest $C_k$-isolating set of $G$. Borg (2020) and Borg et al. (2022) proved that if $G \ncong C_3$ is a connected graph of order $n$ and size $m$, then $\iota(G,C_3) \leq \frac{n}{4}$ and $\iota(G,C_3) \leq \frac{m+1}{5}$. Very recently, Bartolo, Borg and Scicluna showed that if $G$ is a connected graph of order $n$ that is not one of the determined nine graphs, then $\iota(G,C_4) \leq \frac{n}{5}$. In this paper, we prove that if $G \ncong C_4$ is a connected graph of size $m$, then $\iota(G,C_4) \leq \frac{m+1}{6}$, and we characterize the graphs that attain the bound. Moreover, we conjecture that if $G \ncong C_k$ is a connected graph of size $m$, then $\iota(G,C_k) \leq \frac{m+1}{k+2}$., Comment: 15 pages, 2 figures

LiDAR and camera are two critical sensors for multi-modal 3D semantic segmentation and are supposed to be fused efficiently and robustly to promise safety in various real-world scenarios. However, existing multi-modal methods face two key challenges: 1) difficulty with efficient deployment and real-time execution; and 2) drastic performance degradation under weak calibration between LiDAR and cameras. To address these challenges, we propose CPGNet-LCF, a new multi-modal fusion framework extending the LiDAR-only CPGNet. CPGNet-LCF solves the first challenge by inheriting the easy deployment and real-time capabilities of CPGNet. For the second challenge, we introduce a novel weak calibration knowledge distillation strategy during training to improve the robustness against the weak calibration. CPGNet-LCF achieves state-of-the-art performance on the nuScenes and SemanticKITTI benchmarks. Remarkably, it can be easily deployed to run in 20ms per frame on a single Tesla V100 GPU using TensorRT TF16 mode. Furthermore, we benchmark performance over four weak calibration levels, demonstrating the robustness of our proposed approach., Comment: 7 pages, 3 figures

Recently, Vision Transformers (ViTs) have attracted a lot of attention in the field of computer vision. Generally, the powerful representative capacity of ViTs mainly benefits from the self-attention mechanism, which has a high computation complexity. To accelerate ViTs, we propose an integrated compression pipeline based on observed heterogeneous attention patterns across layers. On one hand, different images share more similar attention patterns in early layers than later layers, indicating that the dynamic query-by-key self-attention matrix may be replaced with a static self-attention matrix in early layers. Then, we propose a dynamic-guided static self-attention (DGSSA) method where the matrix inherits self-attention information from the replaced dynamic self-attention to effectively improve the feature representation ability of ViTs. On the other hand, the attention maps have more low-rank patterns, which reflect token redundancy, in later layers than early layers. In a view of linear dimension reduction, we further propose a method of global aggregation pyramid (GLAD) to reduce the number of tokens in later layers of ViTs, such as Deit. Experimentally, the integrated compression pipeline of DGSSA and GLAD can accelerate up to 121% run-time throughput compared with DeiT, which surpasses all SOTA approaches.

We investigate the influence of external fields on the stability of spin helix states in an XXZ Heisenberg model. Exact diagonalization on a finite system shows that random transverse fields in the x and y directions drive the transition from integrability to nonintegrability. In such a system, the helix state can be regarded as a quantum scar. Simultaneously, the presence of uniform z field enables the helix state to better maintain its dynamical nature, allowing for a clearer understanding of its evolutionary behavior. However, the entanglement entropy reveals that irrespective of the presence of a uniform z field, as long as the system remains chaotic, the scar extent of the helix state shows no significant variation., Comment: 7 pages, 4 figures

Let $G$ be a graph. A subset $D \subseteq V(G)$ is called a 1-isolating set of $G$ if $\Delta(G-N[D]) \leq 1$, that is, $G-N[D]$ consists of isolated edges and isolated vertices only. The $1$-isolation number of $G$, denoted by $\iota_1(G)$, is the cardinality of a smallest $1$-isolating set of $G$. In this paper, we prove that if $G \notin \{P_3,C_3,C_7,C_{11}\}$ is a connected graph of order $n$ without $6$-cycles, or without induced 5- and 6-cycles, then $\iota_1(G) \leq \frac{n}{4}$. Both bounds are sharp., Comment: 21 pages, 10 figures

With the continuous improvement of computing power and deep learning algorithms in recent years, the foundation model has grown in popularity. Because of its powerful capabilities and excellent performance, this technology is being adopted and applied by an increasing number of industries. In the intelligent transportation industry, artificial intelligence faces the following typical challenges: few shots, poor generalization, and a lack of multi-modal techniques. Foundation model technology can significantly alleviate the aforementioned issues. To address these, we designed the 1st Foundation Model Challenge, with the goal of increasing the popularity of foundation model technology in traffic scenarios and promoting the rapid development of the intelligent transportation industry. The challenge is divided into two tracks: all-in-one and cross-modal image retrieval. Furthermore, we provide a new baseline and benchmark for the two tracks, called Open-TransMind. According to our knowledge, Open-TransMind is the first open-source transportation foundation model with multi-task and multi-modal capabilities. Simultaneously, Open-TransMind can achieve state-of-the-art performance on detection, classification, and segmentation datasets of traffic scenarios. Our source code is available at https://github.com/Traffic-X/Open-TransMind.

When the spin-orbit coupling (SOC) is absent, almost all the proposed half-metals with the twofold degenerate nodal points at the K (or K') in two-dimensional (2D) materials are misclassified as "Dirac half-metals" owing to the way graphene was utilized in the earliest studies. Actually, each band crossing point at K or K' is described by a 2D Weyl Hamiltonian with definite chirality; hence, it must be a Weyl point. To the best of our knowledge, there have been no reports of a genuine (i.e., fourfold degenerate) Dirac point half-metal in 2D yet. In this Letter, we proposed for the first time that the 2D d0-type ferromagnet Mg4N4 is a genuine Dirac half-metal with a fourfold degenerate Dirac point at the S high-symmetry point, intrinsic magnetism, high Curie temperature, 100% spin-polarization, robustness to the SOC and uniaxial and biaxial strains, and 100% spin-polarized edge states. The work can be seen as a starting point for future predictions of intrinsically magnetic materials with genuine Dirac points, which will aid the frontier of topo-spintronics researchers.

The "pre-training $\rightarrow$ downstream adaptation" presents both new opportunities and challenges for Continual Learning (CL). Although the recent state-of-the-art in CL is achieved through Parameter-Efficient-Tuning (PET) adaptation paradigm, only prompt has been explored, limiting its application to Transformers only. In this paper, we position prompting as one instantiation of PET, and propose a unified CL framework with general PET, dubbed as Learning-Accumulation-Ensemble (LAE). PET, e.g., using Adapter, LoRA, or Prefix, can adapt a pre-trained model to downstream tasks with fewer parameters and resources. Given a PET method, our LAE framework incorporates it for CL with three novel designs. 1) Learning: the pre-trained model adapts to the new task by tuning an online PET module, along with our adaptation speed calibration to align different PET modules, 2) Accumulation: the task-specific knowledge learned by the online PET module is accumulated into an offline PET module through momentum update, 3) Ensemble: During inference, we respectively construct two experts with online/offline PET modules (which are favored by the novel/historical tasks) for prediction ensemble. We show that LAE is compatible with a battery of PET methods and gains strong CL capability. For example, LAE with Adaptor PET surpasses the prior state-of-the-art by 1.3% and 3.6% in last-incremental accuracy on CIFAR100 and ImageNet-R datasets, respectively. Code is available at \url{https://github.com/gqk/LAE}., Comment: Accepted to ICCV 2023

Multi-scale features are essential for dense prediction tasks, such as object detection, instance segmentation, and semantic segmentation. The prevailing methods usually utilize a classification backbone to extract multi-scale features and then fuse these features using a lightweight module (e.g., the fusion module in FPN and BiFPN, two typical object detection methods). However, as these methods allocate most computational resources to the classification backbone, the multi-scale feature fusion in these methods is delayed, which may lead to inadequate feature fusion. While some methods perform feature fusion from early stages, they either fail to fully leverage high-level features to guide low-level feature learning or have complex structures, resulting in sub-optimal performance. We propose a streamlined cascade encoder-decoder network, dubbed CEDNet, tailored for dense \mbox{prediction} tasks. All stages in CEDNet share the same encoder-decoder structure and perform multi-scale feature fusion within the decoder. A hallmark of CEDNet is its ability to incorporate high-level features from early stages to guide low-level feature learning in subsequent stages, thereby enhancing the effectiveness of multi-scale feature fusion. We explored three well-known encoder-decoder structures: Hourglass, UNet, and FPN. When integrated into CEDNet, they performed much better than traditional methods that use a pre-designed classification backbone combined with a lightweight fusion module. Extensive experiments on object detection, instance segmentation, and semantic segmentation demonstrated the effectiveness of our method. The code is available at https://github.com/zhanggang001/CEDNet., Comment: Technical report; Code: https://github.com/zhanggang001/CEDNet

Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation performance for detection tasks. One is the serious imbalance between foreground and background features, another one is that small object lacks enough feature representation. To solve the above issues, we propose a new distillation method named dual relation knowledge distillation (DRKD), including pixel-wise relation distillation and instance-wise relation distillation. The pixel-wise relation distillation embeds pixel-wise features in the graph space and applies graph convolution to capture the global pixel relation. By distilling the global pixel relation, the student detector can learn the relation between foreground and background features, and avoid the difficulty of distilling features directly for the feature imbalance issue. Besides, we find that instance-wise relation supplements valuable knowledge beyond independent features for small objects. Thus, the instance-wise relation distillation is designed, which calculates the similarity of different instances to obtain a relation matrix. More importantly, a relation filter module is designed to highlight valuable instance relations. The proposed dual relation knowledge distillation is general and can be easily applied for both one-stage and two-stage detectors. Our method achieves state-of-the-art performance, which improves Faster R-CNN based on ResNet50 from 38.4% to 41.6% mAP and improves RetinaNet based on ResNet50 from 37.4% to 40.3% mAP on COCO 2017., Comment: Accepted by IJCAI-2023

The discovery of topological quantum states in two-dimensional (2D) systems is one of the most promising advancements in condensed matter physics. Linear Weyl point (LWP) phonons have been theoretically investigated in some 2D materials. Especially, Jin, Wang, and Xu [Nano Lett. 2018, 18, 12, 7755-7760] proposed in 2018 that the candidates with threefold rotational symmetry at the corners of the hexagonal Brillouin zone can host LWP phonons with a quantized valley Berry phase. However, all the candidates with hexagonal lattices may not host LWP phonons at $K$ ($K'$) high-symmetry points (HSPs). Hence, a more accurate recipe for LWP phonons in 2D is highly required. This work provides an exhaustive list of valley LWP phonons at HSPs in 2D by searching the entire 80 layer groups (LGs). We found that the valley LWP phonons can be obtained at HSPs in 11 of the 80 LGs. Guided by the symmetry analysis, we also contributed to realizing the ideal 2D material with valley LWP phonons. We identified the existence of the valley LWP phonons in eleven 2D material candidates with 11 LGs. This work offers a method to search for valley LWPs in 2D phononic systems and proposes 2D material candidates to obtain the valley LWP phonons.

DETR is a novel end-to-end transformer architecture object detector, which significantly outperforms classic detectors when scaling up the model size. In this paper, we focus on the compression of DETR with knowledge distillation. While knowledge distillation has been well-studied in classic detectors, there is a lack of researches on how to make it work effectively on DETR. We first provide experimental and theoretical analysis to point out that the main challenge in DETR distillation is the lack of consistent distillation points. Distillation points refer to the corresponding inputs of the predictions for student to mimic, and reliable distillation requires sufficient distillation points which are consistent between teacher and student. Based on this observation, we propose a general knowledge distillation paradigm for DETR(KD-DETR) with consistent distillation points sampling. Specifically, we decouple detection and distillation tasks by introducing a set of specialized object queries to construct distillation points. In this paradigm, we further propose a general-to-specific distillation points sampling strategy to explore the extensibility of KD-DETR. Extensive experiments on different DETR architectures with various scales of backbones and transformer layers validate the effectiveness and generalization of KD-DETR. KD-DETR boosts the performance of DAB-DETR with ResNet-18 and ResNet-50 backbone to 41.4$\%$, 45.7$\%$ mAP, respectively, which are 5.2$\%$, 3.5$\%$ higher than the baseline, and ResNet-50 even surpasses the teacher model by $2.2\%$.

We present a strong object detector with encoder-decoder pretraining and finetuning. Our method, called Group DETR v2, is built upon a vision transformer encoder ViT-Huge~\cite{dosovitskiy2020image}, a DETR variant DINO~\cite{zhang2022dino}, and an efficient DETR training method Group DETR~\cite{chen2022group}. The training process consists of self-supervised pretraining and finetuning a ViT-Huge encoder on ImageNet-1K, pretraining the detector on Object365, and finally finetuning it on COCO. Group DETR v2 achieves $\textbf{64.5}$ mAP on COCO test-dev, and establishes a new SoTA on the COCO leaderboard https://paperswithcode.com/sota/object-detection-on-coco, Comment: Tech report, 3 pages. We establishes a new SoTA (64.5 mAP) on the COCO test-dev

The requirement of expensive annotations is a major burden for training a well-performed instance segmentation model. In this paper, we present an economic active learning setting, named active pointly-supervised instance segmentation (APIS), which starts with box-level annotations and iteratively samples a point within the box and asks if it falls on the object. The key of APIS is to find the most desirable points to maximize the segmentation accuracy with limited annotation budgets. We formulate this setting and propose several uncertainty-based sampling strategies. The model developed with these strategies yields consistent performance gain on the challenging MS-COCO dataset, compared against other learning strategies. The results suggest that APIS, integrating the advantages of active learning and point-based supervision, is an effective learning paradigm for label-efficient instance segmentation., Comment: ECCV 2022

FASER, the ForwArd Search ExpeRiment, is an experiment dedicated to searching for light, extremely weakly-interacting particles at CERN's Large Hadron Collider (LHC). Such particles may be produced in the very forward direction of the LHC's high-energy collisions and then decay to visible particles inside the FASER detector, which is placed 480 m downstream of the ATLAS interaction point, aligned with the beam collisions axis. FASER also includes a sub-detector, FASER$\nu$, designed to detect neutrinos produced in the LHC collisions and to study their properties. In this paper, each component of the FASER detector is described in detail, as well as the installation of the experiment system and its commissioning using cosmic-rays collected in September 2021 and during the LHC pilot beam test carried out in October 2021. FASER will start taking LHC collision data in 2022, and will run throughout LHC Run 3., Comment: 92 pages, 72 Figures

This paper proposes a novel Unified Feature Optimization (UFO) paradigm for training and deploying deep models under real-world and large-scale scenarios, which requires a collection of multiple AI functions. UFO aims to benefit each single task with a large-scale pretraining on all tasks. Compared with the well known foundation model, UFO has two different points of emphasis, i.e., relatively smaller model size and NO adaptation cost: 1) UFO squeezes a wide range of tasks into a moderate-sized unified model in a multi-task learning manner and further trims the model size when transferred to down-stream tasks. 2) UFO does not emphasize transfer to novel tasks. Instead, it aims to make the trimmed model dedicated for one or more already-seen task. With these two characteristics, UFO provides great convenience for flexible deployment, while maintaining the benefits of large-scale pretraining. A key merit of UFO is that the trimming process not only reduces the model size and inference consumption, but also even improves the accuracy on certain tasks. Specifically, UFO considers the multi-task training and brings two-fold impact on the unified model: some closely related tasks have mutual benefits, while some tasks have conflicts against each other. UFO manages to reduce the conflicts and to preserve the mutual benefits through a novel Network Architecture Search (NAS) method. Experiments on a wide range of deep representation learning tasks (i.e., face recognition, person re-identification, vehicle re-identification and product retrieval) show that the model trimmed from UFO achieves higher accuracy than its single-task-trained counterpart and yet has smaller model size, validating the concept of UFO. Besides, UFO also supported the release of 17 billion parameters computer vision (CV) foundation model which is the largest CV model in the industry., Comment: Accepted in ECCV 2022

LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms. Previous point-based or sparse voxel-based methods are far away from real-time applications since time-consuming neighbor searching or sparse 3D convolution are employed. Recent 2D projection-based methods, including range view and multi-view fusion, can run in real time, but suffer from lower accuracy due to information loss during the 2D projection. Besides, to improve the performance, previous methods usually adopt test time augmentation (TTA), which further slows down the inference process. To achieve a better speed-accuracy trade-off, we propose Cascade Point-Grid Fusion Network (CPGNet), which ensures both effectiveness and efficiency mainly by the following two techniques: 1) the novel Point-Grid (PG) fusion block extracts semantic features mainly on the 2D projected grid for efficiency, while summarizes both 2D and 3D features on 3D point for minimal information loss; 2) the proposed transformation consistency loss narrows the gap between the single-time model inference and TTA. The experiments on the SemanticKITTI and nuScenes benchmarks demonstrate that the CPGNet without ensemble models or TTA is comparable with the state-of-the-art RPVNet, while it runs 4.7 times faster., Comment: Accepted in the 2022 IEEE International Conference on Robotics and Automation (ICRA 2022)

Interatomic potentials beyond quadratic order provide scattering sources for phonon transport in lattice. By using a weakly-interacting interface model, we investigated the relation between the order of interatomic potential and the multiple-phonon scattering process. We find that high order interatomic potential not only causes multiple-phonon scattering processes, but also has significant impacts on elastic phonon scattering processes. Using fourth order potential as an example, we show that it can significantly affects elastic phonon scatterings, through the formation of localized phonons. Such impact is closely related to the correlations of interfacial atoms and it becomes more significant with increasing temperature. Our work suggests that it is insufficient to consider only quadratic potential to investigate elastic phonon transport.

We investigate the anharmonic phonon scattering across a weakly interacting interface by developing a quantum mechanics-based theory. We find that the contribution from anharmonic three-phonon scatterings to interfacial thermal conductance can be cast into Landauer formula with transmission function being temperature-dependent. Surprisingly, in the weak coupling limit, the transmission due to anharmonic phonon scattering is unbounded with increasing temperature, which is physically impossible for two-phonon processes. We further reveal that the anharmonic contribution in a real heterogeneous interface (e.g., between graphene and monolayer molybdenum disulfide) can dominate over the harmonic process even at room temperature, highlighting the important role of anharmonicity in weakly interacting heterogeneous systems.

Extracting cultivated land accurately from high-resolution remote images is a basic task for precision agriculture. This report introduces our solution to the iFLYTEK challenge 2021 cultivated land extraction from high-resolution remote sensing image. The challenge requires segmenting cultivated land objects in very high-resolution multispectral remote sensing images. We established a highly effective and efficient pipeline to solve this problem. We first divided the original images into small tiles and separately performed instance segmentation on each tile. We explored several instance segmentation algorithms that work well on natural images and developed a set of effective methods that are applicable to remote sensing images. Then we merged the prediction results of all small tiles into seamless, continuous segmentation results through our proposed overlap-tile fusion strategy. We achieved the first place among 486 teams in the challenge.

Edge termination plays a vital role in determining the properties of 2D materials. By performing compelling ab initio simulations, a lowest-energy U-edge [ZZ(U)] reconstruction is revealed in the bilayer phosphorene. Such reconstruction reduces 60% edge energy compared with the pristine one and occurs almost without energy barrier, implying it should be the dominating edge in reality. The electronic band structure of phosphorene nanoribbon with such reconstruction resembles that of intrinsic 2D layer, exhibiting nearly edgeless band characteristics. Although ZZ(U) changes the topology of phosphorene nanoribbon (PNR), simulated TEM, STEM and STM images indicates it is very hard to be identified. One possible identify method is IR/Raman analyses because ZZ(U) edge alters vibrational modes dramatically. Beyond, it also increases the thermal conductivity of PNR 1.4 and 2.3 times than the pristine and Klein edges.

Despite the recent success of long-tailed object detection, almost all long-tailed object detectors are developed based on the two-stage paradigm. In practice, one-stage detectors are more prevalent in the industry because they have a simple and fast pipeline that is easy to deploy. However, in the long-tailed scenario, this line of work has not been explored so far. In this paper, we investigate whether one-stage detectors can perform well in this case. We discover the primary obstacle that prevents one-stage detectors from achieving excellent performance is: categories suffer from different degrees of positive-negative imbalance problems under the long-tailed data distribution. The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem. To address this issue, we propose the Equalized Focal Loss (EFL) that rebalances the loss contribution of positive and negative samples of different categories independently according to their imbalance degrees. Specifically, EFL adopts a category-relevant modulating factor which can be adjusted dynamically by the training status of different categories. Extensive experiments conducted on the challenging LVIS v1 benchmark demonstrate the effectiveness of our proposed method. With an end-to-end training pipeline, EFL achieves 29.2% in terms of overall AP and obtains significant performance improvements on rare categories, surpassing all existing state-of-the-art methods. The code is available at https://github.com/ModelTC/EOD., Comment: Accepted by the IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022

Despite superior performance on many computer vision tasks, deep convolution neural networks are well known to be compressed on devices that have resource constraints. Most existing network pruning methods require laborious human efforts and prohibitive computation resources, especially when the constraints are changed. This practically limits the application of model compression when the model needs to be deployed on a wide range of devices. Besides, existing methods are still challenged by the missing theoretical guidance. In this paper we propose an information theory-inspired strategy for automatic model compression. The principle behind our method is the information bottleneck theory, i.e., the hidden representation should compress information with each other. We thus introduce the normalized Hilbert-Schmidt Independence Criterion (nHSIC) on network activations as a stable and generalized indicator of layer importance. When a certain resource constraint is given, we integrate the HSIC indicator with the constraint to transform the architecture search problem into a linear programming problem with quadratic constraints. Such a problem is easily solved by a convex optimization method with a few seconds. We also provide a rigorous proof to reveal that optimizing the normalized HSIC simultaneously minimizes the mutual information between different layers. Without any search process, our method achieves better compression tradeoffs comparing to the state-of-the-art compression algorithms. For instance, with ResNet-50, we achieve a 45.3%-FLOPs reduction, with a 75.75 top-1 accuracy on ImageNet. Codes are avaliable at https://github.com/MAC-AutoML/ITPruner/tree/master.

Microservice architecture advocates a number of technologies and practices such as lightweight container, container orchestration, and DevOps, with the promised benefits of faster delivery, improved scalability, and greater autonomy. However, microservice systems implemented in industry vary a lot in terms of adopted practices and achieved benefits, drastically different from what is advocated in the literature. In this article, we conduct an empirical study, including an online survey with 51 responses and 14 interviews for experienced microservice experts to advance our understanding regarding to microservice practices in industry. As a part of our findings, the empirical study clearly revealed three levels of maturity of microservice systems (from basic to advanced): independent development and deployment, high scalability and availability, and service ecosystem, categorized by the fulfilled benefits of microservices. We also identify 11 practical issues that constrain the microservice capabilities of organizations. For each issue, we summarize the practices that have been explored and adopted in industry, along with the remaining challenges. Our study can help practitioners better position their microservice systems and determine what infrastructures and capabilities are worth investing. Our study can also help researchers better understand industrial microservice practices and identify useful research problems.

Learning discriminative representation using large-scale face datasets in the wild is crucial for real-world applications, yet it remains challenging. The difficulties lie in many aspects and this work focus on computing resource constraint and long-tailed class distribution. Recently, classification-based representation learning with deep neural networks and well-designed losses have demonstrated good recognition performance. However, the computing and memory cost linearly scales up to the number of identities (classes) in the training set, and the learning process suffers from unbalanced classes. In this work, we propose a dynamic class queue (DCQ) to tackle these two problems. Specifically, for each iteration during training, a subset of classes for recognition are dynamically selected and their class weights are dynamically generated on-the-fly which are stored in a queue. Since only a subset of classes is selected for each iteration, the computing requirement is reduced. By using a single server without model parallel, we empirically verify in large-scale datasets that 10% of classes are sufficient to achieve similar performance as using all classes. Moreover, the class weights are dynamically generated in a few-shot manner and therefore suitable for tail classes with only a few instances. We show clear improvement over a strong baseline in the largest public dataset Megaface Challenge2 (MF2) which has 672K identities and over 88% of them have less than 10 instances. Code is available at https://github.com/bilylee/DCQ, Comment: Accepted in CVPR 2021

FASER$\nu$ at the CERN Large Hadron Collider (LHC) is designed to directly detect collider neutrinos for the first time and study their cross sections at TeV energies, where no such measurements currently exist. In 2018, a pilot detector employing emulsion films was installed in the far-forward region of ATLAS, 480 m from the interaction point, and collected 12.2 fb$^{-1}$ of proton-proton collision data at a center-of-mass energy of 13 TeV. We describe the analysis of this pilot run data and the observation of the first neutrino interaction candidates at the LHC. This milestone paves the way for high-energy neutrino measurements at current and future colliders., Comment: Auxiliary materials are available at https://faser.web.cern.ch/fasernu-first-neutrino-interaction-candidates

Experimentally synthesized perovskite-type YRh$_{3}$B with a $Pm\bar{3}m$ type structure was proposed as a novel topological material (TM) via first-principles calculations and the low-energy $k\cdot p$ effective Hamiltonian, which has a quadratic contact triple point (QCTP) at point $\Gamma$ and six pairs of open nodal lines (NLs) of the hybrid type. Clear surface states observed in the surface spectrum confirmed the topological states. When spin-orbit coupling was considered, the QCTP at $\Gamma$ transferred to the quadratic-type Dirac nodal point (NP). Under 1$\%$ tetragonal strained lattice constants, YRh$_{3}$B hosted richer topological states, including a quadratic-type two-fold degenerate NP, six pairs of open NLs of the hybrid type, and two closed NLs of type I and hybrid type. Moreover, it was proved that the NLs of YRh$_{3}$B at its strained lattice constants contain all types of band-crossing points (BCPs) (i.e., type I, type II, and critical type). Such rich types of NP and NL states in one compound make it potentially applicable for multifunctional electronic devices as well as an appropriate platform to study entanglement among topological states.

In parallel to electronic systems, the concept of topology has been extended to phonons, which has led to the birth of topological phonons. Very recently, nodal point phonons, nodal line phonons, and nodal surface phonons have been proposed, and a handful of candidate materials have been predicted in solid-state materials. In this work, based on symmetry analysis and first-principles calculations, we propose that hourglass Weyl nodal line (HWNL) phonons and Dirac nodal line (DNL) phonons coexist in the phonon dispersion of a single material, KCuS, with a $Pnma$-type structure. The HWNLs and DNLs are relatively flat in frequency and well separated from other phonon bands. The corresponding topological phonon surface states appear only in the [100] and [001] surfaces, unlike those of typical phononic nodal-line materials. The reason for this phenomenon is explained based on Zak phase calculations. Our work, for the first time, proves that phononic nodal lines with different types of degeneracies can be achieved in one single material. Thus, KCuS can be viewed as a good platform to investigate the entanglement between HWNL phonons and DNL phonons.

The two-stage methods for instance segmentation, e.g. Mask R-CNN, have achieved excellent performance recently. However, the segmented masks are still very coarse due to the downsampling operations in both the feature pyramid and the instance-wise pooling process, especially for large objects. In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner. Through fusing more detailed information stage by stage, RefineMask is able to refine high-quality masks consistently. RefineMask succeeds in segmenting hard cases such as bent parts of objects that are over-smoothed by most previous methods and outputs accurate boundaries. Without bells and whistles, RefineMask yields significant gains of 2.6, 3.4, 3.8 AP over Mask R-CNN on COCO, LVIS, and Cityscapes benchmarks respectively at a small amount of additional computational cost. Furthermore, our single-model result outperforms the winner of the LVIS Challenge 2020 by 1.3 points on the LVIS test-dev set and establishes a new state-of-the-art. Code will be available at https://github.com/zhanggang001/RefineMask., Comment: Accepted by CVPR 2021. Code is available at https://github.com/zhanggang001/RefineMask

Understanding the limits of phononic heat dissipation from a two-dimensional layered material (2DLM) to its hexagonal boron nitride (h-BN) substrate and how it varies with the structure of the 2DLM is important for the design and thermal management of h-BN-supported nanoelectronic devices. We formulate an elasticity-based theory to model the phonon-mediated heat dissipation between a 2DLM and its h-BN substrate. By treating the h-BN substrate as a semi-infinite stack of harmonically coupled thin plates, we obtain semi-analytical expressions for the thermal boundary conductance (TBC) and interfacial phonon transmission spectrum. We evaluate the temperature-dependent TBC of the $N$-layer 2DLM (graphene or MoS$_{2}$) on different common substrates (h-BN vs. a-SiO$_{2}$) at different values of $N$. The results suggest that h-BN is substantially more effective for heat dissipation from MoS$_{2}$ than a-SiO$_{2}$ especially at large $N$. To understand the limitations of the our stack model, we also compare its predictions in the $N=\infty$ limit to those of the more exact Atomistic Green's Function model for the graphite-BN and molybdenite-BN interfaces. Our stack model provides clear insights into the key role of the flexural modes in the TBC and how the anisotropic elastic properties of h-BN affect heat dissipation., Comment: 11 pages, 7 figures. To be published in 2D Materials

Condensed matter systems contain both fermionic and bosonic quasiparticles. Owing to the constraint imposed by the Fermi level, ideal material candidate for the emergent particles with higher-dimensional degeneracy manifold (i.e., nodal lines and nodal surfaces) has not been found in electronic systems. This paper demonstrates that according to the first-principle calculations and symmetry analysis, realistic ternary nitride Li$_6$WN$_4$ features ideal (nearly flat) nodal-surface and nodal-line structures in its phonon spectra. These nodal degeneracies are shaped like lanterns, and their existence is guaranteed by nonsymmorphic symmetry. The corresponding topological phonon surface state covers exactly half the surface Brillouin zone (BZ) and can thereby be distinguished from those of conventional nodal-line and nodal-surface semimetals. The results of our study demonstrate the existence of ideal lantern-like phonons in realistic materials, which enriches the classification of topological quantum phases and provides a good basis for investigating the interaction between nodal-line and nodal-surface phonons in a single material.

Quantum manipulation based on geometric phases provides a promising way towards robust quantum gates. However, in the current implementation of nonadiabatic geometric phases, operational and/or random errors tend to destruct the conditions that induce geometric phases, thereby smearing their noise-resilient feature. In a recent experiment [Y. Xu et al., Phys. Rev. Lett. 124, 230503 (2020)], high-fidelity universal geometric quantum gates have been implemented in a superconducting circuit, which are robust to different types of errors under different configurations of the geometric evolution paths. Here, we apply the path-design strategy to explain in detail why both configurations can realize universal quantum gates in a single-loop way. Meanwhile, we purposefully induce our geometric manipulation by selecting the path configuration that is robust against the qubit-frequency-drift induced error, which is the dominant error source on realistic superconducting circuits and has not been deliberately addressed. Moreover, our proposal can further integrate with the composite scheme to enhance the gate robustness, which is verified by numerical simulations. Therefore, our scheme provides a promising way towards practical realization of high-fidelity and robust nonadiabatic geometric quantum gates., Comment: 9 pages, 7 figures