arXiv subjects

Wei Jia

Publications and source records attributed to Wei Jia.

At least 37 records · Page 2Linked to original sources

arXiv2025

Unconventional hybrid-order topological insulators

Exploring novel topological matters with exotic quantum states has always been a core issue in the field of condensed matter physics, which can update the understanding of topological phases and broaden the classification of topological materials. Here, we report a class of unconventional hybrid-order topological insulators (HyOTIs), which simultaneously host various different higher-order topological states in a single band gap. Such topological states exhibit a unique bulk-boundary correspondence that is different from the well-known first-order topological states, higher-order topological states, and the coexistence of both. Particularly, we develop a generic surface theory to precisely capture them and discover a three-dimensional unconventional HyOTI protected by inversion symmetry, which renders both helical and corner topological states and exhibits an unprecedented bulk-edge-corner correspondence. By adjusting the parameters of the system, we also observe the nontrivial phase transitions between the inversion-symmetric HyOTI and other conventional phases. We further propose a circuit-based experimental scheme to detect these interesting results. Remarkably, we demonstrate that a modified tight-binding model of bismuth can support the unconventional HyOTI, suggesting a possible route for its material realization. This work shall significantly advance the research of hybrid topological states in both theory and experiment.

cond-mat.mes-hall↗

arXiv2025

DPWMixer: Dual-Path Wavelet Mixer for Long-Term Time Series Forecasting

Long-term time series forecasting (LTSF) is a critical task in computational intelligence. While Transformer-based models effectively capture long-range dependencies, they often suffer from quadratic complexity and overfitting due to data sparsity. Conversely, efficient linear models struggle to depict complex non-linear local dynamics. Furthermore, existing multi-scale frameworks typically rely on average pooling, which acts as a non-ideal low-pass filter, leading to spectral aliasing and the irreversible loss of high-frequency transients. In response, this paper proposes DPWMixer, a computationally efficient Dual-Path architecture. The framework is built upon a Lossless Haar Wavelet Pyramid that replaces traditional pooling, utilizing orthogonal decomposition to explicitly disentangle trends and local fluctuations without information loss. To process these components, we design a Dual-Path Trend Mixer that integrates a global linear mapping for macro-trend anchoring and a flexible patch-based MLP-Mixer for micro-dynamic evolution. Finally, An adaptive multi-scale fusion module then integrates predictions from diverse scales, weighted by channel stationarity to optimize synthesis. Extensive experiments on eight public benchmarks demonstrate that our method achieves a consistent improvement over state-of-the-art baselines. The code is available at https://github.com/hit636/DPWMixer.

cs.LG↗

arXiv2025

Virtual Width Networks

We introduce Virtual Width Networks (VWN), a framework that delivers the benefits of wider representations without incurring the quadratic cost of increasing the hidden size. VWN decouples representational width from backbone width, expanding the embedding space while keeping backbone compute nearly constant. In our large-scale experiment, an 8-times expansion accelerates optimization by over 2 times for next-token and 3 times for next-2-token prediction. The advantage amplifies over training as both the loss gap grows and the convergence-speedup ratio increases, showing that VWN is not only token-efficient but also increasingly effective with scale. Moreover, we identify an approximately log-linear scaling relation between virtual width and loss reduction, offering an initial empirical basis and motivation for exploring virtual-width scaling as a new dimension of large-model efficiency.

cs.LG↗

arXiv2025

Deep Learning in Palmprint Recognition-A Comprehensive Survey

Palmprint recognition has emerged as a prominent biometric technology, widely applied in diverse scenarios. Traditional handcrafted methods for palmprint recognition often fall short in representation capability, as they heavily depend on researchers' prior knowledge. Deep learning (DL) has been introduced to address this limitation, leveraging its remarkable successes across various domains. While existing surveys focus narrowly on specific tasks within palmprint recognition-often grounded in traditional methodologies-there remains a significant gap in comprehensive research exploring DL-based approaches across all facets of palmprint recognition. This paper bridges that gap by thoroughly reviewing recent advancements in DL-powered palmprint recognition. The paper systematically examines progress across key tasks, including region-of-interest segmentation, feature extraction, and security/privacy-oriented challenges. Beyond highlighting these advancements, the paper identifies current challenges and uncovers promising opportunities for future research. By consolidating state-of-the-art progress, this review serves as a valuable resource for researchers, enabling them to stay abreast of cutting-edge technologies and drive innovation in palmprint recognition.

cs.CV↗

arXiv2025

Online Continual Learning via Spiking Neural Networks with Sleep Enhanced Latent Replay

Edge computing scenarios necessitate the development of hardware-efficient online continual learning algorithms to be adaptive to dynamic environment. However, existing algorithms always suffer from high memory overhead and bias towards recently trained tasks. To tackle these issues, this paper proposes a novel online continual learning approach termed as SESLR, which incorporates a sleep enhanced latent replay scheme with spiking neural networks (SNNs). SESLR leverages SNNs' binary spike characteristics to store replay features in single bits, significantly reducing memory overhead. Furthermore, inspired by biological sleep-wake cycles, SESLR introduces a noise-enhanced sleep phase where the model exclusively trains on replay samples with controlled noise injection, effectively mitigating classification bias towards new classes. Extensive experiments on both conventional (MNIST, CIFAR10) and neuromorphic (NMNIST, CIFAR10-DVS) datasets demonstrate SESLR's effectiveness. On Split CIFAR10, SESLR achieves nearly 30% improvement in average accuracy with only one-third of the memory consumption compared to baseline methods. On Split CIFAR10-DVS, it improves accuracy by approximately 10% while reducing memory overhead by a factor of 32. These results validate SESLR as a promising solution for online continual learning in resource-constrained edge computing scenarios.

cs.NE↗

arXiv2025

WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wild

Recent multi-modal Large Language Models (LLMs) such as GPT-4o have demonstrated strong capabilities of direct speech interaction. However, the lack of specialized and comprehensive benchmarks for end-to-end speech LLM evaluation hinders optimizing the user experience of Audio LLMs in real-world applications. Existing evaluation methods often adapt text-based benchmarks, overlooking speech's unique characteristics and challenges, including prosody, homophones, stuttering, and differing user expectations. Here, we introduce the first comprehensive benchmark designed to systematically evaluate end-to-end speechLLMs in practical speech conversations. We systematically curate real-world chat data relevant to spoken scenarios, introduce diversity in speaker attributes and acoustic conditions, and augment the dataset with speech-specific phenomena. We further design a query-aware evaluation method to use customized evaluation checklists and prompts to enhance the accuracy of automatic evaluation. We conduct comprehensive testing and detailed analysis of various mainstream speech models, revealing significant differences in model performance across different speech scenarios. The use of query-aware evaluation further enables a finer-grained assessment under various speech-specific scenarios. Our benchmark can provide valuable insights for speech model development and evaluation.

cs.CL↗

arXiv2025

Multiple topological corner states in the continuum of extended kagome lattice

The kagome lattice is renowned for its exotic electronic properties, such as flat bands, Dirac points, and Van Hove singularities. These features have provided a fertile ground for exploring exotic quantum phenomena. Here, we discover that a breathing kagome lattice with long-range hoppings can host multiple zero-energy corner states, which emerge as topologically protected bound states in the continuum (BICs). This result demonstrates that additional hopping control can induce further non-trivial physics of the kagome lattice. Since the zero-energy corner states in the continuum are intertwined with a substantial number of zero-energy bulk states, we also develop a momentum-space topological characterization theory to precisely quantify the number of corner states, revealing a general bulk-corner correspondence. Furthermore, we uncover three distinct types of topological phase transitions (TPTs) for the BICs driven by shifts in the spatial localization of zero-energy bulk and/or edge states. These TPTs are exactly captured by our characterization theory. This work provides deep insights into the topological physics of the kagome lattice and broadens the understanding of its electronic properties

cond-mat.mes-hall↗

arXiv2025

LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation

Recent research has been increasingly focusing on developing 3D world models that simulate complex real-world scenarios. World models have found broad applications across various domains, including embodied AI, autonomous driving, entertainment, etc. A more realistic simulation with accurate physics will effectively narrow the sim-to-real gap and allow us to gather rich information about the real world conveniently. While traditional manual modeling has enabled the creation of virtual 3D scenes, modern approaches have leveraged advanced machine learning algorithms for 3D world generation, with most recent advances focusing on generative methods that can create virtual worlds based on user instructions. This work explores such a research direction by proposing LatticeWorld, a simple yet effective 3D world generation framework that streamlines the industrial production pipeline of 3D environments. LatticeWorld leverages lightweight LLMs (LLaMA-2-7B) alongside the industry-grade rendering engine (e.g., Unreal Engine 5) to generate a dynamic environment. Our proposed framework accepts textual descriptions and visual instructions as multimodal inputs and creates large-scale 3D interactive worlds with dynamic agents, featuring competitive multi-agent interaction, high-fidelity physics simulation, and real-time rendering. We conduct comprehensive experiments to evaluate LatticeWorld, showing that it achieves superior accuracy in scene layout generation and visual fidelity. Moreover, LatticeWorld achieves over a $90\times$ increase in industrial production efficiency while maintaining high creative quality compared with traditional manual production methods. Our demo video is available at https://youtu.be/8VWZXpERR18

cs.AI↗

arXiv2025

VSAG: An Optimized Search Framework for Graph-based Approximate Nearest Neighbor Search

Approximate nearest neighbor search (ANNS) is a fundamental problem in vector databases and AI infrastructures. Recent graph-based ANNS algorithms have achieved high search accuracy with practical efficiency. Despite the advancements, these algorithms still face performance bottlenecks in production, due to the random memory access patterns of graph-based search and the high computational overheads of vector distance. In addition, the performance of a graph-based ANNS algorithm is highly sensitive to parameters, while selecting the optimal parameters is cost-prohibitive, e.g., manual tuning requires repeatedly re-building the index. This paper introduces VSAG, an open-source framework that aims to enhance the in production performance of graph-based ANNS algorithms. VSAG has been deployed at scale in the services of Ant Group, and it incorporates three key optimizations: (i) efficient memory access: it reduces L3 cache misses with pre-fetching and cache-friendly vector organization; (ii) automated parameter tuning: it automatically selects performance-optimal parameters without requiring index rebuilding; (iii) efficient distance computation: it leverages modern hardware, scalar quantization, and smartly switches to low-precision representation to dramatically reduce the distance computation costs. We evaluate VSAG on real-world datasets. The experimental results show that VSAG achieves the state-of-the-art performance and provides up to 4x speedup over HNSWlib (an industry-standard library) while ensuring the same accuracy.

cs.DB↗

arXiv2025

Understanding Stragglers in Large Model Training Using What-if Analysis

Large language model (LLM) training is one of the most demanding distributed computations today, often requiring thousands of GPUs with frequent synchronization across machines. Such a workload pattern makes it susceptible to stragglers, where the training can be stalled by few slow workers. At ByteDance we find stragglers are not trivially always caused by hardware failures, but can arise from multiple complex factors. This work aims to present a comprehensive study on the straggler issues in LLM training, using a five-month trace collected from our ByteDance LLM training cluster. The core methodology is what-if analysis that simulates the scenario without any stragglers and contrasts with the actual case. We use this method to study the following questions: (1) how often do stragglers affect training jobs, and what effect do they have on job performance; (2) do stragglers exhibit temporal or spatial patterns; and (3) what are the potential root causes for stragglers?

cs.DC↗

arXiv2025

TierBase: A Workload-Driven Cost-Optimized Key-Value Store

In the current era of data-intensive applications, the demand for high-performance, cost-effective storage solutions is paramount. This paper introduces a Space-Performance Cost Model for key-value store, designed to guide cost-effective storage configuration decisions. The model quantifies the trade-offs between performance and storage costs, providing a framework for optimizing resource allocation in large-scale data serving environments. Guided by this cost model, we present TierBase, a distributed key-value store developed by Ant Group that optimizes total cost by strategically synchronizing data between cache and storage tiers, maximizing resource utilization and effectively handling skewed workloads. To enhance cost-efficiency, TierBase incorporates several optimization techniques, including pre-trained data compression, elastic threading mechanisms, and the utilization of persistent memory. We detail TierBase's architecture, key components, and the implementation of cost optimization strategies. Extensive evaluations using both synthetic benchmarks and real-world workloads demonstrate TierBase's superior cost-effectiveness compared to existing solutions. Furthermore, case studies from Ant Group's production environments showcase TierBase's ability to achieve up to 62% cost reduction in primary scenarios, highlighting its practical impact in large-scale online data serving.

cs.DB↗

arXiv2025

Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning

We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 86.7 on AIME 2024, 55.0 on Codeforces and 77.3 on GPQA, demonstrating excellent reasoning abilities in STEM and coding. Beyond reasoning tasks, the method demonstrates notable generalization across diverse domains. For instance, it surpasses DeepSeek R1 by 8% in win rate on non-reasoning tasks, indicating its broader applicability. Compared to other state-of-the-art reasoning models, Seed1.5-Thinking is a Mixture-of-Experts (MoE) model with a relatively small size, featuring 20B activated and 200B total parameters. As part of our effort to assess generalized reasoning, we develop two internal benchmarks, BeyondAIME and Codeforces, both of which will be publicly released to support future research. Model trial link: https://www.volcengine.com/experience/ark.

cs.CL↗

arXiv2025

Diff-Palm: Realistic Palmprint Generation with Polynomial Creases and Intra-Class Variation Controllable Diffusion Models

Palmprint recognition is significantly limited by the lack of large-scale publicly available datasets. Previous methods have adopted Bézier curves to simulate the palm creases, which then serve as input for conditional GANs to generate realistic palmprints. However, without employing real data fine-tuning, the performance of the recognition model trained on these synthetic datasets would drastically decline, indicating a large gap between generated and real palmprints. This is primarily due to the utilization of an inaccurate palm crease representation and challenges in balancing intra-class variation with identity consistency. To address this, we introduce a polynomial-based palm crease representation that provides a new palm crease generation mechanism more closely aligned with the real distribution. We also propose the palm creases conditioned diffusion model with a novel intra-class variation control method. By applying our proposed $K$-step noise-sharing sampling, we are able to synthesize palmprint datasets with large intra-class variation and high identity consistency. Experimental results show that, for the first time, recognition models trained solely on our synthetic datasets, without any fine-tuning, outperform those trained on real datasets. Furthermore, our approach achieves superior recognition performance as the number of generated identities increases.

cs.CV↗

arXiv2025

Degradation of 2.4-kV $Ga_{2}O_{3}$ Schottky Barrier Diode at High Temperatures up to 500 °C

Ga2O3 Schottky barrier diodes featuring a field plate and a composite SiO2/SiNx dielectric layer beneath the field plate were fabricated, achieving a breakdown voltage of 2.4 kV at room temperature. Electrical performance and degradation were analyzed via I-V and C-V measurements from 25 °C to 500 °C, revealing temperature-dependent transport, interface stability, and device stability. Upon returning to room temperature, the diodes exhibited nearly unchanged forward characteristics, while the breakdown voltage declined significantly from 2.4 kV to 700 V. This behavior indicates a temperature-induced reduction in the barrier height. Detailed analysis revealed that variable range hopping (VRH) dominated the leakage mechanism at moderate temperatures, while thermal emission (TE) became increasingly significant at temperatures exceeding 400 °C.

cond-mat.mtrl-sci↗

arXiv2025

PVTree: Realistic and Controllable Palm Vein Generation for Recognition Tasks

Palm vein recognition is an emerging biometric technology that offers enhanced security and privacy. However, acquiring sufficient palm vein data for training deep learning-based recognition models is challenging due to the high costs of data collection and privacy protection constraints. This has led to a growing interest in generating pseudo-palm vein data using generative models. Existing methods, however, often produce unrealistic palm vein patterns or struggle with controlling identity and style attributes. To address these issues, we propose a novel palm vein generation framework named PVTree. First, the palm vein identity is defined by a complex and authentic 3D palm vascular tree, created using an improved Constrained Constructive Optimization (CCO) algorithm. Second, palm vein patterns of the same identity are generated by projecting the same 3D vascular tree into 2D images from different views and converting them into realistic images using a generative model. As a result, PVTree satisfies the need for both identity consistency and intra-class diversity. Extensive experiments conducted on several publicly available datasets demonstrate that our proposed palm vein generation method surpasses existing methods and achieves a higher TAR@FAR=1e-4 under the 1:1 Open-set protocol. To the best of our knowledge, this is the first time that the performance of a recognition model trained on synthetic palm vein data exceeds that of the recognition model trained on real data, which indicates that palm vein image generation research has a promising future.

cs.CV↗

arXiv2025

Generic reduction theory for Fermi sea topology in metallic systems

The Fermi sea of a metal can host exotic quantum topology, which governs its conductance quantization and is characterized by the Euler characteristic ($χ_F$). In contrast to the well-known band topology, which is determined by the global features of wave functions, the topology of such metallic systems is intrinsically linked to the geometry of the Fermi sea. As a result, probing and identifying $χ_F$ in high-dimensional systems presents a challenge. Here, we propose a generic dimensional reduction theory for the Fermi sea topology in $d$-dimensional metallic systems, showing that $χ_F$ can be determined by the features of so-called reduced critical points on Fermi surfaces. Moreover, we reveal that $χ_F$ can be interpreted as a topological invariant of band topology by mapping a metallic system to a gapped system. Building on this nontrivial result, we identify a broad class of topological superconductors (SCs) whose topological numbers are precisely determined by the $χ_F$ of their normally filled bands. This provides an indirect method to capture $χ_F$ by measuring the (pseudo)spin polarizations of these topological SCs. Our findings are expected to significantly advance research into Fermi sea topology.

cond-mat.mes-hall↗

arXiv2025

Effective and General Distance Computation for Approximate Nearest Neighbor Search

Approximate K Nearest Neighbor (AKNN) search in high-dimensional spaces is a critical yet challenging problem. In AKNN search, distance computation is the core task that dominates the runtime. Existing approaches typically use approximate distances to improve computational efficiency, often at the cost of reduced search accuracy. To address this issue, the state-of-the-art method, ADSampling, employs random projections to estimate approximate distances and introduces an additional distance correction process to mitigate accuracy loss. However, ADSampling has limitations in both effectiveness and generality, primarily due to its reliance on random projections for distance approximation and correction. To address the effectiveness limitations of ADSampling, we leverage data distribution to improve distance computation via orthogonal projection. Furthermore, to overcome the generality limitations of ADSampling, we adopt a data-driven approach to distance correction, decoupling the correction process from the distance approximation process. Extensive experiments demonstrate the superiority and effectiveness of our method. In particular, compared to ADSampling, our method achieves a speedup of 1.6 to 2.1 times on real-world datasets while providing higher accuracy.

cs.DB↗

arXiv2025

PoAct: Policy and Action Dual-Control Agent for Generalized Applications

Based on their superior comprehension and reasoning capabilities, Large Language Model (LLM) driven agent frameworks have achieved significant success in numerous complex reasoning tasks. ReAct-like agents can solve various intricate problems step-by-step through progressive planning and tool calls, iteratively optimizing new steps based on environmental feedback. However, as the planning capabilities of LLMs improve, the actions invoked by tool calls in ReAct-like frameworks often misalign with complex planning and challenging data organization. Code Action addresses these issues while also introducing the challenges of a more complex action space and more difficult action organization. To leverage Code Action and tackle the challenges of its complexity, this paper proposes Policy and Action Dual-Control Agent (PoAct) for generalized applications. The aim is to achieve higher-quality code actions and more accurate reasoning paths by dynamically switching reasoning policies and modifying the action space. Experimental results on the Agent Benchmark for both legal and generic scenarios demonstrate the superior reasoning capabilities and reduced token consumption of our approach in complex tasks. On the LegalAgentBench, our method shows a 20 percent improvement over the baseline while requiring fewer tokens. We conducted experiments and analyses on the GPT-4o and GLM-4 series models, demonstrating the significant potential and scalability of our approach to solve complex problems.

cs.AI↗