Searcharxiv⌕ Search

arXiv subjects

Jie Luo

Publications and source records attributed to Jie Luo.

At least 37 records · Page 2Linked to original sources
arXiv2026

Geometry-Aware Cross Modal Alignment for Light Field-LiDAR Semantic Segmentation

Semantic segmentation serves as a cornerstone of scene understanding in autonomous driving but continues to face significant challenges under complex conditions such as occlusion. Light field and LiDAR modalities provide complementary visual and spatial cues that are beneficial for robust perception; however, their effective integration is hindered by limited viewpoint diversity and inherent modality discrepancies. To address these challenges, the first multimodal semantic segmentation dataset integrating light field data and point cloud data is proposed. Based on this dataset, we proposed a multi-modal light field point-cloud fusion segmentation network(Mlpfseg), incorporating feature completion and depth perception to segment both camera images and LiDAR point clouds simultaneously. The feature completion module addresses the density mismatch between point clouds and image pixels by performing differential reconstruction of point-cloud feature maps, enhancing the fusion of these modalities. The depth perception module improves the segmentation of occluded objects by reinforcing attention scores for better occlusion awareness. Our method outperforms image-only segmentation by 1.71 Mean Intersection over Union(mIoU) and point cloud-only segmentation by 2.38 mIoU, demonstrating its effectiveness.

cs.CV↗
arXiv2026

Advances in Josephson Junction Materials and Processes Toward Practical Quantum Computing

The Josephson junction is the fundamental nonlinear building block of superconducting quantum technologies. Its macroscopic quantum tunneling physics underpins superconducting quantum computing, sensing, and communication, but scaling these platforms to utility-scale architectures places increasingly stringent demands on junction materials, interfaces, and fabrication. In quantum computing, these demands include high reproducibility, low dissipation, tunability, compact device footprint, and resilience to noise and defects. This review surveys how advances in materials science, device characterization, and nanofabrication are addressing these challenges and redefining the figures of merit for next-generation Josephson junctions. We also examine the evolution of fabrication strategies, from conventional multi-angle evaporation to foundry-compatible superconducting processes and the integration of emerging junction materials. Progress along these directions will determine how rapidly Josephson junctions move from laboratory-scale components to the foundation of industrial-scale quantum processors.

quant-ph↗
arXiv2026

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments.

cs.CL↗
arXiv2025

Time-Aware Adaptive Side Information Fusion for Sequential Recommendation

Incorporating item-side information, such as category and brand, into sequential recommendation is a well-established and effective approach for improving performance. However, despite significant advancements, current models are generally limited by three key challenges: they often overlook the fine-grained temporal dynamics inherent in timestamps, exhibit vulnerability to noise in user interaction sequences, and rely on computationally expensive fusion architectures. To systematically address these challenges, we propose the Time-Aware Adaptive Side Information Fusion (TASIF) framework. TASIF integrates three synergistic components: (1) a simple, plug-and-play time span partitioning mechanism to capture global temporal patterns; (2) an adaptive frequency filter that leverages a learnable gate to denoise feature sequences adaptively, thereby providing higher-quality inputs for subsequent fusion modules; and (3) an efficient adaptive side information fusion layer, this layer employs a "guide-not-mix" architecture, where attributes guide the attention mechanism without being mixed into the content-representing item embeddings, ensuring deep interaction while ensuring computational efficiency. Extensive experiments on four public datasets demonstrate that TASIF significantly outperforms state-of-the-art baselines while maintaining excellent efficiency in training. Our source code is available at https://github.com/jluo00/TASIF.

cs.IR↗
arXiv2025

EfficientECG: Cross-Attention with Feature Fusion for Efficient Electrocardiogram Classification

Electrocardiogram is a useful diagnostic signal that can detect cardiac abnormalities by measuring the electrical activity generated by the heart. Due to its rapid, non-invasive, and richly informative characteristics, ECG has many emerging applications. In this paper, we study novel deep learning technologies to effectively manage and analyse ECG data, with the aim of building a diagnostic model, accurately and quickly, that can substantially reduce the burden on medical workers. Unlike the existing ECG models that exhibit a high misdiagnosis rate, our deep learning approaches can automatically extract the features of ECG data through end-to-end training. Specifically, we first devise EfficientECG, an accurate and lightweight classification model for ECG analysis based on the existing EfficientNet model, which can effectively handle high-frequency long-sequence ECG data with various leading types. On top of that, we next propose a cross-attention-based feature fusion model of EfficientECG for analysing multi-lead ECG data with multiple features (e.g., gender and age). Our evaluations on representative ECG datasets validate the superiority of our model against state-of-the-art works in terms of high precision, multi-feature fusion, and lightweights.

cs.LG↗
arXiv2025

VoQA: Visual-only Question Answering

Visual understanding requires interpreting both natural scenes and the textual information that appears within them, motivating tasks such as Visual Question Answering (VQA). However, current VQA benchmarks overlook scenarios with visually embedded questions, whereas advanced agents should be able to see the question without separate text input as humans. We introduce Visual-only Question Answering (VoQA), where both the scene and the question appear within a single image, requiring models to perceive and reason purely through vision. This setting supports more realistic visual understanding and interaction in scenarios where questions or instructions are embedded directly in the visual scene. Evaluations under pure visual-only zero-shot, prompt-guided and OCR-assisted settings show that current models exhibit a clear performance drop compared to traditional VQA. To address this, we investigate question-alignment fine-tuning strategies designed to guide models toward interpreting the visual question prior to reasoning. Leveraging VoQA dataset together with these strategies yields robust vision-only reasoning while preserving cross-task generalization to traditional VQA, reflecting the complementary visual and textual reasoning capabilities fostered through VoQA training. The code and data are publicly available.

cs.CV↗
arXiv2025

Unified Error Analysis for Synchronous and Asynchronous Two-User Random Access

We consider a two-user random access system in which each user independently selects a coding scheme from a finite set for every message, without sharing these choices with the other user or with the receiver. The receiver aims to decode only user 1 message but may also decode user 2 message when beneficial. In the synchronous setting, the receiver employs two parallel sub-decoders: one dedicated to decoding user 1 message and another that jointly decodes both users messages. Their outputs are synthesized to produce the final decoding or collision decision. For the asynchronous setting, we examine a time interval containing $L$ consecutive codewords from each user. The receiver deploys $2^{2L}$ parallel sub-decoders, each responsible for decoding a subset of the message-code index pairs. In both synchronous and asynchronous cases, every sub-decoder partitions the coding space into three disjoint regions: operation, margin, and collision, and outputs either decoded messages or a collision report according to the region in which the estimated code index vector lies. Error events are defined for each sub-decoder and for the overall receiver whenever the expected output is not produced. We derive achievable upper bounds on the generalized error performance, defined as a weighted sum of incorrect-decoding, collision, and miss-detection probabilities, for both synchronous and asynchronous scenarios.

cs.IT↗
arXiv2025

Training Hybrid Deep Quantum Neural Network for Efficient Reinforcement Learning

Quantum circuits embed data in a Hilbert space whose dimensionality grows exponentially with the number of qubits, allowing even shallow parameterised quantum circuits (PQCs) to represent highly-correlated probability distributions that are costly for classical networks to capture. Reinforcement-learning (RL) agents, which must reason over long-horizon, continuous-control tasks, stand to benefit from this expressive quantum feature space, but only if the quantum layers can be trained jointly with the surrounding deep-neural components. Current gradient-estimation techniques (e.g., parameter-shift rule) make such hybrid training impractical for realistic RL workloads, because every gradient step requires a prohibitive number of circuit evaluations and thus erodes the potential quantum advantage. We introduce qtDNN, a tangential surrogate that locally approximates a PQC with a small differentiable network trained on-the-fly from the same minibatch. Embedding qtDNN inside the computation graph yields scalable batch gradients while keeping the original quantum layer for inference. Building on qtDNN we design hDQNN-TD3, a hybrid deep quantum neural network for continuous-control reinforcement learning based on the TD3 architecture, which matches or exceeds state-of-the-art classical performance on popular benchmarks. The method opens a path toward applying hybrid quantum models to large-scale RL and other gradient-intensive machine-learning tasks.

quant-ph↗
arXiv2025

Self-Optimizing Machine Learning Potential Assisted Automated Workflow for Highly Efficient Complex Systems Material Design

Machine learning interatomic potentials have revolutionized complex materials design by enabling rapid exploration of material configurational spaces via crystal structure prediction with ab initio accuracy. However, critical challenges persist in ensuring robust generalization to unknown structures and minimizing the requirement for substantial expert knowledge and time-consuming manual interventions. Here, we propose an automated crystal structure prediction framework built upon the attention-coupled neural networks potential to address these limitations. The generalizability of the potential is achieved by sampling regions across the local minima of the potential energy surface, where the self-evolving pipeline autonomously refines the potential iteratively while minimizing human intervention. The workflow is validated on Mg-Ca-H ternary and Be-P-N-O quaternary systems by exploring nearly 10 million configurations, demonstrating substantial speedup compared to first-principles calculations. These results underscore the effectiveness of our approach in accelerating the exploration and discovery of complex multi-component functional materials.

cond-mat.mtrl-sci↗
arXiv2025

Symmetry-Guided Multi-Agent Inverse Reinforcement Learning

In robotic systems, the performance of reinforcement learning depends on the rationality of predefined reward functions. However, manually designed reward functions often lead to policy failures due to inaccuracies. Inverse Reinforcement Learning (IRL) addresses this problem by inferring implicit reward functions from expert demonstrations. Nevertheless, existing methods rely heavily on large amounts of expert demonstrations to accurately recover the reward function. The high cost of collecting expert demonstrations in robotic applications, particularly in multi-robot systems, severely hinders the practical deployment of IRL. Consequently, improving sample efficiency has emerged as a critical challenge in multi-agent inverse reinforcement learning (MIRL). Inspired by the symmetry inherent in multi-agent systems, this work theoretically demonstrates that leveraging symmetry enables the recovery of more accurate reward functions. Building upon this insight, we propose a universal framework that integrates symmetry into existing multi-agent adversarial IRL algorithms, thereby significantly enhancing sample efficiency. Experimental results from multiple challenging tasks have demonstrated the effectiveness of this framework. Further validation in physical multi-robot systems has shown the practicality of our method.

cs.RO↗
arXiv2025

Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding

Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hardware-aware model-system co-design optimized for minimizing decoding costs. Step-3 innovates in two key dimensions: (1) A novel Multi-Matrix Factorization Attention (MFA) mechanism that significantly reduces both KV cache size and computation while maintaining high attention expressiveness, and (2) Attention-FFN Disaggregation (AFD), a distributed inference system that decouples attention and Feed-Forward Network (FFN) layers into specialized subsystems. This co-design achieves unprecedented cost efficiency: Step-3 significantly reduces theoretical decoding costs compared with models like DeepSeek-V3 and Qwen3 MoE 235B, with the gains widening at longer context. Step-3 achieves low cost while activating 38B parameters per token (more than DeepSeek-V3 and Qwen3 MoE 235B), demonstrating that hardware-aligned attention arithmetic intensity, MoE sparsity, and AFD are critical to cost-effectiveness. We perform a head-to-head comparison with DeepSeek-V3 in its favorable scenarios. Our implementation on Hopper GPUs achieves a decoding throughput of up to 4,039 tokens per second per GPU under 50ms TPOT SLA (4K context, FP8, no MTP). It is higher than DeepSeek-V3's 2,324 in the same setup and sets a new Pareto frontier for LLM decoding.

cs.LG↗
arXiv2025

BiVM: Accurate Binarized Neural Network for Efficient Video Matting

Deep neural networks for real-time video matting suffer significant computational limitations on edge devices, hindering their adoption in widespread applications such as online conferences and short-form video production. Binarization emerges as one of the most common compression approaches with compact 1-bit parameters and efficient bitwise operations. However, accuracy and efficiency limitations exist in the binarized video matting network due to its degenerated encoder and redundant decoder. Following a theoretical analysis based on the information bottleneck principle, the limitations are mainly caused by the degradation of prediction-relevant information in the intermediate features and the redundant computation in prediction-irrelevant areas. We present BiVM, an accurate and resource-efficient Binarized neural network for Video Matting. First, we present a series of binarized computation structures with elastic shortcuts and evolvable topologies, enabling the constructed encoder backbone to extract high-quality representation from input videos for accurate prediction. Second, we sparse the intermediate feature of the binarized decoder by masking homogeneous parts, allowing the decoder to focus on representation with diverse details while alleviating the computation burden for efficient inference. Furthermore, we construct a localized binarization-aware mimicking framework with the information-guided strategy, prompting matting-related representation in full-precision counterparts to be accurately and fully utilized. Comprehensive experiments show that the proposed BiVM surpasses alternative binarized video matting networks, including state-of-the-art (SOTA) binarization methods, by a substantial margin. Moreover, our BiVM achieves significant savings of 14.3x and 21.6x in computation and storage costs, respectively. We also evaluate BiVM on ARM CPU hardware.

cs.CV↗
arXiv2025

Drive Any Mesh: 4D Latent Diffusion for Mesh Deformation from Video

We propose DriveAnyMesh, a method for driving mesh guided by monocular video. Current 4D generation techniques encounter challenges with modern rendering engines. Implicit methods have low rendering efficiency and are unfriendly to rasterization-based engines, while skeletal methods demand significant manual effort and lack cross-category generalization. Animating existing 3D assets, instead of creating 4D assets from scratch, demands a deep understanding of the input's 3D structure. To tackle these challenges, we present a 4D diffusion model that denoises sequences of latent sets, which are then decoded to produce mesh animations from point cloud trajectory sequences. These latent sets leverage a transformer-based variational autoencoder, simultaneously capturing 3D shape and motion information. By employing a spatiotemporal, transformer-based diffusion model, information is exchanged across multiple latent frames, enhancing the efficiency and generalization of the generated results. Our experimental results demonstrate that DriveAnyMesh can rapidly produce high-quality animations for complex motions and is compatible with modern rendering engines. This method holds potential for applications in both the gaming and filming industries.

cs.CV↗
arXiv2025

Robust Knowledge Graph Embedding via Denoising

We focus on obtaining robust knowledge graph embedding under perturbation in the embedding space. To address these challenges, we introduce a novel framework, Robust Knowledge Graph Embedding via Denoising, which enhances the robustness of KGE models on noisy triples. By treating KGE methods as energy-based models, we leverage the established connection between denoising and score matching, enabling the training of a robust denoising KGE model. Furthermore, we propose certified robustness evaluation metrics for KGE methods based on the concept of randomized smoothing. Through comprehensive experiments on benchmark datasets, our framework consistently shows superior performance compared to existing state-of-the-art KGE methods when faced with perturbed entity embedding.

cs.LG↗
arXiv2025

Clustering Properties of Self-Supervised Learning

Self-supervised learning (SSL) methods via joint embedding architectures have proven remarkably effective at capturing semantically rich representations with strong clustering properties, magically in the absence of label supervision. Despite this, few of them have explored leveraging these untapped properties to improve themselves. In this paper, we provide an evidence through various metrics that the encoder's output $encoding$ exhibits superior and more stable clustering properties compared to other components. Building on this insight, we propose a novel positive-feedback SSL method, termed Representation Self-Assignment (ReSA), which leverages the model's clustering properties to promote learning in a self-guided manner. Extensive experiments on standard SSL benchmarks reveal that models pretrained with ReSA outperform other state-of-the-art SSL methods by a significant margin. Finally, we analyze how ReSA facilitates better clustering properties, demonstrating that it effectively enhances clustering performance at both fine-grained and coarse-grained levels, shaping representations that are inherently more structured and semantically meaningful.

cs.LG↗