Researcher profile

Yang Zhao

Yang Zhao contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

60works

0followers

44topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations

Operating and maintaining (O&M) large-scale online engine systems (eg, search, recommendation and advertising) demands substantial human effort for release monitoring, alert response, and root cause analysis. Despite the inherent suitability of LLM-based agents for such operational scenarios, the critical bottleneck impeding their practical deployment lies not in reasoning, but in orchestration capability - specifically, the precise selection of relevant data (encompassing metrics, logs, and change events) and applicable knowledge (including handbook-defined rules and empirically derived practitioner experience) tailored to each individual operational event. Feeding all signals indiscriminately causes dilution and hallucination, while manually curating the event-to-(data, knowledge) mapping is intractable under dozens of daily releases. Here we present Bian Que, an agentic operating framework with three contributions: (i) The unified operational paradigm, which abstracts routine daily O&M actions into three canonical patterns: release interception, proactive inspection, and alert root cause analysis; (ii) The flexible Skill Arrangement, each predefined Skill explicitly defines the requisite data and operational knowledge for each specific context. Such Skills can be automatically generated and updated by LLM agents, and can also be iteratively optimized by on-call engineers via natural language instructions. (iii) The unified self-evolving mechanism, where each correction signal enables two parallel evolutionary pathways: distilling event memory into knowledge, and targeted refinement of Skills. Deployed on the e-commerce search engine of KuaiShou, Bian Que reduces alert volume by 75%, achieves 80% root-cause analysis accuracy, cuts mean time to resolution by over 50%, and attains a 99.0% pass rate on offline evaluations. Codes are at https://github.com/benchen4395/BianQue_Assistant.

preprint2026arXiv

Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention

Multi-Agent Path Finding (MAPF) is a coordination problem that requires computing globally consistent, collision-free trajectories from individual start positions to assigned goal positions under combinatorial planning complexity. In dense environments, suboptimal initial plans induce compound conflicts that hinder feasible repair. For repair-based solvers like LNS2, initial plan quality critically affects downstream repair, yet this factor remains underexplored. We propose DiffLNS, a hybrid framework that integrates a discrete denoising diffusion probabilistic model (D3PM) with LNS2. The D3PM serves as an initializer with sparse social attention that learns a spatiotemporal prior over coordinated multi-agent action trajectories from expert demonstrations and samples multiple joint plans. Operating directly on the categorical action space, our discrete diffusion preserves the MAPF action structure and samples from a multimodal joint-plan distribution to produce diverse drafts well suited for neighborhood repair. These drafts act as warm starts for downstream repair, which completes unfinished trajectories and resolves remaining conflicts under hard MAPF constraints. Experimental results show that despite being trained only on instances with at most 96 agents, the initializer generalizes to scenarios with up to 312 agents at inference time. Across 20 complex and congested settings, DiffLNS achieves an average success rate of 95.8%, outperforming the strongest tested baseline by 9.6 percentage points and matching or exceeding all baselines in all 20 settings. To the best of our knowledge, this is the first work to leverage discrete diffusion for warm-starting an LNS-based MAPF solver.

preprint2026arXiv

ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices

The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffusion-3 and FLUX.1. However, deploying these models on resource-constrained mobile devices entails prohibitive computational and memory overhead. While efficiency-driven approaches like Linear-DiT and static pruning alleviate bottlenecks, they often incur quality degradation. Unlike cloud environments, mobile constraints require a single-model paradigm that dynamically balances fidelity and latency. We introduce ElasticDiT, which achieves this dynamic trade-off by adjusting spatial compression ratios and DiT block depths. By integrating Shift Sparse Block Attention (SSBA) and a Tiny DWT-Distilled VAE (T-DVAE), ElasticDiT reduces inference latency and memory footprint while maintaining image quality. Experiments confirm that ElasticDiT effectively covers a wide range of fidelity-latency trade-offs within a single set of parameters. By jointly adjusting compression and depth, a single ElasticDiT model can be reconfigured on-the-fly to outperform task-specific baselines. Specifically, our flex lite variant achieves an HPS of 32.87, surpassing the Flux model, while maintaining competitive quality at 84.16 percent average sparsity through SSBA. Furthermore, the plug-and-play T-DVAE provides SD3-level reconstruction with only 1/8x the computational cost of standard VAEs, and Flow-GRPO boosts semantic alignment (GenEval: 66.93 to 73.62). These results demonstrate that ElasticDiT offers a versatile, hardware-adaptive solution that eliminates the need for multiple specialized models, providing a promising path for future high-resolution image generation on mobile devices.

preprint2026arXiv

GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models

Currently, process reward models (PRMs) have exhibited remarkable potential for test-time scaling. Since large language models (LLMs) regularly generate flawed intermediate reasoning steps when tackling a broad spectrum of reasoning and decision-making tasks, PRMs are required to possess capabilities for detecting process-level errors in real-world scenarios. However, existing benchmarks primarily focus on mathematical reasoning, thereby failing to comprehensively evaluate the error detection ability of PRMs across diverse reasoning scenarios. To mitigate this gap, we introduce GR-Ben, a process-level benchmark specifically designed for assessing PRM's performance across two primary reasoning domains (science and logic) and nine subdomains. We conduct extensive experiments on a diverse set of 22 models, encompassing both PRMs and LLMs, and derive two key findings: (1) In domains beyond mathematical reasoning, the error-detection ability of existing PRMs and LLMs is found to be markedly weaker by comparison.(2) In general, PRMs are less adept at identifying knowledge-based errors, whereas LLMs exhibit poorer performance in detecting computational errors. We hope GR-Ben can foster future researches on PRMs for general domains, thereby enhancing the reasoning capabilities of LLMs.

preprint2026arXiv

Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction

Transformer-based 3D reconstruction has emerged as a powerful paradigm for recovering geometry and appearance from multi-view observations, offering strong performance across challenging visual conditions. As these models scale to larger backbones and higher-resolution inputs, improving their efficiency becomes increasingly important for practical deployment. However, modern 3D transformer pipelines face two coupled challenges: dense multi-view attention creates substantial token-mixing overhead, and low-precision execution can destabilize geometry-sensitive representations and degrade depth, pose, and 3D consistency. To address the first challenge, we propose Lite3R, a model-agnostic teacher-student framework that replaces dense attention with Sparse Linear Attention to preserve important geometric interactions while reducing attention cost. To address the second challenge, we introduce a parameter-efficient FP8-aware quantization-aware training (FP8-aware QAT) strategy with partial attention distillation, which freezes the vast majority of pretrained backbone parameters and trains only lightweight linear-branch projection layers, enabling stable low-precision deployment while retaining pretrained geometric priors. We further evaluate Lite3R on two representative backbones, VGGT and DA3-Large, over BlendedMVS and DTU64, showing that it substantially reduces latency (1.7-2.0x) and memory usage (1.9-2.4x) while preserving competitive reconstruction quality overall. These results demonstrate that Lite3R provides an effective algorithm-system co-design approach for practical transformer-based 3D reconstruction. Code: https://github.com/AIGeeksGroup/Lite3R. Website: https://aigeeksgroup.github.io/Lite3R.

preprint2026arXiv

MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory

Agentic memory evolves across tasks into durable derived artifacts: summaries, cached outputs, embeddings, learned skills, and executable tool procedures. When a source artifact is deleted, corrected, or invalidated by tool or API migration, descendants derived from that source can remain visible and steer future actions with stale support. We formalize this failure mode as the cascade update problem, where repair targets the visible derived state of the memory store. We present MemoRepair, a barrier-first cascade-repair contract for agentic memory. A repair event induces a controlled transition from invalidated descendant state to validated successor state: affected descendants are withdrawn before repair, successors are constructed from retained support and staged repaired predecessors under the current interface, and republication is restricted to validated predecessor-closed successors. This contract induces a scalarized repair-selection problem for a fixed repair-cost tradeoff. We show that the induced publication problem reduces to maximum-weight predecessor closure and can be solved exactly by a single s-t min-cut. Experiments on ToolBench and MemoryArena show that, with complete influence provenance, MemoRepair reduces invalidated-memory exposure from 69.8-94.3% under systems without cascade repair to 0%. Compared with exhaustive Repair all, it recovers 91.1-94.3% of validated successors while reducing normalized repair-operator cost from 1.00 to 0.57-0.76.

preprint2026arXiv

Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation

Autonomous 3D indoor scene synthesis breaks down in non-convex rooms with tightly coupled spatial constraints. Data-driven generators lack topological priors for long-horizon planning, while iterative agents fragment semantics and become geometrically brittle. We present ZoneMaestro, a unified framework that shifts the paradigm from object-centric synthesis to Zone-Graph Orchestration. By internalizing a novel zone-based logic, ZoneMaestro translates high-level semantic intent into functional zones and topological constraints, enabling robust adaptation to diverse architectural forms. To support this, we construct Zone-Scene-10K, a large-scale dataset enriched with explicit Zone-Graph annotations. We further introduce an Alternating Alignment Strategy that cycles between reasoning internalization and Zone-Aware Group Relative Policy Optimization (Z-GRPO), effectively reconciling the tension between semantic richness and geometric validity without relying on external physics engines. To rigorously evaluate spatial intelligence beyond convex primitives, we formally define the task of Intricate Spatial Orchestration and release SCALE, a stress-test benchmark for irregular indoor scenarios with complex, dense spatial relations. Extensive experiments demonstrate that ZoneMaestro resolves the density-safety dichotomy, significantly outperforming state-of-the-art baselines in both structural coherence and intent adherence.

preprint2026arXiv

PresentAgent-2: Towards Generalist Multimodal Presentation Agents

Presentation generation is moving beyond static slide creation toward end-to-end presentation video generation with research grounding, multimodal media, and interactive delivery. We introduce PresentAgent-2, an agentic framework for generating presentation videos from user queries. Given an open-ended user query and a selected presentation mode, PresentAgent-2 first summarizes the query into a focused topic and performs deep research over presentation-friendly sources to collect multimodal resources, including relevant text, images, GIFs, and videos. It then constructs presentation slides, generates mode-specific scripts, and composes slides, audio, and dynamic media into a complete presentation video. PresentAgent-2 supports three independent presentation modes within a unified framework: Single Presentation, which generates a single-speaker narrated presentation video; Discussion, which creates a multi-speaker presentation with structured speaker roles, such as for asking guiding questions, explaining concepts, clarifying details, and summarizing key points; and Interaction, which independently supports answering audience questions grounded in the generated slides, scripts, retrieved evidence, and presentation context. To evaluate these capabilities, we build a multimodal presentation benchmark covering single presentation, discussion, and interaction scenarios, with task-specific evaluation criteria for content quality, media relevance, dynamic media use, dialogue naturalness, and interaction grounding. Overall, PresentAgent-2 extends presentation generation from document-dependent slide creation to query-driven, research-grounded presentation video generation with multimodal media, dialogue, and interaction. Code: https://github.com/AIGeeksGroup/PresentAgent-2. Website: https://aigeeksgroup.github.io/PresentAgent-2.

preprint2026arXiv

VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement

We present VoxScene, a novel anchor-conditioned voxel diffusion framework tailored for 3D scene synthesis. Current data-driven layout generation techniques typically rely on bounding proxies or implicit representations, which overlook volumetric structures. This geometric blindness inevitably leads to severe physical collisions and structural entanglement, particularly in densely populated environments. To overcome these limitations, we shift the paradigm to an explicit, object-centric voxel representation. Our pipeline sequentially synthesizes discrete volumetric occupancies conditioned on prior anchors and local context. By exploiting the mutually exclusive nature of discrete voxels, our approach eliminates spatial ambiguities and guarantees collision-free arrangements, even in highly complex environments. Furthermore, the synthesized high-fidelity voxel grids serve as discriminative geometric queries for downstream asset retrieval. Extensive experiments demonstrate the universality of our method, achieving state-of-the-art physical plausibility and unlocking shape diversity compared to existing layout planners.

preprint2025arXiv

Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning

Vision-Language Models (VLMs) often appear culturally competent but rely on superficial pattern matching rather than genuine cultural understanding. We introduce a diagnostic framework to probe VLM reasoning on fire-themed cultural imagery through both classification and explanation analysis. Testing multiple models on Western festivals, non-Western traditions, and emergency scenes reveals systematic biases: models correctly identify prominent Western festivals but struggle with underrepresented cultural events, frequently offering vague labels or dangerously misclassifying emergencies as celebrations. These failures expose the risks of symbolic shortcuts and highlight the need for cultural evaluation beyond accuracy metrics to ensure interpretable and fair multimodal systems.

preprint2024arXiv

Instruct-Imagen: Image Generation with Multi-modal Instruction

This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision. It uses natural language to amalgamate disparate modalities (e.g., text, edge, style, subject, etc.), such that abundant generation intents can be standardized in a uniform format. We then build instruct-imagen by fine-tuning a pre-trained text-to-image diffusion model with a two-stage framework. First, we adapt the model using the retrieval-augmented training, to enhance model's capabilities to ground its generation on external multimodal context. Subsequently, we fine-tune the adapted model on diverse image generation tasks that requires vision-language understanding (e.g., subject-driven generation, etc.), each paired with a multi-modal instruction encapsulating the task's essence. Human evaluation on various image generation datasets reveals that instruct-imagen matches or surpasses prior task-specific models in-domain and demonstrates promising generalization to unseen and more complex tasks.

preprint2023arXiv

Deformation measurement of a soil mixing retaining wall using terrestrial laser scanning

Retaining walls are often built to prevent excessive lateral movements of the ground surrounding an excavation site. During an excavation, failure of retaining walls could cause catastrophic accidents and hence their lateral deformations are monitored regularly. Laser scanning can rapidly acquire the spatial data of a relatively large area at fine spatial resolutions, which is ideal for monitoring retaining walls' deformations. This paper attempts to apply laser scanning to measurements of the lateral deformations of a soil mixing retaining wall at an ongoing excavation site. Reference measurements by total station and inclinometer were also conducted to verify those from the laser scanning. The deformations derived using laser scanning data were consistent with the reference measurements at the top part of the retaining wall (i.e., mainly the ring beam of the wall). This research also shows that the multi-scale-model-to-model method was the most accurate deformation estimation method on the research data.

preprint2022arXiv

AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism

In recent days, streaming technology has greatly promoted the development in the field of livestream. Due to the excessive length of livestream records, it's quite essential to extract highlight segments with the aim of effective reproduction and redistribution. Although there are lots of approaches proven to be effective in the highlight detection for other modals, the challenges existing in livestream processing, such as the extreme durations, large topic shifts, much irrelevant information and so forth, heavily hamper the adaptation and compatibility of these methods. In this paper, we formulate a new task Livestream Highlight Detection, discuss and analyze the difficulties listed above and propose a novel architecture AntPivot to solve this problem. Concretely, we first encode the original data into multiple views and model their temporal relations to capture clues in a hierarchical attention mechanism. Afterwards, we try to convert the detection of highlight clips into the search for optimal decision sequences and use the fully integrated representations to predict the final results in a dynamic-programming mechanism. Furthermore, we construct a fully-annotated dataset AntHighlight to instantiate this task and evaluate the performance of our model. The extensive experiments indicate the effectiveness and validity of our proposed method.

preprint2022arXiv

BRIGHT -- Graph Neural Networks in Real-Time Fraud Detection

Detecting fraudulent transactions is an essential component to control risk in e-commerce marketplaces. Apart from rule-based and machine learning filters that are already deployed in production, we want to enable efficient real-time inference with graph neural networks (GNNs), which is useful to catch multihop risk propagation in a transaction graph. However, two challenges arise in the implementation of GNNs in production. First, future information in a dynamic graph should not be considered in message passing to predict the past. Second, the latency of graph query and GNN model inference is usually up to hundreds of milliseconds, which is costly for some critical online services. To tackle these challenges, we propose a Batch and Real-time Inception GrapH Topology (BRIGHT) framework to conduct an end-to-end GNN learning that allows efficient online real-time inference. BRIGHT framework consists of a graph transformation module (Two-Stage Directed Graph) and a corresponding GNN architecture (Lambda Neural Network). The Two-Stage Directed Graph guarantees that the information passed through neighbors is only from the historical payment transactions. It consists of two subgraphs representing historical relationships and real-time links, respectively. The Lambda Neural Network decouples inference into two stages: batch inference of entity embeddings and real-time inference of transaction prediction. Our experiments show that BRIGHT outperforms the baseline models by >2\% in average w.r.t.~precision. Furthermore, BRIGHT is computationally efficient for real-time fraud detection. Regarding end-to-end performance (including neighbor query and inference), BRIGHT can reduce the P99 latency by >75\%. For the inference stage, our speedup is on average 7.8$\times$ compared to the traditional GNN.

preprint2022arXiv

Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation

Unsupervised domain adaptation (UDA) is an approach to minimizing domain gap. Generative methods are common approaches to minimizing the domain gap of aerial images which improves the performance of the downstream tasks, e.g., cross-domain semantic segmentation. For aerial images, the digital surface model (DSM) is usually available in both the source domain and the target domain. Depth information in DSM brings external information to generative models. However, little research utilizes it. In this paper, depth-assisted ResiDualGAN (DRDG) is proposed where depth supervised loss (DSL), and depth cycle consistency loss (DCCL) are used to bring depth information into the generative model. Experimental results show that DRDG reaches state-of-the-art accuracy between generative methods in cross-domain semantic segmentation tasks.

preprint2022arXiv

e-G2C: A 0.14-to-8.31 $μ$J/Inference NN-based Processor with Continuous On-chip Adaptation for Anomaly Detection and ECG Conversion from EGM

This work presents the first silicon-validated dedicated EGM-to-ECG (G2C) processor, dubbed e-G2C, featuring continuous lightweight anomaly detection, event-driven coarse/precise conversion, and on-chip adaptation. e-G2C utilizes neural network (NN) based G2C conversion and integrates 1) an architecture supporting anomaly detection and coarse/precise conversion via time multiplexing to balance the effectiveness and power, 2) an algorithm-hardware co-designed vector-wise sparsity resulting in a 1.6-1.7$\times$ speedup, 3) hybrid dataflows for enhancing near 100% utilization for normal/depth-wise(DW)/point-wise(PW) convolutions (Convs), and 4) an on-chip detection threshold adaptation engine for continuous effectiveness. The achieved 0.14-8.31 $μ$J/inference energy efficiency outperforms prior arts under similar complexity, promising real-time detection/conversion and possibly life-critical interventions

preprint2022arXiv

Equivalence between algorithmic instability and transition to replica symmetry breaking in perceptron learning systems

Binary perceptron is a fundamental model of supervised learning for the non-convex optimization, which is a root of the popular deep learning. Binary perceptron is able to achieve a classification of random high-dimensional data by computing the marginal probabilities of binary synapses. The relationship between the algorithmic instability and the equilibrium analysis of the model remains elusive. Here, we establish the relationship by showing that the instability condition around the algorithmic fixed point is identical to the instability for breaking the replica symmetric saddle point solution of the free energy function. Therefore, our analysis would hopefully provide insights towards other learning systems in bridging the gap between non-convex learning dynamics and statistical mechanics properties of more complex neural networks.

preprint2022arXiv

Industrial Experience of Finding Cryptographic Vulnerabilities in Large-scale Codebases

Enterprise environment often screens large-scale (millions of lines of code) codebases with static analysis tools to find bugs and vulnerabilities. Parfait is a static code analysis tool used in Oracle to find security vulnerabilities in industrial codebases. Recently, many studies show that there are complicated cryptographic vulnerabilities caused by misusing cryptographic APIs in Java. In this paper, we describe how we realize a precise and scalable detection of these complicated cryptographic vulnerabilities based on Parfait framework. The key challenge in the detection of cryptographic vulnerabilities is the high false alarm rate caused by pseudo-influences. Pseudo-influences happen if security-irrelevant constants are used in constructing security-critical values. Static analysis is usually unable to distinguish them from hard-coded constants that expose sensitive information. We tackle this problem by specializing the backward dataflow analysis used in Parfait with refinement insights, an idea from the tool CryptoGuard. We evaluate our analyzer on a comprehensive Java cryptographic vulnerability benchmark and eleven large real-world applications. The results show that the Parfait-based cryptographic vulnerability detector can find real-world cryptographic vulnerabilities in large-scale codebases with high true-positive rates and low runtime cost.

preprint2022arXiv

Joint Optimization of STAR-RIS Assisted UAV Communication Systems

In this letter, we study the simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted unmanned aerial vehicle (UAV) communications. Our goal is to maximize the sum rate of all users by jointly optimizing the STAR-RIS's beamforming vectors, the UAV's trajectory and power allocation. We decompose the formulated non-convex problem into three subproblems and solve them alternately to obtain the solution. Simulations show that: 1) the STAR-RIS achieves a higher sum rate than traditional RIS; 2) to exploit the benefits of STAR-RIS, the UAV's trajectory is closer to STAR-RIS than that of RIS; 3) the energy splitting for reflection and transmission highly depends on the real-time trajectory of UAV.

preprint2022arXiv

Learning an Efficient Multimodal Depth Completion Model

With the wide application of sparse ToF sensors in mobile devices, RGB image-guided sparse depth completion has attracted extensive attention recently, but still faces some problems. First, the fusion of multimodal information requires more network modules to process different modalities. But the application scenarios of sparse ToF measurements usually demand lightweight structure and low computational cost. Second, fusing sparse and noisy depth data with dense pixel-wise RGB data may introduce artifacts. In this paper, a light but efficient depth completion network is proposed, which consists of a two-branch global and local depth prediction module and a funnel convolutional spatial propagation network. The two-branch structure extracts and fuses cross-modal features with lightweight backbones. The improved spatial propagation module can refine the completed depth map gradually. Furthermore, corrected gradient loss is presented for the depth completion problem. Experimental results demonstrate the proposed method can outperform some state-of-the-art methods with a lightweight architecture. The proposed method also wins the championship in the MIPI2022 RGB+TOF depth completion challenge.

preprint2022arXiv

Modelling graph dynamics in fraud detection with "Attention"

At online retail platforms, detecting fraudulent accounts and transactions is crucial to improve customer experience, minimize loss, and avoid unauthorized transactions. Despite the variety of different models for deep learning on graphs, few approaches have been proposed for dealing with graphs that are both heterogeneous and dynamic. In this paper, we propose DyHGN (Dynamic Heterogeneous Graph Neural Network) and its variants to capture both temporal and heterogeneous information. We first construct dynamic heterogeneous graphs from registration and transaction data from eBay. Then, we build models with diachronic entity embedding and heterogeneous graph transformer. We also use model explainability techniques to understand the behaviors of DyHGN-* models. Our findings reveal that modelling graph dynamics with heterogeneous inputs need to be conducted with "attention" depending on the data structure, distribution, and computation cost.

preprint2022arXiv

Neighborhood Region Smoothing Regularization for Finding Flat Minima In Deep Neural Networks

Due to diverse architectures in deep neural networks (DNNs) with severe overparameterization, regularization techniques are critical for finding optimal solutions in the huge hypothesis space. In this paper, we propose an effective regularization technique, called Neighborhood Region Smoothing (NRS). NRS leverages the finding that models would benefit from converging to flat minima, and tries to regularize the neighborhood region in weight space to yield approximate outputs. Specifically, gap between outputs of models in the neighborhood region is gauged by a defined metric based on Kullback-Leibler divergence. This metric provides similar insights with the minimum description length principle on interpreting flat minima. By minimizing both this divergence and empirical loss, NRS could explicitly drive the optimizer towards converging to flat minima. We confirm the effectiveness of NRS by performing image classification tasks across a wide range of model architectures on commonly-used datasets such as CIFAR and ImageNet, where generalization ability could be universally improved. Also, we empirically show that the minima found by NRS would have relatively smaller Hessian eigenvalues compared to the conventional method, which is considered as the evidence of flat minima.

preprint2022arXiv

Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning

How to train deep neural networks (DNNs) to generalize well is a central concern in deep learning, especially for severely overparameterized networks nowadays. In this paper, we propose an effective method to improve the model generalization by additionally penalizing the gradient norm of loss function during optimization. We demonstrate that confining the gradient norm of loss function could help lead the optimizers towards finding flat minima. We leverage the first-order approximation to efficiently implement the corresponding gradient to fit well in the gradient descent framework. In our experiments, we confirm that when using our methods, generalization performance of various models could be improved on different datasets. Also, we show that the recent sharpness-aware minimization method (Foret et al., 2021) is a special, but not the best, case of our method, where the best case of our method could give new state-of-art performance on these tasks. Code is available at {https://github.com/zhaoyang-0204/gnp}.

preprint2022arXiv

Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation

Identifying the status of individual network units is critical for understanding the mechanism of convolutional neural networks (CNNs). However, it is still challenging to reliably give a general indication of unit status, especially for units in different network models. To this end, we propose a novel method for quantitatively clarifying the status of single unit in CNN using algebraic topological tools. Unit status is indicated via the calculation of a defined topological-based entropy, called feature entropy, which measures the degree of chaos of the global spatial pattern hidden in the unit for a category. In this way, feature entropy could provide an accurate indication of status for units in different networks with diverse situations like weight-rescaling operation. Further, we show that feature entropy decreases as the layer goes deeper and shares almost simultaneous trend with loss during training. We show that by investigating the feature entropy of units on only training data, it could give discrimination between networks with different generalization ability from the view of the effectiveness of feature representations.

preprint2022arXiv

Scalar Diffraction Analysis Of Dispersion In Low-Index Thin Flat Lenses

We analyze the dispersion property of low-index thin lenses by using scalar diffraction and finite difference time domain (FDTD) methods. We compare the dispersion results obtained by using these methods with reported experimental results, and the well-known analytical formula for focal length (f) of diffractive lenses as a function of wavelength (λ),f(λ)=(f_0 λ_0)/λ,where f_0 is the designed focal length for wavelength λ_0. We show that when the analytical formula is applied to thin flat lenses with low-refractive index, the results are accurate for small numerical aperture (NA) up to 0.2. For larger NA, the error between the analytical approximation and the FDTD analysis remains around 8% over a wide range of NA.

preprint2022arXiv

Spatio-temporal Gait Feature with Global Distance Alignment

Gait recognition is an important recognition technology, because gait is not easy to camouflage and does not need cooperation to recognize subjects. However, many existing methods are inadequate in preserving both temporal information and fine-grained information, thus reducing its discrimination. This problem is more serious when the subjects with similar walking postures are identified. In this paper, we try to enhance the discrimination of spatio-temporal gait features from two aspects: effective extraction of spatio-temporal gait features and reasonable refinement of extracted features. Thus our method is proposed, it consists of Spatio-temporal Feature Extraction (SFE) and Global Distance Alignment (GDA). SFE uses Temporal Feature Fusion (TFF) and Fine-grained Feature Extraction (FFE) to effectively extract the spatio-temporal features from raw silhouettes. GDA uses a large number of unlabeled gait data in real life as a benchmark to refine the extracted spatio-temporal features. GDA can make the extracted features have low inter-class similarity and high intra-class similarity, thus enhancing their discrimination. Extensive experiments on mini-OUMVLP and CASIA-B have proved that we have a better result than some state-of-the-art methods.

preprint2022arXiv

The fractional Chern insulator with Rydberg-dressed neutral atoms

Topological nontrivial bands can be realized via Rydberg-dressed neutral atoms. We propose a two-dimensional hard-core boson model with a topological ground enrgy at band on a honeycomb lattice, where the particle hopping is realized via van der Waals interaction that exchanges the Rydberg states of two interacting atoms, while nonzero phases associated with hopping is created by transferring the optical phase of laser fields to the atomic pair wave function. Using exactly diagonalization and infinite density matrix renormalization group simulation, we find in the system a fractional Chern insulator phase with a Chern number C = 1/2, which can persist in the presence of weak many-body interactions. Our studies indicate that fractional Chern insulators can be studied with neutral-atom arrays.

preprint2022arXiv

Video-Guided Curriculum Learning for Spoken Video Grounding

In this paper, we introduce a new task, spoken video grounding (SVG), which aims to localize the desired video fragments from spoken language descriptions. Compared with using text, employing audio requires the model to directly exploit the useful phonemes and syllables related to the video from raw speech. Moreover, we randomly add environmental noises to this speech audio, further increasing the difficulty of this task and better simulating real applications. To rectify the discriminative phonemes and extract video-related information from noisy audio, we develop a novel video-guided curriculum learning (VGCL) during the audio pre-training process, which can make use of the vital visual perceptions to help understand the spoken language and suppress the external noise. Considering during inference the model can not obtain ground truth video segments, we design a curriculum strategy that gradually shifts the input video from the ground truth to the entire video content during pre-training. Finally, the model can learn how to extract critical visual information from the entire video clip to help understand the spoken language. In addition, we collect the first large-scale spoken video grounding dataset based on ActivityNet, which is named as ActivityNet Speech dataset. Extensive experiments demonstrate our proposed video-guided curriculum learning can facilitate the pre-training process to obtain a mutual audio encoder, significantly promoting the performance of spoken video grounding tasks. Moreover, we prove that in the case of noisy sound, our model outperforms the method that grounding video with ASR transcripts, further demonstrating the effectiveness of our curriculum strategy.

preprint2022arXiv

xFraud: Explainable Fraud Transaction Detection

At online retail platforms, it is crucial to actively detect the risks of transactions to improve customer experience and minimize financial loss. In this work, we propose xFraud, an explainable fraud transaction prediction framework which is mainly composed of a detector and an explainer. The xFraud detector can effectively and efficiently predict the legitimacy of incoming transactions. Specifically, it utilizes a heterogeneous graph neural network to learn expressive representations from the informative heterogeneously typed entities in the transaction logs. The explainer in xFraud can generate meaningful and human-understandable explanations from graphs to facilitate further processes in the business unit. In our experiments with xFraud on real transaction networks with up to 1.1 billion nodes and 3.7 billion edges, xFraud is able to outperform various baseline models in many evaluation metrics while remaining scalable in distributed settings. In addition, we show that xFraud explainer can generate reasonable explanations to significantly assist the business analysis via both quantitative and qualitative evaluations.

preprint2021arXiv

A Comprehensive Survey of 6G Wireless Communications

While fifth-generation (5G) communications are being rolled out worldwide, sixth-generation (6G) communications have attracted much attention from both the industry and the academia. Compared with 5G, 6G will have a wider frequency band, higher transmission rate, spectrum efficiency, greater connection capacity, shorter delay, broader coverage, and more robust anti-interference capability to satisfy various network requirements. This survey presents an insightful understanding of 6G wireless communications by introducing requirements, features, critical technologies, challenges, and applications. First, we give an overview of 6G from perspectives of technologies, security and privacy, and applications. Subsequently, we introduce various 6G technologies and their existing challenges in detail, e.g., artificial intelligence (AI), intelligent surfaces, THz, space-air-ground-sea integrated network, cell-free massive MIMO, etc. Because of these technologies, 6G is expected to outperform existing wireless communication systems regarding the transmission rate, latency, global coverage, etc. Next, we discuss security and privacy techniques that can be applied to protect data in 6G. Since edge devices are expected to gain popularity soon, the vast amount of generated data and frequent data exchange make the leakage of data easily. Finally, we predict real-world applications built on the technologies and features of 6G; for example, smart healthcare, smart city, and smart manufacturing will be implemented by taking advantage of AI.

preprint2021arXiv

FaultNet: A Deep Convolutional Neural Network for bearing fault classification

The increased presence of advanced sensors on the production floors has led to the collection of datasets that can provide significant insights into machine health. An important and reliable indicator of machine health, vibration signal data can provide us a greater understanding of different faults occurring in mechanical systems. In this work, we analyze vibration signal data of mechanical systems with bearings by combining different signal processing methods and coupling them with machine learning techniques to classify different types of bearing faults. We also highlight the importance of using different signal processing methods and analyze their effect on accuracy for bearing fault detection. Apart from the traditional machine learning algorithms we also propose a convolutional neural network FaultNet which can effectively determine the type of bearing fault with a high degree of accuracy. The distinguishing factor of this work is the idea of channels proposed to extract more information from the signal, we have stacked the Mean and Median channels to raw signal to extract more useful features to classify the signals with greater accuracy.

preprint2021arXiv

Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck

Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. However, the sequential text generation common pitfall with VAEs is that the model tends to ignore latent variables with a strong auto-regressive decoder. In this paper, we propose a principled approach to alleviate this issue by applying a discretized bottleneck to enforce an implicit latent feature matching in a more compact latent space. We impose a shared discrete latent space where each input is learned to choose a combination of latent atoms as a regularized latent representation. Our model endows a promising capability to model underlying semantics of discrete sequences and thus provide more interpretative latent structures. Empirically, we demonstrate our model's efficiency and effectiveness on a broad range of tasks, including language modeling, unaligned text style transfer, dialog response generation, and neural machine translation.

preprint2021arXiv

Interaction between optical pulse and tumor using finite element analysis

Photoacoustic imaging is an emerging technology based on the photoacoustic effect that has developed rapidly in recent years. It combines the high contrast of optical imaging and the high penetration and high resolution of acoustic imaging. As a non-destructive biological tissue imaging technology, photoacoustic imaging has important application value in the field of biomedicine. With its high efficiency bi-oimaging capabilities and excellent biosafety performance, it has been favored by researchers. The visualization of photoacoustic imaging has great research signifi-cance in the early diagnosis of some diseases, especially tumors. In photoacoustic imaging, light transmission and thermal effects are important processes. This article is based on COMSOL software and uses finite element analysis to construct a physi-cal model for simulation. Through laser pulses into the stomach tissue containing tumor, the physical process of light transmission and biological heat transfer was studied, and a photothermal model composed of two physical fields was built, and finally a series of visualization graphics were obtained. This work has certain theo-retical guiding significance for further promoting the application of photoacoustic imaging in the field of biomedicine.

preprint2021arXiv

Performance of a focal plane detector for soft X-ray imaging spectroscopy based on back-illuminated sCMOS

Spectroscopy focusing array (SFA) and Polarimetry focusing array (PFA) are the two major payloads of enhanced X-ray Timing and Polarimetry mission (eXTP). Nested Wolter-\RNum{1} X-ray mirror module is implemented in SFA and PFA to achive high effective area. When evaluating the properties of the mirror module, the alignment of the optical axis of the X-ray mirror module and a quasi-parallel X-ray beam is a prerequisite to ensure the accuracy of the results. Hence, to assist the alignment of the X-ray mirror module, an X-ray focal plane detector is designed based on the back-illuminated scientific Complementary Metal-Oxide-Semiconductor Transistor (sCMOS) sensor GSENSE6060BSI, one of the largest detection areas, is produced by \textit{Gpixel Inc}. Then the characteristics of readout noise, dark current, and split-pixel event properties of the detector are studied with the self-developed multi-target fluorescence X-ray source in a 100 m long X-ray test facility. The energy calibration is carried out with the single-pixel event and the energy non-linearity of the detector is also obtained. Eventually, the simulation of the eXTP mirror module based on the optical model is conducted and the alignment test of the Wolter-\RNum{1} X-ray mirror module designed for \textit{EP/FXT} (Einstein Probe/Follow-up X-ray Telescope) with "Burkert test" method is shown.

preprint2021arXiv

Photon-assisted Landau-Zener transitions in a periodically driven Rabi dimer coupled to a dissipative mode

We investigate multiple photon-assisted Landau-Zener (LZ) transitions in a hybrid circuit quantum electrodynamics device in which each of two interacting transmission-line resonators is coupled to a qubit, and the qubits are driven by periodic driving fields and also coupled to a common phonon mode. The quantum state of the entire composite system is modeled using the multi-$\rm D_2$ Ansatz in combination with the time-dependent Dirac-Frenkel variational principle. Applying a sinusoidal driving field to one of the qubits, this device is an ideal platform to study the photon-assisted LZ transitions by comparing the dynamics of the two qubits. A series of interfering photon-assisted LZ transitions take place if the photon frequency is much smaller than the driving amplitude. Once the two energy scales are comparable, independent LZ transitions arise and a transition pathway is revealed using an energy diagram. It is found that both adiabatic and nonadiabatic transitions are involved in the dynamics. Used to model environmental effects on the LZ transitions, the common phonon mode coupled to the qubits allows for more available states to facilitate the LZ transitions. An analytical formula is obtained to estimate the short-time phonon population and produces results in reasonable agreement with numerical calculations. Equipped with the knowledge of the photon-assisted LZ transitions in the system, we can precisely manipulate the qubit state and successfully generate the qubit dynamics with a square-wave pattern by applying driving fields to both qubits, opening up new venues to manipulate the states of qubits and photons in quantum information devices and quantum computers

preprint2021arXiv

Photovoltaic Self-Powered Gas Sensing: A Review

The self-powered sensing system could harness ambient energy to power the sensor without the need for external electrical energy. Recently, the concept of photovoltaic (PV) self-powered gas sensing has aroused wider attentions due to room-temperature operation, low power consumption, small size and potential applications. The PV self-powered gas sensors integrate the photovoltaic effects and the gas sensing function into a single chip, which could truly achieve the goal of zero power consumption for an independent gas sensing device. As an emerging concept, the PV self-powered gas sensing has been achieved by using different strategies, including integrated gas sensor and solar cell, integrated light filter and solar cell, gas-sensitive heterojunction photovoltaics, and gas-sensitive lateral photovoltaics, respectively. The purpose of this review is to summarize recent advances of PV self-powered gas sensing and also remark on the directions for future research in this topic.

preprint2021arXiv

Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices

Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a smart home system. To help manufacturers develop a smart home system, we design a federated learning (FL) system leveraging the reputation mechanism to assist home appliance manufacturers to train a machine learning model based on customers' data. Then, manufacturers can predict customers' requirements and consumption behaviors in the future. The working flow of the system includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile edge computing (MEC) server. Customers collect data from various home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL system. Since records on the blockchain are untampered, malicious customers or manufacturers' activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers' privacy and improve the test accuracy, we enforce differential privacy on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under differential privacy protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.

preprint2021arXiv

SDA: Improving Text Generation with Self Data Augmentation

Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision. However, less work has been done in the context of text, partially due to its discrete nature and the complexity of natural languages. In this paper, we propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation. Unlike most existing sentence-level augmentation strategies, which are only applied to specific models, our method is more general and could be easily adapted to any MLE-based training procedure. In addition, our framework allows task-specific evaluation metrics to be designed to flexibly control the generated sentences, for example, in terms of controlling vocabulary usage and avoiding nontrivial repetitions. Extensive experimental results demonstrate the superiority of our method on two synthetic and several standard real datasets, significantly improving related baselines.

Yang Zhao

Quick read

Decide how to stay connected

How to connect with this researcher

Open a focused conversation when the fit is right

See the researcher in context

Building this graph slice

60 published item(s)

Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations

Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention

ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices

GR-Ben: A General Reasoning Benchmark for Evaluating Process Reward Models

Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction

MEMOREPAIR: Barrier-First Cascade Repair in Agentic Memory

Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation

PresentAgent-2: Towards Generalist Multimodal Presentation Agents

VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement

Seeing Symbols, Missing Cultures: Probing Vision-Language Models&#39; Reasoning on Fire Imagery and Cultural Meaning

Instruct-Imagen: Image Generation with Multi-modal Instruction

Deformation measurement of a soil mixing retaining wall using terrestrial laser scanning

AntPivot: Livestream Highlight Detection via Hierarchical Attention Mechanism

BRIGHT -- Graph Neural Networks in Real-Time Fraud Detection

Depth-Assisted ResiDualGAN for Cross-Domain Aerial Images Semantic Segmentation

e-G2C: A 0.14-to-8.31 $μ$J/Inference NN-based Processor with Continuous On-chip Adaptation for Anomaly Detection and ECG Conversion from EGM

Equivalence between algorithmic instability and transition to replica symmetry breaking in perceptron learning systems

Industrial Experience of Finding Cryptographic Vulnerabilities in Large-scale Codebases

Joint Optimization of STAR-RIS Assisted UAV Communication Systems

Learning an Efficient Multimodal Depth Completion Model

Modelling graph dynamics in fraud detection with &#34;Attention&#34;

Neighborhood Region Smoothing Regularization for Finding Flat Minima In Deep Neural Networks

Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning

Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation

Scalar Diffraction Analysis Of Dispersion In Low-Index Thin Flat Lenses

Spatio-temporal Gait Feature with Global Distance Alignment

The fractional Chern insulator with Rydberg-dressed neutral atoms

Video-Guided Curriculum Learning for Spoken Video Grounding

xFraud: Explainable Fraud Transaction Detection

A Comprehensive Survey of 6G Wireless Communications

FaultNet: A Deep Convolutional Neural Network for bearing fault classification

Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck

Interaction between optical pulse and tumor using finite element analysis

Performance of a focal plane detector for soft X-ray imaging spectroscopy based on back-illuminated sCMOS

Photon-assisted Landau-Zener transitions in a periodically driven Rabi dimer coupled to a dissipative mode

Photovoltaic Self-Powered Gas Sensing: A Review

Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices

SDA: Improving Text Generation with Self Data Augmentation

3D Face Reconstruction from A Single Image Assisted by 2D Face Images in the Wild

A New MRAM-based Process In-Memory Accelerator for Efficient Neural Network Training with Floating Point Precision

Attacks to Federated Learning: Responsive Web User Interface to Recover Training Data from User Gradients

AutoDNNchip: An Automated DNN Chip Predictor and Builder for Both FPGAs and ASICs

Blockchain-Based Differential Privacy Cost Management System

Correlating magnetic structure and magnetotransport in semimetal thin films of Eu$_{1-x}$Sm$_x$TiO$_3$

Deep High-Resolution Representation Learning for Visual Recognition

DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition

Dual-discriminator GAN: A GAN way of profile face recognition

Feature Quantization Improves GAN Training

IRS-Assisted Millimeter Wave Communications: Joint Power Allocation and Beamforming Design

Magnetic Order and Competition With Superconductivity in (Er-Ho)Ni$_{2}$B$_{2}$C

Materializing Rival Ground States in the Barlowite Family of Kagome Magnets: Quantum Spin Liquid, Spin Ordered, and Valence Bond Crystal States

SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation

Structure-Aware Human-Action Generation

The Algebraic Expressions of Huygens Principle and Holographic Principle of Light

TIMELY: Pushing Data Movements and Interfaces in PIM Accelerators Towards Local and in Time Domain

Topological Singularity Induced Chiral Kohn Anomaly in a Weyl Semimetal

Variational approach to time-dependent fluorescence of a driven qubit

Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences

Signatures of many-body localization and metastability by weak perturbation

A Novel Carrier Waveform Inter-Displacement Modulation Method in Underwater Communication Channel

Seeing Symbols, Missing Cultures: Probing Vision-Language Models' Reasoning on Fire Imagery and Cultural Meaning

Modelling graph dynamics in fraud detection with "Attention"