arXiv subjects

Mingzhe Wang

Publications and source records attributed to Mingzhe Wang.

At least 19 recordsLinked to original sources

arXiv2026

Efficient Coreset Selection via K-Nearest Neighbor Graphs

Coreset selection reduces the cost of model training by replacing a large training set with a small representative subset. Existing gradient-approximation coreset methods such as CRAIG and cluster-based variants can preserve model accuracy. Still, their selection stages often rely on dense pairwise distances or large item-cluster bound matrices, leading to high time and memory costs on large datasets. This paper proposes KNNG-CS, a lightweight coreset selection method based on a $K$-nearest neighbor graph. KNNG-CS exploits local neighborhood structures to estimate the importance of each data item and greedily selects representative nodes without maintaining a quadratic distance matrix. The method requires only linear storage in the number of edges. Experiments on four real-world datasets show that KNNG-CS achieves accuracy comparable to representative gradient-approximation coreset methods, while reducing selection time by $2.3\times$-$41.2\times$ and peak memory to $0.3\%$-$7.5\%$ of the baselines.

cs.LG↗

arXiv2026

When EER Hides Deployment Failure: Auditing Threshold Transfer and Unlabeled Score Calibration for Speech Deepfake Detectors

Speech deepfake countermeasures (CMs) are compared almost exclusively by equal error rate (EER), a metric computed at an oracle threshold chosen on the labeled test set. Deployed CMs enjoy no such oracle: a threshold must be fixed in advance and applied to unlabeled target data. We audit this gap with a frozen state-of-the-art SSL-AASIST detector trained on ASVspoof 2019 LA. While its in-domain EER is 0.21%, transferring its LA-calibrated threshold to the In-the-Wild corpus yields a half total error rate (HTER) of 39.5%, with 78.7% of bona fide speech rejected, even though the In-the-Wild EER (11.2%) appears moderate. We then test whether popular unlabeled test-time corrections close this gap, and first prove a simple proposition: any strictly increasing score transform, including z-norm, temperature/shift calibration, and embedding mean alignment under a frozen linear head, cannot change EER. An audit of seven corrections on In-the-Wild and ASVspoof 2021 DF confirms the proposition empirically and exposes two further failure modes: AS-norm with an unlabeled target cohort collapses (EER 11.2% to 60.2%), and pseudo-label calibration that reduces HTER by 38% relative on In-the-Wild degenerates to 50% HTER on DF21, whose spoof prior is 96%. No audited correction reduces EER by more than 1% relative. We recommend reporting HTER at a transferred threshold alongside EER.

cs.SD↗

arXiv2026

How Fragile Are Training-Free AI-Generated Image Detectors? A Controlled Audit of Score Direction, Preprocessing, and Compression

Training-free detectors of AI-generated images promise generator-agnostic deployment without classifier training, yet their reported numbers are rarely compared under a single controlled protocol. We audit two representative training-free scores -- an autoencoder-reconstruction score (AEROBLADE-style) and a noise-perturbation feature-similarity score (RIGID-style) -- plus a naive feature-kNN control, on a common 1,500-image GenImage-derived benchmark spanning seven generators and JPEG compression at quality 70 and 50. The audit yields three cautionary findings. (i) Implementation details masquerade as method differences: replacing the LPIPS backbone (AlexNet -> VGG-16) changes overall AUROC by +0.085, and switching between resize-to-512 and native-resolution preprocessing flips per-generator conclusions by up to 0.38 AUROC. (ii) Score direction is not a property of the method but of its hyperparameters: the RIGID-style score is inverted (AUROC < 0.5) on SD1.5 and Wukong at noise level sigma=0.05, recovers to >0.5 for every generator at sigma=0.01, and collapses to 0.15 at sigma=0.3. (iii) Dataset format bias inflates robustness claims: without unified re-encoding, AUROC under JPEG-50 exceeds the clean condition for the AlexNet-backbone reconstruction score; after bias correction the residual anomaly localizes to a single generator (BigGAN). The audited scores have complementary per-generator failure sets, but naive z-score fusion does not beat the best single score, indicating that exploiting complementarity requires direction-aware combination.

cs.CV↗

arXiv2026

Scoring Backends Matter More Than Pooling: A Systematic Study of Training-Free Anomalous Sound Detection under Domain Shift

Training-free anomalous sound detection (ASD) scores a test clip against a memory bank of normal embeddings from a frozen pretrained audio encoder. Recent work attributes domain-shift robustness mainly to how frame-level features are pooled over time; the scoring backend applied on top of the pooled embedding has received far less systematic attention. Using a single frozen BEATs encoder on the DCASE 2023 Task 2 development set (all seven machine types), we cross four classical backends -- nearest-neighbor cosine distance, Mahalanobis distance, locally density-normalized kNN, and PCA-subspace reconstruction residual -- with three temporal poolings (mean, GeM, max). Switching the backend moves target-domain AUC by 13.8 points on average (up to 53.8), whereas switching the pooling moves it by only 3.2 points: in this training-free regime, the backend, not the pooling, dominates domain-shift robustness. No backend wins everywhere, but the machine-dependent pattern reproduces on the DCASE 2025 development data (fan, bearing). Exploiting this, we propose a label-free score fusion that z-normalizes each backend with its training-bank self-scores and takes the minimum; it reaches a harmonic-mean target AUC of 63.3% versus 64.4% for the per-machine oracle, surpassing every fixed single backend while preserving source-domain accuracy. We also report a negative result: selecting a backend by source-domain pseudo-validation with proxy outliers fails, because all backends saturate on the proxy task.

cs.SD↗

arXiv2026

Transductive Zero-Shot Audio Classification with Audio-Language Models

Contrastive language-audio pretraining (CLAP) enables zero-shot audio classification, but standard inference classifies each clip in isolation and ignores the structure of the unlabeled test set. We present the first systematic study of TransCLIP-style transductive inference for CLAP: a text-anchored spherical Gaussian-mixture EM that refines zero-shot posteriors using the audio-embedding statistics of the test batch, with no labels, no gradients, and negligible compute (about 15 ms on one CPU core for 2,000 clips). Across ESC-50, UrbanSound8K, and VocalSound, this consistently improves top-1 accuracy by +4.6 to +9.2 points over the zero-shot baseline (e.g., 89.1 -> 94.8% on ESC-50, 73.8 -> 81.8% on UrbanSound8K). We further show that the gain (i) is governed by a simple operating boundary -- roughly 2.5 test samples per class per batch are required, with diminishing returns beyond ~5; (ii) is complementary to entropy-guided prompt weighting, with the combination reaching 96.2% on ESC-50; and (iii) attenuates but remains positive under long-tailed batches (+4.9 -> +3.1 points at a 20:1 imbalance), which we report as an explicit limitation. We also document a negative result: on TUT Urban Acoustic Scenes 2018, where zero-shot CLAP is near chance, transduction has no signal to amplify.

cs.SD↗

arXiv2026

False Sense of Safety in Selective Signal Classification: Auditing Bound Tightness and Exchangeability for Risk Control

Selective prediction with distribution-free risk control promises that, with confidence 1-delta over the calibration draw, the error rate of accepted inputs stays below a user budget alpha. We audit this promise on signal-domain detectors -- machine anomalous-sound detection (ASD) and AI-generated-image forensics -- for four calibration rules: uncertified empirical thresholding (NAIVE) and certified Hoeffding, Clopper-Pearson (CP), and betting (WSR) upper confidence bounds. We report three findings. (i) NAIVE thresholding, common in practice, exceeds its declared budget in 49-73% of synthetic trials (n=200 calibration points) and in up to 68% of real-data splits: a false sense of safety rather than a broken theorem, since the rule never had a certificate. (ii) Tightness matters: CP and WSR certify substantial coverage where Hoeffding certifies none, with zero observed budget overruns under exchangeable splits. (iii) Under grouped deployment (unseen machine types or generators), certified rules overrun in 9-30% of trials -- far above delta -- showing the failure lies in the broken exchangeability premise, not in the bounds; a conservative per-group threshold restores validity at a severe coverage cost.

cs.LG↗

arXiv2025

RcAE: Recursive Reconstruction Framework for Unsupervised Industrial Anomaly Detection

Unsupervised industrial anomaly detection requires accurately identifying defects without labeled data. Traditional autoencoder-based methods often struggle with incomplete anomaly suppression and loss of fine details, as their single-pass decoding fails to effectively handle anomalies with varying severity and scale. We propose a recursive architecture for autoencoder (RcAE), which performs reconstruction iteratively to progressively suppress anomalies while refining normal structures. Unlike traditional single-pass models, this recursive design naturally produces a sequence of reconstructions, progressively exposing suppressed abnormal patterns. To leverage this reconstruction dynamics, we introduce a Cross Recursion Detection (CRD) module that tracks inconsistencies across recursion steps, enhancing detection of both subtle and large-scale anomalies. Additionally, we incorporate a Detail Preservation Network (DPN) to recover high-frequency textures typically lost during reconstruction. Extensive experiments demonstrate that our method significantly outperforms existing non-diffusion methods, and achieves performance on par with recent diffusion models with only 10% of their parameters and offering substantially faster inference. These results highlight the practicality and efficiency of our approach for real-world applications.

cs.CV↗

arXiv2024

When Fuzzing Meets LLMs: Challenges and Opportunities

Fuzzing, a widely-used technique for bug detection, has seen advancements through Large Language Models (LLMs). Despite their potential, LLMs face specific challenges in fuzzing. In this paper, we identified five major challenges of LLM-assisted fuzzing. To support our findings, we revisited the most recent papers from top-tier conferences, confirming that these challenges are widespread. As a remedy, we propose some actionable recommendations to help improve applying LLM in Fuzzing and conduct preliminary evaluations on DBMS fuzzing. The results demonstrate that our recommendations effectively address the identified challenges.

cs.SE↗

arXiv2023

Infinite Photorealistic Worlds using Procedural Generation

We introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from scratch via randomized mathematical rules, using no external source and allowing infinite variation and composition. Infinigen offers broad coverage of objects and scenes in the natural world including plants, animals, terrains, and natural phenomena such as fire, cloud, rain, and snow. Infinigen can be used to generate unlimited, diverse training data for a wide range of computer vision tasks including object detection, semantic segmentation, optical flow, and 3D reconstruction. We expect Infinigen to be a useful resource for computer vision research and beyond. Please visit https://infinigen.org for videos, code and pre-generated data.

cs.CV↗

arXiv2022

Adaptive Task Offloading for Space Missions: A State-Graph-Based Approach

Advances in space exploration have led to an explosion of tasks. Conventionally, these tasks are offloaded to ground servers for enhanced computing capability, or to adjacent low-earth-orbit satellites for reduced transmission delay. However, the overall delay is determined by both computation and transmission costs. The existing offloading schemes, while being highly-optimized for either costs, can be abysmal for the overall performance. The computation-transmission cost dilemma is yet to be solved. In this paper, we propose an adaptive offloading scheme to reduce the overall delay. The core idea is to jointly model and optimize the transmission-computation process over the entire network. Specifically, to represent the computation state migrations, we generalize graph nodes with multiple states. In this way, the joint optimization problem is transformed into a shortest path problem over the state graph. We further provide an extended Dijkstra's algorithm for efficient path finding. Simulation results show that the proposed scheme outperforms the ground and one-hop offloading schemes by up to 37.56% and 39.35% respectively on SpaceCube v2.0.

eess.SP↗

arXiv2022

Computing-Aware Routing for LEO Satellite Networks: A Transmission and Computation Integration Approach

The advancements of remote sensing (RS) pose increasingly high demands on computation and transmission resources. Conventional ground-offloading techniques, which transmit large amounts of raw data to the ground, suffer from poor satellite-to-ground link quality. In addition, existing satellite-offloading techniques, which offload computational tasks to low earth orbit (LEO) satellites located within the visible range of RS satellites for processing, cannot leverage the full computing capability of the network because the computational resources of visible LEO satellites are limited. This situation is even worse in hotspot areas. In this paper, for efficient offloading via LEO satellite networks, we propose a novel computing-aware routing scheme. It fuses the transmission and computation processes and optimizes the overall delay of both. Specifically, we first model the LEO satellite network as a snapshot-free dynamic network, whose nodes and edges both have time-varying weights. By utilizing time-varying network parameters to characterize the network dynamics, the proposed method establishes a continuous-time model which scales well on large networks and improves the accuracy. Next, we propose a computing-aware routing scheme following the model. It processes tasks during the routing process instead of offloading raw data to ground stations, reducing the overall delay and avoiding network congestion consequently. Finally, we formulate the computing-aware routing problem in the dynamic network as a combination of multiple dynamic single source shortest path (DSSSP) problems and propose a genetic algorithm (GA) based method to approximate the results in a reasonable time. Simulation results show that the computing-aware routing scheme decreases the overall delay by up to 78.31% compared with offloading raw data to the ground to process.

cs.NI↗

arXiv2022

Network-Wide Task Offloading With LEO Satellites: A Computation and Transmission Fusion Approach

Computing tasks are ubiquitous in space missions. Conventionally, these tasks are offloaded to ground servers for computation, where the transmission of raw data on satellite-to-ground links severely constrains the performance. To overcome this limitation, recent works offload tasks to visible low-earth-orbit (LEO) satellites. However, this offloading scheme is difficult to achieve good performance in actual networks with uneven loads because visible satellites over hotspots tend to be overloaded. Therefore, it is urgent to extend the offloading targets to the entire network. To address the network-wide offloading problem, we propose a metagraph-based computation and transmission fusion offloading scheme for multi-tier networks. Specifically, virtual edges, between the original network and its duplicate, are generated to fuse computation and transmission in single-tier networks. Then, a metagraph is employed to integrate the fusion in multi-tier networks. After assigning appropriate edge weights to the metagraph, the network-wide offloading problem can be solved by searching the shortest path. In addition, we apply the proposed scheme to solve the spatial computation offloading problem in a real multi-tier network. The superiority of the proposed scheme over two benchmark schemes are proved theoretically and empirically. Simulation results show that the proposed scheme decreases the weighted average delay by up to 87.51% and 18.70% compared with the ground offloading scheme and the visible offloading scheme, respectively.

eess.SY↗

arXiv2021

Industry Practice of Coverage-Guided Enterprise-Level DBMS Fuzzing

As an infrastructure for data persistence and analysis, Database Management Systems (DBMSs) are the cornerstones of modern enterprise software. To improve their correctness, the industry has been applying blackbox fuzzing for decades. Recently, the research community achieved impressive fuzzing gains using coverage guidance. However, due to the complexity and distributed nature of enterprise-level DBMSs, seldom are these researches applied to the industry. In this paper, we apply coverage-guided fuzzing to enterprise-level DBMSs from Huawei and Bloomberg LP. In our practice of testing GaussDB and Comdb2, we found major challenges in all three testing stages. The challenges are collecting precise coverage, optimizing fuzzing performance, and analyzing root causes. In search of a general method to overcome these challenges, we propose Ratel, a coverage-guided fuzzer for enterprise-level DBMSs. With its industry-oriented design, Ratel improves the feedback precision, enhances the robustness of input generation, and performs an on-line investigation on the root cause of bugs. As a result, Ratel outperformed other fuzzers in terms of coverage and bugs. Compared to industrial black box fuzzers SQLsmith and SQLancer, as well as coverage-guided academic fuzzer Squirrel, Ratel covered 38.38%, 106.14%, 583.05% more basic blocks than the best results of other three fuzzers in GaussDB, PostgreSQL, and Comdb2, respectively. More importantly, Ratel has discovered 32, 42, and 5 unknown bugs in GaussDB, Comdb2, and PostgreSQL.

cs.SE↗

arXiv2020

Learning to Prove Theorems by Learning to Generate Theorems

We consider the task of automated theorem proving, a key AI task. Deep learning has shown promise for training theorem provers, but there are limited human-written theorems and proofs available for supervised learning. To address this limitation, we propose to learn a neural generator that automatically synthesizes theorems and proofs for the purpose of training a theorem prover. Experiments on real-world tasks demonstrate that synthetic data from our approach improves the theorem prover and advances the state of the art of automated theorem proving in Metamath. Code is available at https://github.com/princeton-vl/MetaGen.

cs.LO↗

arXiv2020

A Unified Framework of Surrogate Loss by Refactoring and Interpolation

We introduce UniLoss, a unified framework to generate surrogate losses for training deep networks with gradient descent, reducing the amount of manual design of task-specific surrogate losses. Our key observation is that in many cases, evaluating a model with a performance metric on a batch of examples can be refactored into four steps: from input to real-valued scores, from scores to comparisons of pairs of scores, from comparisons to binary variables, and from binary variables to the final performance metric. Using this refactoring we generate differentiable approximations for each non-differentiable step through interpolation. Using UniLoss, we can optimize for different tasks and metrics using one unified framework, achieving comparable performance compared with task-specific losses. We validate the effectiveness of UniLoss on three tasks and four datasets. Code is available at https://github.com/princeton-vl/uniloss.

cs.CV↗

arXiv2019

EnFuzz: Ensemble Fuzzing with Seed Synchronization among Diverse Fuzzers

Fuzzing is widely used for software vulnerability detection. There are various kinds of fuzzers with different fuzzing strategies, and most of them perform well on their targets. However, in industry practice and empirical study, the performance and generalization ability of those well-designed fuzzing strategies are challenged by the complexity and diversity of real-world applications. In this paper, inspired by the idea of ensemble learning, we first propose an ensemble fuzzing approach EnFuzz, that integrates multiple fuzzing strategies to obtain better performance and generalization ability than that of any constituent fuzzer alone. First, we define the diversity of the base fuzzers and choose those most recent and well-designed fuzzers as base fuzzers. Then, EnFuzz ensembles those base fuzzers with seed synchronization and result integration mechanisms. For evaluation, we implement EnFuzz , a prototype basing on four strong open-source fuzzers (AFL, AFLFast, AFLGo, FairFuzz), and test them on Google's fuzzing test suite, which consists of widely used real-world applications. The 24-hour experiment indicates that, with the same resources usage, these four base fuzzers perform variously on different applications, while EnFuzz shows better generalization ability and always outperforms others in terms of path coverage, branch coverage and crash discovery. Even compared with the best cases of AFL, AFLFast, AFLGo and FairFuzz, EnFuzz discovers 26.8%, 117%, 38.8% and 39.5% more unique crashes, executes 9.16%, 39.2%, 19.9% and 20.0% more paths and covers 5.96%, 12.0%, 21.4% and 11.1% more branches respectively.

cs.SE↗

arXiv2018

Speaker Naming in Movies

We propose a new model for speaker naming in movies that leverages visual, textual, and acoustic modalities in an unified optimization framework. To evaluate the performance of our model, we introduce a new dataset consisting of six episodes of the Big Bang Theory TV show and eighteen full movies covering different genres. Our experiments show that our multimodal model significantly outperforms several competitive baselines on the average weighted F-score metric. To demonstrate the effectiveness of our framework, we design an end-to-end memory network model that leverages our speaker naming model and achieves state-of-the-art results on the subtitles task of the MovieQA 2017 Challenge.

cs.CL↗

arXiv2017

Premise Selection for Theorem Proving by Deep Graph Embedding

We propose a deep learning-based approach to the problem of premise selection: selecting mathematical statements relevant for proving a given conjecture. We represent a higher-order logic formula as a graph that is invariant to variable renaming but still fully preserves syntactic and semantic information. We then embed the graph into a vector via a novel embedding method that preserves the information of edge ordering. Our approach achieves state-of-the-art results on the HolStep dataset, improving the classification accuracy from 83% to 90.3%.

cs.AI↗