arXiv AI

Training-Free Model Selection and Domain-Aware Score Calibration for First-Shot Anomalous Sound Detection

arXiv:2607. 04526v1 Announce Type: cross Abstract: First-shot anomalous sound detection in DCASE Challenge Task 2 must flag anomalies of unseen machine types with a single threshold, without knowing whether a test clip comes from the data-rich source domain (990 normal training clips) or the data-scarce target domain (10).

Hugging Face Trending Papers

Aug 3

Can Foundation Models Hear What Made That Sound? A Tiered Benchmark of Audio-Language Models and Traditional Classifiers for Closed-Set Sound Source Identification

We benchmark eleven audio classification methods: five task-aware closed-set LLMs (four Gemini models plus open-weight Kimi-Audio-7B-Instruct), four fixed-vocabulary taggers (YAMNet, PANNs, Whisper-AT, and SSLAM), a zero-shot audio-text model (CLAP), and an audio-grounded LLM (BAT). We evaluate them on a closed-set sound-source identification task over 2,242 clips spanning 23 fine-grained classes and 11 categories.

llms multimodal benchmarks

arXiv Machine Learning

Jun 16

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

arXiv:2606. 15153v1 Announce Type: new Abstract: 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.

By Jingwen Zhou, Mingzhe Wang

safety

Hugging Face Trending Papers

Jul 30

DS@GT ARC at ImageCLEFmedical 2026: Architectural Diversity for Concept Detection and Foundation-Model Scaling for Caption Prediction in Medical Image Analysis

We describe the DS@GT submissions to the ImageCLEFmedical Caption 2026 challenge, which continues a long-running benchmark on the ROCOv2 dataset with two tracks: Concept Detection (Task 1), assigning UMLS Concept Unique Identifiers (CUIs) to radiology images, and Caption Prediction (Task 2), generating natural-language captions. For Task 1, our primary submission was a three-way late-fusion ensemble of ConvNeXt-V2, BiomedCLIP ViT-B/16, and DenseNet-169 with a regularized ''Honest Threshold Tuning'' procedure designed to avoid validation overfitting on rare concepts; this submission ranked first on the official submission with a primary $F_1$ of $0.

rag fine-tuning benchmarks

arXiv Machine Learning

Jul 31

DS@GT ARC at ImageCLEFmedical 2026: Architectural Diversity for Concept Detection and Foundation-Model Scaling for Caption Prediction in Medical Image Analysis

arXiv:2607. 27763v1 Announce Type: cross Abstract: We describe the DS@GT submissions to the ImageCLEFmedical Caption 2026 challenge, which continues a long-running benchmark on the ROCOv2 dataset with two tracks: Concept Detection (Task 1), assigning UMLS Concept Unique Identifiers (CUIs) to radiology images, and Caption Prediction (Task 2), generating natural-language captions.

By Bowen Wang, Youwen Zhang, Ritesh Mehta

rag fine-tuning benchmarks

arXiv AI

Jul 23

Anatomy of a Sound Neural Reasoner: One-Shot Amortization, First-Pass Poisoning, and Search Inertness in Clue-Rich Completion

arXiv:2607. 19635v1 Announce Type: cross Abstract: Neural solvers are built to deduce, branch, and revise intermediate states.

By Aleksey Komissarov

llms

Hugging Face Trending Papers

Jul 22

Anatomy of a Sound Neural Reasoner: One-Shot Amortization, First-Pass Poisoning, and Search Inertness in Clue-Rich Completion

Neural solvers are built to deduce, branch, and revise intermediate states. The Lattice Deduction Transformer (LDT) appears to do exactly that.

llms

arXiv AI

Jun 2

VocSim: A Training-free Benchmark for Zero-shot Content Identity in Single-source Audio

arXiv:2512. 10120v2 Announce Type: replace-cross Abstract: General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting.

By Maris Basha, Anja Zai, Sabine Stoll, Richard Hahnloser

rag multimodal benchmarks safety

arXiv Machine Learning

Aug 4

Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs

arXiv:2608. 01023v1 Announce Type: new Abstract: We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and the provable per-input query cost of recovering the clean logits.

By Chi Wang, Hanwen Wang, Yu Xia, Zihan Wang, Guangdong Bai

efficiency

arXiv Machine Learning

Jun 25

A Spectral Phase Diagram for Binary Few-Shot Classification: Intrinsic Dimensionality, Geometric Saturation, and Representational Diagnosis

arXiv:2606. 24903v1 Announce Type: new Abstract: Deciding when to stop collecting labeled examples is a fundamental but undertheorized problem in applied machine learning.

By Arnav Gupta

arXiv Machine Learning

Jun 30

The Calibrated Deepfake Trust Score (CDTS): Competence-Coupled Trust Degradation Across Deepfake Detectors

arXiv:2606. 29484v1 Announce Type: cross Abstract: Modern deepfake detectors are rarely consumed as bare classifiers.

By Md Anas Biswas

llms computer-vision

arXiv AI

Jul 17

Certified Domain Consistency for Multi-Domain Retrieval: Label-Free Per-Domain Contamination Control with Conformal Risk Guarantees

arXiv:2607. 14157v1 Announce Type: cross Abstract: Retrieval over corpora that mix several domains often returns relevant but wrong-domain evidence that ranking metrics miss and that conformal risk control bounds only marginally, under-covering the worst domains.

By Jayakumar Manoharan

llms

arXiv Machine Learning

Jul 15

Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection

arXiv:2607. 11969v1 Announce Type: cross Abstract: Point-adjustment (PA), long the default scoring protocol in time-series anomaly detection (TSAD), was shown by Kim et al.

By Zongye Lyu

benchmarks safety

Related stories