arXiv AI
Focus on What Matters: Fisher-Guided Adaptive Multimodal Fusion for Vulnerability Detection
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 13
Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing
arXiv:2607. 08839v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference.
arXiv AI
Aug 18
Invariant Pretraining for Robust Code Representations
arXiv:2608. 15412v1 Announce Type: cross Abstract: Encoder-based code representation models remain widely deployed for discriminative tasks such as clone detection and code classification, where their small size and low inference cost are decisive.
arXiv Machine Learning
Aug 5
DAIF: A Data-Driven Intermediate Fusion Framework for Multimodal Supervised Learning via Approximate Message Passing
arXiv:2608. 02769v1 Announce Type: cross Abstract: Multimodal supervised learning seeks to leverage multiple heterogeneous data sources to improve predictive performance.
arXiv Machine Learning
Jun 30
ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data
arXiv:2408. 16028v4 Announce Type: replace-cross Abstract: Supervised-learning-based vulnerability detectors often fall short due to limited labelled training data.
arXiv Machine Learning
Jul 3
From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection
arXiv:2512. 10485v2 Announce Type: replace-cross Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored.
arXiv AI
Aug 26
OmniJudge or OmniBias? Diagnosing Multimodal Judges through Balanced, Decoupled Lenses
The paper introduces D3-Omni, a balanced and decoupled benchmark designed to diagnose fine‑grained multimodal understanding in OmniJudges that evaluate text‑to‑image, text‑to‑video, and text‑to‑speech generation. D3-Omni covers 53 orthogonal binary dimensions across 10,671 samples, using fixed positive seeds and controlled prompt rewriting to generate negatives, thereby ensuring each error can be attributed to a single capability. The benchmark’s dual‑balanced, decoupled, and dynamic design achieves near 1:1 per‑dimension parity and a uniform total‑score distribution, revealing that strong OmniJudges often miss modality‑related failures and treat distinct attributes as a single decision, masking systematic blind spots.