arXiv:2608. 10289v1 Announce Type: cross Abstract: Deep neural networks are increasingly deployed in safety-critical domains as perception modules, where failures are often caused due to rare and under-represented scenarios.
Deep neural networks are increasingly deployed in safety-critical domains as perception modules, where failures are often caused due to rare and under-represented scenarios. This necessitates the need to evaluate the semantic robustness of perception models; conformance of behavior to high-level requirements over real-world perceptual variability.
arXiv:2601.08355v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) are increasingly deployed in autonomous driving and embodied AI systems, where reliable perception is critical for sa...
arXiv:2606. 18839v1 Announce Type: new Abstract: Vision-language models (VLMs) are now widely used in downstream tasks.
arXiv:2606. 25034v2 Announce Type: replace-cross Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety.
The paper introduces FailSAE, a method that uses Sparse Autoencoders to predict failures in vision‑language models (VLMs) such as CLIP. By treating failure prediction as a classification over sparse SAE latent activations and employing a three‑stage training pipeline, the approach yields higher prediction accuracy than existing confidence‑score or auxiliary‑classifier baselines. Analysis shows that the SAE captures class‑specific concepts and reveals a shift toward ambiguous or style‑related concepts during failures, offering insights for runtime failure recovery.
arXiv:2608. 09011v1 Announce Type: new Abstract: Uncertainty Quantification (UQ) aims to measure the reliability of model predictions, serving as a critical safeguard for deploying Vision-Language Models (VLMs) in safety-critical scenarios.
While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing bias evaluation protocols predominantly rely on static datasets, which provide only a superficial assessment, as their fixed test cases cannot adaptively evolve to measure the true depth and limits of model vulnerabilities.
TestifAI is a deep learning testing framework that estimates model robustness against combinations of input perturbations efficiently. It allows users to define structured spaces of semantic perturbations and severity levels, then query robustness for any combination. By using partial model tomography, TestifAI reconstructs higher-order perturbation effects from low-order tests, achieving less than 7% error while reducing inferences by 60–80%.
arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.
arXiv:2607. 11228v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases.
arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.
TestifAI is a deep learning testing framework that estimates model robustness against combinations of input perturbations efficiently. It allows users to define structured spaces of semantic perturbations and severity levels, then query robustness for any combination. By employing partial model tomography, TestifAI reconstructs higher‑order perturbation effects from low‑order tests, achieving less than 7% error while cutting inference counts by 60‑80% on image and language classification tasks.