January 2025

Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization

arXiv · Jan 23 · Research CV

This paper introduces Adaptive Entropy-aware Optimization (AEO), a new framework to tackle Multimodal Open-set Test-time Adaptation (MM-OSTTA). AEO uses Unknown-aware Adaptive Entropy Optimization (UAE) and Adaptive Modality Prediction Discrepancy Optimization (AMP) to distinguish unknown class samples during online adaptation by amplifying the entropy difference between known and unknown samples. The study establishes a new benchmark derived from existing datasets with five modalities and evaluates AEO's performance across various domain shift scenarios, demonstrating its effectiveness in long-term and continual MM-OSTTA settings.

VENOM: Text-driven Unrestricted Adversarial Example Generation with Diffusion Models

arXiv · Jan 14 · Research CV

The paper introduces VENOM, a text-driven framework for generating high-quality unrestricted adversarial examples using diffusion models. VENOM unifies image content generation and adversarial synthesis into a single reverse diffusion process, enhancing both attack success rate and image quality. The framework incorporates an adaptive adversarial guidance strategy with momentum to ensure the generated adversarial examples align with the distribution of natural images.

GenAI Content Detection Task 1: English and Multilingual Machine-Generated Text Detection: AI vs. Human

arXiv · Jan 19 · NLP LLM

MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments

arXiv · Jan 3 · LLM Research