Search Results for author:
Found 14 papers, 4 papers with code
AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models
Remarkably, our findings shed light on a consistent AIGC \textbf{hallucination bias}: the object hallucinations induced by synthetic images are characterized by a greater quantity and a more uniform position distribution, even these synthetic images do not manifest unrealistic or additional relevant visual features compared to natural images.
An Ontology of Co-Creative AI Systems
The term co-creativity has been used to describe a wide variety of human-AI assemblages in which human and AI are both involved in a creative endeavor.
A Controllable Co-Creative Agent for Game System Design
Many advancements have been made in procedural content generation for games, and with mixed-initiative co-creativity, have the potential for great benefits to human designers.
Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method
Black-box attack, which is a more realistic threat and has led to various black-box adversarial training-based defense methods, however, does not attract considerable attention in adversarial example detection.
Beyond Prompts: Exploring the Design Space of Mixed-Initiative Co-Creativity Systems
We find out that MI-CC systems with more extensive coverage of the design space are rated higher or on par on a variety of creative and goal-completion metrics, demonstrating that wider coverage of the design space can improve user experience and achievement when using the system; Preference varies greatly between expertise groups, suggesting the development of adaptive, personalized MI-CC systems; Participants identified new design space dimensions including scrutability -- the ability to poke and prod at models -- and explainability.
Neuro-Symbolic World Models for Adapting to Open World Novelty
Additionally, WorldCloner augments the policy learning process using imagination-based adaptation, where the world model simulates transitions of the post-novelty environment to help the policy adapt.
Artificial Intelligence Security Competition (AISC)
The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems.
Creative Wand: A System to Study Effects of Communications in Co-Creative Settings
Recent neural generation systems have demonstrated the potential for procedurally generating game content, images, stories, and more.
Investigating and Explaining the Frequency Bias in Image Classification
Specifically, our investigations verify that the spectral density of datasets mainly affects the learning priority, while the class consistency mainly affects the feature discrimination.
NovGrid: A Flexible Grid World for Evaluating Agent Response to Novelty
We provide an ontology of for novelties most relevant to sequential decision making, which distinguishes between novelties that affect objects versus actions, unary properties versus non-unary relations, and the distribution of solutions to a task.
Benign Adversarial Attack: Tricking Models for Goodness
In spite of the successful application in many fields, machine learning models today suffer from notorious problems like vulnerability to adversarial examples.
Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes
Large pre-trained neural language models (LM) have very powerful text generation capabilities.
Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds
We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback.
A Hierarchical Distributed Processing Framework for Big Image Data
The proposed ICP framework consists of two mechanisms, i. e. SICP (Static ICP) and DICP (Dynamic ICP).
