Anh Totti Nguyen https://validator.w3.org/feed/docs/rss2.html Work with me About me Vision Language Models Are Blind TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models Vision Language Models are Biased Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces Lab Understanding Generative AI Capabilities in Everyday Image Editing Tasks Understanding Neural Networks Through Deep Visualization 3DTouch: A Wearable 3D Input Device for 3D Applications Innovation Engine: Automated Creativity and Improving Stochastic Optimization via Deep Learning Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks Synthesizing the preferred inputs for neurons in neural networks via deep generator networks Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning VectorDefense: Vectorization as a Defense to Adversarial Examples Strike (with) a Pose: Neural networks are easily fooled by strange poses of familiar objects A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings Explaining image classifiers by removing input features using generative models SAM: The Sensitivity of Attribution Methods to Hyperparameters The shape and simplicity biases of adversarially robust ImageNet-trained CNNs Press & Exhibition Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks? Low-cost Augmented Reality prototype for controlling network devices The effectiveness of feature attribution methods and its correlation with automatic evaluation scores baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modeling Improving zero-shot object-level change detection by incorporating visual correspondence HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs B-score: Detecting biases in large language models using response history PCNN: Probable-Class Nearest-Neighbor Explanations Improve Fine-Grained Image Classification Accuracy for AIs and Humans PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck GlitchBench: Can large multimodal models detect video game glitches? Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification gScoreCAM: What objects is CLIP looking at? Visual correspondence-based explanations improve AI robustness and human-AI team accuracy PiC: A Phrase-in-Context Dataset for Phrase Understanding and Semantic Search How explainable are adversarially-robust CNNs? K-6 AI club DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover’s Distance Improves Out-Of-Distribution Face Identification Low-cost Augmented Reality prototype for controlling network devices Double Trouble: How to not explain a text classifier’s decisions using counterfactuals synthesized by masked language models Inverting Adversarially Robust Networks for Image Synthesis Interpretable LLM-based Table Question Answering A modular wearable 3D input device ExtJS Vertical TabPanel example Deep Neural Network are Easily Fooled: High Confidence Predictions for Unrecognizable Images Courses How to configure a Waf C++ project in Eclipse Research