Workshop
Sat Jul 29 12:00 PM -- 08:00 PM (PDT) @ Meeting Room 311 None
Artificial Intelligence & Human Computer Interaction
Artificial intelligence (AI) and Human Computer Interaction (HCI) share common roots: early work on conversational agents has laid the foundation for both fields. However, economic and political influences have driven these fields to remain separate in subsequent decades. The recent rise of data-centric methods in machine learning has propelled few-shot emergent AI capabilities, resulting in a raft of practical tools. In particular, modern AI techniques now power new ways for machines and humans to interact. Recently, a wave of HCI tasks have been proposed to the machine learning community, which direct AI research by contributing new datasets and benchmarks, and challenging existing modeling techniques, learning methodologies, and evaluation protocols. This workshop offers a forum for researchers to discuss these new research directions, identifying important challenges, showcasing new computational and scientific ideas that can be applied, sharing datasets/tools that are already available, or proposing those that should be further developed.
| Meet & Setup for Morning Poster Session (Break) | |
| Opening Remarks (Presentation) | |
| “AI For Good” Isn’t Good Enough: A Call for Human-Centered AI by James Landay (Presentation) | |
| Break | |
| Designing Easy and Useful Human Feedback by Anca Dragan (Presentation) | |
| Morning Poster Session (Poster Session) | |
| Lunch (Break) | |
| Setup for Afternoon Poster Session (Break) | |
| Beyond RLHF: A Human-Centered Approach to AI Development and Evaluation by Meredith Ringel Morris (Presentation) | |
| Human-Centered AI Transparency: Lessons Learned and Open Questions in the Age of LLMs by Q. Vera Liao (Presentation) | |
| Break | |
| Detecting and Countering Untrustworthy Artificial Intelligence by Nikola Banovic (Presentation) | |
| Afternoon Poster Session (Poster Session) | |
| Closing Remarks (Presentation) | |
| Personalized Prediction of Recurrent Stress Events Using Self-Supervised Learning on Multimodal Time-Series Data (Morning Poster) | |
| Designing Data: Proactive Data Collection and Iteration for Machine Learning Using Reflexive Planning, Monitoring, and Density Estimation (Afternoon Poster) | |
| Towards Mitigating Spurious Correlations in Image Classifiers with Simple Yes-no Feedback (Morning Poster) | |
| Creating a Bias-Free Dataset of Food Delivery App Reviews with Data Poisoning Attacks (Afternoon Poster) | |
| Computational Approaches for App-to-App Retrieval and Design Consistency Check (Afternoon Poster) | |
| Prediction without Preclusion Recourse Verification with Reachable Sets (Morning Poster) | |
| Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-loop feedback (Afternoon Poster) | |
| Give Weight to Human Reactions: Optimizing Complementary AI in Practical Human-AI Teams (Morning Poster) | |
| Rethinking Model Evaluation as Narrowing the Socio-Technical Gap (Afternoon Poster) | |
| Dissenting Explanations: Leveraging Disagreement to Reduce Model Overreliance (Morning Poster) | |
| Exploring Mobile UI Layout Generation using Large Language Models Guided by UI Grammar (Morning Poster) | |
| Iterative Disambiguation: Towards LLM-Supported Programming and System Design (Morning Poster) | |
| HateXplain2.0: An Explainable Hate Speech Detection Framework Utilizing Subjective Projection from Contextual Knowledge Space to Disjoint Concept Space (Morning Poster) | |
| ConvGenVisMo: Evaluation of conversational generative vision models (Morning Poster) | |
| Designing Decision Support Systems Using Counterfactual Prediction Sets (Afternoon Poster) | |
| Neuro-Symbolic Models of Human Moral Judgment: LLMs as Automatic Feature Extractors (Afternoon Poster) | |
| Language Models can Solve Computer Tasks (Afternoon Poster) | |
| Uncertainty Fingerprints: Interpreting Model Decisions with Human Conceptual Hierarchies (Afternoon Poster) | |
| feather - a Python SDK to share and deploy models (Afternoon Poster) | |
| Are Good Explainers Secretly Human-in-the-Loop Active Learners? (Morning Poster) | |
| Toward Model Selection Through Measuring Dataset Similarity on TensorFlow Hub (Afternoon Poster) | |
| Semi-supervised Concept Bottleneck Models (Morning Poster) | |
| How Can AI Reason Your Character? (Afternoon Poster) | |
| Informed Novelty Detection in Sequential Data by Per-Cluster Modeling (Afternoon Poster) | |
| Designing interactions with AI to support the scientific peer review process (Morning Poster) | |
| The corrupting influence of AI as a boss or Counterparty (Afternoon Poster) | |
| Ada-TTA: Towards Adaptive High-Quality Text-to-Talking Avatar Synthesis (Afternoon Poster) | |
| Human-Aligned Calibration for AI-Assisted Decision Making (Afternoon Poster) | |
| Do Users Write More Insecure Code with AI Assistants? (Morning Poster) | |
| SAP-sLDA: An Interpretable Interface for Exploring Unstructured Text (Morning Poster) | |
| Adaptive interventions for both accuracy and time in AI-assisted human decision making (Morning Poster) | |
| Discovering User Types: Characterization of User Traits by Task-Specific Behaviors in Reinforcement Learning (Morning Poster) | |
| Adaptive User-centered Neuro-symbolic Learning for Multimodal Interaction with Autonomous Systems (Afternoon Poster) | |
| Crowdsourced Clustering via Active Querying: Practical Algorithm with Theoretical Guarantees (Afternoon Poster) | |
| Demystifying the Role of Feedback in GPT Self-Repair for Code Generation (Morning Poster) | |
| Human-in-the-Loop Out-of-Distribution Detection with False Positive Rate Control (Morning Poster) | |
| Mitigating Label Bias via Decoupled Confident Learning (Morning Poster) | |
| Exploring Open Domain Image Super-Resolution through Text (Morning Poster) | |
| Towards Semantically-Aware UI Design Tools: Design, Implementation and Evaluation of Semantic Grouping Guidelines (Morning Poster) | |
| Interactively Optimizing Layout Transfer for Vector Graphics (Morning Poster) | |
| Unsupervised Learning of Distributional Properties can Supplement Human Labeling and Increase Active Learning Efficiency in Anomaly Detection (Morning Poster) | |
| LayerDiffusion: Layered Controlled Image Editing with Diffusion Models (Afternoon Poster) | |
| PromptCrafter: Crafting Text-to-Image Prompt through Mixed-Initiative Dialogue with LLM (Afternoon Poster) | |
| Co-creating a globally interpretable model with human input (Afternoon Poster) | |
| Workflow Discovery from Dialogues in the Low Data Regime (Afternoon Poster) | |
| LeetPrompt: Leveraging Collective Human Intelligence to Study LLMs (Afternoon Poster) | |
| How vulnerable are doctors to unsafe hallucinatory AI suggestions? A framework for evaluation of safety in clinical human-AI cooperation (Afternoon Poster) | |
| State trajectory abstraction and visualization method for explainability in reinforcement learning (Afternoon Poster) | |
| Towards Never-ending Learning of User Interfaces (Afternoon Poster) | |
| A More Robust Baseline for Active Learning by Injecting Randomness to Uncertainty Sampling (Morning Poster) | |
| Large Language Models as a Proxy For Human Evaluation in Assessing the Comprehensibility of Disordered Speech Transcription (Afternoon Poster) | |
| Symbiotic Co-Creation with AI (Morning Poster) | |
| An Interactive Human-Machine Learning Interface for Collecting and Learning from Complex Annotations (Morning Poster) | |
| Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus (Morning Poster) | |
| Partial Label Learning meets Active Learning: Enhancing Annotation Efficiency through Binary Questioning (Morning Poster) | |
| Black-Box Batch Active Learning for Regression (Afternoon Poster) | |
| CHILLI: A data context-aware perturbation method for XAI (Afternoon Poster) | |
| ConceptEvo: Interpreting Concept Evolution in Deep Learning Training (Morning Poster) | |
| Active Reinforcement Learning from Demonstration in Continuous Action Spaces (Morning Poster) | |
| Participatory Personalization in Classification (Afternoon Poster) | |
Successful Page Load