MEDebiaser: A Human-AI Feedback System for Mitigating Bias in Multi-label Medical Image Classific...
MEDebiaser: A Human-AI Feedback System for Mitigating Bias in Multi-label Medical Image Classific... Shaohan Shi, Yuheng Shao, Haoran Jiang, Yunjie Yao, Zhijun Zhang, Xu Ding, Quan Li UIST 2025: The 38th Annual ACM Symposium on User Interface Software and Technology Session: 4. Searching, Classifying and Understanding Data Medical images often contain multiple labels with imbalanced distributions and co-occurrence, leading to bias in multi-label medical image classification. Close collaboration between medical professionals and machine learning practitioners has significantly advanced medical image analysis. However, traditional collaboration modes struggle to facilitate effective feedback between physicians and AI models, as integrating medical expertise into the training process via engineers can be time-consuming and labor-intensive. To bridge this gap, we introduce MEDebiaser, an interactive system enabling physicians to directly refine AI models using local explanations. By combining prediction with attention loss functions and employing a customized ranking strategy to alleviate scalability, MEDebiaser allows physicians to mitigate biases without technical expertise, reducing reliance on engineers, and thus enhancing more direct human-AI feedback. Our mechanism and user studies demonstrate that it effectively reduces biases, improves usability, and enhances collaboration efficiency, providing a practical solution for integrating medical expertise into AI-driven healthcare. DOI:: doi.org/10.1145/3746059.3747725 Web:: https://programs.sigchi.org/uist/2025... Video presentations for UIST 2025 papers

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification

Why Aliens Would NEVER Invade Africa

Inside the Mind of Anthropic CEO Dario Amodei | The Circuit | Extended Interview
![[CHI 2026] Using LLM for Conversational Assessment of Mental Health](https://i.ytimg.com/vi/aW4aaDUz2zY/hqdefault.jpg?sqp=-oaymwE9CNACELwBSFryq4qpAy8IARUAAAAAGAElAADIQj0AgKJDeAHwAQH4Af4JgALQBYoCDAgAEAEYZSBlKGUwDw==&rs=AOn4CLC-jSh5n5TQWjUgNY0eEW7UOAGsKw)
[CHI 2026] Using LLM for Conversational Assessment of Mental Health

The Future of AI Agents with Andrew Ng | Interrupt 26

Preference-Guided Multi-Objective UI Adaptation

Young Men in Expensive Cars

StepWrite: Adaptive Planning for Speech-Driven Text Generation

The FULL VIDEO of Trump they didn’t want released

How ASML Makes Chips Faster With Its New $400 Million High NA Machine

What do tech pioneers think about the AI revolution? - The Engineers, BBC World Service

Sei achtsam! Lisa Eckhart bei Humorzone - Die Gala 2026 | MDR SPASSZONE

How I Created OpenClaw, the Breakthrough AI Agent | Peter Steinberger | TED

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

How reading changes the way your brain works - BBC World Service

Geschenk und Herausforderung: Edgar und seine musikalische Hochbegabung I 37 Grad

What to teach when AI writes the code | Rainer Stropek | TEDxLinz

How AI Could Empower Any Business | Andrew Ng | TED

