Beyond the Black Box: Vision Language Models That Explain and Empower скачать в хорошем качестве

Beyond the Black Box: Vision Language Models That Explain and Empower

As Vision Language Models (VLMs) become embedded in how we process and interpret data, we face a critical challenge: these models often provide answers without evidence and support users without building their skills. To create a trustworthy future for AI, we must move toward explainable systems that foster human autonomy. In this talk, I will present two recent works addressing these pillars. First, I will introduce RADAR, a reasoning-guided attribution framework that transforms VLMs into transparent analysts. While standard models often hallucinate justifications for complex data, RADAR enables them to attribute reasoning steps to specific visual regions in charts and graphs, improving attribution accuracy by 15% and allowing users to verify logic through precise visual grounding. Second, using a month-long longitudinal study, I will explore the cognitive "Dependency Paradox"—while AI interaction boosts immediate accuracy in misinformation tasks by 21%, a user's independent ability to discern truth declines by 15.3% over time. The path forward isn't just better models—it's designing AI that makes humans better. Resources • Longitudinal Study: https://arxiv.org/pdf/2510.01537 • Chart Attribution: https://arxiv.org/pdf/2508.16850v1 • Connect with Anku on LinkedIn:   / anku-rani   About the Speaker Anku Rani is a doctoral researcher at the Massachusetts Institute of Technology, investigating machine learning models for video generation along with projects at the intersection of natural language processing and human-computer interaction. Her research spans multimodality, mathematical reasoning, attribution, and fact verification, with work published in leading AI conferences. Prior to MIT, Anku conducted research at Adobe Research and the University of South Carolina's Artificial Intelligence Institute. Anku actively contributes to the academic community through conference reviews, workshop organization, and program committee service. She holds postgraduate degrees in AI and ML and brings over 5 years of industrial and startup experience to her doctoral research. #computervision #ai #artificialintelligence #machinelearning