Matheus Kunzler Maldaner

  • About
  • News
  • Projects
  • Research
  • Blog
  • CV

Publications

Featured Papers

  • SentinelBench: A Benchmark for Long-Running Monitoring Agents
  • Plato's Cave: A Human-Centered Research Verification System
  • Seeing Twice: How Side-by-Side T2I Comparison Changes Auditing Strategies

All Publications

  • MM-SCALE: Grounded Multimodal Moral Reasoning via Scalar Judgment and Listwise Alignment
  • Magentic-UI: Towards Human-in-the-loop Agentic Systems
  • eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks
  • MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI
  • Abstracting General Syntax for XAI after Decomposing Explanation Sub-Components
  • Efficient and Transparent Machine Learning: Exploring Applications of Differentiable Logic Gate Networks

Posters

Last edited on: