Iclr2026

Excited to announce the following five papers accepted to ICLR 2026! Calibrating Verbalized Confidence with Self-Generated Distractors, Gistify! Codebase-Level Understanding via Runtime Execution, One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration, PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions, TrustGen: A Platform of Dynamic Benchmarking on the Trustworthiness of Generative Foundation Models.