Yulun Jiang

Paper (* indicates equal contribution)

• RECAP: Training Long-horizon LLM Agents with Context Compaction

  Yulun Jiang, Maria Brbić, Michael Moor

  Manuscript Under Review

• MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Visual Abstraction

  Yulun Jiang, Naël Ouerghemi, Yekun Chai, Maria Brbić, Michael Moor

  NeurIPs 2026 Evaluations & Datasets Track

• Meta-RL Induces Exploration in Language Agents

  Yulun Jiang^*, Liangze Jiang^*, Damien Teney, Michael Moor, Maria Brbić

  ICLR 2026 - [paper] [code] [project]

• Large (Vision) Language Models Are Unsupervised In-Context Learners

  Artyom Gadetsky^*, Andrei Atanov^*, Yulun Jiang^*, Zhitong Gao, Ghazal Mighan, Amir Zamir, Maria Brbić

  ICLR 2025 - [paper] [code] [project]

• Let Go of Your Labels with Unsupervised Transfer

  Artyom Gadetsky^*, Yulun Jiang^*, Maria Brbić

  ICML 2024 - [paper] [code] [project]

• Towards Stable and Efficient Adversarial Training against l1 Bounded Adversarial Attacks

  Yulun Jiang^*, Chen Liu^*, Zhichao Huang, Mathieu Salzmann, Sabine Süsstrunk

  ICML 2023 - [paper] [code] [poster]

• Predicting and Diagnosing User Engagement with Mobile UI Animation via a Data-Driven Approach

  Ziming Wu, Yulun Jiang, Yiding Liu, Xiaojuan Ma

  CHI 2020 - [paper]