Publications

Also on Google Scholar. * Equal contribution.

2026

  1. Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces

    John Gkountouras, Ivan Titov

    NeurIPS 2026Oral

    Paper Project
  2. Learning to Surpass: Training Tool-Using Agents with Anchored Feedback

    John Gkountouras, Fengjun Wang, Angelantonio Castelli, Satendra Kumar

    NeurIPS 2026

    Project
  3. Consensus as Privileged Context for Label-Free Self-Distillation

    John Gkountouras, Josip Jukić, Ivan Titov

    arXiv preprint, 2026

    Paper Project

2025

  1. Language Agents Meet Causality: Bridging LLMs and Causal World Models

    John Gkountouras, Matthias Lindemann, Phillip Lippe, Efstratios Gavves, Ivan Titov

    ICLR 2025

    Paper Code Project

2023

  1. INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation

    Yuji Chai*, John Gkountouras*, Glenn G. Ko, David Brooks, Gu-Yeon Wei

    arXiv preprint, 2023

    Paper
  2. VISION DIFFMASK: Interpretability of Computer Vision Models with Differentiable Patch Masking

    Angelos Nalmpantis*, Apostolos Panagiotopoulos*, John Gkountouras*, Konstantinos Papakostas*, Wilker Aziz

    CVPR 2023 Workshop on Explainable AI for Computer Vision (XAI4CV)

    Paper Code Demo

2022

  1. [Re] Exacerbating Algorithmic Bias through Fairness Attacks

    Angelos Nalmpantis*, Apostolos Panagiotopoulos*, John Gkountouras*, Konstantinos Papakostas*

    ReScience C, 2022 (NeurIPS 2022 Journal Showcase)

    Paper Code