Publications

Publications by categories in reversed chronological order.

2025

  1. GenProCC @ NeurIPS
    The Mind's Eye: A Multi‑Faceted Reward Framework for Guiding Visual Metaphor Generation
    G. A. Koushik, F. Nazarieh, K. Birch, S. Qian & D. Kanojia
    arXiv preprint, 2025
    arXiv PDF GitHub
  2. RANLP
    Cyberbullying Detection via Aggression‑Enhanced Prompting
    A. Saeid, A. Sabu, G. A. Koushik, F. Neri & D. Kanojia
    Proceedings of Recent Advances in Natural Language Processing, 2025
    arXiv PDF
  3. AAAI AISI
    TRACE: Textual Relevance Augmentation and Contextual Encoding for Multimodal Hate Detection
    G. A. Koushik, D. Kanojia, H. Treharne & A. Joshi
    arXiv preprint, 2025
    arXiv PDF GitHub
  4. MM4SG @ The Web Conf
    Towards a Robust Framework for Multimodal Hate Detection: A Study on Video vs. Image‑based Content
    G. A. Koushik, D. Kanojia & H. Treharne
    arXiv preprint, 2025
    arXiv PDF GitHub

2024

  1. ICLR SSI‑FM
    Natural Language Reinforcement Learning
    X. Feng, B. Liu, Y. Song, H. Fu, Z. Wan, G. A. Koushik, Z. Hu, M. Yang, Y. Wen & J. Wang
    ICLR 2025 Workshop on Safe and Secure Foundation Models (SSI‑FM), 2024
    arXiv PDF GitHub