Publications

Google Scholar Profile

Under Review / Preprint [*: Equal Contribution / Supervision]

  • Y. Zhu, Md Mofijul Islam, S. Chao, W. Wang, “RETROAGENT: Agentic Retrosynthesis Planning with Search Over Structured Memory”, COLM-2026
  • M. T. Hossain, S. H. Shifat, Md Mofijul Islam, M. K. Morol, M. R. Parvez, “BnIdiomEval: LLMs in the Translation of Bengali Idioms”, COLM-2026
  • M. M. Ahasan, R. H. Khan, T. Mohiuddin, A. Chadha, T. Iqbal, M. M. Amin, A. A. Ali, Md Mofijul Islam *, A. Rahman *, “FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs”, InterSpeech-2026 [ArXiv]
  • M. A. R. Iftee, M. S. Hossain, R. H. Rajib, A. Rahman, T. Iqbal, Md Mofijul Islam, M. M. Amin, A. A. Ali *, “SloMo-FAST: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation”, ECCV-2026 (Under Review) [ArXiv]
  • A. T. Azad, I. S. Apan, F. Ahmed, S. K. Katha, E. Jubaer, A. Alam, P. K. Nandi, A. A. Ali, A. Chadha, Md Mofijul Islam *, A. Rahman *, “BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension”, ECCV-2026

Conference Publications (Peer Reviewed) [*: Equal Contribution / Supervision]

  • M. F. A. Sayeedi, M. M. Alam, S. S. Rahman, M. A. Islam, J. F. Deepti, T. Mohiuddin, Md Mofijul Islam *, S. Shatabda *, “Ready to Translate, Not to Represent? Bias and Performance Gaps in Multilingual LLMs Across Language Families and Domains,” ACL-2026 [ArXiv]
  • Md Mofijul Islam, M. S. Salekin, N. Balakrishnan, V. C. Bishop III, N. Jain, S. Romo, B. Strahan, B. Xie, D. A. Socolinsky, “DocSplit: A Comprehensive Benchmark Dataset and Evaluation Approach for Document Packet Recognition and Splitting,” ACL-2026 (Industry Track) [Benchmark]
  • Md Mofijul Islam, M. S. Salekin, J. King, P. Roy, V. T. Gudi, S. Romo, B. Strahan, B. Xie, D. A. Socolinsky, “IDP Accelerator: Agentic Document Intelligence from Extraction to Compliance Validation,” ACL-2026 (Demo)
  • A. Gladstone, G. Nanduru, Md Mofijul Islam, P. Han, H. Ha, A. Chadha, Y. Du, H. Ji, J. Li, T. Iqbal, “Energy-Based Transformers are Scalable Learners and Thinkers,” ICLR-2026 (Oral) [ArXiv]
  • M. E. Sobhani, M. F. A. Sayeedi, T. Mohiuddin, Md Mofijul Islam *, S. Shatabda *, “MATHMIST: A Parallel Multilingual Benchmark Dataset for Mathematical Problem Solving and Reasoning,” EACL-2026 [ArXiv]
  • Md Mofijul Islam, A. Gladstone, S. Sarker, G. Nanduru, M. Fahim, K. Du, A. Chadha, T. Iqbal, “Embodied Referring Expression Comprehension Through Multimodal Residual Learning,” HRI-2026 [ArXiv]
  • M. M. Ahasan, M. Fahim, T. Mohiuddin, A. Rahman, A. Chadha, T. Iqbal, M. M. Amin, Md Mofijul Islam *, A. A. Ali *, “DM-Codec: Distilling Multimodal Representations for Speech Tokenization,” EMNLP-2025 [ArXiv] [Code]
  • Md Mofijul Islam, Alexi Gladstone, Riashat Islam, Tariq Iqbal, “EQA-MX: Embodied Question Answering using Multimodal Human Expression,” ICLR-2024 (Spotlight; 5% acceptance rate)
  • Mohammad Samin Yasar, Md Mofijul Islam, Tariq Iqbal, “PoseTron: Enabling Close-Proximity Human-Robot Collaboration Through Multi-Human Motion Prediction,” ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2024
  • Riashat Islam, Hongyu Zang, Manan Tomar, Aniket Didolkar, Md Mofijul Islam, Samin Yeasar Arnob, Tariq Iqbal, Xin Li, Anirudh Goyal, Nicolas Heess, Alex Lamb, “Representation Learning in Deep RL via Discrete Information Bottleneck,” AISTATS-2023
  • Md Mofijul Islam, Alexi Gladstone, Tariq Iqbal, “PATRON: Perspective-Aware Multitask Model for Referring Expression Grounding using Embodied Multimodal Cues,” AAAI-2023 (Main Track; 19.6% acceptance rate)
  • Md Mofijul Islam, Reza Manuel Mirzaiee, Alexi Gladstone, Haley N. Green, Tariq Iqbal, “CAESAR: An Embodied Simulator for Generating Multimodal Referring Expression Datasets,” NeurIPS 2022 (Datasets and Benchmarks Track)
  • Md Mofijul Islam, Tariq Iqbal, “MuMu: Cooperative Multitask Learning-based Guided Multimodal Fusion,” AAAI-2022 (Main Track, Oral; 4.6% oral acceptance rate) [Pre-print] [Video] [Flash Talk]
  • Haley N. Green, Md Mofijul Islam, Shahira Ali, Tariq Iqbal, “Who’s Laughing NAO? Examining Perceptions of Failure in a Humorous Robot Partner,” HRI-2022 (24.8% acceptance rate)
  • Md Mofijul Islam, Tariq Iqbal, “HAMLET: A Hierarchical Multimodal Attention-based Human Activity Recognition,” IROS-2020 [PDF] [Video]
  • Amar Debnath, Redoan Rahman, Md Mofijul Islam, Md Abdur Razzaque, “A Hierarchical Learning Model for Claim Validation,” International Joint Conference on Computational Intelligence (IJCCI) 2018
  • Md. Tanvir Alam, Md Mofijul Islam, “BARD: Bangla Article Classification using a New Comprehensive Dataset,” International Conference on Bangla Speech and Language Processing (ICBSLP) 2018 [Dataset & Code] [Web App] [Video]