2026

1. EMNLP

   

   EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing

   Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter, and 1 more author

   In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026
2. EMNLP

   

   Spectral DPO: Mitigating Validation Collapse via Heavy-Tailed Regularization

   Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

   In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026
3. EMNLP Findings

   

   Counterfactual Sensitivity Regularization for Trace-Sensitive Reasoning in Large Language Models

   Sanjeda Akter, Ibne Farabi Shihab, and Anuj Sharma

   In Findings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026

   arXiv
4. EMNLP Findings

   

   Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAG

   Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter, and 1 more author

   In Findings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026
5. BMVC

   

   Enhancing Traffic Incident Response through Sub-Second Temporal Localization with HybridMamba

   Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

   In Proceedings of the 37th British Machine Vision Conference (BMVC 2026), 2026

   arXiv
6. BMVC

   

   Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization

   Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

   In Proceedings of the 37th British Machine Vision Conference (BMVC 2026), 2026

   arXiv
7. ICML

   

   CalPro: Prior-Aware Evidential Conformal Prediction with Structure-Aware Sensitivity Bounds for Protein Structures

   Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

   In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), 2026

   arXiv
8. ICML

   

   What Reward Structure Enables Efficient Sparse-Reward RL? A Proof-of-Concept with Policy-Aware Matrix Completion

   Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

   In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), 2026

   arXiv
9. ICML

   

   CGRiC: Compositional Risk Certification for Structured LLM Outputs

   Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

   In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), 2026
10. ICML

    

    Certificate-Guided Pruning for Stochastic Lipschitz Optimization

    Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

    In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), 2026

    arXiv
11. T-ITS

    Image Segmentation with Large Language Models: A Survey with Perspectives for Intelligent Transportation Systems

    Sanjeda Akter, Ibne Farabi Shihab, and Anuj Sharma

    IEEE Transactions on Intelligent Transportation Systems, 2026

    arXiv
12. JSR

    Improving Crash Data Quality by Identifying Misclassified Alcohol-Involved Crashes Using NLP on Narrative Data

    Sudesh Bhagat, Ibne Farabi Shihab, Raghupathi Kandiboina, and 3 more authors

    Journal of Safety Research, 2026

    DOI arXiv
13. ITSC

    

    Beyond Accuracy: Empirical Spectral Diagnostics for Crash Classification Models

    Ibne Farabi Shihab, Sanjeda Akter, Sudesh Bhagat, and 2 more authors

    In 2026 IEEE International Conference on Intelligent Transportation Systems (ITSC), 2026

    arXiv
14. ITSC

    

    LLM-Guided Meta-Prior Reinforcement Learning for Adaptive Traffic Signal Synchronization

    Sanjeda Akter, Ibne Farabi Shihab, and Anuj Sharma

    In 2026 IEEE International Conference on Intelligent Transportation Systems (ITSC), 2026
15. CVPR

    

    LLM-Guided Probabilistic Fusion for Label-Efficient Document Layout Analysis

    Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

    arXiv preprint arXiv:2511.08903, 2026

    Accepted to IEEE/CVF CVPR 2026

    arXiv
16. ACL

    

    Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning

    Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), 2026

    arXiv
17. ACL

    

    Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics

    Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), 2026

    arXiv
18. ACL Findings

    

    Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests

    Sanjeda Akter, Ibne Farabi Shihab, and Anuj Sharma

    In Findings of the Association for Computational Linguistics: ACL 2026, 2026

    arXiv

2025

1. 

   HMAE: Self-Supervised Few-Shot Learning for Quantum Spin Systems

   Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

   In ECAI 2025 – 27th European Conference on Artificial Intelligence, 2025

   DOI

2. 

   Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments

   Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Nov 2025

   Abs DOI

   As the deployment of AI models shifts towards edge devices, developing efficient sequence models has become critical. State-space models (SSMs), particularly Mamba, have emerged as strong rivals to Transformers due to their linear-time complexity and impressive performance across a range of tasks. However, their large parameter counts still hinder their use in resource-constrained environments. To address this, we propose a novel unstructured pruning framework specifically tailored for Mamba, achieving up to 70% parameter reduction with only a 3–9% drop in performance. Unlike pruning techniques designed for Transformers, our approach leverages Mamba’s unique recurrent dynamics by incorporating pruning based on both weight and gradient importance to preserve critical parameters, a gradual pruning schedule to maintain model stability, and a global strategy to optimize parameter allocation across the model. Extensive experiments on the WikiText-103, Long Range Arena, and ETT benchmarks demonstrate significant efficiency gains, including 1.77× faster inference and a 46% reduction in memory usage. Our component analysis confirms Mamba’s robustness to pruning, highlighting the framework’s potential for enabling practical deployment while underscoring the need for careful evaluation to avoid introducing biases in sensitive applications.

3. 

   Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains

   Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma

   In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Nov 2025

   Abs DOI

   Integrating large language models (LLMs) as action proposers in reinforcement learning (RL) significantly boosts performance in text-based environments but incurs prohibitive computational costs. We introduce a cache-efficient framework for Bayesian RL that leverages LLM-derived action suggestions, drastically reducing these costs while maintaining near-optimal performance. Our approach features an adaptive caching mechanism, optimized via meta-learning based on policy performance, to enable efficient inference across text-based games (e.g., TextWorld, ALFWorld) and robotic control tasks (e.g., MuJoCo, MetaWorld). This framework achieves a 3.8×–4.7× reduction in LLM queries and 4.0×–12.0× lower median latencies (85–93ms on consumer hardware), while retaining 96–98% of the uncached policy’s performance. We provide theoretical guarantees on the reliability of cached decisions with Kullback-Leibler (KL) divergence bounds, which are validated empirically by high success rates (90.4–95.6%) in complex text environments. For offline RL, our proposed CQL-Prior variant improves performance by 14–29% and reduces training time by 38–40%. Evaluations across eight diverse tasks demonstrate the framework’s generalizability and practicality for resource-constrained settings, making LLM-guided RL a viable and accessible approach for both text-based and robotic applications.

4. ITSC

   

   ClearVision: Leveraging CycleGAN and SigLIP-2 for Robust All-Weather Classification in Traffic Camera Imagery

   Anush L. Sivaraman, Kwadwo Adu-Gyamfi, Ibne Farabi Shihab, and 1 more author

   In 2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), Nov 2025

   DOI arXiv
5. ITSC

   

   Accuracy Is Not Agreement: Expert-Aligned Evaluation of Crash Narrative Classification Models

   Sudesh Ramesh Bhagat, Ibne Farabi Shihab, and Anuj Sharma

   In 2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), Nov 2025

   DOI arXiv

6. 

   Quantum-driven Zero Trust Architecture with Dynamic Anomaly Detection in 7G Technology: A Neural Network Approach

   Shakil Ahmed, Ibne Farabi Shihab, and Ashfaq Khokhar

   Measurement: Digitalization, Nov 2025

   DOI

2024

1. CVPR

   

   DeepLocalization: Using Change Point Detection for Temporal Action Localization

   Mohammed Shaiqur Rahman, Ibne Farabi Shihab, Lu Chu, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Nov 2024

   DOI
2. Biotech

   

   Reinforcement Learning-Guided Control Strategies for CAR T-Cell Activation and Expansion

   Sakib Ferdous, Ibne Farabi Shihab, Ratul Chowdhury, and 1 more author

   Biotechnology and Bioengineering, Nov 2024

   DOI
3. TRC-30

   

   Leveraging Video-LLMs for Crash Detection and Narrative Generation: Performance Analysis and Challenges

   Ibne Farabi Shihab, B. I. Alvee, and Anuj Sharma

   In Proceedings of the TRC-30 Conference, Nov 2024

2023

1. ITSC

   

   Robust and Precise Sidewalk Detection with Ensemble Learning: Enhancing Road Safety and Facilitating Curb Space Management

   Ibne Farabi Shihab, Sudesh Ramesh Bhagat, and Anuj Sharma

   In 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Nov 2023

   DOI

2022

1. ICCIT

   

   Detecting Faulty Machinery of Waste Water Treatment Plant Using Statistical Analysis & Machine Learning

   Md. Mazed Ul Islam, Joyanta J. Mondal, and Ibne Farabi Shihab

   In 2022 25th International Conference on Computer and Information Technology (ICCIT), Nov 2022
2. BEJ

   

   Effects of Sequence Features on Machine-Learned Enzyme Classification Fidelity

   Sakib Ferdous, Ibne Farabi Shihab, and Nigel F. Reuel

   Biochemical Engineering Journal, Nov 2022

   DOI

2018

1. R10-HTC

   

   A Machine Learning Approach to Suggest Ideal Geographical Location for New Restaurant Establishment

   Ibne Farabi Shihab, Maliha Moonwara Oishi, Samiul Islam, and 2 more authors

   In 2018 IEEE Region 10 Humanitarian Technology Conference (R10-HTC), Nov 2018

   DOI