Muhammad Rafsan Kabir

Orcid: 0009-0006-4431-3916

According to our database1, Muhammad Rafsan Kabir authored at least 12 papers between 2024 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Beyond Real Weights: Hypercomplex Representations for Stable Quantization.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

2025
Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learning.
CoRR, September, 2025

Z-Pruner: Post-Training Pruning of Large Language Models for Efficiency without Retraining.
CoRR, August, 2025

Effective depression detection and interpretation: Integrating machine learning, deep learning, language models, and explainable AI.
Array, 2025

Federated learning for human activity recognition: Balancing privacy, efficiency, and accuracy through innovative aggregation techniques.
Array, 2025

LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval.
Proceedings of the International Joint Conference on Neural Networks, 2025

Bidirectional Reasoning Supervision for Multilingual Financial Decision Making.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

AutoDSPy: Automating Modular Prompt Design with Reinforcement Learning for Small and Large Language Models.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

LAET: A Layer-Wise Adaptive Ensemble Tuning Framework for Pretrained Language Models.
Proceedings of the IEEE International Conference on Big Data, 2025

Z -Prunear: Post-Training Pruning of Large Language Models for Efficiency without Retraining.
Proceedings of the 22nd IEEE/ACS International Conference on Computer Systems and Applications, 2025

2024
Beyond Labels: Aligning Large Language Models with Human-Like Reasoning.
Proceedings of the Pattern Recognition - 27th International Conference, 2024

BanglaEmbed: Efficient Sentence Embedding Models for a Low-Resource Language Using Cross-Lingual Distillation Techniques.
Proceedings of the 7th International Conference on Algorithms, 2024


  Loading...