Published in arXiv, 2025
This work investigates how large language models learn from near-miss negative examples, exploring the subtle differences between correct and incorrect examples that are almost correct.
Recommended citation: D. Yuret, S. Hamdan, "How much do LLMs learn from negative examples?," on arXiv https://arxiv.org/abs/2503.14391
Published in ICCV 2025, 2025
This paper proposes a dual-system architecture that enables the use of slow, heavy vision-language model planners in tandem with lightweight planners for autonomous driving. ETA achieves state-of-the-art performance in the Bench2Drive benchmark with a 6x speedup compared to previous approaches.
Recommended citation: S. Hamdan et al., "ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models", ICCV 2025 https://arxiv.org/abs/2506.07725
Published in ECCV 2024, 2024
In CarFormer, we propose to learn object-centric representations in bird’s eye view (BEV) to distill a complex scene into more actionable information for self-driving in a self-supervised manner. Using this representation, we outperform both scene-level and object-level approaches that use the exact attributes of objects. Our model with slots achieves an increased completion rate of the provided routes and, consequently, a higher driving score, with a lower variance across multiple runs, affirming slots as a reliable alternative in object-centric approaches.
Recommended citation: Hamdan, S. et al (2024). CarFormer: Self-Driving with Learned Object-Centric Representations. ArXiv, abs/2407.15843. https://arxiv.org/abs/2407.15843
Published in NeurIPS, 2022
This article proposes a self-supervised learning method that uses a second-order statistics-based mutual information measure that reflects the level of correlation among its arguments and prevents dimensional collapse by encouraging the spread of information across the whole feature space.
Recommended citation: Ozsoy, S., Hamdan, S.S., Arik, S.Ö., Yuret, D., & Erdogan, A.T. (2022). Self-Supervised Learning with an Information Maximization Criterion. ArXiv, abs/2209.07999. https://arxiv.org/abs/2209.07999
Published in TMLR, 2022
The Beyond the Imitation Game Benchmark (BIG-bench) is a collaborative benchmark intended to probe large language models and extrapolate their future capabilities.
Recommended citation: Srivastava, A. et al (2022). Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models. ArXiv, abs/2206.04615. https://arxiv.org/abs/2206.04615
Published in The 39th International Symposium on Reliable Distributed Systems (SRDS 2020), 2020
Y. Hassanzadeh-Nazarabadi, N. Nayal, S. Sameh Hamdan, A. Utkan Şahin, Ö. Özkasap, and A. Küpçü, ”Demo: Skip Graph Middleware Implementation”, in SRDS 2020.
Recommended citation: Y. Hassanzadeh-Nazarabadi, N. Nayal, S. Sameh Hamdan, A. Utkan Şahin, Ö. Özkasap, and A. Küpçü, ”Demo: Skip Graph Middleware Implementation”, in SRDS 2020. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9169463
Published in IEEE International Conference on Blockchain and Cryptocurrency, 2020
This publication features our implementation of proof of concept of LightChain System.
Recommended citation: Y. Hassanzadeh-Nazarabadi, N. Nayal, S. Sameh Hamdan, Ö. Özkasap, and A. Küpçü, “A containerized proof-of-concept implementation of lightchain system,” in ICBC. IEEE, 2020. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9169463