Baturay Saglam

37 papers A* 1B 4Journal 22Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report. CoRR Zhuoran Yang, Ed Li, Jianliang He, Aman Priyanshu, Baturay Saglam, Paul Kassianik, Sajana Weerawardhena, Anu Vellore, Blaine Nelson, Neusha Javidnia, Arthur Goldblatt, Fraser Burch, Avi Zohary, Assaf Eisenman, Mahdi Sabbaghi, Supriti Vijay, Rahim Dharssi, Dhruv Kedia, Kojin Oshiba, Yaron Singer, Amin Karbasi
2026	J	`jnl`	Test-Time Detoxification without Training or Learning Anything. CoRR Baturay Saglam, Dionysis Kalogerias
2025	—	`conf`	Large Language Models Encode Semantics and Alignment in Linearly Separable Representations. IJCNLP-AACL (long papers) Baturay Saglam, Paul Kassianik, Blaine Nelson, Sajana Weerawardhena, Yaron Singer, Amin Karbasi
2025	J	`jnl`	Large Language Models Encode Semantics in Low-Dimensional Linear Subspaces. CoRR Baturay Saglam, Paul Kassianik, Blaine Nelson, Sajana Weerawardhena, Yaron Singer, Amin Karbasi
2025	—	`conf`	Learning Task Representations from In-Context Learning. ACL (Findings) Baturay Saglam, Xinyang Hu, Zhuoran Yang, Dionysis Kalogerias, Amin Karbasi
2025	J	`jnl`	Learning Task Representations from In-Context Learning. CoRR Baturay Saglam, Zhuoran Yang, Dionysis Kalogerias, Amin Karbasi
2025	J	`jnl`	Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report. CoRR Sajana Weerawardhena, Paul Kassianik, Blaine Nelson, Baturay Saglam, Anu Vellore, Aman Priyanshu, Supriti Vijay, Massimo Aufiero, Arthur Goldblatt, Fraser Burch, Ed Li, Jianliang He, Dhruv Kedia, Kojin Oshiba, Zhouran Yang, Yaron Singer, Amin Karbasi
2025	J	`jnl`	Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report. CoRR Paul Kassianik, Baturay Saglam, Alexander Chen, Blaine Nelson, Anu Vellore, Massimo Aufiero, Fraser Burch, Dhruv Kedia, Avi Zohary, Sajana Weerawardhena, Aman Priyanshu, Adam Swanda, Amy Chang, Hyrum S. Anderson, Kojin Oshiba, Omar Santos, Yaron Singer, Amin Karbasi
2025	J	`jnl`	Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents. CoRR Jane H. Lee, Baturay Saglam, Spyridon Pougkakiotis, Amin Karbasi, Dionysis Kalogerias
2025	J	`jnl`	Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models. CoRR Supriti Vijay, Aman Priyanshu, Anu Vellore, Baturay Saglam, Amin Karbasi
2024	A*	`conf`	Actor Prioritized Experience Replay (Abstract Reprint). AAAI Baturay Saglam, Furkan B. Mutlu, Dogan Can Çiçek, Suleyman S. Kozat
2024	J	`jnl`	Compatible Gradient Approximations for Actor-Critic Algorithms. CoRR Baturay Saglam, Dionysis Kalogerias
2024	J	`jnl`	Mitigating Off-Policy Bias in Actor-Critic Methods with One-Step Q-learning: A Novel Correction Approach. Trans. Mach. Learn. Res. Baturay Saglam, Dogan Can Çiçek, Furkan Burak Mutlu, Suleyman S. Kozat
2024	J	`jnl`	Parameter-Free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients. Neural Process. Lett. Baturay Saglam, Furkan B. Mutlu, Dogan Can Çiçek, Suleyman Serdar Kozat
2023	J	`jnl`	Actor Prioritized Experience Replay. J. Artif. Intell. Res. Baturay Saglam, Furkan B. Mutlu, Dogan Can Çiçek, Suleyman S. Kozat
2023	—	`conf`	Deep Reinforcement Learning Based Joint Downlink Beamforming and RIS Configuration in RIS-Aided MU-MISO Systems Under Hardware Impairments and Imperfect CSI. ICC Workshops Baturay Saglam, Doga Gürgünoglu, Suleyman S. Kozat
2023	J	`jnl`	Deep intrinsically motivated exploration in continuous control. Mach. Learn. Baturay Saglam, Suleyman S. Kozat
2023	—	`conf`	Denoising Diffusion Adversarial Models for Unconditional Medical Image Generation. SIU Onat Dalmaz, Baturay Saglam, Gökberk Elmas, Muhammad Usama Mirza, Tolga Çukur
2023	B	`conf`	User Feedback-based Online Learning for Intent Classification. ICMI Kaan Gönç, Baturay Saglam, Onat Dalmaz, Tolga Çukur, Suleyman Serdar Kozat, Hamdi Dibeklioglu
2022	J	`jnl`	Actor Prioritized Experience Replay. CoRR Baturay Saglam, Furkan B. Mutlu, Dogan Can Çiçek, Suleyman S. Kozat
2022	—	`conf`	An Intrinsic Motivation Based Artificial Goal Generation in On-Policy Continuous Control. SIU Baturay Saglam, Furkan B. Mutlu, Kaan Gonc, Onat Dalmaz, Suleyman S. Kozat
2022	—	`conf`	An Optimistic Approach to the Temporal Difference Error in Off-Policy Actor-Critic Algorithms. SSCI Baturay Saglam, Furkan B. Mutlu, Suleyman S. Kozat
2022	—	`conf`	Bottleneck Sharing Generative Adversarial Networks for Unified Multi-Contrast MR Image Synthesis. SIU Onat Dalmaz, Baturay Saglam, Kaan Gönç, Salman Ul Hassan Dar, Tolga Çukur
2022	J	`jnl`	Deep Intrinsically Motivated Exploration in Continuous Control. CoRR Baturay Saglam, Suleyman S. Kozat
2022	J	`jnl`	Deep Reinforcement Learning Based Joint Downlink Beamforming and RIS Configuration in RIS-aided MU-MISO Systems Under Hardware Impairments and Imperfect CSI. CoRR Baturay Saglam, Doga Gürgünoglu, Suleyman S. Kozat
2022	—	`conf`	Face Inpainting with Pre-trained Image Transformers. SIU Kaan Gonc, Baturay Saglam, Suleyman S. Kozat, Hamdi Dibeklioglu
2022	—	`conf`	Improving the Performance of Batch-Constrained Reinforcement Learning in Continuous Action Domains via Generative Adversarial Networks. SIU Baturay Saglam, Onat Dalmaz, Kaan Gonc, Suleyman S. Kozat
2022	J	`jnl`	Off-Policy Correction for Actor-Critic Algorithms in Deep Reinforcement Learning. CoRR Baturay Saglam, Dogan Can Çiçek, Furkan B. Mutlu, Suleyman S. Kozat
2022	J	`jnl`	Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms. CoRR Baturay Saglam, Dogan Can Çiçek, Furkan B. Mutlu, Suleyman S. Kozat
2022	—	`conf`	Unified Intrinsically Motivated Exploration for Off-Policy Learning in Continuous Action Spaces. SIU Baturay Saglam, Furkan B. Mutlu, Onat Dalmaz, Suleyman S. Kozat
2021	B	`conf`	AWD3: Dynamic Reduction of the Estimation Bias. ICTAI Dogan Can Çiçek, Enes Duran, Baturay Saglam, Kagan Kaya, Furkan B. Mutlu, Suleyman S. Kozat
2021	J	`jnl`	AWD3: Dynamic Reduction of the Estimation Bias. CoRR Dogan Can Çiçek, Enes Duran, Baturay Saglam, Kagan Kaya, Furkan B. Mutlu, Suleyman S. Kozat
2021	B	`conf`	Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods. ICTAI Baturay Saglam, Enes Duran, Dogan Can Çiçek, Furkan B. Mutlu, Suleyman S. Kozat
2021	J	`jnl`	Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods. CoRR Baturay Saglam, Enes Duran, Dogan Can Çiçek, Furkan B. Mutlu, Suleyman S. Kozat
2021	B	`conf`	Off-Policy Correction for Deep Deterministic Policy Gradient Algorithms via Batch Prioritized Experience Replay. ICTAI Dogan Can Çiçek, Enes Duran, Baturay Saglam, Furkan B. Mutlu, Suleyman S. Kozat
2021	J	`jnl`	Off-Policy Correction for Deep Deterministic Policy Gradient Algorithms via Batch Prioritized Experience Replay. CoRR Dogan Can Çiçek, Enes Duran, Baturay Saglam, Furkan B. Mutlu, Suleyman S. Kozat
2021	J	`jnl`	Parameter-Free Deterministic Reduction of the Estimation Bias in Continuous Control. CoRR Baturay Saglam, Enes Duran, Dogan Can Çiçek, Furkan B. Mutlu, Suleyman S. Kozat