Seminerler
-
Towards Extreme Video Compression Using General World Knowledge
MSc Thesis📅 03.09.2026 — 14:15 👤 Speaker: FURKAN KUCUK 🎓 Supervisor(s): ASSOC.PROF.DR.R.GOKBERK CINBIS 📍 Location: A105 ⏲ Duration: 90 min. 📝 Abstract: Classical and learned video codecs rebuild a generic visual prior at every receiver and transmit the residual it fails to predict. This thesis inverts that premise. A pretrained… -
Generative Super-Resolution of 3D Gaussian Splat Sets
MSc Thesis📅 03.09.2026 — 13:30 👤 Speaker: BATUHAN BAL 🎓 Supervisor(s): ASSOC.PROF.DR.R.GOKBERK CINBIS 📍 Location: A105 ⏲ Duration: 90 min. 📝 Abstract: 3D Gaussian Splatting (3DGS) enables real-time novel view synthesis, but Gaussian representations reconstructed from low-resolution observations are typically sparse and lack… -
CONWISE-FT: ENHANCING FEW-SHOT LEARNING THROUGH CONTRASTIVE PROJECTION TUNING AND POST-TRAINING WEIGHT ENSEMBLING
MSc Thesis📅 27.08.2026 — 15:00 👤 Speaker: ALPER BAHCEKAPILI 🎓 Supervisor(s): ASSOC.PROF.DR.EMRE AKBAS 📍 Location: A105 ⏲ Duration: 90 min. 📝 Abstract: Foundation vision–language models such as CLIP achieve strong zero-shot performance, but adapting them to specialised few-shot tasks still remains difficult. Two failure modes… -
GRAPH-BASED CHAIN CONSTRUCTION APPROACH TO LANDMARK-GUIDED REINFORCEMENT LEARNING
MSc Thesis📅 13.08.2026 — 15:00 👤 Speaker: ANIL ERDEM DERINOZ 🎓 Supervisor(s): PROF.DR.FARUK POLAT, ASST.PROF.DR.HUSEYIN AYDIN 📍 Location: A105 ⏲ Duration: 90 min. 📝 Abstract: Reinforcement Learning (RL) provides a powerful framework for autonomous deci-sion making; however, its real-world applicability is often bottlenecked by… -
Long-Tailed Visual Recognition with Learnable Average Precision Loss
MSc Thesis📅 12.08.2026 — 13:00 👤 Speaker: BURAK FERIT AKTAN 🎓 Supervisor(s): PROF.DR.SINAN KALKAN, ASSOC.PROF.DR.EMRE AKBAS 📍 Location: A105 ⏲ Duration: 90 min. 📝 Abstract: Real-world data is often long-tailed. Most of the training samples belong to common classes, while rare classes have limited samples. Models trained on long… -
A Multimodal Framework for Source Code Vulnerability Detection, Explanation, and Mitigation
PhD Thesis📅 30.07.2026 — 13:30 👤 Speaker: IBRAHIM TARAKCI 🎓 Supervisor(s): PROF.DR.HALIT OGUZTUZUN, ASST.PROF.DR.SELMA SULOGLU 📍 Location: A105 ⏲ Duration: 120 min. 📝 Abstract: This thesis develops a multimodal approach to source code vulnerability detection, explanation, and mitigation. It investigates complementary software… -
HARDWARE ACCELERATORS FOR TRANSFORMERS BASED AI APPLICATIONS
MSc Thesis📅 22.07.2026 — 13:30 👤 Speaker: ARDA CEKIC 🎓 Supervisor(s): ASSOC.PROF.DR.SEYDA ERTEKIN 📍 Location: METU DTX ⏲ Duration: 90 min. 📝 Abstract: Large Language Models (LLMs) achieve strong performance in many natural language processing tasks, but their high computational and memory requirements make hardware deployment… -
HARDWARE ORIENTED MODELING OF LLM ACCELERATOR PIPELINE
MSc Thesis📅 22.07.2026 — 13:30 👤 Speaker: ARDA CEKIC 🎓 Supervisor(s): ASSOC.PROF.DR.SEYDA ERTEKIN 📍 Location: METU DTX ⏲ Duration: 90 min. 📝 Abstract: Large Language Models (LLMs) achieve strong performance in many natural language processing tasks, but their high computational and memory requirements make hardware deployment… -
Beyond Models: Building the Next Generation AI Platforms for Science and Society
Seminar📅 13.07.2026 — 13:30 👤 Speaker: Dr. İlkay Altıntaş 📍 Location: BMB5 ⏲ Duration: 60 min. 📝 Abstract: Artificial intelligence is entering a new phase where the greatest opportunity lies beyond foundation models. The next frontier is building AI platforms that integrate data, computation, agents, workflows, and scientific expertise to… -
Generalizable Deep Learning Approaches for Computational Drug Discovery
PhD Thesis📅 24.06.2026 — 13:00 👤 Speaker: GOKHAN OZSARI 🎓 Supervisor(s): PROF.DR.HALIT OGUZTUZUN,PROF.DR.M.VOLKAN ATALAY 📍 Location: A101 ⏲ Duration: 120 min. 📝 Abstract: Computational prediction of drug–target interactions is central to modern drug discovery, enabling the prioritization of candidate compounds before costly…