11 papers
Certified Interface Aliases: Exact Collisions in Vision-Language Preprocessing, and When They Exist
Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic +1
Vision-language verifiers and routers must distinguish errors repairable by more reasoning from those caused by visual evidence never reaching the language model. This distinction…
Oracle Gaps in Reliability Coverage: Sampling Noise or Policy Specialization?
Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan Kurban
Policies trained from the same base model can appear to solve different problems. An oracle that chooses the best policy for each problem may therefore appear much stronger than an…
When Does Retrieval Help Time-Series Forecasting?
Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic +1
Retrieval plug-ins supply a deep forecaster with information its lookback window cannot carry. Published evaluations report consistent gains, and each credits its own mechanism. We…
Cross-Lingual Transfer for Machine Translation in Turkic Languages
Omer Burak Cinar, Mehmet Mert Dalkilic, Cagri Toraman
Cross-lingual transfer is central to low-resource machine translation, but its behavior within closely related language families remains insufficiently characterized. We study tran…
Detect Early, Escalate Rarely: Anytime Detection of AI-Generated Video from the Compressed Bitstream
Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan Kurban
Detectors for AI-generated video are evaluated offline. A clip is decoded to pixels and scored once, increasingly by a large vision-language model. Detection, however, is deployed…
The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting
Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan Kurban
A growing family of indices scores how predictable a series is from its spectrum. Practitioners increasingly read these scores as answering a different question: whether \emph{addi…
Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit
Mert Onur Cakiroglu, Zhihe Lu, Mehmet Dalkilic +1
AI-generated video detection benchmarks such as GenVidBench and AIGVDBench are the de facto leaderboards, yet most evaluation protocols leave uncontrolled confounds that can inflat…
LGQ: Learnable Geometric Quantization for Image Tokenization
Idil Bilge Altun, Mert Onur Cakiroglu, Elham Buxton +2
Recent collapse-free quantizers such as FSQ achieve stable training by replacing the learnable codebook with an engineered geometry: a fixed scalar grid whose structure is dictated…
Temporal Realism Evaluation of Generated Videos Using Compressed-Domain Motion Vectors
Mert Onur Cakiroglu, Idil Bilge Altun, Zhihe Lu +2
Temporal realism remains a central weakness of current generative video models, as most evaluation metrics prioritize spatial appearance and offer limited sensitivity to motion. We…
Geometric-k-means: A Bound Free Approach to Fast and Eco-Friendly k-means
Parichit Sharma, Marcin Stanislaw, Hasan Kurban +2
This paper introduces Geometric-k-means (or Gk-means for short), a novel approach that significantly enhances the efficiency and energy economy of the widely utilized k-means algor…
Multivariate de Bruijn Graphs: A Symbolic Graph Framework for Time Series Forecasting
Mert Onur Cakiroglu, Idil Bilge Altun, Mehmet Dalkilic +2
Time series forecasting remains a challenging task for foundation models due to temporal heterogeneity, high dimensionality, and the lack of inherent symbolic structure. In this wo…