950 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
Machine learning interatomic potentials (MLIPs) are commonly trained and evaluated by their ability to reproduce first-principles energies and forces. Practical value, however, is often determined by downstream processes…
Panoramic cameras provide a 360° field of view and are widely used in panoramic vision, immersive visual computing, and robotic perception. However, changes in camera orientation can produce non-upright panoramas, introd…
Large language models (LLMs) have shown impressive capabilities in code generation across many programming languages but even state-of-the-art LLMs generate programs that contain syntactic errors and fail to complete the…
Tensor-train (TT) compression reduces neural-network parameters, but the latency of a tensorized layer is set by its contraction order and its mapping onto hardware: a contraction path with fewer multiply-accumulate oper…
The quantity of interest in the classical Cramér-Rao theory of unbiased estimation (e.g., the Cramér-Rao lower bound, its exact attainment for exponential families, and asymptotic efficiency of maximum likelihood estimat…
Programming assistants powered by large language models (LLMs) have become widely available, with conversational assistants such as ChatGPT particularly accessible to novice programmers. However, varied tool capabilities…
As Large Language Models (LLMs) are increasingly integrated into software development workflows, they also become prime targets for adversarial attacks. Among these, backdoor attacks are a significant threat, allowing at…
For the combinatorial graph alignment problem (GAP), finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs, the classical Frank-Wolfe heuristic FAQ remains a strong …
Image reconstruction from corrupted images is crucial across many domains. Most reconstruction networks are trained on post-ISP sRGB images, even though the image-signal-processing pipeline irreversibly mixes colors, cli…
Post-training LLM compression often relies on low-rank approximations, which force all columns of a projection matrix to share a single low-dimensional subspace. We propose CoSpaDi, a training-free compression framework …
Collegiate cross country teams often build their season schedules on intuition rather than evidence, partly because large-scale performance datasets were not publicly accessible prior to the National Running Club Databas…
This paper introduces Quaternion Approximate Networks (QUAN), a novel deep learning framework that leverages quaternion algebra for rotation equivariant image classification and object detection. Unlike conventional quat…
Video diffusion models have achieved remarkable progress in recent years, yet generating high-resolution videos remain a fundamental challenge. Most video generators are trained at limited spatial resolutions due to the …
In linear models, visualizing a weight vector naturally reveals the model's preferred input direction, but extending this intuition to deep networks via gradients or GradientAscent often yields brittle or adversarial-loo…
Developing new abstract interpretation-based DNN certifiers is difficult because their mathematical design is expressed at the neuron level, while implementations must operate at the tensor level. Existing libraries such…