980 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
Mevcut talimat tabanlı görüntü alma sistemleri güçlüdür, ancak karmaşık, gerçek dünyadaki görsel aramaların yinelemeli doğasını yakalayamayan tek turlu etkileşimlerle sınırlıdır. Bu sınırlamanın üstesinden gelmek için, k…
Multispectral object detection combines visible and thermal imagery to improve perception under challenging illumination and environmental conditions. However, differences in modality appearance and reliability can intro…
Persian medical NLP is limited by scarce domain-specific resources and insufficient characterization of their coverage, quality, and limitations. We present Gaokerena, a suite of Persian medical resources, and evaluate t…
The iterated learning model was introduced to investigate language evolution: the way in which the characteristic properties of human languages have been shaped, at least partly, by repeated transmission from one languag…
Over-parameterized linear regression has been widely studied over the last decade. However, most existing works assume that the covariates are independent and that their covariance matrices are non-degenerate. In this pa…
Siri Expressive Voices, Apple'ın en güçlü cihaz içi temel modeli olan AFM 3 Core Advanced tarafından desteklenen zengin, yapılandırılabilir konuşmayı gerçek zamanlı olarak ve tamamen cihaz üzerinde sentezler. Bu çalışma,…
Speculative decoding accelerates autoregressive generation by having a draft propose tokens that a target verifies in parallel. Frontier models increasingly ship a built-in Multi-Token-Prediction (MTP) draft head, assume…
Video modeller vizyon temeli modellerine dönüşüyor, ancak yine de insan benzeri çok adımlı akıl yürütmeden yoksunlar. Akış otoregresif difüzyon modelleri verimli ancak akıl yürütmede sınırlıdır, çift yönlü difüzyon ise y…
İnsan geri bildiriminden pekiştirmeli öğrenme (RLHF), büyük dil modellerini (LLM'ler) insan tercihleriyle uyumlu hale getirmek için ana paradigma olarak ortaya çıkmıştır. Tipik olarak, RLHF, genellikle önceden eğitilmiş …
Predictive world models enable robots to simulate the visual outcomes of their actions, but state-of-the-art diffusion-based models remain costly because generating each rollout requires multi-step iterative denoising. W…
Human-in-the-loop Reinforcement Learning has become a popular approach for training, finetuning, and aligning robot behavior with user preferences. Our paper explores the feasibility of using brain signals via functional…
For robots to work reliably in commercial and industrial applications, recent advances in agentic coding systems have potential to combine interpretable robot programming with the open-world adaptability of model-free po…
What does a discrete diffusion model actually learn? The literature trains denoisers, bridge plug-ins, and concrete scores, each deriving its own ELBO objective under different conventions. This fragmentation makes the o…
Software agents are becoming increasingly important in modern coding workflows, where they solve complex tasks through multi-step interaction with code repositories. A central component of these systems is the execution …
Post-training a code generator against a learned judge can optimize proxy features that raise the score without improving the artifact. We study the opposite signal: a deterministic, judge-free filter that asks only whet…