980 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
Fairness in clustering has attracted sustained research interest, motivated by the need to ensure equitable representation of protected groups in machine learning applications. We study fair $k$-means clustering in Eucli…
Language-model agents are vulnerable to indirect prompt injection (IPI) during tool use: adversarial instructions hidden in untrusted tool outputs can covertly redirect legitimate task execution. Existing work often trai…
The same underlying computational problem is solved across unrelated fields under different names: recursive Bayesian state estimation appears as a "Kalman filter" in control, "Bayesian forecasting" in pharmacokinetics, …
A voice agent must decide, at each pause, whether the speaker has finished or is still thinking. Without a model of the language, systems fall back to a fixed silence timeout: too short, and the agent interrupts; too lon…
Computational molecular property prediction requires representations that capture local chemistry, long-range interactions, and molecular topology. Conventional fingerprints provide efficient local substructure features,…
Segmenting a new microscopy dataset usually means training a deep network on its annotations, and training again for every added image. Exemplar solves a segmentation readout in closed form and updates it exactly with ea…
Solving problems through repeated attempts is a sequential modeling task: at each step, the solver receives feedback and decides how to revise their solutions. Predicting whether performance improves, plateaus, or regres…
Geleneksel birleşik öğrenme (FL), istemcileri iki kat homojen olmaya zorlayan parametre ortalamasına dayanır: özdeş bir mimari gerektirir ve IID olmayan veriler altında bozulur. Gerçek dünyadaki dağıtımlar genellikle her…
Bir LLM hakeminin aracı yörüngelerine ilişkin doğrudan testi, hataları doğru çalıştırmalara enjekte eder ve hata türüne göre veya hatanın ortam sonucunu (yüksek) bozup bozmadığına (sessiz) göre geri çağırma raporlarını v…
How do large language models (LLMs) organize moral knowledge? Models detect moral content broadly, but detection is a low bar. We ask whether they go further, distinguishing moral foundations from one another and organiz…
We introduce ClusterAttention, a general training-free speedup of bidirectional attention at large token counts. We point out two common assumptions in contemporary training-free methods; attention sparsity, and context …
High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. However, preserving fine detail across the physically based rendering (PBR) modalities needed for relighting r…
Pi0.5 gibi son teknoloji ürünü görüş-dil-eylem (VLA) modelleri, güçlü anlamsal anlayış, talimat takibi ve görev davranışı sergiler. Bununla birlikte, yeni robotlara yerleştirildiğinde, donanım konfigürasyonundaki ön eğit…
Volatility control converts risk estimates into portfolio exposure, yet existing approaches often rely on a fixed volatility estimator or a pre-defined control rule that may not adapt to changing market conditions. We pr…
Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control. While applicable to post-hoc inspection,…