980 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
Numerical methods and neural networks have transformed our understanding of nonlinear partial differential equations (PDEs), yet discovering mathematical representations that explain their dynamics remains largely an exp…
Machine learning models are predominantly evaluated through predictive performance metrics such as ranking quality, prediction error, or classification accuracy. While these metrics effectively quantify how closely predi…
Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically limited to text encoding, while denoising is handled by newly trained generative backbones. The emergence of representat…
Safe reinforcement learning (RL) aims to learn policies that optimize rewards while satisfying constraints. Predominant approaches rely on soft-constrained policy optimization, which has achieved empirical success but do…
Vehicle color recognition is an important cue for vehicle identification in surveillance systems, especially when license plates are illegible due to low resolution, occlusion, motion blur, or poor illumination. However,…
Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inherently sequential token generation. Specul…
Adapting Large Language Models (LLMs) to specific tasks usually involves fine-tuning: Low-Rank Adaptation (LoRA) edits the weights, while soft prompting prepends trainable virtual tokens. Both change how an already-optim…
Vision-Language-Action (VLA) models provide a natural language interface to robot control, but the mapping from language to behavior is often brittle and unintuitive: semantically similar instructions can induce drastica…
Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within one policy. A natural design choice is between a single (unified) critic that estimates the combined value of …
Temsilci becerilerinin büyümesi, aracılı sistemlerin nasıl oluşturulduğunu, değerlendirildiğini ve konuşlandırıldığını değiştirdi. Beceri kitaplıkları ölçeklenmeye devam ettikçe, bunların gerçek dünya uygulamalarında kul…
Video retrieval at scale is central to data curation and safety validation in autonomous driving, where users want to find not only scenes but also dynamic events such as cut-ins and hard braking. Existing vision-languag…
Domain-specific text-to-SQL systems ground a large language model by retrieving annotated few-shot examples, and each example needs expert-written SQL. We treat the choice of which queries to annotate as constrained expe…
Document image binarization must preserve thin, broken, and low-contrast strokes against degraded backgrounds; Mamba-based state space models have so far been explored only preliminarily for it. We measure what state-spa…
Robust visual classification often depends on localizing the main foreground objects in an image while ignoring contextual distractors. Surprisingly, we find that the last layer attention maps of smaller self-supervised …
Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs. Yet annotation protocols may not purely reflect relevance: they select only a subset of documents for labeling, and …