950 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
Retrieval over semi-structured knowledge bases (SKBs) must handle both textual descriptions and relational constraints. Text-based retrievers capture the overall semantics of a query but struggle with multi-hop relations…
Autonomous AI research agents aim to speed up scientific discovery by automating the research pipeline from hypothesis generation to peer review. However, existing benchmarks rarely test a fundamental bottleneck whether …
Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales.…
As LLMs improve, data agents are emerging as a new interface for analytics, while semantic query processing engines use LLMs to operate over structured and unstructured data. Existing benchmarks largely evaluate agents a…
We consider one-hidden layer neural networks trained in the feature-learning regime using gradient descent, and relate the output of the finite-width network $f_{hatρ_t^m}$ to its infinite-width counterpart $f_{ρ_t^{MF}}…
Large language models (LLMs) have emerged as flexible regressors capable of predicting real-valued quantities from heterogeneous inputs. Yet most LLM regression objectives optimize predictions independently, often yieldi…
Generative sequence models are often trained to plan motion in physical domains, from robotics to mechanical simulations. When constructing a dataset to train such a model, engineers may curate demonstrations to specify …
Single-cell trajectory inference from destructive time-course snapshots is fundamentally ill-posed: neither cross-time cell correspondences nor continuous trajectories are observed, so the snapshot distributions alone do…
Clinical language models increasingly operate over electronic health records (EHRs), yet patient records are not stored as temporally grounded trajectories. Clinical notes describe symptoms, assessments, and disease prog…
Before deployment, an AI system might be evaluated on thousands or even millions of inputs, but after deployment it may encounter billions, so its worst failures may not appear during evaluation. Jones et al. (2025) prop…
Graph neural networks (GNNs) deployed as cloud services can be *stolen* through *model-extraction attacks*, which train a surrogate from query responses to reproduce the target's behaviour, and a growing line of ownershi…
Reinforcement learning (RL) is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fragility is especially visible in large-model training using nom…
Soft Actor-Critic (SAC) ve çeşitleri, politika dışı örnek verimliliği nedeniyle Çok Görevli Güçlendirme Öğrenimine (MTRL) hakimken, Proksimal Politika Optimizasyonu (PPO) gibi politika içi yöntemler yeterince araştırılma…
Online reinforcement learning (RL) relies on the Markov property for guaranteed performance, but real-world applications often lack well-defined states given raw observed variables. While causal RL has attracted growing …
We present a novel theoretical framework, Q-MMR, for off-policy evaluation in finite-horizon MDPs. Q-MMR learns a set of scalar weights, one for each data point, such that the reweighted rewards approximate the expected …