941 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
Deploying a new decision policy creates a cold-start problem for prediction models whose targets depend on the policy's actions: historical observations reflect earlier policies, while real observations under the new pol…
Autoregressive (AR) video models excel at causal generation, but their reliance on next-chunk prediction confines them to a short-sighted, reactive paradigm. This limitation is particularly consequential for reasoning-or…
Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex reasoning. However, they face a distinct credit-assignment challenge, since a few commitments during den…
Policy-gradient methods are central to modern reinforcement learning, including LLM post-training. When they struggle, the usual suspects are exploration, credit assignment and action-sampling noise. Classification has n…
LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance g…
The dynamics of cells, organisms, and fluids are often modeled as probability distributions evolving over time. Reconstructing and extrapolating this evolution from unpaired snapshots requires assumptions about the under…
We examine the transfer of a pretrained SigLIP2 image encoder to seven class fire risk classification from aerial imagery. We introduce a reproducible partition of the public FireRisk training mirror and an implementatio…
We present FlowHMR, a framework for recovering physically plausible global 3D human motion from monocular video. Previous learning-based methods typically regress human motion directly from video and train the network wi…
Scarcity of labeled data limits development of deep learning biomarkers in oncology. We develop a two-stage AI model predicting pathological complete response (pCR) to neoadjuvant therapy in breast cancer. The first stag…
Modern chess engines are silent experts: they play at a superhuman level, but do not offer explanations for their play. On the other hand, language models (LMs) can generate plausible-sounding explanations, but their wea…
Self-supervised Vision Transformers (ViTs), such as DINOv2, learn rich visual representations, but the functions of their internal tokens remain poorly understood. Recent architectures introduce dedicated register tokens…
The choice of post-training data for large language models substantially affects downstream performance. Gradient-based data selection is a popular approach that ranks training data by how well their gradients align with…
We study the minimization of sums of smooth strongly convex functions over undirected graphs, with each function held by one agent and communication restricted to neighbors in the graph. Existing decentralized methods, w…
Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. EyeRobot 2.0 physically attends to a 3D fixation point in the scene by s…
Ribonucleic acid (RNA) functions through conformational changes that are not fully captured by static structures. However, large-scale standardized RNA dynamics data remain limited, and existing approaches typically trea…