941 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
In real-world deployments, large language model (LLM) systems are increasingly evolving from single-model invocation toward heterogeneous deployments in which different models are dynamically invoked for inference. When …
In the random allocation sampling scheme each user's data is used in $k$ steps chosen randomly and uniformly from a sequence of $t$ steps. This scheme is known to improve on Poisson sampling in private optimization and i…
Understanding how gradient descent learns features remains a central challenge in neural network theory. We study this question in a minimal multi-index setting that already exhibits rich multi-phase gradient dynamics: a…
Objective: To distinguish the transferable predictive value of physiological trajectories from that of observation patterns in ICU mortality prediction, and to assess whether measurement timing affects performance indepe…
Decision models target structured tasks by directly predicting choices or scores, avoiding autoregressive decoding latency. However, transferring a generative LLM's ranking knowledge to a decision model remains challengi…
Instance-dependent limits for bandit regret, sequential tests, best-arm identification and Markov decision processes are proved by one chain. It runs from a divergence decomposition through data processing to a statistic…
Distribution Matching Distillation (DMD) trains a few-step student using the difference between a teacher's score and an online critic's estimate of the student distribution's score. We investigate what the critic needs,…
Dense 3D tracking from monocular video requires establishing point correspondences over time, estimating their depth, and inferring their trajectories during occlusion. Existing methods typically learn these tasks jointl…
In many practical deployments of Differentially Private Stochastic Gradient Descent (DP-SGD), the server processes data in batches. Randomly sampling these batches allows for better privacy bounds via privacy amplificati…
Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or command the arm directly. Yet today these harnesses …
Representing 3D shapes using a set of primitives - known as shape abstraction - is an actively studied problem in computer graphics with wide applications in shape understanding, analysis, and simulation due to the compa…
Planning with world models enables test-time adaptation for embodied agents, offering superior generalization over direct policy learning. However, long-horizon tasks remain hindered by cumulative errors and search compl…
Agentic workflows are increasingly shifting towards long-horizon tasks, such as open-ended scientific work, where models benefit from long context windows. However, at ultra-long context (above 1M tokens), full attention…
Decision models such as Jev have emerged as a highly promising paradigm for LLM agent systems, providing lightweight and reliable categorical reasoning for rapid System One execution. However, existing generation-oriente…
Unified Multimodal Models (UMMs) achieve remarkable success on diverse multimodal understanding and generation tasks, yet they still struggle to effectively leverage language-based chain-of-thought reasoning for image ge…