980 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
We present a representation-learning framework for composite adaptive tracking control under dynamically coupled disturbances. The framework connects classical disturbance-accommodating control (DAC) to recent last-layer…
When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs. The agent chooses its next steps based on tool feedback and intermediate results, whil…
LLMs have demonstrated strong capabilities in creative writing. However, scaling them to full-length novels remains challenging, as maintaining narrative consistency becomes increasingly difficult. Existing story-generat…
emph{Distributional training} provides collective supervision for one-step visual generation by matching real and generated features in frozen representation spaces. We introduce emph{a unified theoretical framework} tha…
Sparse inertial pose estimation promises camera-free motion capture from consumer devices, but consumer sensors are unreliable: firmware-fused orientations are biased, mounting varies between sessions, and streams drift …
Identifying intertextual references is central to literary scholarship, but computationally difficult when source material is transformed through paraphrase, allusion, historical language, and translation. We investigate…
Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the result, and diagnose again. Whether a revisio…
Modern video diffusion models require tens of denoising evaluations over long spatiotemporal token sequences. Distribution Matching Distillation (DMD) reduces the number of function evaluations (NFE) to just a few. Howev…
One deployed language model must often serve many compute budgets, yet serving each budget still means a separate training or compression run per point. We train a Telescopic Language Model (TLM) to be that continuum: a …
Realistic and editable animal fur reconstruction from multi-view images is challenging due to fine-scale detail, self-occlusion and obfuscation, and, unlike human hair, the lack of animal-fur datasets. Fur usually covers…
World models improve sample efficiency by training policies on imagined trajectories, but their usefulness depends on learning representations that capture the information needed for future control. We study whether self…
The lower asymptotic proportion of distinct nontrivial zeros of the Riemann zeta function, relative to the total number counted with multiplicity, is at least $0.8369928814ldots$. Earlier work proves $0.83625ldots$, and …
Directional multi-transmitter localization from sparse received-power observations is difficult because the receiver observes only the source-unresolved aggregate field: multiple directional sources superpose, building b…
In offline goal-conditioned reinforcement learning (GCRL), divide-and-conquer scales to long horizons by joining two shorter segments at a subgoal. However, under stochastic dynamics, the base case of this rule values th…
Forced alignment estimates the timestamps of each word, phone or character in speech given its transcript. Published comparisons normalize transcripts, split the data and match boundaries differently, so their numbers ca…