941 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
Continual learning treats degradation on previously seen data as evidence of failure, a convention inherited from settings with a stationary prediction target, where a correct label remains correct indefinitely. World mo…
We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as executable graphics programs. To accomplish this, agents must translate visu…
Dense 3D point tracking has been a prominent paradigm for modeling motion in dynamic scenes, but a point track is just a 3-DoF translation curve per pixel: it captures where pixels go, not the rotation of the underlying …
This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning. In principle, NVS should reason about 3D scene structure, thereby enabling transferable multi-view geometric representation…
Current controllable video generation systems often rely on 2D motion trajectories or sparse drag signals for object motion. These controls are ambiguous because the same 2D trajectory can correspond to different 3D moti…
We present OmniSeek, an agentic framework that transforms an Omni Large Language Model (Omni-LLM) into an active, multi-turn reasoning agent with native tool use. Rather than passively processing an entire audio-visual s…
Quasi-Newton (QN) methods have long been among the most effective methods for large-scale unconstrained convex optimization. Two obstacles have limited their use in deep learning: non-convexity and enormous parameter siz…
Looped Transformers achieve parameter efficiency by repeatedly executing a shared block across recurrent loops. Each loop yields an intermediate representation decodable for the same next token, yet standard decoding dis…
Molecular learning models are strongly shaped by their underlying representations. Yet standard sequential and graph formalisms struggle to explicitly encode higher-order topology, such as ring systems and recurring moti…
Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated target and student scores, so it must keep an auxiliary diffusion model fitted to the student's evolving…
Intrinsically disordered protein regions (IDRs) play central roles in cellular processes such as transcriptional regulation, signal transduction, and subcellular localization, yet their functional design remains challeng…
Step-size selection remains a central challenge in large-scale neural network optimization; conservative steps slow convergence, while aggressive steps can destabilize it. We combine textbf{Z}ero-and-textbf{F}irst-textbf…
While Large Language Models (LLMs) have demonstrated striking capabilities on frontier mathematical problems, it remains unclear whether they possess the structural mathematical understanding underlying their solutions. …
Discrete diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bidirectional reasoning and global constraint satisfaction. Yet they share a structural bottleneck: when …
The generalized Schrödinger bridge on a graph moves mass between two distributions while charging a cost for the states visited. It has been approached by learning the rates of a controlled continuous-time Markov chain, …