980 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
The success of the transformer architecture is in large part due to its use of attention layers. An attention layer follows the standard neural network paradigm: it takes the residual stream as input and thereby produces…
Dominant programming paradigms inherit an execution model optimised for a bygone era of a single human mind instructing a local machine, leaving contemporary systems burdened with path dependencies. When forced to host m…
Agentic forecasting is important for decision-making in dynamic environments, but it remains challenging because agents must reason from incomplete, time-limited evidence and produce calibrated probabilities before outco…
Son zamanlarda, seyrek otomatik kodlayıcılar (SAE'ler), pratik sinir ağlarındaki temsilleri yorumlamak ve bunlarla etkileşime geçmek için çekici bir araç olarak ortaya çıkmıştır. Yaygın ampirik folklor olmakla birlikte, …
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 …
RAG-based legal assistants have been growing in popularity, but LLM hallucinations remain a key issue and potentially undermines justice. While benchmarks have been developed to evaluate progress, many rely on synthetic …
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…
3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insufficient for inferring missing structure. We present DinoComplete, a d…
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.…
Large Language Model (LLM) interactions are typically underspecified, with users clarifying all necessary details across multiple conversational turns. Yet recent work shows that LLMs perform far worse in this multi-turn…
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}}…
Yapılandırılmış iş akışları, Büyük Dil Modellerini (LLM'ler) karmaşık sorunların üstesinden gelme konusunda güçlendirse de, bunların oluşturulmasının otomatikleştirilmesi, geniş bir kombinatoryal arama alanı tarafından c…
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 …