941 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
How is computation organized and reused across tasks and time in a trained recurrent network? Most analyses emphasize the geometry of neural activity, dynamical motifs, or local perturbation growth. We instead study the …
Web text makes up the majority of pretraining data and is increasingly AI-generated. After applying FineWeb quality filtering, we find that 27.5% of tokens from June 2026 web data are labeled as AI-generated by Pangram, …
Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large Language Model (LLM) pr…
Improving text-to-image models has traditionally relied on increasing model size or the number of denoising steps. In this work, we explore an alternative way to scale computation by repeatedly running shared Transformer…
Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than…
Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect update geometry. In this work, we instead treat the compressor's resp…
While talking head generation has advanced rapidly, generating natural listener behavior in dyadic conversations, which know when to react, how to react, and with what type of response, remains underexplored. Existing dy…
Looped transformers and Mixture-of-Experts (MoE) offer complementary routes to efficient scaling: recurrence increases computational depth at fixed parameters, while MoE sparsity expands total capacity at fixed active co…
Most vision architectures assume that observations lie on a regular grid, an effective abstraction for natural images but a restrictive one for sensing data whose channels, temporal sampling, spatial resolution, and geom…
Material generation should produce not only an appearance, but also the rules that construct it. We introduce MatLoom, a compact, layer-oriented language for text-to-material generation with pretrained language models. E…
We present Cogentic, a multi-agent harness for automated proof discovery on open research problems. While frontier language models can generate strong mathematical ideas in a single shot, single-shot generation is often …
As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomalies in these simulated environments, such as floating objects, trave…
Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a single global harness that is applied uniformly ac…
Self-supervised learning draws inspiration from infant visual development, yet standard training pipelines bear little resemblance to it: images are independently sampled and globally shuffled across epochs. We study sel…
Differentially Private Stochastic Gradient Descent (DP-SGD) is a leading approach for privacy-preserving fine-tuning of large language models (LLMs). Many decoder-only LLMs employ weight tying between input and output em…