47 makale — arXiv, NeurIPS, ICML, ACL ve Türk üniversitelerinden seçtiğimiz çalışmalar. Her birinin Türkçe özeti, içindekiler ve aihaber okuma görünümü var. Kayıt gerekmez.
We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. ScienceBuddy supports researchers in carrying …
Large language models can produce fluent answers when their factual support is weak. This paper introduces Chain-of-Self-Questioning (CoSQ), a prompt-only framework that makes answer commitment conditional on an explicit…
Pruning can reduce the deployment cost of large language models (LLMs), but its impact on context-grounded tool calling remains poorly understood. We systematically study pruning-induced degradation in smart-home tool ca…
Neural audio codecs are a key component in speech language modeling. However, their high frame rates lead to long sequence lengths, increasing computational costs. Dynamic frame rate codecs mitigate this by reducing the …
LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i) it requires setups where the assistant learns about social situati…
Language models can produce plausible short proofs, but may still be unreliable on long-horizon research problems, where progress depends on a sequence of uncertain and interdependent decisions. We introduce Stellar Colo…
The same underlying computational problem is solved across unrelated fields under different names: recursive Bayesian state estimation appears as a "Kalman filter" in control, "Bayesian forecasting" in pharmacokinetics, …
Otomatik Metin-Konuşma (TTS) değerlendirme yöntemlerinin (Ortalama Görüş Puanı (MOS) yordayıcıları ve Ses Büyük Dil Modelleri (Audio-LLM) yargıçları) insan algısını yansıtması beklenir, ancak bunların dinleyicilerin gerç…
Düşünme Modu Füzyonu (TMF), düşünmeyen modu ve düşünme modunu tek bir modelde birleştirerek büyük dil modellerinin hem kısa yanıtları hem de uzun biçimli akıl yürütmeyi desteklemesini sağlar. Ancak, iki mod arasındaki em…
Modeling student misconceptions in a realistic manner is critical for AI in education. In this work, we examine how large language models (LLMs) reason about misconceptions when generating distractor answers for multiple…
Nefret mesajlarındaki sosyal onay sinyallerinin daha fazla nefret ve toksisiteyi öngördüğünü savunan sosyal onay teorisi aracılığıyla, sosyal onayın çevrimiçi nefreti nasıl motive ettiğini inceledik. Parler'dan (2018-202…