arXiv:2605.00969v1 Announce Type: cross
Abstract: We present MedMosaic, a medical audio question-answering dataset designed to benchmark language and audio reasoning models under realistic clinical constraints. Medical audio data is difficult to colle…
arXiv:2605.01605v1 Announce Type: cross
Abstract: Large language models are sensitive to minor prompt perturbations, yet existing robustness methods usually enforce consistency at the whole-sequence level. This holistic view can hide an important fail…
arXiv:2604.19351v3 Announce Type: replace
Abstract: The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compressio…
arXiv:2605.01630v1 Announce Type: cross
Abstract: Rankings produced by holistic LLM-as-a-judge scoring are sensitive to the bias of the chosen judge model. We show that switching to binary rubric scoring with multi-judge filtering removes this sensiti…
arXiv:2601.03267v2 Announce Type: replace-cross
Abstract: This is the system card published alongside the OpenAI GPT-5 launch, August 2025.
GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model f…
arXiv:2605.01101v1 Announce Type: new
Abstract: This paper develops Virtual Speech Therapist (VST), an intelligent agent-based platform that streamlines stuttering assessment and delivers customized therapy planning through automated and adaptive AI-d…
arXiv:2601.19827v3 Announce Type: replace-cross
Abstract: Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-reasoning loops meaningfully outperform static …
arXiv:2502.16435v4 Announce Type: replace-cross
Abstract: Humans develop perception through a bottom-up hierarchy: from basic primitives and Gestalt principles to high-level semantics. In contrast, current Multimodal Large Language Models (MLLMs) are …
arXiv:2605.01148v1 Announce Type: new
Abstract: Does structure in representations imply structure in computation? We study how Llama-3.1-8B reasons over cyclic concepts (e.g., “what month is six months after August?”). Even though Llama-3.1-8B’s repre…
arXiv:2605.01749v1 Announce Type: new
Abstract: Large Reasoning Models achieve strong performance on complex tasks but remain prone to hallucinations, particularly in long-form generation where errors compound across reasoning steps. Existing approach…