Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
Academic
arXiv:2604.00002v1 Announce Type: cross Abstract: Here we introduce the Olfactory Perception (OP) benchmark, designed to assess the capability of large language models (LLMs) to reason …
arXiv:2604.00323v1 Announce Type: new Abstract: Online abuse has grown increasingly complex, spanning toxic language, harassment, manipulation, and fraudulent behavior. Traditional machine-learning approaches dependent on static …
arXiv:2604.00688v2 Announce Type: new Abstract: We present OmniVoice, a massive multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is …
arXiv:2604.00842v1 Announce Type: new Abstract: Proactive agents that anticipate user needs and autonomously execute tasks hold great promise as digital assistants, yet the lack of …
arXiv:2604.00001v1 Announce Type: cross Abstract: Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but existing methods …
arXiv:2604.00414v1 Announce Type: new Abstract: LLM systems must make control decisions in addition to generating outputs: whether to answer, clarify, retrieve, call tools, repair, or …
arXiv:2604.00788v1 Announce Type: new Abstract: This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow …
arXiv:2604.01329v1 Announce Type: new Abstract: Model merging provides a way of cheaply combining individual models to produce a model that inherits each individual's capabilities. While …
arXiv:2604.01802v1 Announce Type: new Abstract: Accurate sensing of spatially distributed physical fields typically requires dense instrumentation, which is often infeasible in real-world systems due to …
arXiv:2604.01411v1 Announce Type: new Abstract: Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of …
arXiv:2604.01506v1 Announce Type: new Abstract: Long-tailed classification, where a small number of frequent classes dominate many rare ones, remains challenging because models systematically favor frequent …
arXiv:2604.00594v1 Announce Type: new Abstract: As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, …