Quality follows upgrading
Academic
arXiv:2604.01613v1 Announce Type: new Abstract: In reinforcement learning (RL), temporal difference (TD) errors are widely adopted for optimizing value and policy functions. However, since the …
arXiv:2604.01007v2 Announce Type: new Abstract: AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a …
arXiv:2604.01526v1 Announce Type: new Abstract: Electrocardiograms (ECGs) are among the most widely used diagnostic tools for cardiovascular diseases, and a large amount of ECG data …
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:2604.00023v1 Announce Type: new Abstract: Basic vocabulary in many Sulawesi Austronesian languages includes forms resisting reconstruction to any proto-form with phonological patterns inconsistent with inherited …
arXiv:2604.01727v1 Announce Type: new Abstract: Forecasting evolving clinical risks relies on intrinsic pathological dependencies rather than mere chronological proximity, yet current methods struggle with coarse …
arXiv:2604.00085v1 Announce Type: new Abstract: Large language models applied to clinical prediction exhibit case-level heterogeneity: simple cases yield consistent outputs, while complex cases produce divergent …
arXiv:2604.00536v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong downstream performance largely due to abundant supervised fine-tuning (SFT) data. However, high-quality SFT data …
arXiv:2604.00284v1 Announce Type: new Abstract: We formally introduce a improvisational wordplay game called Connections to explore reasoning capabilities of AI agents. Playing Connections combines skills …
arXiv:2604.01477v1 Announce Type: new Abstract: Reinforcement learning (RL) and model predictive control (MPC) offer complementary strengths, yet combining them at scale remains computationally challenging. We …
arXiv:2604.00018v1 Announce Type: cross Abstract: Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as …
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 …