Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
Academic
arXiv:2604.03634v1 Announce Type: new Abstract: We prove that temporal averaging over multiple observations can be replaced by algebraic group action on a single observation for …
arXiv:2604.03870v1 Announce Type: new Abstract: The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including …
arXiv:2604.04064v1 Announce Type: new Abstract: Small language models (SLMs) in the 100M-10B parameter range increasingly power production systems, yet whether they possess the internal emotion …
arXiv:2604.03742v1 Announce Type: new Abstract: Effective evaluation of large language models (LLMs) remains a critical bottleneck, as conventional direct scoring often yields inconsistent and opaque …
arXiv:2604.04074v1 Announce Type: new Abstract: Peer review in machine learning is under growing pressure from rising submission volume and limited reviewer time. Most LLM-based reviewing …
arXiv:2604.03553v1 Announce Type: new Abstract: AI is supporting, accelerating, and automating scientific discovery across a diverse set of fields. However, AI adoption in historical research …
arXiv:2604.03419v1 Announce Type: new Abstract: Submodular maximization under matroid constraints is a fundamental problem in combinatorial optimization with applications in sensing, data summarization, active learning, …
arXiv:2604.04013v1 Announce Type: new Abstract: The increasing size and complexity of large language models (LLMs) have raised significant challenges in deployment efficiency, particularly under resource …
arXiv:2604.03270v1 Announce Type: new Abstract: RAG wastes tokens. We propose Knowledge Packs: pre-computed KV caches that deliver the same knowledge at zero token cost. For …
arXiv:2604.03641v1 Announce Type: new Abstract: Reinforcement learning in real-world systems is often accompanied by delayed feedback, which breaks the Markov assumption and impedes both learning …
arXiv:2604.03541v1 Announce Type: new Abstract: This study surveys the historical development of regularization, tracing its evolution from stepwise regression in the 1960s to recent advancements …
arXiv:2604.03962v1 Announce Type: new Abstract: In many practical LLM deployments, a single guardrail is used for both prompt and response moderation. Prompt moderation operates on …