Quality follows upgrading
Academic
arXiv:2604.03532v1 Announce Type: new Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering …
arXiv:2604.03789v1 Announce Type: new Abstract: Recent advances in large language models have significantly improved their ability to perform mathematical reasoning, extending from elementary problem solving …
arXiv:2604.03873v1 Announce Type: new Abstract: Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowledge distillation) struggle to …
arXiv:2604.03525v1 Announce Type: new Abstract: We study adversarial online learning of real-valued functions on $\mathbb{R}$. In each round the learner is queried at $x_t\in\mathbb{R}$, predicts …
arXiv:2604.03768v1 Announce Type: new Abstract: Unsustainable land-use practices in ecologically sensitive regions threaten biodiversity, water resources, and the livelihoods of millions. This paper presents a …
arXiv:2604.03779v1 Announce Type: new Abstract: Diffusion models have excelled at generative tasks for both continuous and token-based domains, but their application to discrete ordinal data …
arXiv:2604.03616v1 Announce Type: new Abstract: Asking a large language model to respond in JSON should be a formatting choice, not a capability tax. Yet we …
arXiv:2604.03388v1 Announce Type: new Abstract: When deploying large language models (LLMs) to safety-critical applications, uncertainty quantification (UQ) is of utmost importance to self-assess the reliability …
arXiv:2604.03976v1 Announce Type: new Abstract: Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI systems evolve …
arXiv:2604.03240v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge, yielding relevance responses that are aligned …
arXiv:2604.03928v1 Announce Type: new Abstract: Effective ride-hailing dispatch requires anticipating demand patterns that vary substantially across time-of-day, day-of-week, season, and special events. We propose a …
arXiv:2604.03489v1 Announce Type: new Abstract: Enforcing complex (e.g., nonconvex) operational constraints is a critical challenge in real-world learning and control systems. However, existing methods struggle …