Ensuring safety is a critical challenge in applying Reinforcement Learning (RL) to real-world scenarios. Constrained Reinforcement Learning (CRL) addresses this by maximizing returns under predefined constraints, typically formulated as the expected cumulative cost. However, expectation-based constraints overlook rare but high-impact extreme value events in the tail distribution, such as black swan incidents, which can lead to severe constraint violations. To address this issue, we propose the Extreme Value policy Optimization (EVO) algorithm, leveraging Extreme Value Theory (EVT) to […]

Ver mais

arXiv:2602.04936v1 Announce Type: new Abstract: We study deterministic top-k retrieval under Longest Common Prefix (LCP) similarity for N sequences of length L. We prove a tight Omega(N) space lower bound (cell-probe model) and present a trie-based index using O(N*L) space with O(L+k) query time. We contrast this with pairwise materialization (Theta(N^2)), which hits a practical OOM wall at scale, while our indexed approach remains O(N) in memory. We then introduce Thermal-Aware Logic (TAL), which turns prefix structure into […]

Ver mais

arXiv:2602.15973v1 Announce Type: new Abstract: Neuromorphic engineering has a data problem. Despite the meteoric rise in the number of neuromorphic datasets published over the past ten years, the conclusion of a significant portion of neuromorphic research papers still states that there is a need for yet more data and even larger datasets. Whilst this need is driven in part by the sheer volume of data required by modern deep learning approaches, it is also fuelled by the current […]

Ver mais

Every day, billions of users scroll through personalized feeds on TikTok, Instagram, and YouTube, each experiencing a uniquely tailored stream of content. Behind this seemingly effortless personalization lies one of the most challenging problems in modern machine learning: how do you build recommendation systems that adapt to user interests in real-time, learning from every interaction within the same scrolling session? The engineering required to make this work, processing billions of events per second, updating models every few hours, […]

Ver mais

Google is updating its image generator to make it faster and cheaper, making it a more useful tool for creators looking to make AI content.

Ver mais

Bayesian active learning relies on the precise quantification of predictive uncertainty to explore unknown function landscapes. While Gaussian process surrogates are the standard for such tasks, an underappreciated fact is that their posterior variance depends on the observed outputs only through the hyperparameters, rendering exploration largely insensitive to the actual measurements. We propose to inject observation-dependent feedback by warping the input space with a learned, monotone reparameterization. This mechanism allows the design policy to expand or compress regions […]

Ver mais

Temperature is a crucial hyperparameter in large language models (LLMs), controlling the trade-off between exploration and exploitation during text generation. High temperatures encourage diverse but noisy outputs, while low temperatures produce focused outputs but may cause premature convergence. Yet static or heuristic temperature schedules fail to adapt to the dynamic demands of reinforcement learning (RL) throughout training, often limiting policy improvement. We propose Temperature Adaptive Meta Policy Optimization (TAMPO), a new framework that recasts temperature control as a […]

Ver mais