arXiv:2604.03146v4 Announce Type: replace Abstract: We study high-dimensional convex empirical risk minimization (ERM) under general non-Gaussian data designs. By heuristically extending the Convex Gaussian Min-Max Theorem…
arXiv:2504.18587v2 Announce Type: replace-cross Abstract: Reinforcement learning has emerged as a powerful approach for improving the reasoning capabilities of large language models, as demonstrated by systems…
arXiv:2608.07537v1 Announce Type: new Abstract: In this study, we propose a framework that incorporates subjective evaluations provided by a Vision-Language Model (VLM) into the fitness evaluation…
arXiv:2608.08156v1 Announce Type: cross Abstract: In evolutionary algorithms powered by language models, the LLM acts as a single operator that simultaneously updates structural components (like control…
arXiv:2608.09888v1 Announce Type: new Abstract: We introduce BDH-CQ, a reasoning model that combines in-context learning with recurrent latent reasoning. Inputs presented at inference time continuously update…
arXiv:2608.09833v1 Announce Type: new Abstract: In this work, we introduce analytical replay experiments to the evolutionary computing community. Replay experiments originated in the context of laboratory…
arXiv:2605.21379v3 Announce Type: replace Abstract: In The Algebraic Mind (2001), Marcus held that any adequate cognitive architecture needs operations over variables, recursively structured representations, and an…
arXiv:2608.07544v1 Announce Type: new Abstract: Automated heuristic design (AHD) with large language models (LLMs) has produced strong heuristics for combinatorial optimization problems (COPs). Yet existing frameworks…
arXiv:2608.07545v1 Announce Type: new Abstract: An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement…
arXiv:2608.07587v1 Announce Type: new Abstract: Particle swarm optimization (PSO) has been widely applied to solve complex optimization problems from real-world applications due to its efficient exploration…
arXiv:2608.08081v1 Announce Type: new Abstract: Large mixture-of-experts (MoE) language models with 26--120 billion parameters exceed the memory capacity of consumer devices through three simultaneous pressures: resident…
arXiv:2608.07754v1 Announce Type: new Abstract: State-space models (SSMs) provide a powerful theoretical framework to enable parallel training of recurrent networks. We expand on previous work adapting…
arXiv:2608.08898v1 Announce Type: new Abstract: Characterising optimisation problem instances is a fundamental part of understanding the behaviour and performance of different algorithms as well as providing…
arXiv:2608.08479v1 Announce Type: new Abstract: Spiking neural networks (SNNs) offer a promising pathway to energy-efficient AI and brain-inspired computing. However, their widespread adoption is hindered by…
arXiv:2603.28385v2 Announce Type: replace-cross Abstract: Maritime surveillance missions, such as search and rescue and environmental monitoring, rely on the efficient allocation of sensing assets over vast…
arXiv:2608.08226v1 Announce Type: cross Abstract: Generalized Hopfield networks are introduced where memories and neurons are continuous variables that lie on a Riemannian manifold. We explicitly focus…
arXiv:2608.07539v1 Announce Type: new Abstract: Particle swarm optimization (PSO) is a widely used metaheuristic, prized for its simplicity and small parameter set. Although decades of research…
arXiv:2608.09902v1 Announce Type: cross Abstract: We introduce the Dark Souls Learning Environment (DSLE), a containerized platform that presents all 22 boss encounters of Dark Souls: Remastered…
arXiv:2608.08541v1 Announce Type: cross Abstract: Spiking Transformers provide a promising paradigm for efficient visual processing with spike-driven computation, yet their Softmax-free Spiking Self-Attention (SSA) struggles to…
arXiv:2206.13280v4 Announce Type: replace Abstract: We show that deep binary ReLU networks and deep sparse ternary ReLU networks can approximate $beta$-H"older functions on $[0,1]^d$. We also…
arXiv:2604.26836v3 Announce Type: replace Abstract: Predictive safety filters (PSFs) leverage model predictive control to enforce constraint satisfaction during deep reinforcement learning (RL) exploration, yet their reliance…
arXiv:2608.07827v1 Announce Type: new Abstract: Confidence estimation for large language models (LLMs) aims to estimate the probability that a generated answer is correct, while calibration aligns…
arXiv:2603.00040v3 Announce Type: replace Abstract: Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle…
arXiv:2608.07814v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models deliver high capacity at low per-token compute, but deploying them cheaply requires compressing their many expert weight…