Hello everyone, I’m preparing to submit a research paper to arXiv (cs.AI) focused on: – Multi-agent systems – Backend code synthesis Since my arXiv account is new, I require an endorsement from an existing arXiv author to proceed (as per the updated policy). What I’m looking for: An arXiv author in Computer Science (cs.AI or related) With a few recent publications What’s involved: A quick endorsement via arXiv (~1–2 minutes) Not peer review — just a verification step […]

Ver mais

arXiv:2603.09742v1 Announce Type: cross Abstract: Neural oscillators that originate from the second-order ordinary differential equations (ODEs) have shown competitive performance in learning mappings between dynamic loads and responses of complex nonlinear structural systems. Despite this empirical success, theoretically quantifying the generalization capacities of their neural network architectures remains undeveloped. In this study, the neural oscillator consisting of a second-order ODE followed by a multilayer perceptron (MLP) is considered. Its upper probably approximately correct (PAC) generalization bound for approximating […]

Ver mais

arXiv:2602.16790v1 Announce Type: new Abstract: In audio-related creative tasks, sound designers often seek to extend and morph different sounds from their libraries. Generative audio models, capable of creating audio using examples as references, offer promising solutions. By masking the noisy latents of a DiT and applying a novel variant of classifier-free guidance on such masked latents, we demonstrate that: (i) given an audio reference, we can extend it both forward and backward for a specified duration, and (ii) […]

Ver mais

Hi, in my first real RL project, where an agent learns to play a strategy game with incomplete information in an on-policy, self-play PPO setting, I have hit a major roadblock, where I maxed out my Legion 5 pros performance and take like 30mins for a single update with only 2 epochs and 128 minibatches. The problem is that the simulation of the played games are rather cheap and parallelizing them among multiple workers will return me a […]

Ver mais

arXiv:2602.02574v1 Announce Type: new Abstract: We introduce WritePolicyBench, a benchmark for evaluating memory write policies: decision rules that choose what to store, merge, and evict under a strict byte budget while processing a stream with document/API drift. The benchmark provides (i) task generators with controlled non-stationarity, (ii) an explicit action interface for external memory, (iii) a byte-accurate cost model, and (iv) standardized metrics that measure both task success and budget efficiency.

Ver mais

arXiv:2604.08603v1 Announce Type: new Abstract: Existing LLM-based agent systems share a common architectural failure: they answer from the unrestricted knowledge space without first simulating how active business scenarios reshape that space for the event at hand — producing decisions that are fluent but ungrounded and carrying no audit trail. We present LOM-action, which equips enterprise AI with emph{event-driven ontology simulation}: business events trigger scenario conditions encoded in the enterprise ontology~(EO), which drive deterministic graph mutations in an isolated […]

Ver mais

arXiv:2601.03927v1 Announce Type: cross Abstract: Index tracking, also known as passive investing, has gained significant traction in financial markets due to its cost-effective and efficient approach to replicating the performance of a specific market index. This review paper provides a comprehensive overview of the various modeling approaches and strategies developed for index tracking, highlighting the strengths and limitations of each approach. We categorize the index tracking models into three broad frameworks: optimization-based models, statistical-based models and machine learning […]

Ver mais

Accurate prediction of shaft rotational speed, shaft power, and fuel consumption is crucial for enhancing operational efficiency and sustainability in maritime transportation. Conventional physics-based models provide interpretability but struggle with real-world variability, while purely data-driven approaches achieve accuracy at the expense of physical plausibility. This paper introduces a Physics-Informed Kolmogorov-Arnold Network (PI-KAN), a hybrid method that integrates interpretable univariate feature transformations with a physics-informed loss function and a leakage-free chained prediction pipeline. Using operational and environmental data from […]

Ver mais

arXiv:2604.09824v1 Announce Type: new Abstract: Vision language action (VLA) models enable generalist robotic agents but often exhibit language ignorance, relying on visual shortcuts and remaining insensitive to instruction changes. We present Prospective Grounding and Alignment VLA (ProGAL-VLA), which constructs a 3D entity-centric graph (GSM), uses a slow planner to produce symbolic sub-goals, and aligns them with grounded entities via a Grounding Alignment Contrastive (GAC) loss. All actions are conditioned on a verified goal embedding $g_t$, whose attention entropy […]

Ver mais