arXiv:2602.10204v1 Announce Type: new Abstract: We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary ideas: variance-based normalization and momentum applied after normalization. MVN-Grad scales each coordinate by an exponential moving average of gradient uncertainty and applies momentum to the resulting normalized gradients, eliminating the cross-time coupling between stale momentum and a stochastic normalizer present in standard Adam-type updates. We prove that this decoupling yields strictly smaller one-step conditional […]

Ver mais

arXiv:2602.04932v1 Announce Type: new Abstract: Hyperbolic representation learning has been widely used to extract implicit hierarchies within data, and recently it has found its way to the open-world classification task of Generalized Category Discovery (GCD). However, prior hyperbolic GCD methods only use hyperbolic geometry for representation learning and transform back to Euclidean geometry when clustering. We hypothesize this is suboptimal. Therefore, we present Hyperbolic Clustered GCD (HC-GCD), which learns embeddings in the Lorentz Hyperboloid model of hyperbolic geometry, […]

Ver mais

We consider robustness against data corruption in offline multi-agent reinforcement learning from human feedback (MARLHF) under a strong-contamination model: given a dataset $D$ of trajectory-preference tuples (each preference being an $n$-dimensional binary label vector representing each of the $n$ agents’ preferences), an $ε$-fraction of the samples may be arbitrarily corrupted. We model the problem using the framework of linear Markov games. First, under a uniform coverage assumption – where every policy of interest is sufficiently represented in the […]

Ver mais

arXiv:2602.08907v2 Announce Type: replace-cross Abstract: We study a setting where the goal is to learn a target function f(x) with respect to a target distribution D(x), but training is done on i.i.d. samples from a different training distribution D'(x), labeled by the true target f(x). Such a distribution shift (here in the form of covariate shift) is usually viewed negatively, as hurting or making learning harder, and the traditional distribution shift literature is mostly concerned with limiting or […]

Ver mais

arXiv:2602.10332v1 Announce Type: cross Abstract: In the partially-observed outcome setting, a recent set of proposals known as “prediction-powered inference” (PPI) involve (i) applying a pre-trained machine learning model to predict the response, and then (ii) using these predictions to obtain an estimator of the parameter of interest with asymptotic variance no greater than that which would be obtained using only the labeled observations. While existing PPI proposals consider estimators arising from M-estimation, in this paper we generalize PPI […]

Ver mais

This paper presents a reinforcement learning-based path-following controller for a fixed-wing small uncrewed aircraft system (sUAS) that is robust to certain actuator failures. The controller is conditioned on a parameterization of actuator faults using hypernetwork-based adaptation. We consider parameter-efficient formulations based on Feature-wise Linear Modulation (FiLM) and Low-Rank Adaptation (LoRA), trained using proximal policy optimization. We demonstrate that hypernetwork-conditioned policies can improve robustness compared to standard multilayer perceptron policies. In particular, hypernetwork-conditioned policies generalize effectively to time-varying actuator […]

Ver mais

Doginal Dogs Went From Free Claim to High-Value Hold Doginal Dogs is being talked about as one of the strangest success stories in NFTs for a simple reason: the collection started as a free mint and still managed to turn early holders into serious winners. According to the project’s own telling, minters paid nothing to claim. The founder covered the gas costs, and users were able to mint directly on Dogecoin through inscription technology. What looked like a […]

Ver mais

arXiv:2604.08591v1 Announce Type: new Abstract: Hallucinations in large ASR models present a critical safety risk. In this work, we propose the textit{Spectral Sensitivity Theorem}, which predicts a phase transition in deep networks from a dispersive regime (signal decay) to an attractor regime (rank-1 collapse) governed by layer-wise gain and alignment. We validate this theory by analyzing the eigenspectra of activation graphs in Whisper models (Tiny to Large-v3-Turbo) under adversarial stress. Our results confirm the theoretical prediction: intermediate models […]

Ver mais

In the modern microservice environment, library dependencies for inter-system communication have become bloated, and conflicts and complications during build and operation have become problems. In particular, in the conventional communication architecture that depends on the MySQL database, the multi-layer dependencies included in texttt{libmysqlclient} restrict the flexibility of system design. In this study, a replication-protocol-compatible patch was applied to the lightweight MySQL client library Trilogy, and a loosely coupled, low-footprint IPC library connecting the control plane and the data […]

Ver mais

Geometric and Topological Deep Learning are rapidly growing research areas that enhance machine learning through the use of geometric and topological structures. Within this framework, Group Equivariant Non-Expansive Operators (GENEOs) have emerged as a powerful class of operators for encoding symmetries and designing efficient, interpretable neural architectures. Originally introduced in Topological Data Analysis, GENEOs have since found applications in Deep Learning as tools for constructing equivariant models with reduced parameter complexity. GENEOs provide a unifying framework bridging Geometric […]

Ver mais