nestdaddy
Web World Financial Country Tech
Showing 20 of 128 tech news articles in Research
Research
Arxiv 23 hours ago

Lightweight Adaptive ReduNet via Hyperspherical Manifold Learning

arXiv:2608.20668v1 Announce Type: new Abstract: In recent years, a white-box neural network called ReduNet has been proposed, which employs the maximal coding rate reduction (MCR$^2$) principle to transform raw data into low-dimensional discriminative features via a forward layer-wise construction

Research
Arxiv 23 hours ago

Reinforcement Learning for Continuous-Time Jump Markov Decision Processes with Applications to Network Dynamic Pricing

arXiv:2608.20680v1 Announce Type: new Abstract: We study reinforcement learning (RL) in Continuous-Time Jump Markov Decision Processes (CTJMDPs) featuring general discrete state spaces (which need not possess a vector space structure) and continuous/discrete action spaces. The setup covers many wel

Research
Arxiv 23 hours ago

Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges

arXiv:2608.20710v1 Announce Type: new Abstract: Real-world semi-supervised learning (SSL) often encounters significant challenges with long-tailed label distributions and noisy pseudo-labels, which hinder generalization and amplify confirmation bias. In this work, we introduce a novel framework, Ga

Research
Arxiv 23 hours ago

Hidden Axis of Uncertainty: Latent-Posterior Alignment in Graph Neural Networks with Bayesian Output Layers

arXiv:2608.20758v1 Announce Type: new Abstract: Bayesian Neural Networks (BNNs) with Bayesian output layers provide a principled and tractable framework for quantifying predictive uncertainty, yet the mechanisms shaping that uncertainty remain unclear. While conventional theory attributes uncertain

Research
Arxiv 23 hours ago

Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting

arXiv:2608.20761v1 Announce Type: new Abstract: In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous latent dynamic states, while existing deep forecasting models usually compress them into a unified end-to-end mapping, leading to suboptimal modeli

Research
Arxiv 23 hours ago

Resolution-Consistent Greedy Neural Approximation on Infinite-Dimensional Spaces

arXiv:2608.20812v1 Announce Type: new Abstract: We develop constructive approximation and learning guarantees for shallow neural models with infinite-dimensional inputs observed through finitely many coordinates. The analysis is based on a parameter-normalized neural dictionary and its associated w

Research
Arxiv 23 hours ago

Scaling Muon for Diffusion Transformers

arXiv:2608.20818v1 Announce Type: new Abstract: The matrix-aware optimizer Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-end efficiency on large Diffusion Transformers (DiTs) remain unclear. We first establish Muon's scaling

Research
Arxiv 23 hours ago

Nothing Changed but the Model: CellFill -- Bounded In-Cell Learning for Bit-Identical, Revocable Updates to Quantized LLMs

arXiv:2608.20873v1 Announce Type: new Abstract: Every way of teaching a deployed language model something new -- full fine-tuning, adapter merging, model editing -- replaces the released checkpoint, and with it every evaluation and cache that referred to those exact bits. We instead learn inside th

Research
Arxiv 23 hours ago

Decoupling Policy Extraction for Offline Reinforcement Learning

arXiv:2608.20909v1 Announce Type: new Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled learning process is well motivated in online RL, where an improved actor collects new data that can f

Research
Arxiv 23 hours ago

Training, learning and inference: unified dynamics of neural systems

arXiv:2608.20965v1 Announce Type: new Abstract: We define an atomic generation fact f=(u,tau,omega,z;rho), recording the origin, realized transformation, concrete occurrence, generated result and relation role. Compiled into a Generation-Fact Graph (GFG), these facts provide an AI-native, compilabl

Research
Arxiv 23 hours ago

A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Baselines

arXiv:2608.20980v1 Announce Type: new Abstract: Graph neural networks (GNNs) are routinely employed for short-range forecasting on multivariate time series with a spatial graph structure. Despite the availability of many alternative datasets, method innovations within this domain are predominantly

Research
Arxiv 23 hours ago

Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models

arXiv:2608.20988v1 Announce Type: new Abstract: Quantization of Large Language Models (LLMs) is often hindered by the sensitivity of the self-attention mechanism to discretization errors. We identify the softmax operator as a bottleneck for quantization stability due to its sensitivity to outliers

Research
Arxiv 23 hours ago

Trojaning the Alignment: Stealthy Backdoor Attacks against Graph Foundation Models

arXiv:2608.20991v1 Announce Type: new Abstract: Graph Foundation Models (GFMs) on text-attributed graphs (TAGs) align graph representations with language semantics to support transferable graph learning. Despite these advantages, the backdoor vulnerability of GFMs on TAGs remains insufficiently und

Research
Arxiv 23 hours ago

Free-Probability Kernels for Zero-Rollout Hyperparameter Selection in Reservoir Computing

arXiv:2608.20998v1 Announce Type: new Abstract: Reservoir computing (RC) couples a fixed recurrent dynamical system with a trained lightweight readout, but this efficiency is partly lost during hyperparameter selection: the recurrent gain, input scale, and leakage rate determine the reservoir's sta

Research
Arxiv 23 hours ago

RODE: A Radial-Orthogonal Decoupled Engine for Optimization

arXiv:2608.21024v1 Announce Type: new Abstract: Modern neural network training increasingly uses matrix-aware optimizers, yet their conditioned matrix step is typically added directly to the weight, jointly changing its norm and direction. This interaction matters because the current norm determine

Research
Arxiv 23 hours ago

Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human Alignment

arXiv:2608.21057v1 Announce Type: new Abstract: Agentic large language model (LLM) systems are reshaping scientific workflows in chemistry and drug discovery, but evaluating their open-ended, tool-augmented outputs remains a fundamental bottleneck. Reference-based metrics such as BLEU and ROUGE fai

Research
Arxiv 23 hours ago

TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics

arXiv:2608.21070v1 Announce Type: new Abstract: Inferring continuous system evolution from sparse temporal snapshots is a key challenge in generative modeling and single-cell omics. While Optimal Transport (OT) is popular, existing frameworks are largely restricted to first-order dynamics, assuming

Research
Arxiv 23 hours ago

Causal Modeling of Adverse Pregnancy Outcomes via Adaptive LLM Proposals

arXiv:2608.21079v1 Announce Type: new Abstract: Adverse Pregnancy Outcomes (APOs) such as preterm birth and gestational diabetes can have long-term consequences for both the mother and child, yet an understanding of their causes remains elusive. Causal discovery in this domain is especially challen

Research
Arxiv 23 hours ago

FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space

arXiv:2608.21096v1 Announce Type: new Abstract: Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph federated learning where clients possess structurally diverse graphs. Existing personalized federated le

Research
Arxiv 23 hours ago

BackDFL: A Unified Benchmark For Backdoor Attacks and Defenses In Decentralized Federated Learning

arXiv:2608.21137v1 Announce Type: new Abstract: Decentralized Federated Learning (DFL) promises trust-free collaborative learning by replacing the centralized parameter server with peer-to-peer model exchange. However, this architectural shift fundamentally reshapes the threat landscape. Without gl

Link copied to clipboard!