$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models
arXiv:2604.06260v1 Announce Type: new Abstract: Test-time scaling investigates whether a fixed diffusion language model (DLM) can generate better outputs when given more inference compute, without additional training. However, naive best-of-$K$ sampling is fundamentally limited because it repeatedly draws from the...
Spectral Edge Dynamics Reveal Functional Modes of Learning
arXiv:2604.06256v1 Announce Type: new Abstract: Training dynamics during grokking concentrate along a small number of dominant update directions -- the spectral edge -- which reliably distinguishes grokking from non-grokking regimes. We show that standard mechanistic interpretability tools (head attribution, activation...
State election dispute on political speech comes to Supreme Court on interim docket
Lawyers for Ohio Secretary of State Frank LaRose, as well as county election officials, urged the Supreme Court on Wednesday to let them go ahead with a ballot that does […]The postState election dispute on political speech comes to Supreme...
AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations Modeling
arXiv:2604.06475v1 Announce Type: new Abstract: Deep Learning Reduced Order Models (ROMs) are becoming increasingly popular as surrogate models for parametric partial differential equations (PDEs) due to their ability to handle high-dimensional data, approximate highly nonlinear mappings, and utilize GPUs. Existing...
Inference-Time Code Selection via Symbolic Equivalence Partitioning
arXiv:2604.06485v1 Announce Type: new Abstract: "Best-of-N" selection is a popular inference-time scaling method for code generation using Large Language Models (LLMs). However, to reliably identify correct solutions, existing methods often depend on expensive or stochastic external verifiers. In this paper,...
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
arXiv:2604.06427v1 Announce Type: new Abstract: The viability of chain-of-thought (CoT) monitoring hinges on models being unable to reason effectively in their latent representations. Yet little is known about the limits of such latent reasoning in LLMs. We test these limits...
Toward a universal foundation model for graph-structured data
arXiv:2604.06391v1 Announce Type: new Abstract: Graphs are a central representation in biomedical research, capturing molecular interaction networks, gene regulatory circuits, cell--cell communication maps, and knowledge graphs. Despite their importance, currently there is not a broadly reusable foundation model available for...
AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent
arXiv:2604.06296v1 Announce Type: new Abstract: AI agents are increasingly deployed in real-world applications, including systems such as Manus, OpenClaw, and coding agents. Existing research has primarily focused on \emph{server-side} efficiency, proposing methods such as caching, speculative execution, traffic scheduling, and...
SMT-AD: a scalable quantum-inspired anomaly detection approach
arXiv:2604.06265v1 Announce Type: new Abstract: Quantum-inspired tensor networks algorithms have shown to be effective and efficient models for machine learning tasks, including anomaly detection. Here, we propose a highly parallelizable quantum-inspired approach which we call SMT-AD from Superposition of Multiresolution...
Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise
arXiv:2604.06468v1 Announce Type: new Abstract: Most methods for learning with noisy labels require privileged knowledge such as noise transition matrices, clean subsets or pretrained feature extractors, resources typically unavailable when robustness is most needed. We propose Conformal Margin Risk Minimization...
TwinLoop: Simulation-in-the-Loop Digital Twins for Online Multi-Agent Reinforcement Learning
arXiv:2604.06610v1 Announce Type: new Abstract: Decentralised online learning enables runtime adaptation in cyber-physical multi-agent systems, but when operating conditions change, learned policies often require substantial trial-and-error interaction before recovering performance. To address this, we propose TwinLoop, a simulation-in-the-loop digital twin...
When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction
arXiv:2604.06558v1 Announce Type: new Abstract: We present the first systematic study of when target context helps molecular property prediction, evaluating context conditioning across 10 diverse protein families, 4 fusion architectures, data regimes spanning 67-9,409 training compounds, and both temporal and...
Thousands of consumer routers hacked by Russia's military
End-of-life routers in homes and small offices hacked in 120 countries.
SCOTUStoday for Wednesday, April 8
Yesterday marked four years since Justice Ketanji Brown Jackson was confirmed to the Supreme Court, paving the way for her to become the first Black woman to serve as a […]The postSCOTUStoday for Wednesday, April 8appeared first onSCOTUSblog.
Supreme Court summarily closes the courthouse doors again
Civil Rights and Wrongs is a recurring series by Daniel Harawa covering criminal justice and civil rights cases before the court. I have written before about the Supreme Court’s troubling […]The postSupreme Court summarily closes the courthouse doors againappeared first...
Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
arXiv:2604.06501v1 Announce Type: new Abstract: Analogical reasoning is a hallmark of human intelligence, enabling us to solve new problems by transferring knowledge from one situation to another. Yet, developing artificial intelligence systems capable of robust human-like analogical reasoning has proven...
Discrete Flow Matching Policy Optimization
arXiv:2604.06491v1 Announce Type: new Abstract: We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matching (DFM) models under a broad class of policy gradient methods. Our key idea is to view...
Quality-preserving Model for Electronics Production Quality Tests Reduction
arXiv:2604.06451v1 Announce Type: new Abstract: Manufacturing test flows in high-volume electronics production are typically fixed during product development and executed unchanged on every unit, even as failure patterns and process conditions evolve. This protects quality, but it also imposes unnecessary...
From Load Tests to Live Streams: Graph Embedding-Based Anomaly Detection in Microservice Architectures
arXiv:2604.06448v1 Announce Type: new Abstract: Prime Video regularly conducts load tests to simulate the viewer traffic spikes seen during live events such as Thursday Night Football as well as video-on-demand (VOD) events such as Rings of Power. While these stress...
ODE-free Neural Flow Matching for One-Step Generative Modeling
arXiv:2604.06413v1 Announce Type: new Abstract: Diffusion and flow matching models generate samples by learning time-dependent vector fields whose integration transports noise to data, requiring tens to hundreds of network evaluations at inference. We instead learn the transport map directly. We...
Bridging Theory and Practice in Crafting Robust Spiking Reservoirs
arXiv:2604.06395v1 Announce Type: new Abstract: Spiking reservoir computing provides an energy-efficient approach to temporal processing, but reliably tuning reservoirs to operate at the edge-of-chaos is challenging due to experimental uncertainty. This work bridges abstract notions of criticality and practical stability...
Bi-Level Optimization for Single Domain Generalization
arXiv:2604.06349v1 Announce Type: new Abstract: Generalizing from a single labeled source domain to unseen target domains, without access to any target data during training, remains a fundamental challenge in robust machine learning. We address this underexplored setting, known as Single...
BiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning
arXiv:2604.06336v1 Announce Type: new Abstract: Graph Transformers have recently attracted attention for molecular property prediction by combining the inductive biases of graph neural networks (GNNs) with the global receptive field of Transformers. However, many existing hybrid architectures remain GNN-dominated, causing...
Asymptotic-Preserving Neural Networks for Viscoelastic Parameter Identification in Multiscale Blood Flow Modeling
arXiv:2604.06287v1 Announce Type: new Abstract: Mathematical models and numerical simulations offer a non-invasive way to explore cardiovascular phenomena, providing access to quantities that cannot be measured directly. In this study, we start with a one-dimensional multiscale blood flow model that...
MO-RiskVAE: A Multi-Omics Variational Autoencoder for Survival Risk Modeling in Multiple MyelomaMO-RiskVAE
arXiv:2604.06267v1 Announce Type: new Abstract: Multimodal variational autoencoders (VAEs) have emerged as a powerful framework for survival risk modeling in multiple myeloma by integrating heterogeneous omics and clinical data. However, when trained under survival supervision, standard latent regularization strategies often...
MICA: Multivariate Infini Compressive Attention for Time Series Forecasting
arXiv:2604.06473v1 Announce Type: new Abstract: Multivariate forecasting with Transformers faces a core scalability challenge: modeling cross-channel dependencies via attention compounds attention's quadratic sequence complexity with quadratic channel scaling, making full cross-channel attention impractical for high-dimensional time series. We propose Multivariate...
The Rhetoric of Machine Learning
arXiv:2604.06754v1 Announce Type: new Abstract: I examine the technology of machine learning from the perspective of rhetoric, which is simply the art of persuasion. Rather than being a neutral and "objective" way to build "world models" from data, machine learning...
Learning to Interrupt in Language-based Multi-agent Communication
arXiv:2604.06452v1 Announce Type: new Abstract: Multi-agent systems using large language models (LLMs) have demonstrated impressive capabilities across various domains. However, current agent communication suffers from verbose output that overload context and increase computational costs. Although existing approaches focus on compressing...
Stochastic Gradient Descent in the Saddle-to-Saddle Regime of Deep Linear Networks
arXiv:2604.06366v1 Announce Type: new Abstract: Deep linear networks (DLNs) are used as an analytically tractable model of the training dynamics of deep neural networks. While gradient descent in DLNs is known to exhibit saddle-to-saddle dynamics, the impact of stochastic gradient...
Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse
arXiv:2604.06228v1 Announce Type: new Abstract: We introduce probabilistic language tries (PLTs), a unified representation that makes explicit the prefix structure implicitly defined by any generative model over sequences. By assigning to each outgoing edge the conditional probability of the corresponding...