MST-Direct: Matching via Sinkhorn Transport for Multivariate Geostatistical Simulation with Complex Non-Linear Dependencies
arXiv:2603.18036v1 Announce Type: new Abstract: Multivariate geostatistical simulation requires the faithful reproduction of complex non-linear dependencies among geological variables, including bimodal distributions, step functions, and heteroscedastic relationships. Traditional methods such as the Gaussian Copula and LU Decomposition assume linear correlation...
Adapting Methods for Domain-Specific Japanese Small LMs: Scale, Architecture, and Quantization
arXiv:2603.18037v1 Announce Type: new Abstract: This paper presents a systematic methodology for building domain-specific Japanese small language models using QLoRA fine-tuning. We address three core questions: optimal training scale, base-model selection, and architecture-aware quantization. Stage 1 (Training scale): Scale-learning experiments...
Quotient Geometry and Persistence-Stable Metrics for Swarm Configurations
arXiv:2603.18041v1 Announce Type: new Abstract: Swarm and constellation reconfiguration can be viewed as motion of an unordered point configuration in an ambient space. Here, we provide persistence-stable, symmetry-invariant geometric representations for comparing and monitoring multi-agent configuration data. We introduce a...
SLEA-RL: Step-Level Experience Augmented Reinforcement Learning for Multi-Turn Agentic Training
arXiv:2603.18079v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown strong results on multi-turn tool-use tasks, yet they operate in isolation during training, failing to leverage experiences accumulated across episodes. Existing experience-augmented methods address this by organizing trajectories...
Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning
arXiv:2603.18257v1 Announce Type: new Abstract: Selecting relevant state dimensions in the presence of confounded distractors is a causal identification problem: observational statistics alone cannot reliably distinguish dimensions that correlate with actions from those that actions cause. We formalize this as...
Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization
arXiv:2603.18258v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) has emerged as a popular algorithm for aligning pretrained large language models with human preferences, owing to its simplicity and training stability. However, DPO suffers from the recently identified squeezing effect...
Escaping Offline Pessimism: Vector-Field Reward Shaping for Safe Frontier Exploration
arXiv:2603.18326v1 Announce Type: new Abstract: While offline reinforcement learning provides reliable policies for real-world deployment, its inherent pessimism severely restricts an agent's ability to explore and collect novel data online. Drawing inspiration from safe reinforcement learning, exploring near the boundary...
Epistemic Generative Adversarial Networks
arXiv:2603.18348v1 Announce Type: new Abstract: Generative models, particularly Generative Adversarial Networks (GANs), often suffer from a lack of output diversity, frequently generating similar samples rather than a wide range of variations. This paper introduces a novel generalization of the GAN...
Discounted Beta--Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards
arXiv:2603.18444v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for improving the reasoning capabilities of large language models. However, existing group-based RLVR methods often suffer from severe sample inefficiency. This inefficiency...
AcceRL: A Distributed Asynchronous Reinforcement Learning and World Model Framework for Vision-Language-Action Models
arXiv:2603.18464v1 Announce Type: new Abstract: Reinforcement learning (RL) for large-scale Vision-Language-Action (VLA) models faces significant challenges in computational efficiency and data acquisition. We propose AcceRL, a fully asynchronous and decoupled RL framework designed to eliminate synchronization barriers by physically isolating...
A foundation model for electrodermal activity data
arXiv:2603.16878v1 Announce Type: new Abstract: Foundation models have recently extended beyond natural language and vision to timeseries domains, including physiological signals. However, progress in electrodermal activity (EDA) modeling is hindered by the absence of large-scale, curated, and openly accessible datasets....
Formal verification of tree-based machine learning models for lateral spreading
arXiv:2603.16983v1 Announce Type: new Abstract: Machine learning models for geotechnical hazard prediction can achieve high accuracy while learning physically inconsistent relationships from sparse or biased training data. Current remedies (post-hoc explainability, such as SHAP and LIME, and training-time constraints) either...
Integrating Inductive Biases in Transformers via Distillation for Financial Time Series Forecasting
arXiv:2603.16985v1 Announce Type: new Abstract: Transformer-based models have been widely adopted for time-series forecasting due to their high representational capacity and architectural flexibility. However, many Transformer variants implicitly assume stationarity and stable temporal dynamics -- assumptions routinely violated in financial...
Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models
arXiv:2603.17044v1 Announce Type: new Abstract: Unified multimodal models share a language model backbone for both understanding and generating images. Can DPO align both capabilities simultaneously? We present the first systematic study of this question, applying DPO to Janus-Pro at 1B...
PRISM: Demystifying Retention and Interaction in Mid-Training
arXiv:2603.17074v1 Announce Type: new Abstract: We present PRISM, a comprehensive empirical study of mid-training design choices for large language models. Through controlled experiments across seven base models spanning four families (Granite, LLaMA, Mistral, Nemotron-H), two architecture types (dense Transformer and...
CircuitBuilder: From Polynomials to Circuits via Reinforcement Learning
arXiv:2603.17075v1 Announce Type: new Abstract: Motivated by auto-proof generation and Valiant's VP vs. VNP conjecture, we study the problem of discovering efficient arithmetic circuits to compute polynomials, using addition and multiplication gates. We formulate this problem as a single-player game,...
Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication
arXiv:2603.17126v1 Announce Type: new Abstract: Many wireless vision applications, such as autonomous driving, require preservation of global structural information rather than only per-pixel fidelity. However, existing Deep joint source-channel coding (DeepJSCC) schemes mainly optimize pixel-wise losses and provide no explicit...
Domain-informed explainable boosting machines for trustworthy lateral spread predictions
arXiv:2603.17175v1 Announce Type: new Abstract: Explainable Boosting Machines (EBMs) provide transparent predictions through additive shape functions, enabling direct inspection of feature contributions. However, EBMs can learn non-physical relationships that reduce their reliability in natural hazard applications. This study presents a...
Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
arXiv:2603.17199v1 Announce Type: new Abstract: Large language models (LLMs) can produce chains of thought (CoT) that do not accurately reflect the actual factors driving their answers. In multiple-choice settings with an injected hint favoring a particular option, models may shift...
Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction
arXiv:2603.17248v1 Announce Type: new Abstract: Reconstructing a 12-lead electrocardiogram (ECG) from a reduced lead set is an ill-posed inverse problem due to anatomical variability. Standard deep learning methods often ignore underlying cardiac pathology losing vital morphology in precordial leads. We...
Classifier Pooling for Modern Ordinal Classification
arXiv:2603.17278v1 Announce Type: new Abstract: Ordinal data is widely prevalent in clinical and other domains, yet there is a lack of both modern, machine-learning based methods and publicly available software to address it. In this paper, we present a model-agnostic...
Cohomological Obstructions to Global Counterfactuals: A Sheaf-Theoretic Foundation for Generative Causal Models
arXiv:2603.17384v1 Announce Type: new Abstract: Current continuous generative models (e.g., Diffusion Models, Flow Matching) implicitly assume that locally consistent causal mechanisms naturally yield globally coherent counterfactuals. In this paper, we prove that this assumption fails fundamentally when the causal graph...
Causal Representation Learning on High-Dimensional Data: Benchmarks, Reproducibility, and Evaluation Metrics
arXiv:2603.17405v1 Announce Type: new Abstract: Causal representation learning (CRL) models aim to transform high-dimensional data into a latent space, enabling interventions to generate counterfactual samples or modify existing data based on the causal relationships among latent variables. To facilitate the...
Efficient Soft Actor-Critic with LLM-Based Action-Level Guidance for Continuous Control
arXiv:2603.17468v1 Announce Type: new Abstract: We present GuidedSAC, a novel reinforcement learning (RL) algorithm that facilitates efficient exploration in vast state-action spaces. GuidedSAC leverages large language models (LLMs) as intelligent supervisors that provide action-level guidance for the Soft Actor-Critic (SAC)...
QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation
arXiv:2603.17507v1 Announce Type: new Abstract: Federated Learning (FL) enables privacy-preserving intelligence on Internet of Things (IoT) devices but incurs a significant carbon footprint due to the high energy cost of frequent uplink transmission. While pre-trained models are increasingly available on...
Nvidia is quietly building a multibillion-dollar behemoth to rival its chips business
Nvidia's networking business raked in $11 billion last quarter despite getting significantly less fanfare than chips and gaming.
Patreon CEO calls AI companies’ fair use argument ‘bogus,’ says creators should be paid
Patreon CEO Jack Conte says AI companies should pay creators for training data, arguing their fair use defense falls apart when they license content from major publishers.
Rebel Audio is a new AI podcasting tool aimed at first-time creators
Rebel Audio is a new all-in-one podcasting tool that allows creators to record podcasts, edit, clip content for social, and publish episodes, all without ever leaving the platform.
The leaderboard “you can’t game,” funded by the companies it ranks
Artificial intelligence models are multiplying fast, and competition is stiff. With so many players crowding the space, which one will be the best — and who decides that? Arena, formerly LM Arena, has emerged as the de facto public leaderboard...