Skip to content

Papers 5476 stories

arXiv cs.AI Papers

Learning Cardiac Motion Priors for Implicit Neural Representations

arXiv:2607.00955v2 Announce Type: replace-cross Abstract: Implicit neural representations (INRs) are well suited to cardiac motion estimation, providing continuous, compact representations of motion fields. However, fitting an…

arXiv cs.AI Papers

Evaluating Generative Agents with Actions Grounded in Socially Distributed Task Environments using Incognita

arXiv:2607.02975v1 Announce Type: new Abstract: Effective agency in social environments depends on when an agent seeks knowledge, when it acts, and whether its actions are justified…

arXiv cs.CL Papers

Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion

arXiv:2607.02862v1 Announce Type: new Abstract: Automatic Speech Recognition (ASR) and Dialect Identification (DID) are crucial for Indian languages, many of which are low-resource and exhibit significant…

arXiv cs.CV Papers

AULLM++: Structured-Token-Conditioned Large Language Models for Micro-Expression Action Unit Detection

arXiv:2603.08387v2 Announce Type: replace Abstract: Micro-expression Action Unit (AU) detection identifies localized AUs from subtle facial muscle activations, providing a foundation for decoding affective cues. Previous…

arXiv cs.CV Papers

From Raw Segmentations to Simulation-Ready Cardiac Meshes: An Automated Framework for Anatomical Reconstruction and Virtual Cohort Generation

arXiv:2607.02564v1 Announce Type: new Abstract: Computational models of the human heart are widely used to study electromechanical and fluid-dynamical cardiac function and to support applications such…

arXiv cs.LG Papers

Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting

arXiv:2607.02637v1 Announce Type: new Abstract: Recent generative models can produce high-quality synthetic images, offering scalable training training data for data-hungry models. Existing approaches to exploiting this…

arXiv cs.NE Papers

Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fields

arXiv:2507.23033v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) provide an energy-efficient computing paradigm for neural rendering, but existing spike-based Neural Radiance Field (NeRF) models usually…

arXiv stat.ML Papers

A Random Matrix Theory Perspective on the Consistency of Diffusion Models

arXiv:2602.02908v2 Announce Type: replace-cross Abstract: Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise seed.…

arXiv stat.ML Papers

Tightening the Score Matching Gap for Diffusion Models

arXiv:2607.04442v1 Announce Type: new Abstract: Diffusion models (DMs) are a state-of-the-art generative method to approximately sample from an unknown distribution. Their training and evaluation primarily rely…

arXiv cs.AI Papers

LLM-Based Test Oracles: Source-of-Authority Taxonomy — A Systematic Literature Review

arXiv:2607.05031v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to produce test oracles, the part of a test that decides whether observed behavior…

arXiv cs.AI Papers

Trust-Region Noise Search for Black-Box Alignment of Diffusion and Flow Models

arXiv:2603.14504v2 Announce Type: replace-cross Abstract: Optimizing the noise samples of diffusion and flow models is an increasingly popular approach to align these models to target rewards…

arXiv cs.CL Papers

Gemma 4 Technical Report

arXiv:2607.02770v1 Announce Type: new Abstract: We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance…

arXiv cs.CV Papers

Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens

arXiv:2508.04928v5 Announce Type: replace Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images. Despite being trained…

arXiv cs.CV Papers

NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning

arXiv:2606.27771v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training improves the reward alignment of flow-based generators, but often degrades perceptual quality in ways that are not…

arXiv cs.LG Papers

A Granularity-Aware EEG Feature Framework for Psychopathology Dimension Prediction

arXiv:2607.02670v1 Announce Type: new Abstract: Electroencephalography (EEG) offers a noninvasive approach for examining neurophysiological correlates of dimensional psychopathology, yet systematic evidence across EEG paradigms and feature…

arXiv cs.NE Papers

ParetoPilot: Zero-Surrogate Offline Multi-Objective Optimization via Infer-Perturb-Guide Diffusion

arXiv:2606.04468v2 Announce Type: replace-cross Abstract: Offline multi-objective optimization (Offline MOO) seeks Pareto-optimal designs from static datasets without additional environment interactions. Existing generative methods typically guide sampling…

arXiv stat.ML Papers

Attention is Just Another Name for Coupling? A Fast-Slow ODE Perspective on Hierarchical Pretraining

arXiv:2606.16730v2 Announce Type: replace Abstract: We re-interpret Transformer pretraining as a fast-slow, singularly perturbed flow along depth, with untied weights as its non-autonomous feature. The linearised…

arXiv stat.ML Papers

Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Data

arXiv:2607.04527v1 Announce Type: new Abstract: Biological systems exhibit a hierarchical structure, characterised by directed flow from upstream regulators to downstream effects. Although this ordering provides a…

arXiv cs.AI Papers

MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources

arXiv:2601.22054v2 Announce Type: replace-cross Abstract: Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging due to…

arXiv cs.AI Papers

Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Models

arXiv:2607.02983v1 Announce Type: new Abstract: Recent reasoning-centric Large Language Models (LLMs) have made significant strides, yet they predominantly operate on a passive-inference pattern that assumes complete…

arXiv cs.CL Papers

LuxSQA: Ask Me in Luxembourgish with TTS-Augmented Spoken Question Answering

arXiv:2607.02763v1 Announce Type: new Abstract: Spoken Question Answering (SQA) remains largely focused on high-resource languages and carefully recorded speech, limiting the reach of speech-LLM methods in…

arXiv cs.CV Papers

MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments

arXiv:2512.22867v2 Announce Type: replace Abstract: Socially compliant navigation requires structured reasoning about dynamic pedestrians and physical constraints to ensure safe and interpretable decisions. Vision-language models (VLMs)…

arXiv cs.CV Papers

Coordinate Singularities Break Conformal Coverage for Gaze and Head Pose

arXiv:2607.02565v1 Announce Type: new Abstract: Conformal prediction provides distribution-free reliability guarantees for vision systems, but these guarantees depend on how prediction errors are measured in the…

arXiv cs.LG Papers

Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data

arXiv:2607.02636v1 Announce Type: new Abstract: Object detection is a fundamental capability for AI-driven perception in safety-critical drone and edge-vision systems, including disaster response, operational security environments,…