You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis …
Explorar
Noticias de IA
21270 elementos — filtrados, clasificados y sin duplicados
Towards Collaborative Joint Perception and Prediction: Framework, Baseline Evaluation, an…
TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Resea…
TriView-YOLO: Early Multi-View Fusion for Ground Penetrating Radar Cavity Detection in So…
XFeat Revisited: Reproducibility and Evaluation of a Lightweight Image Matcher
Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verif…
GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction
RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vis…
Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal …
Peer review is overwhelmed—can it survive in the AI era?
One Model to Magnify Them All: Efficient Scale-Invariant Histopathology via Conditional N…
From Objectives to What Models Learn: A Landau Theory of Invariant Learning
CoInS-Net: A Continuous Position-Aware Network for Joint Medical Image Interpolation and …
Imaginative Generative AI: Crossing the Entropy Wall into Worlds Beyond Imitation
Making Knowledge Distillation Cheap Enough to Run at Scale
Preserve More Details: Mitigating Content Drift in Real-World Image Super-Resolution
A Machine Learning Based Search for Lunar Anomalies
Control-Oriented Scenario Tree Construction through Reinforcement Learning
GeoPhysAdapter: Scale-Matched Geophysical Adaptation for Cross-Domain Landslide Mapping w…
Warp-free Cross-view Geo-localization via Feature-space Consensus Mining
WorldSimProbe: Diagnosing Simulator Faithfulness in Action-Conditioned World Models for E…
Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents
MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts
Emotion2Skill: Model-Internal Emotion Signals for Adaptive Skill Selection and Evolution
Omni2LoRA: Coherence-Preserving Parametric Memory for Efficient Omni Language Models
RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation
Reading Cognition as Decisions Unfold in Words: A Factorized Inverse Decision Model
FedTVD: Balancing Data Quality and Quantity for Robust Federated Learning
Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers