Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Eff…
Explorar
Noticias de IA
22318 elementos — filtrados, clasificados y sin duplicados
Evaluation of Small Language Models for Arabic Language Processing
MIRCaps: A Large-Scale Mixed-Domain Dataset with Image-Level and Region-Level Captions fo…
THREAD: Trajectory Planning for Hybrid Rigid-Soft Manipulators with Environment-Aware Dif…
MemoryVAM: Integrating Memory into Video Action Model for Robot Manipulation
VQ4SNN: Vector Quantization for Memory-Efficient FPGA Spiking Neural Networks
NeuroShield: A Device-Agnostic Foundation Model for EEG Authentication
A Projection-Based Surrogate Gradient Interpretation for Neural Codec Wrappers
Improving Text-to-Music Generation with Human Preference Rewards
Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Exp…
When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Il…
Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse A…
2D Versus 3D Diffusion for In Silico Training of Interventional X-ray AI Models
SwarmX: Agentic Scheduling for Low-Latency Agentic Systems
Unsupervised Disentanglement Without Compromises : How Functional Orthogonality Enforces …
Graph-of-Differences: Anatomy-Structured Difference Alignment for Medical Image Re-Identi…
SOHET: Sequence Of Heterogeneous Events Transformer with Self-Supervised Pre-Training
Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling
An Empirical Study of OpenPangu Quantization on Ascend NPUs
ACE-GS: Acing the Trade-off with Accurate, Compact and Efficient 3D Gaussian Splatting
AInterviewer: A Platform for Designing and Conducting AI-led Qualitative Interviews
DramaDirector: Geometry-Guided Short Drama Generation
NavWM: A Unified Navigation World Model for Foresight-Driven Planning
Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent
DynaWM: Dynamics-Aware Distillation with World Model and Momentum Targets for Smooth Loco…
CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression
Sentence-Level Contextual Entrainment in Large Language Models
VieSpeaker: A Large-Scale Vietnamese Speaker Recognition Dataset Beyond Visual Dependency
Selective Capability Unlearning in End-to-End Spoken Language Understanding
EPEdit: Redefining Image Editing with Generative AI and User-Centric Design