KidRisk: Benchmark Dataset for Children Dangerous Action Recognition
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Communicability-Inspired Positional Encoding (CIPE)
UC-Search: Risk-Aware Test-Time Search for Delayed Constrained Time-Series Control
Variational Inference via Entropic Transport Descent
Pre-Warm: Input-Conditioned Weight Initialization for Convolutional Neural Networks
Dual Agreement Consistency Learning for Semi-Supervised Fetal Ultrasound Segmentation
Automatic Generation of Highlights for Academic Paper Via Prompt-based Learning
Multilingual Hematology Visual Question Answering Dataset
Introducing the FFASR Leaderboard: Benchmarking ASR in the Real World
MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Lea…
Cage-based Texture Transfer with Geometric Filtering
Phoneme-Level Mispronunciation Screening in Polish-Speaking Children with an Explainable …
The Gentle Collapse: Distributional Metrics for Continual Learning
Benchmarking the Alignment of Data-Quality Metrics, Human Judgment and Land-Cover Segment…
Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
InSight: Self-Guided Skill Acquisition via Steerable VLAs
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
Real vs. Complex Spectral Bases for Neural Operators: The Role of Green's Function Alignm…
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
Scalable Peptide Design via Memory-Efficient Equivariant Transformer
Less is More: Quality-Aware Training Data Selection for Scientific Summarization
How GPT-5 helped immunologist Derya Unutmaz solve a 3-year-old mystery
OrbitForge: Text-to-3D Scene Generation via Reconstruction-Anchored Video Synthesis
Grad Detect: Gradient-Based Hallucination Detection in LLMs
Paying to Know: Micro-Transaction Markets for Verified Product Information in Agentic E-C…
Revealing Training Data Exposure in Vision Language Large Models via Parameter Gradients
Compact Object-Level Representations with Open-Vocabulary Understanding for Indoor Visual…
UniDrive: A Unified Vision-Language and Grounding Framework for Interpretable Risk Unders…
CANDLE: Character-level Arabic Noise Deduplication using Lightweight Encoder