Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
ENTLORE: A Graph-Grounded Benchmark for Latent Organizational Reasoning in Enterprise Que…
AI Is Helping Solve the Intricate Genetic Puzzle of Schizophrenia
Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory
FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs
Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Exper…
Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization
DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Predi…
$π$-SUB: A Physics-Informed Synthetic Underwater Benchmark Dataset for Underwater Image E…
HexEval: An Evidence-Driven Hexagonal Framework for Multidimensional Scholar Assessment
Iterative Erasure Count Is Not an Affine-Invariant Concept Dimension
Retrieval-Corrected Conformal Prediction for Time Series
SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Lan…
When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, …
Improving TensorSketch Using Complex Random Variables
SparSTAR: Sparse Attention for SpaceTime AutoRegressive Video Synthesis
Towards Color-Faithful Low-Light Image Enhancement via Adaptive Color Debiasing and Satur…
MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows
CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deploymen…
RadFusion: Towards Threshold-Controllable Radiology Report Generation
DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic A…
Exploration-Driven Personalized Federated Reinforcement Learning via Intrinsic Motivation
When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs
Multi-Granular Rationale-Guided Molecular LLM for Property Prediction
Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection
Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging
MixFormer: Linear Transformer with Mixture of Memory Experts
AI Evaluation Should Measure Verification Cost, Not Correctness Alone
Tabular Numeric Stretch Transformation
SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL