MSSP: Multi-Scale Spatially-Constrained Partition for Unsupervised Semantic Segmentation …
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-Tra…
Generative Action-Chunk Sampling for Adaptive Stiffness Control in Physical Human-Robot C…
The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persi…
Steering Interference Reflects the Model's Defaults, Not the Behavior Directions
ARNAI: Artifact Removal Network based on Autoencoding and Inpainting for Robust Spinal Im…
Performance of Clinical AI System and Physicians and Frontier Language Models in primary …
Fine PT-PT Web: A High-Quality 41 Billion Tokens Data Collection of the European Portugue…
From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation Models
Novel Methods for Catheter and Guidewire Segmentation in X-ray Fluoroscopy under a Federa…
AutoLexSteer: Automatic Contrast Construction for Lexical Activation Steering
What Does Animal Re-Identification Learn? Linear Biological Concepts and Their Origins in…
Constrained Online Learning with Noisy Constraint Values
CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records
WAPP: Safe Learning of Positive Security WAF Policies from Live Traffic
XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?
You Are What You Read: Misalignment via In-Context Persona Induction
Emo-DVS: A Multimodal Benchmark for Privacy-Aware Emotion Recognition with Event Cameras
Foundation Models for Generalizable Semantic and Goal-Oriented Communication
Token-Oriented Semantic Communication with Pretrained Vision Transformers
Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction
Companion-style QA Assistance in Ego-Vision
Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Froze…
Evaluating the Scalability and Adversarial Generalization of GRPO-Trained NLI Models
A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content
Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models
AuthBench: A Large-Scale Multilingual Benchmark for Authorship Representation across Genr…
ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics
FSAN: Flow State Attention Network for Aerodynamic Prediction
Attention-Enhanced Deep Features with Heterogeneous Ensemble Learning for Glaucoma Detect…