ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
RetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents
AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics
Anatomy-Aware Promptable Segmentation with Online Interactive Training for AUTOPET V
NL2AGBench: Benchmarking LLM Auto-Formalization for AlphaGeometry
Real-Time Musculoskeletal Surrogates for Pediatric Cerebral Palsy: a Credibility Pilot
Low-Altitude Fluid Antenna Network with Multi-Agent Reinforcement Learning
LandingAgent: A Reference-Annotated Dataset and Agentic Generation Framework for Landing …
SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning
FedEHR-Agents: Federated Agentic Optimization for Automated EHR Modeling
Actionable CBFI: Integrating Structural Decomposition and Causal Counterfactual Recourse …
FISGuard: Defending Against Membership Inference via Fixed Input Subspaces
Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers
Video Generative Models as Geometry Learner
OpenStamp: A Watermark for Open-Source Language Models
PanelShield: Verifiable Closed-Loop Safe Planning for Robotic Industrial Panel Operation
The Approximation Rank of Softmax Attention: Sharp Geometric Laws and Robust Interaction …
Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss
LongGuard: Mechanistic Analysis and Training-Free Mitigation of Long-Context Failure in S…
SETU: An Agentic Ecosystem for Multilingual, Persona-Aware Communication Coaching
Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failu…
Evaluating Loss Functions in Differentiable Out-of-Domain Sound-Matching with Partial Par…
Compositional Failure in Audio-Visual LLMs: Late-Layer Prior Dominance Under Cross-modal …
ContextLeak: Exfiltrating LLM Agent Context via Malicious Tools
Finding Where the Buck Stops: An Automated Failure Attribution-Based Reflection Framework…
RECAST: Recent & Context-Aware Sampling for Test-Time Adaptation in Streaming Biosignals
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
A Probabilistic Interpretation of KV Cache Eviction
REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features
Generative AI Alignment with Hinduism's Theological Plurality and Sacred Representation