RUFNet: Query-Guided Support Mask Refinement and Uncertainty Fusion based on Hybrid Mamba…
Explorar
Noticias de IA
30934 elementos — filtrados, clasificados y sin duplicados
Agent Data Injection Attacks are Realistic Threats to AI Agents
Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Mode…
Evaluating Generative Agents with Actions Grounded in Socially Distributed Task Environme…
Unified Audio Intelligence Without Regressing on Text Intelligence
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent P…
Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-…
SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing
Multi-Turn On-Policy Distillation with Prefix Replay
Machine Learning for Depression Screening and Intervention: an Original Circadian Rhythm …
Privacy-Preserving Robustness Verification for Neural Networks
Shifting from Discrete to Continuous Reference Data: QSM-Derived Horizontal Tree Biomass …
ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Dist…
URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment
Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards
Wasserstein Residuals: Learning Gradient Flows from Population Dynamics
Predicting Drafted Deck Strength for "Magic: the Gathering"
Pretraining Curricula Enable Selective Fine-tuning
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language…
From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model
LLM for the development of FCM
The Map Behind the Flow: Finite-Step Gradient Descent as a Dynamical System
Comparison of Loss Functions for Robust Deep Learning-based Echocardiography Segmentation…
ImputeECG: Deep Learning Reconstruction of Complete 12-Lead Electrocardiograms from Incom…
Insect-inspired Visual Point-goal Navigation
Serious Games: Human-AI Interaction, Evolution, and Coevolution
Policy Improvement with Style-Specific Demonstrations
Correlation-Weighted Multi-Reward Optimization for Compositional Generation
Evolutionary Guided Decoding: Iterative Value Refinement for LLMs