Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Models
Research
Research News
New papers, breakthroughs and academic AI research
Diff-RF: Mutually Reinforced Image Registration and Fusion via Degradation-Aware Learning
Research
A Unified Framework and Dataset for Oriented Object Visual Grounding in Remote Sensing
Research
Two Global Crops Suffice: Locating Semantic Emergence in DINO-Style Self-Supervised Learning
Research
ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus
Research
Do Center Biases Propagate? Robustness of Pathology Foundation Models in Whole-Slide Image Classification
Research
When Accuracy Gaps Fail to Certify: Auditing Cross-Domain Recalibration of LLM Judges
Research
Quality over Quantity: Semi-Supervised Detection of Illicit Bitcoin Flows via Feature Engineering
Research
![Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions](/media/images/2026/09/gen-6cb4df82950e6778.webp)
Binary Quantized Neural Network Training Is W[1]-Hard Parameterized by Input and Output Dimensions
Research
From ECG Signals to Representative-Morphology Heatmaps for Biometric Recognition
Research
Depth-Guided Contrastive Learning for 2D Representations with 3D Spatial Awareness
Research
Reliable Fusion of Conflicting Experts
Research