Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent Attacks
Research
Research News
New papers, breakthroughs and academic AI research
MedRECT: A Bilingual Medical Reasoning Benchmark for Error Correction in Clinical Texts
Research
Mutual Equilibrium: Multimodal Representation Learning through Reciprocal Feedback
Research
ActionGuard: Tool Call Authorization under Poisoned Skills
Research
Fast Generalized Neural Tangent Kernel Statistics via Trace Estimation
Research
Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
Research
TIQA: Human-Aligned Perceptual Text Quality Assessment in Generated Images
Research
Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts
Research
From Speech to Editable Concepts: Probing Emotion Recognition with Concept Bottleneck Models
Research
A Reusable Semantic Web Framework for Evidence-Grounded Fundamental Rights Impact Assessments under the EU AI Act
Research
GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearning
Research
ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference
Research