System Switch: When Should a Fast Decision Model Stop and Think?
Research
Research News
New papers, breakthroughs and academic AI research
Steering Follows Geometry, Not Labels: Emotion Directions in a Full-Duplex Speech Model
Research
HCPN-GCN: Scaling Hierarchical Prototype Networks with Cone Geometry for Continual Graph Learning
Research
Sigma-Hunter: A Domain-Specific Language Model for Threat Hunting and Detection Engineering
Research
Shaer: Controlled Arabic Poetry Generation with Meter Subform and Semantic Conditioning
Research
CARE: Certifying Acceleration for Vision-Language-Action Inference
Research
FinVector-Market-4B: A Controlled Study of LoRA Adaptation for Structured Financial Tasks
Research
GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents
Research
Pathwise Information Certificates for Decentralized Adaptive Sensing
Research
Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputs
Research
sk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak
Research
Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution
Research