AI
MoNe: Modular Neural Memory for Efficient Long Context Inference
Researchers have developed MoNe, a lightweight neural memory system that can handle long context inf...
AI
Validated Adaptation for Aerial Crowd Monitoring at Mass Gathering Scale: A Deployment Protocol, a Severity Law, and a Diagnostic for Label-Free Drone Crowd Counting, Toward the FIFA World Cup 2034 (Saudi Arabia)
Researchers have developed a method to accurately count crowds using drones without labeled training...
AI
Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models
Researchers have developed a precise correspondence between two ways of describing the do-operator i...
AI
Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing
Researchers have developed a new method to read out the internal reasoning states of mixture-of-expe...
AI
LLM-Derived Preference Judgments Are Not Self-Consistent
Researchers have found that large language models (LLMs) are not consistent in t...
AI
GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities
Researchers from China have developed an AI-powered tool called GraphWake that c...
AI
Auditing Self-Evolution in Financial Agents: Capability Gains, Security Drift, and Execution-Interface Mismatch
Researchers have audited the behavior of three AI systems designed to evolve and...
AI
Mixture-of-Expert Blocks Contain Strong Hallucination Detection Signals
Researchers have developed a new method called InnerExpert that can detect hallu...