Sign in Subscribe

FINWAX

Finite-State Automata Reduce Edge AI Power Consumption

Finite-State Automata Reduce Edge AI Power Consumption

Replacing arithmetic-heavy networks with finite-state learning automata cuts edge energy draw without turning decision logic into an unreadable black box. Running artificial intelligence at the microedge hits an immediate bottleneck when continuous arithmetic drives power consumption past strict hardware budgets. The Tsetlin machine replaces standard arithmetic compute with

Evolved scheduling policies beat handcrafted heuristics under uncertainty

Evolved scheduling policies beat handcrafted heuristics under uncertainty

Handcrafted scheduling heuristics fall apart when satellite task visibility, operational profits, and onboard resource consumption fluctuate dynamically. Static Earth observation scheduling assumes fixed execution windows and deterministic parameters. In reality, actual operational conditions cannot be known beforehand. The Uncertain Agile Earth Observation Satellite Scheduling Problem (UAEOSSP) addresses this gap directly,

CAITLYN lets agent defenses synthesize their own countermeasures

CAITLYN lets agent defenses synthesize their own countermeasures

Static defenses against prompt injection cannot survive novel attack vectors. If your defense cannot synthesize its own countermeasures when new patterns appear, your agent runtime is already compromised. Prompt injection attacks against LLM agents manipulate external text retrieved during execution, forcing models to run harmful actions outside their intended scope.