Tag: LLM Optimization
Browse our exclusive articles!
HTPO: Balanced Policy Optimization for Large Language Models
Discover HTPO, a novel RL algorithm enhancing exploration-exploitation balance in LLMs via hierarchical token-level control for superior reasoning performa...
Agent-X: Accelerate On-Device AI Agents with Speed
Discover how Agent-X boosts on-device AI agent speed by 1.61x without losing accuracy, optimizing AI performance for edge devices.
Cumulative Token Importance Sampling for LLM Policy Optimization
Discover how cumulative token importance sampling improves LLM policy optimization by reducing variance and bias for stable, efficient reinforcement learni...
CSR Framework: Real-Time AI Policies with Massive State Caches
Discover how the CSR framework and ASR algorithm reduce latency for real-time AI policies using massive cached state representations in robotics.
CommFuse: Reduce Tail Latency in Distributed LLM Training
Discover how CommFuse optimizes communication to reduce tail latency and boost efficiency in distributed large language model training.