Tag: LLM Optimization
Browse our exclusive articles!
Evergreen: Fast, Accurate Claim Verification for Semantic Data
Discover Evergreen, a system that ensures efficient and reliable claim verification for semantic aggregates with reduced cost and latency.
Entropy Centroids for Efficient Test-Time Scaling in LLMs
Discover how entropy centroids improve test-time scaling by using intrinsic rewards to boost large language model response quality without external models.
Kwai Summary Attention: Efficient Long-Context AI Model
Discover Kwai Summary Attention, a novel mechanism improving long-context handling in AI models for better semantic understanding and efficiency.
AgenticCache: Efficient Cache-Driven Planning for Embodied AI
Discover AgenticCache, a novel cache-driven asynchronous planning framework that boosts embodied AI agents' efficiency and cuts latency by 65%.
SFT-then-RL Beats Mixed-Policy Methods in LLM Reasoning
Discover how the SFT-then-RL pipeline outperforms mixed-policy methods in large language model reasoning after fixing key optimization bugs.