Tag: language model optimization
Browse our exclusive articles!
DepCap: Fast Adaptive Block-Wise Decoding for Diffusion LMs
DepCap enhances diffusion language model inference with adaptive block-wise decoding, boosting speed up to 5.63x while maintaining high-quality output.
Optimizing Adaptive Retrieval in LLMs with AdaRankLLM
Discover how AdaRankLLM enhances adaptive retrieval in large language models, improving efficiency and reducing noise with advanced listwise ranking.
S3: Enhanced Test-Time Scaling for Diffusion Language Models
Discover S3, a novel test-time scaling method that boosts diffusion language model outputs using verifier-guided search during denoising.
Profile-Then-Reason: Efficient Tool-Augmented Language Agents
Discover Profile-Then-Reason, a framework enhancing efficiency and reliability in tool-augmented language agents by minimizing model calls and reducing lat...