#LLM Efficiency

4 articles with this tag

LOCKS Unlocks LLM Long Context Efficiency
AI Research

LOCKS Unlocks LLM Long Context Efficiency

LOCKS revolutionizes long-context LLMs by approximating KV cache with spectral summaries, achieving near full-quality inference while drastically cutting latency and computation.

6 days ago
From LLM APIs to Local Neural Artifacts
AI Research

From LLM APIs to Local Neural Artifacts

Fuzzy-function programming enables compiling LLM-powered functions locally, matching large model performance with minimal resources.

about 1 month ago
AdaCodec: Efficient Video MLLM Encoding
AI Research

AdaCodec: Efficient Video MLLM Encoding

AdaCodec revolutionizes video MLLMs by using predictive visual coding to drastically cut tokenization costs and latency, achieving superior performance at a fraction of the budget.

2 months ago
DMax: Parallel Decoding for Diffusion LLMs
AI Research

DMax: Parallel Decoding for Diffusion LLMs

DMax revolutionizes diffusion language models with Soft Parallel Decoding, boosting TPF significantly while preserving accuracy and achieving 1,338 TPS.

4 months ago