AI News
5297 articles in this category (Page 30 of 221)
Sakana AI and NVIDIA Introduce TwELL: 20.5% Faster LLM Inference via Unstructured Sparsity
Sakana AI and NVIDIA introduced TwELL and custom CUDA kernels, achieving 20.5% inference and 21.9% training speedups in LLMs by exploiting activation sparsity.
Mastering LLM Distillation: Soft-Label, Hard-Label, and Co-distillation Strategies
LLM distillation uses teacher-student models to transfer reasoning capabilities, reducing costs while maintaining performance through techniques like soft-label and co-distillation.
NadirClaw: Building Cost-Aware LLM Routing with Local Prompt Classification
NadirClaw introduces an intelligent local routing layer that classifies prompts into simple and complex tiers, enabling dynamic switching between Gemini Flash and Pro to reduce LLM costs by up to 50%.
Challenging Google Play Security: A Technical Proposal for Manifest-Level Verification
Developer Indigotime proposes replacing Google's identity verification with technical declarations of public keys and hardcoded web addresses to stop data interception.