Prevent Unauthorized Distillation of Language Models
Learn how trace rewriting protects large language models from unauthorized knowledge distillation while embedding verifiable watermarks.
AscendKernelGen: LLM-Based Kernel Generation for NPUs
Discover AscendKernelGen, an advanced LLM framework improving kernel generation for Neural Processing Units with 95.5% compilation success.
Cost-Aware Model Selection for Efficient LLM Systems
Boost LLM system efficiency with cost-aware model selection, improving accuracy, energy use, and latency for smarter AI orchestration.
MM-Telco: Multimodal LLM Benchmarks for Telecom
Discover MM-Telco, multimodal large language models and benchmarks designed to optimize telecom network operations and customer support.
Optimizing Agentic AI Execution with CPU-Centric Methods
Explore CPU-focused strategies to boost Agentic AI performance by reducing latency and balancing resource allocation in heterogeneous systems.