Model Quantization, Inference Optimization, GGUF Format, Privacy-preserving AI
HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption
arxiv.org·2d
Why Your Next LLM Might Not Have A Tokenizer
towardsdatascience.com·2d
Semantic-Preserving Adversarial Attacks on LLMs: An Adaptive Greedy Binary Search Approach
arxiv.org·2d
Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning
arxiv.org·2d
COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees
arxiv.org·19h
Loading...Loading more...