PinnedPublished inTowards AIVision Embedding Comparison for Image Similarity Search: EfficientNet vs.What are the differences in embeddings among these models?Oct 12, 2024A response icon7Oct 12, 2024A response icon7
PinnedPublished inIntuitionUnderstanding L1 and L2 regularization with analytical and probabilistic viewsDerive L1 and L2 regularization via analytical and probabilistic solutionMay 25, 2024A response icon4May 25, 2024A response icon4
Published inThe Quantastic JournalA Gentle Introduction to Gaussian Discriminant Analysis: Gaussian Naive Bayes, Linear Discriminant…To understand Gaussian discriminant analysis deeply based on the mathematics and a Python implementation from scratchJan 27A response icon1Jan 27A response icon1
Published inGenerative AIPractical Guide of LLM Quantization: GPTQ, AWQ, BitsandBytes, and UnslothLet’s learn modern quantization techniques and their implementation with Mistral and Llama 3.2Dec 16, 2024A response icon2Dec 16, 2024A response icon2
Published inTowards AIUnlocking CLIP: LLM2CLIP Can Enhance CLIP to Get a Further Visual RepresentationMicrosoft developed a more powerful CLIP by leveraging LLMNov 25, 2024Nov 25, 2024
Published inTowards AIAutomatic Speech Recognition -Whisper Variants Comparison: What Are Their Features And How To…Which Whisper variant is suitable for what case? Whisper vs Faster-Whisper vs WhisperX vs Distil-WhisperNov 14, 2024Nov 14, 2024
Published inGenerative AIUnlocking Mixture-of-Experts (MoE) LLM : Your MoE model can be embedding model for freeMixture-of-experts (MoE) LLM can be used as an embedding model for free.Nov 3, 2024A response icon5Nov 3, 2024A response icon5
Published inGenerative AIPixtral 12B is released : Novel SOTA Open-Source Multimodal Language ModelMistralAI team released Pixtral 12B, a novel open-source multimodal model that outperforms other open-source models. How does it works and…Oct 23, 2024A response icon1Oct 23, 2024A response icon1
Published inGenerative AIUnlocking the Diffusion Model Power!The introduction of a novel tuning-free style transfer method: InstantStyle. How can it work without additional fine-tuning, and how can it…Sep 29, 2024A response icon2Sep 29, 2024A response icon2
Published inAI AdvancesNovel personalized image generation: InstantID — Theoretical Understanding and ApplicationsInstantID is a novel personalized image generation based on the diffusion model. This blog covers the theoretical understanding and how to…Sep 25, 2024Sep 25, 2024