Product Quantization for Nearest Neighbor Search
将 Product Quantization 用于搜索以降低存储占用
Empirical
Bridging Textual-Collaborative Gap through Semantic Codes for Sequential Recommendation
通过 Q-Former 将 semantic IDs 转换为 textual IDs
An Image is Worth 32 Tokens for Reconstruction and Generation
非结构化的一维离散 Visual Tokens 生成策略
BEiT: BERT Pre-Training of Image Transformers
Visual Tokens & Masked Image Modeling
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
自回归图像生成: Multi-scale Quantization & Next-scale Prediction
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
兼顾 Low-level 的 Pixel 信息和 High-level 的 Semantic 信息
UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation
非常自然的 Image-Codeword+Text-LLM-NextCodeWord-Generation 流程
Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
符号序列的自动切分, 探究非 Subword Tokenizer 的可能性
SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
TiTok 框架 + Softmax 版 Vector Quantization 以期更高的压缩比
MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers
多尺度 Transformer, 探究非 Subword Tokenizer 的可能性