InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation

ArXi:2605.14333v1 Announce Type: new Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer: aggressive downsampling and quantization often discard the fine-grained structures needed to preserve readable glyphs and distinctive facial features.