按年被提到
20242024 · 1 次2026
视觉、语音与图像生成›图像与视频生成·arXiv:2412.10208 · cs.LG

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens

Jaehyeon Kim, Taehong Moon, Keon Lee, Jaewoong Cho · 2024
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2024-12-29 · 最近 2026-07-08
2不同的人
2活跃月份
2讨论串
1被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We introduce ResGen, an efficient Residual Vector Quantization (RVQ)-based generative model for high-fidelity generation with fast sampling. RVQ improves data fidelity by increasing the number of quantization steps, referred to as depth, but deeper quantization typically increases inference steps in generative models. To address this, ResGen directly predicts the vector embedding of collective tokens rather than individual ones, ensuring that inference steps remain independent of RVQ depth. Additionally, we formulate token masking and multi-token prediction within a probabilistic framework using discrete diffusion and variational inference. We validate the efficacy and generalizability of the proposed method on two challenging tasks across different modalities: conditional image generation on ImageNet 256x256 and zero-shot text-to-speech synthesis. Experimental results demonstrate that ResGen outperforms autoregressive counterparts in both tasks, delivering superior performance without compromising sampling speed. Furthermore, as we scale the depth of RVQ, our generative models exhibit enhanced generation fidelity or faster sampling speeds compared to similarly sized baseline models.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论quotemstr · 2026-07

“> GPT-Live-1 is the first version of a new generation of models, and we believe the full-duplex architecture + delegation enables entirely new ways of human-AI interaction. Awesome. Are you guys able to share anything about the model architecture? I've been interested lately in split-transformer RVQ-based conversational agents, e.g. via stuff like https:…”

GPT‑Live原评论 ↗
被提交为 story · 1 次