Jianyong Wang, Li Dong, Hangbo Bao, Shaohan Huang, Yutao Sun, Wenhui Wang, Zhiliang Peng, Fu-Ru Wei
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Multimodal generative models require a unified approach to handle both discrete data (e.g., text and code) and continuous data (e.g., image, audio, video). In this work, we propose Latent Language Modeling (LatentLM), which seamlessly integrates continuous and discrete data using causal Transformers. Specifically, we employ a variational autoencoder (VAE) to represent continuous data as latent vectors and introduce next-token diffusion for autoregressive generation of these vectors. Additionally, we develop σ-VAE to address the challenges of variance collapse, which is crucial for autoregressive modeling. Extensive experiments demonstrate the effectiveness of LatentLM across various modalities. In image generation, LatentLM surpasses Diffusion Transformers in both performance and scalability. When integrated into multimodal large language models, LatentLM provides a general-purpose interface that unifies multimodal generation and understanding. Experimental results show that LatentLM achieves favorable performance compared to Transfusion and vector quantized models in the setting of scaling up training tokens. In text-to-speech synthesis, LatentLM outperforms the state-ofthe-art VALL-E 2 model in speaker similarity and robustness, while requiring 10× fewer decoding steps. The results establish LatentLM as a highly effective and scalable approach to advance large multimodal models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2412.08635")
get_code_for_paper("2412.08635")
have("2412.08635")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2412.08635.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2412.08635)
Connect an agent — have() is free.