STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
Unified multimodal models that understand, reason over, and generate interleaved text–image sequences remain structurally fragmented: existing approaches either sacrifice visual fidelity through discrete tokenization, impose structural asymmetry by combining causal text generation with iterative diffusion-based denoising, or degrade pretrained understanding when adapting vision-language models for generation. We observe that autoregressive normalizing flows are autoregressive Transformers—sharing the same causal mask, KV-cache mechanism, and left-to-right structure as LLMs—making them the most…
content type paperpublished August 2026
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
AuthorsYing Shen†**, Tianrong Chen, Yuan Gao, Yizhe Zhang, Yuyang Wang, Miguel Angel Bautista Martin, Shuangfei Zhai, Josh Susskind, Jiatao Gu
View publication
Unified multimodal models that understand, reason over, and generate interleaved text–image sequences remain structurally fragmented: existing approaches either sacrifice visual fidelity through discrete tokenization, impose structural asymmetry by combining causal text generation with iterative diffusion-based denoising, or degrade pretrained understanding when adapting vision-language models for generation. We observe that autoregressive normalizing flows are autoregressive Transformers—sharing the same causal mask, KV-cache mechanism, and left-to-right structure as LLMs—making them the most natural paradigm for truly unified multimodal generation that is continuous, single-pass, and purely causal. We present STARFlow2, built on the Pretzel architecture that vertically interleaves a frozen pretrained VLM stream with a TARFlow stream via residual skip connections, both operating under the same causal mask. This design simultaneously preserves pretrained multimodal understanding, enables high-fidelity continuous image generation, and achieves structural unification under a single causal mechanism. Combined with a deep-shallow flow design and a unified FAE latent space, STARFlow2 supports cache-friendly interleaved generation where both text and visual outputs directly enter the KV-cache without re-encoding. Experiments demonstrate strong performance across image generation and multimodal understanding benchmarks, validating autoregressive flows as a viable foundation for unified multimodal modeling.
† UIUC
** Work done while at Apple
STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows
April 30, 2026research area Computer Vision, research area Methods and Algorithmsconference CVPR
Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, state-of-the-art systems almost exclusively rely on diffusion-based models. In this work, we revisit this design space by presenting STARFlow-V, a…
Read more
KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation
May 14, 2024research area Methods and Algorithms, research area Speech and Natural Language Processingconference ICML
Large Language Model or LLM inference has two phases, the prompt (or prefill) phase to output the first token and the extension (or decoding) phase to the generate subsequent tokens. In this work, we propose an efficient parallelization scheme, KV-Runahead to accelerate the prompt phase. The key observation is that the extension phase generates tokens faster than the prompt phase because of key-value cache (KV-cache). Hence, KV-Runahead…
Read more