cs.CVNov 18, 2026

ViLFlow: Parallel Vision-Language Generation with Continuous Latent Flows

Authors: Kevin Zhai, Bian Sun, Zhenyi Wang, Song Wang

Organizations: University of Central Florida · Institute of Artificial Intelligence

Abstract

Vision-language generation has predominantly relied on autoregressive and discrete diffusion models. Autoregressive models generate tokens sequentially, while discrete diffusion models typically predict tokens independently within each denoising step. We propose ViLFlow (Vision-Language Flow), a continuous-flow vision-language model that combines joint modeling of output embeddings with parallel token decoding. ViLFlow adapts pretrained continuous language generation to visual question answering and image captioning through learned image guidance and prediction-aware token decoding. A visually adapted teacher provides image-guided predictions as additional denoising supervision. The denoiser learns to reproduce these predictions directly, retaining one image-conditioned prediction per generation step. We train the token decoder on denoiser predictions and paired reference text to improve the conversion of continuous outputs into words. The decoder can be adapted independently, improving answering and captioning without further denoiser training. For captioning, it also supplies text feedback during late denoising, allowing decoded words to inform subsequent refinement. ViLFlow outperforms autoregressive and masked-diffusion baselines by up to 8.46 percentage points on VQAv2 and 4.50 points on GQA without GQA training. On COCO Karpathy test, it improves CIDEr by 16.25 over masked diffusion and 17.81 over sampled autoregression.

Figures & tables

Explore similar work

May 19, 2026

FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generation

Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vision--language models derived from them recover bidirectional capability through large-scale joint pretraining or substantial retraining of the text pathway, discarding the strong image prior the text-to-image backbone already encodes. We introduce FullFlow, a parameter-efficient recipe that upgrades a pretrained rectified-flow text-to-image model into a bidirectional vision--language generator by training only LoRA adapters and lightweight text heads. FullFlow keeps images in their native continuous flow and adds a discrete insertion process for text. Separate image and text timesteps turn inference into trajectory selection in a two-dimensional generative space, enabling text→\rightarrowimage, image→\rightarrowtext, joint sampling, and partial-text prediction with a single backbone. On Stable Diffusion 3 (SD3) under an identical trainable-parameter count and matched LoRA rank, FullFlow improves text→\rightarrowimage FID from 62.762.7 to 31.631.6 and image→\rightarrowtext CIDEr from 2.02.0 to 99.499.4 over a LoRA equivalent following the previous SOTA formulation (Dual Diffusion) at matched wall-clock training time, while reducing peak VRAM from ∼84{\sim}84,GB to ∼38{\sim}38,GB and raising throughput by ∼8×{\sim}8\times on two RTX A5000 GPUs in under 24 hours, training only ∼5%{\sim}5\% of the backbone parameters. The same recipe transfers to FLUX.1-dev and supports downstream VQA through partial-text generation. These results show that strong bidirectional vision--language capability can be unlocked from pretrained text-to-image flow models without full multimodal pretraining.
May 8, 2026

TextLDM: Language Modeling with Continuous Latent Diffusion

Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos. A natural next step toward a single architecture for both generation (visual synthesis) and understanding (text generation) is to apply this framework to language modeling. We propose TextLDM, which transfers the visual latent diffusion recipe to text generation with minimal architectural modification. A Transformer-based VAE maps discrete tokens to continuous latents, enhanced by Representation Alignment (REPA) with a frozen pretrained language model to produce representations effective for conditional denoising. A standard DiT then performs flow matching in this latent space, identical in architecture to its visual counterpart. The central challenge we address is obtaining high-quality continuous text representations: we find that reconstruction fidelity alone is insufficient, and that aligning latent features with a pretrained language model via REPA is critical for downstream generation quality. Trained from scratch on OpenWebText2, TextLDM substantially outperforms prior diffusion language models and matches GPT-2 under the same settings. Our results establish that the visual DiT recipe transfers effectively to language, taking a concrete step toward unified diffusion architectures for multimodal generation and understanding.
Apr 17, 2026

Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow

Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grounding. Nevertheless, recent work shows that while VLMs often manage to capture the correct image region corresponding to the question, they do not necessarily produce the correct answers. In this work, we demonstrate that this misalignment could be attributed to suboptimal information flow within VLMs, where text tokens distribute too much attention to irrelevant visual tokens, leading to incorrect answers. Based on the observation, we show that modulating the information flow during inference can improve the perception capability of VLMs. The idea is that text tokens should only be associated with important visual tokens during decoding, eliminating the interference of irrelevant regions. To achieve this, we propose a token dynamics-based method to determine the importance of visual tokens, where visual tokens that exhibit distinct activation patterns during different decoding stages are viewed as important. We apply our approach to representative open-source VLMs and evaluate on various datasets, including visual question answering, visual grounding and counting, optical character recognition, and object hallucination. The results show that our approach significantly improves the performance of baselines. Project page: https://cxliu0.github.io/AIF/.