FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation

• URL: http://arxiv.org/abs/2609.16591v1
• Date: Tue, 15 Sep 2026 03:35:59 GMT
• Title: FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation
• Abstract summary: Flat is a representation pre-training framework that jointly optimize a shared multimodal encoder alongside downstream text-to-image (T2I) and image-to-text (I2T) decoders.<n>A single pre-training stage allows FLAT to perform cross-modal retrieval and generation across variable prefix K, achieving a T2I GenEval score of 71.1.
• Score: 29.59094476146176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traditional multimodal representation learning and generation are two stages: a contrastive or self-supervised visual encoder is trained first, followed by a separate downstream generative model. This setup bottlenecks generative performance behind frozen embeddings. To bridge this gap, we revisit joint multimodal representation learning and generation to produce linearly interpolatable embeddings that are directly consumable by generative decoders. We present FLAT (Flexible-Length Aligned Transmodal representations), a representation pre-training framework that jointly optimizes a shared multimodal encoder alongside downstream text-to-image (T2I) and image-to-text (I2T) decoders. By combining contrastive alignment with bidirectional cross-modal generative objectives, FLAT ensures its representations function as both discriminative semantic descriptors and generative conditions. Architecturally, FLAT maps visual and textual inputs into a unified continuous 1D sequence space, applying nested dropout over prefix-K tokens to enable dynamic output lengths. A single pre-training stage allows FLAT to perform cross-modal retrieval and generation across variable prefix K, achieving a T2I GenEval score of 71.1. Task-specific fine-tuning aligns model performance with state-of-the-art baselines: 83.1 GenEval on T2I generation; 40.5 BLEU-4 and 138.6 CIDEr on MS-COCO image captioning; and Recall@5 scores of 86.8 (I2T) / 75.8 (T2I) on MS-COCO alongside 98.3 (I2T) / 93.6 (T2I) on Flickr30K. Finally, qualitative evaluations demonstrate that FLAT representations natively support linear interpolation, latent space arithmetic, and zero-shot composed retrieval.

Related papers

• Coupled Continuous-Discrete Generation for Scene Text Image Super-Resolution [51.31474187379532]
  Scene text image super-resolution (STISR) aims to recover visually plausible appearance while preserving character semantics from degraded inputs.<n>We present DualTSR, a unified framework that formulates STISR as coupled continuous-discrete generation.<n> Conditional flow matching restores continuous image latents, while absorbing-state discrete diffusion reconstructs text tokens.
  arXiv  Detail & Related papers  (2026-08-05T06:57:30Z)
• Imagine Before You Draw: Visual Prompt Engineering for Image Generation [67.81347924426714]
  We propose Visual Prompt Engineering (VPE), which can be seamlessly integrated into internal frameworks.<n>We validate VPE across class-conditional generation, text-to-image generation, and image editing.<n>Results show that VPE can accelerate convergence, raise quality ceilings, and through internal integration, achieve substantially better editing preservation.
  arXiv  Detail & Related papers  (2026-06-03T05:01:36Z)
• STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation [56.964292897565024]
  We present autoregressive normalizing flows, sharing the same causal mask, KV-cache mechanism, and left-to-right structure as LLMs.<n>We demonstrate strong performance across image generation and multimodal understanding benchmarks, validating autoregressive flows as a viable foundation for unified multimodal modeling.
  arXiv  Detail & Related papers  (2026-05-08T17:14:43Z)
• TextLDM: Language Modeling with Continuous Latent Diffusion [89.69255520673248]
  Diffusion Transformers (DiT) trained with flow matching in a VAE latent space have unified visual generation across images and videos.<n>We propose TextLDM, which transfers the visual latent diffusion recipe to text generation with minimal architectural modification.
  arXiv  Detail & Related papers  (2026-05-08T13:54:34Z)
• End-to-End Training for Unified Tokenization and Latent Denoising [82.91537591286554]
  We propose UNITE - an autoencoder architecture for unified tokenization and latent diffusion.<n>UNITE consists of a Generative that serves as both image tokenizer and latent generator via weight sharing.<n>We show that single stage joint training of tokenization & generation from scratch is feasible.
  arXiv  Detail & Related papers  (2026-03-23T17:59:49Z)
• COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval [59.15034487974549]
  We propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval. Our COTS achieves the highest performance among all two-stream methods and comparable performance with 10,800X faster in inference. Importantly, our COTS is also applicable to text-to-video retrieval, yielding new state-ofthe-art on the widely-used MSR-VTT dataset.
  arXiv  Detail & Related papers  (2022-04-15T12:34:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.