The paper introduces Giraffe, a new mapping architecture that converts hidden text token representations into visual embeddings for graphic design tasks. It uses a single [IMG] token per image and two shallow MLP blocks—one for training and one for inference—to compress and expand embeddings, trained with six loss functions. The approach achieves strong performance in both image‑to‑design and text‑to‑design generation while remaining lightweight.
arXiv:2609.37225v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have shown strong potential for universal multimodal representation learning. However, existing methods eith...
arXiv:2605.00809v3 Announce Type: replace Abstract: In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining...
arXiv:2607. 26596v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified transformer architecture.
arXiv:2605. 18160v2 Announce Type: replace-cross Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information.
TokenSwap introduces a method to benchmark and reduce the modality gap in multimodal large language models (MLLMs) by interleaving semantically aligned images with text tokens. By transforming text-only benchmarks like MMLU into image‑interleaved versions (TokenSwap‑Bench), the authors reveal a pervasive performance drop—averaging 19.6%—across 42 MLLMs, with reasoning models showing smaller gaps. Training with TokenSwap mitigates this gap while maintaining strong text‑only and vision‑language performance.
arXiv:2506. 03096v2 Announce Type: replace-cross Abstract: Contrastive language-image pre-training aligns features of text-image pairs in a common latent space via distinct encoders for each modality.
arXiv:2609.40362v1 Announce Type: new Abstract: We present Multimodal Flow, a fully continuous generative model of language and vision. Most unified multimodal models either model both language and q...
ASCIIBench is a new benchmark that evaluates large language models on generating and classifying ASCII-text images, using a dataset of 5,315 labeled ASCII images. The authors also release a fine‑tuned CLIP model adapted to capture ASCII structure for evaluation. Their analysis shows that cosine similarity on CLIP embeddings fails to separate most categories, indicating a representation bottleneck rather than generational variance.
VisionWeave introduces elastic visual representation weaving, a native capability for multimodal large language models that learns where and at what granularity to encode visual information. The method combines a gated spatial pooler for coarse representations with a granularity router that allocates content‑adaptive token usage, trained end‑to‑end on large‑scale data. Experiments on Qwen3.5‑4B and Qwen3.8‑27B show that VisionWeave can save 43.0% of tokens while preserving 98.9% of performance across eight benchmarks, and delivers significant throughput gains and latency reductions when deployed on the SGLang serving engine.
arXiv:2606. 13288v1 Announce Type: cross Abstract: Contrastively trained vision-language models like CLIP, have made remarkable progress in learning joint image-text representations, but still face challenges in compositional understanding.
Intern Lumina U2 is a diffusion large language model that uses multi-codebook visual tokens in a fully discrete space, allowing each visual position to be represented by a group of complementary codes. The model concatenates embeddings at each position and employs a lightweight autoregressive head to predict codes sequentially while the diffusion backbone processes all positions in parallel. Built on the unified 4D representation of AToken, it supports image, video, and 3D inputs, achieves leading performance in visual understanding, image generation, and editing, and includes a cross‑platform training, inference, and evaluation system with a stability‑aware sampling strategy that speeds up image generation by 4.45×.
arXiv:2608. 08676v1 Announce Type: cross Abstract: Semantic vision encoders have become a central visual interface for multimodal understanding and semantic conditioning in image generation.