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:2606. 01207v1 Announce Type: cross Abstract: The choice between cross-attention and concatenation for multimodal fusion remains governed by practitioner intuition rather than principled understanding.
arXiv:2508. 12466v2 Announce Type: replace-cross Abstract: Traditional multimodal learning approaches rely on alignment pre-training to bridge vision and language modalities, typically by projecting visual features into discrete text token spaces using large-scale image--text data.
arXiv:2604. 00086v2 Announce Type: replace-cross Abstract: The field of computer vision has experienced significant advancements through scalable vision encoders and multimodal pre-training frameworks.
VIVAS is a new Vision‑Language Model pre‑training framework that addresses the lack of fine‑grained visual perception in existing VLMs. It introduces a unified token space and a dense‑structural‑semantic vision tokenizer that expands the textual vocabulary with visual tokens, enabling vision‑language unified autoregressive supervision over both visual details and linguistic content. Trained on 12.4 T tokens, VIVAS achieves state‑of‑the‑art results on 7 tasks and 39 multimodal benchmarks.
arXiv:2609.37775v1 Announce Type: cross Abstract: Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. M...
UVU is a vision-language unified autoregressive framework that integrates visual supervision directly into the pre-training stage of multimodal large language models. By using continuous visual encoding and a large-scale iterative hierarchical clustering algorithm to build a pixel-level visual codebook, UVU enables lossless representation of visual inputs and autoregressive generation of pixel-level image tokens alongside textual tokens. This approach synergizes pixel-level visual perception with semantic-level visual understanding, allowing models to internalize visual reconstruction capabilities and improve multimodal understanding performance.
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...
arXiv:2608. 05000v1 Announce Type: cross Abstract: Vision offers a critical axis for advancing foundation models, driving a shift towards natively unified multimodal pretraining.
arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.
arXiv:2602. 07026v3 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions.
arXiv:2507.00754v3 Announce Type: replace Abstract: The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the...