arXiv:2607. 03624v1 Announce Type: cross Abstract: This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features.
Vision-language models commonly project all tokens produced by a pretrained vision encoder into a large language model. However, final-layer features can discard text, local attributes, and spatial relationships, while high-resolution inputs substantially increase context length and inference latency.
Built on pretrained vision foundation models (VFMs), representation autoencoders (RAEs) have recently emerged as a promising approach for constructing semantically rich latent spaces for image generation. However, their reconstruction quality often remains suboptimal, largely because deep VFM representations do not preserve sufficient fine-grained visual detail.
arXiv:2607. 25527v1 Announce Type: cross Abstract: Unifying visual understanding and generation in one model holds immense promise, but remains challenging and expensive due to heavy compute and data demands and conflicts between the visual features needed for these two capabilities.
arXiv:2606. 07451v1 Announce Type: cross Abstract: Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space.
arXiv:2607. 28627v1 Announce Type: cross Abstract: Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once is computationally infeasible under GPU memory constraints.
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:2607. 04593v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large number of visual tokens fed to the language model.
arXiv:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.
arXiv:2605. 18714v2 Announce Type: replace-cross Abstract: Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture.
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.
In video understanding, vision-language models (VLMs) must ingest massive numbers of visual tokens, causing the computational and memory cost of the prefill stage to rise sharply. Such visual sequences are highly redundant along the spatio-temporal dimension, yet a high compression ratio is often accompanied by the loss of critical details.
arXiv:2608. 10635v1 Announce Type: cross Abstract: Medical Vision-Language Models (Med-VLMs) excel at verbalizing visual content, yet precise visual perception, segmentation, and grounding remain challenging.