LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models
arXiv:2607. 16305v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding.
arXiv:2607. 16305v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding.
CausalEmbed is an auto‑regressive method for generating compact multi‑vector embeddings in visual document retrieval. By using iterative margin loss during contrastive training, it reduces the number of visual tokens needed by 30‑155× while keeping performance competitive across different backbones and benchmarks. The approach offers efficient training, scalable test‑time performance, and a flexible scaling strategy for multi‑vector representations.
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:2603. 01471v3 Announce Type: replace-cross Abstract: Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classification.
arXiv:2603. 01471v2 Announce Type: replace-cross Abstract: Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classification.
The paper introduces PACE, a Pareto‑adaptive compression framework designed for native multimodal large language models (MLLMs) that directly tokenize pixel patches without external vision encoders. By analyzing token discriminability and heterogeneous redundancy across spatial dimensions, PACE decomposes attention into height‑ and width‑specific saliency maps and applies a Pareto‑optimization strategy to allocate token budgets, achieving near‑lossless performance with only 25‑50% of visual tokens and more than 2× FLOP savings. Experiments demonstrate that PACE not only preserves but sometimes improves benchmark results compared to existing ViT‑based compression methods.
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.
Universal multimodal embeddings are becoming a core component of modern AI systems, enabling heterogeneous content to be represented in a shared space for applications such as retrieval, recommendatio...
The paper introduces ReT-2, a unified retrieval model that handles multimodal queries containing both images and text and searches across multimodal document collections. It employs a recurrent Transformer architecture with LSTM-inspired gating to integrate information across layers and modalities, capturing fine-grained visual and textual details. Evaluations on M2KR and M-BEIR benchmarks show state‑of‑the‑art performance, faster inference, and lower memory usage, and the model also boosts downstream tasks in retrieval‑augmented generation pipelines.
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:2606. 14747v1 Announce Type: cross Abstract: Recent advancements have significantly expanded the theoretical context windows of Multimodal Embedding Models (MEMs).
arXiv:2609.23715v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images....