NeoMME: an efficient Multimodal-native and Multilingual Encoder

SigLIP 2: A better multilingual vision language encoder

Introducing Gemma 4 12B: a unified, encoder-free multimodal model

NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference

NeoMME is a family of 260M and 800M‑parameter multimodal‑native multilingual encoders that process text and raw image patches in a single bidirectional Transformer. Trained from scratch with a masked discrete‑diffusion objective conditioned on visible image patches, NeoMME supports a 16,384‑token context, enabling encoding of up to two 4K UHD images. In downstream tests, NeoMME‑Retriever models outperform all sub‑800M‑parameter baselines on the ViDoRe v3 benchmark and achieve twice the throughput of ColModernVBERT on an NVIDIA L40S, while hierarchical token pooling and asymmetric quantization compress embeddings 255× with minimal loss in retrieval performance.

NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference

Multimodal models often build on architectures designed for generative vision-language modeling, typically combining separately pretrained vision encoders with causal language models. Visual document...

EuroBERT: Scaling Multilingual Encoders for European Languages

arXiv:2503. 05500v3 Announce Type: replace-cross Abstract: General-purpose multilingual vector representations, used in retrieval, regression and classification, are traditionally obtained from bidirectional encoder models.

FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens

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.

Virtual Encoders in Multimodal Transformers

The paper investigates how multimodal language models can generate perceptual representations without dedicated encoders. It shows that the shared transformer can internally create these representations in its early-to-middle layers, a structure termed a Virtual Encoder. Experiments with linear probing, similarity metrics, and causal analysis reveal that this encoder-like computation emerges even when models receive only perceptual tokens, indicating that perception and language processing can be decoupled within a single architecture.

A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders

arXiv:2608. 04586v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).

Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders

arXiv:2608. 04586v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT).

Can Frontier LLMs Match Natively Multimodal Embeddings? A Comparison on Hard-Negative Text-to-Image Retrieval

arXiv:2608. 11343v1 Announce Type: new Abstract: Multimodal retrieval and classification across different types of media, spanning text, images,video and audio, has traditionally relied on dual-encoder models that align visual and textual representations through contrastive learning.

Projector Is All You Train

arXiv:2608. 19726v1 Announce Type: cross Abstract: The typical training process of a multimodal large language model (MLLM) involves adapting both the language model backbone and the projector between the backbone and a modality-specific encoder.