We introduce Blink, a new benchmark for multimodal language models (LLMs) that focuses
on core visual perception abilities not found in other evaluations. Most of the Blink tasks can …

In the era of Artificial Intelligence Generated Content (AIGC), conditional multimodal
synthesis technologies (eg, text-to-image) are dynamically resha** the natural content …

Vision-language models (VLMs) are typically composed of a vision encoder, eg CLIP, and a
language model (LM) that interprets the encoded features to solve downstream tasks …

VILA-U is a Unified foundation model that integrates Video, Image, Language understanding
and generation. Traditional visual language models (VLMs) use separate modules for …

Abstract Rotary Position Embedding (RoPE) performs remarkably on language models,
especially for length extrapolation of Transformers. However, the impacts of RoPE on …

Connecting text and visual modalities plays an essential role in generative intelligence. For
this reason, inspired by the success of large language models, significant research efforts …

We present Lumina-mGPT, a family of multimodal autoregressive models capable of various
vision and language tasks, particularly excelling in generating flexible photorealistic images …

Personalized recommendation serves as a ubiquitous channel for users to discover
information tailored to their interests. However, traditional recommendation models primarily …

World models are progressively being employed across diverse fields, extending from basic
environment simulation to complex scenario construction. However, existing models are …

We introduce MoMa, a novel modality-aware mixture-of-experts (MoE) architecture designed
for pre-training mixed-modal, early-fusion language models. MoMa processes images and …