We present DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-
Language Models that significantly improves upon its predecessor, DeepSeek-VL, through …

Multimodal Sentiment Analysis (MSA) focuses on leveraging multimodal signals for
understanding human sentiment. Most of the existing works rely on superficial information …

Vision language models (VLMs) have achieved impressive progress in diverse applications,
becoming a prevalent research direction. In this paper, we build FIRE, a feedback …

Large Vision-Language Models (LVLMs) have achieved remarkable performance in many
vision-language tasks, yet their capabilities in fine-grained visual understanding remain …

With the growing adoption and capabilities of vision-language models (VLMs) comes the
need for benchmarks that capture authentic user-VLM interactions. In response, we create …

Multimodal LLMs (MLLMs) equip language models with visual capabilities by aligning vision
encoders with language models. Existing methods to enhance the visual perception of …

While diffusion models are powerful in generating high-quality, diverse synthetic data for
object-centric tasks, existing methods struggle with scene-aware tasks such as Visual …

Human-scene vision-language tasks are increasingly prevalent in diverse social
applications, yet recent advancements predominantly rely on models specifically tailored to …

Vision-Language adaptation (VL adaptation) transforms Large Language Models (LLMs)
into Large Vision-Language Models (LVLMs) for multimodal tasks, but this process often …

Understanding time from visual representations is a fundamental cognitive skill, yet it
remains a challenge for multimodal large language models (MLLMs). In this work, we …