We introduce InternVL 2.5, an advanced multimodal large language model (MLLM) series
that builds upon InternVL 2.0, maintaining its core model architecture while introducing …

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 …

Low precision training and inference affect both the quality and cost of language models, but
current scaling laws do not account for this. In this work, we devise" precision-aware" scaling …

Vision-language models (VLMs) have made significant progress in recent visual-question-
answering (VQA) benchmarks that evaluate complex visio-linguistic reasoning. However …

We present MEGA-Bench, an evaluation suite that scales multimodal evaluation to over 500
real-world tasks, to address the highly heterogeneous daily use cases of end users. Our …

Text-rich images, where text serves as the central visual element guiding the overall
understanding, are prevalent in real-world applications, such as presentation slides …

While problem solving is a standard evaluation task for foundation models, a crucial
component of problem solving--actively and strategically gathering information to test …

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly
in languages other than English and in underrepresented cultural contexts. To evaluate their …

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and
evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current …

Despite recent advances in Vision-Language Models (VLMs), many still over-rely on visual
language priors present in their training data rather than true visual reasoning. To examine …