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 …

Recently, slow-thinking reasoning systems, such as o1, have demonstrated remarkable
capabilities in solving complex reasoning tasks. These systems typically engage in an …

Dense process rewards have proven a more effective alternative to the sparse outcome-
level rewards in the inference-time scaling of large language models (LLMs), particularly in …

Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate
annotated responses for given instructions. In this paper, we challenge this paradigm and …

AI for Mathematics (AI4Math) is not only intriguing intellectually but also crucial for AI-driven
discovery in science, engineering, and beyond. Extensive efforts on AI4Math have mirrored …

We present a fundamental discovery that challenges our understanding of how complex
reasoning emerges in large language models. While conventional wisdom suggests that …

Recently, test-time scaling has garnered significant attention from the research community,
largely due to the substantial advancements of the o1 model released by OpenAI. By …

Reasoning abilities, especially those for solving complex math problems, are crucial
components of general intelligence. Recent advances by proprietary companies, such as o …

In this paper, we propose VideoLLaMA3, a more advanced multimodal foundation model for
image and video understanding. The core design philosophy of VideoLLaMA3 is vision …

Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have
made significant advancements in reasoning capabilities. However, they still face …