We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the
state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our …

During our discussion at workshops for writing “What Does ChatGPT Say: The DAO from
Algorithmic Intelligence to Linguistic Intelligence”[1], we had expected the next milestone for …

With the development of artificial intelligence and breakthroughs in deep learning, large-
scale foundation models (FMs), such as generative pre-trained transformer (GPT), Sora, etc …

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP)
on the other hand, works by mapping an image and its caption to a single vector--limiting …

Despite the rapid integration of video perception capabilities into Large Multimodal Models
(LMMs), the underlying mechanisms driving their video understanding remain poorly …

In the rapidly evolving landscape of autonomous driving, the capability to accurately predict
future events and assess their implications is paramount for both safety and efficiency …

We propose ViC-MAE, a model that combines both Masked AutoEncoders (MAE) and
contrastive learning. ViC-MAE is trained using a global representation obtained by pooling …

Complex 3D scene understanding has gained increasing attention, with scene encoding
strategies playing a crucial role in this success. However, the optimal scene encoding …

We introduce Image-GOal Representations (IGOR), aiming to learn a unified, semantically
consistent action space across human and various robots. Through this unified latent action …

World models and video generation are pivotal technologies in the domain of autonomous
driving, each playing a critical role in enhancing the robustness and reliability of …