Most work on reward learning has used simulated environments, but complex information about values is often expressed in natural language, and we believe reward learning for language is a key to making RL practical and safe for real-world tasks.
Recent advances in face manipulation using StyleGAN have produced impressive results.
Towards a more comprehensive perception of a 3D scene, in this paper, we propose a SurroundOcc method to predict the 3D occupancy with multi-camera images.
We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Recent vision-language models have shown impressive multi-modal generation capabilities.
Ranked #1 on Image Captioning on nocaps val
This is the first use of sparse convolution for 2D masked modeling.
Ranked #1 on Instance Segmentation on COCO 2017 val
As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency.
Ranked #3 on Object Detection on COCO 2017 (mAP metric)
The incredible generative ability of large-scale text-to-image (T2I) models has demonstrated strong power of learning complex structures and meaningful semantics.
We find that existing detectors struggle to detect images generated by diffusion models, even if we include generated images from a specific diffusion model in their training data.