We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image.
Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models.
Ranked #9 on Text-to-Image Generation on COCO
Retrieval-augmented in-context learning has emerged as a powerful approach for addressing knowledge-intensive tasks using frozen language models (LM) and retrieval models (RM).
We introduce k-planes, a white-box model for radiance fields in arbitrary dimensions.
Ranked #1 on Novel View Synthesis on LLFF
Furthermore, we propose a latent-mapping algorithm in the latent space to convert the amateur vocal tone to the professional one.
First, we use synthetic language modeling tasks to understand the gap between SSMs and attention.
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.
In this work, we describe a single-loop method, with no back-tracking or line searches, which does not require knowledge of $D$ yet asymptotically achieves the optimal rate of convergence for the complexity class of convex Lipschitz functions.
In this paper, we demonstrate that a learned discrete codebook prior in a small proxy space largely reduces the uncertainty and ambiguity of restoration mapping by casting blind face restoration as a code prediction task, while providing rich visual atoms for generating high-quality faces.
Ranked #1 on Blind Face Restoration on WIDER