Large language models require updates to remain up-to-date or adapt to new domains by fine-tuning them with new documents. One key is memorizing the latest information in a way that the memorized information is extractable with a query prompt. However, LLMs suffer from a phenomenon called "perplexity curse"; despite minimizing document perplexity during fine-tuning, LLMs struggle to extract information through a prompt sentence. In this new knowledge acquisition and extraction, we find a very intriguing fact that LLMs can accurately answer questions about the first sentence, but they struggle to extract information described in the middle or end of the documents used for fine-tuning. Our study suggests that the auto-regressive training causes this issue; each token is prompted by reliance on all previous tokens, which hinders the model from recalling information from training documents by question prompts. To conduct the in-depth study, we publish both synthetic and real datasets, enabling the evaluation of the QA performance w.r.t. the position of the corresponding answer in a document. Our investigation shows that even a large model suffers from the "perplexity curse", but regularization such as denoising auto-regressive loss can enhance the information extraction from diverse positions. These findings will be (i) a key to improving knowledge extraction from LLMs and (ii) new elements to discuss the trade-off between RAG and fine-tuning in adapting LLMs to a new domain.

We present a simple and efficient method to leverage emerging text-to-image generative models in creating large-scale synthetic supervision for the task of damage assessment from aerial images. While significant recent advances have resulted in improved techniques for damage assessment using aerial or satellite imagery, they still suffer from poor robustness to domains where manual labeled data is unavailable, directly impacting post-disaster humanitarian assistance in such under-resourced geographies. Our contribution towards improving domain robustness in this scenario is two-fold. Firstly, we leverage the text-guided mask-based image editing capabilities of generative models and build an efficient and easily scalable pipeline to generate thousands of post-disaster images from low-resource domains. Secondly, we propose a simple two-stage training approach to train robust models while using manual supervision from different source domains along with the generated synthetic target domain data. We validate the strength of our proposed framework under cross-geography domain transfer setting from xBD and SKAI images in both single-source and multi-source settings, achieving significant improvements over a source-only baseline in each case.

This paper presents instruct-imagen, a model that tackles heterogeneous image generation tasks and generalizes across unseen tasks. We introduce *multi-modal instruction* for image generation, a task representation articulating a range of generation intents with precision. It uses natural language to amalgamate disparate modalities (e.g., text, edge, style, subject, etc.), such that abundant generation intents can be standardized in a uniform format. We then build instruct-imagen by fine-tuning a pre-trained text-to-image diffusion model with a two-stage framework. First, we adapt the model using the retrieval-augmented training, to enhance model's capabilities to ground its generation on external multimodal context. Subsequently, we fine-tune the adapted model on diverse image generation tasks that requires vision-language understanding (e.g., subject-driven generation, etc.), each paired with a multi-modal instruction encapsulating the task's essence. Human evaluation on various image generation datasets reveals that instruct-imagen matches or surpasses prior task-specific models in-domain and demonstrates promising generalization to unseen and more complex tasks.

We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/

We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance. Finally, we also train a cascade of three models for the task of text-to-video generation consisting of a base latent video diffusion model, and two video super-resolution diffusion models to generate videos of $512 \times 896$ resolution at $8$ frames per second.

While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this paper, we introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images using a common token vocabulary. Equipped with this new tokenizer, we show that LLMs outperform diffusion models on standard image and video generation benchmarks including ImageNet and Kinetics. In addition, we demonstrate that our tokenizer surpasses the previously top-performing video tokenizer on two more tasks: (1) video compression comparable to the next-generation video codec (VCC) according to human evaluations, and (2) learning effective representations for action recognition tasks.

The cost of labeling data often limits the performance of machine learning systems. In multi-task learning, related tasks provide information to each other and improve overall performance, but the label cost can vary among tasks. How should the label budget (i.e. the amount of money spent on labeling) be allocated among different tasks to achieve optimal multi-task performance? We are the first to propose and formally define the label budget allocation problem in multi-task learning and to empirically show that different budget allocation strategies make a big difference to its performance. We propose a Task-Adaptive Budget Allocation algorithm to robustly generate the optimal budget allocation adaptive to different multi-task learning settings. Specifically, we estimate and then maximize the extent of new information obtained from the allocated budget as a proxy for multi-task learning performance. Experiments on PASCAL VOC and Taskonomy demonstrate the efficacy of our approach over other widely used heuristic labeling strategies.

Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting these priors to complex visual modalities, often represented as multiple images (e.g., video), achieving consistency across a set of images is challenging. In this paper, we address this challenge with a novel method, Collaborative Score Distillation (CSD). CSD is based on the Stein Variational Gradient Descent (SVGD). Specifically, we propose to consider multiple samples as "particles" in the SVGD update and combine their score functions to distill generative priors over a set of images synchronously. Thus, CSD facilitates seamless integration of information across 2D images, leading to a consistent visual synthesis across multiple samples. We show the effectiveness of CSD in a variety of tasks, encompassing the visual editing of panorama images, videos, and 3D scenes. Our results underline the competency of CSD as a versatile method for enhancing inter-sample consistency, thereby broadening the applicability of text-to-image diffusion models.

The recent advent of self-supervised pre-training techniques has led to a surge in the use of multimodal learning in form document understanding. However, existing approaches that extend the mask language modeling to other modalities require careful multi-task tuning, complex reconstruction target designs, or additional pre-training data. In FormNetV2, we introduce a centralized multimodal graph contrastive learning strategy to unify self-supervised pre-training for all modalities in one loss. The graph contrastive objective maximizes the agreement of multimodal representations, providing a natural interplay for all modalities without special customization. In addition, we extract image features within the bounding box that joins a pair of tokens connected by a graph edge, capturing more targeted visual cues without loading a sophisticated and separately pre-trained image embedder. FormNetV2 establishes new state-of-the-art performance on FUNSD, CORD, SROIE and Payment benchmarks with a more compact model size.

We study domain-adaptive image synthesis, the problem of teaching pretrained image generative models a new style or concept from as few as one image to synthesize novel images, to better understand the compositional image synthesis. We present a framework that leverages a pretrained class-conditional generation model and visual prompt tuning. Specifically, we propose a novel source class distilled visual prompt that learns disentangled prompts of semantic (e.g., class) and domain (e.g., style) from a few images. Learned domain prompt is then used to synthesize images of any classes in the style of target domain. We conduct studies on various target domains with the number of images ranging from one to a few to many, and show qualitative results which show the compositional generalization of our method. Moreover, we show that our method can help improve zero-shot domain adaptation classification accuracy.