Search

Current language models fall short in understanding aspects of the world not easily described in words, and struggle with complex, long-form tasks. Video sequences offer valuable temporal information absent in language and static images, making them attractive for joint modeling with language. Such models could develop a understanding of both human textual knowledge and the physical world, enabling broader AI capabilities for assisting humans. However, learning from millions of tokens of video and language sequences poses challenges due to memory constraints, computational complexity, and limited datasets. To address these challenges, we curate a large dataset of diverse videos and books, utilize the Blockwise RingAttention technique to scalably train on long sequences, and gradually increase context size from 4K to 1M tokens. This paper makes the following contributions: (a) Largest context size neural network: We train one of the largest context size transformers on long video and language sequences, setting new benchmarks in difficult retrieval tasks and long video understanding. (b) Solutions for overcoming vision-language training challenges, including using masked sequence packing for mixing different sequence lengths, loss weighting to balance language and vision, and model-generated QA dataset for long sequence chat. (c) A highly-optimized implementation with RingAttention, Blockwise Transformers, masked sequence packing, and other key features for training on millions-length multimodal sequences. (d) Fully open-sourced a family of 7B parameter models capable of processing long text documents (LWM-Text, LWM-Text-Chat) and videos (LWM, LWM-Chat) of over 1M tokens. This work paves the way for training on massive datasets of long video and language to develop understanding of both human knowledge and the multimodal world, and broader capabilities.

Current methods in training and benchmarking vision models exhibit an over-reliance on passive, curated datasets. Although models trained on these datasets have shown strong performance in a wide variety of tasks such as classification, detection, and segmentation, they fundamentally are unable to generalize to an ever-evolving world due to constant out-of-distribution shifts of input data. Therefore, instead of training on fixed datasets, can we approach learning in a more human-centric and adaptive manner? In this paper, we introduce Action-Aware Embodied Learning for Perception (ALP), an embodied learning framework that incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective. Our method actively explores in complex 3D environments to both learn generalizable task-agnostic visual representations as well as collect downstream training data. We show that ALP outperforms existing baselines in several downstream perception tasks. In addition, we show that by training on actively collected data more relevant to the environment and task, our method generalizes more robustly to downstream tasks compared to models pre-trained on fixed datasets such as ImageNet., Comment: project website available at https://xinranliang.github.io/alp/

Specifying reward signals that allow agents to learn complex behaviors is a long-standing challenge in reinforcement learning. A promising approach is to extract preferences for behaviors from unlabeled videos, which are widely available on the internet. We present Video Prediction Rewards (VIPER), an algorithm that leverages pretrained video prediction models as action-free reward signals for reinforcement learning. Specifically, we first train an autoregressive transformer on expert videos and then use the video prediction likelihoods as reward signals for a reinforcement learning agent. VIPER enables expert-level control without programmatic task rewards across a wide range of DMC, Atari, and RLBench tasks. Moreover, generalization of the video prediction model allows us to derive rewards for an out-of-distribution environment where no expert data is available, enabling cross-embodiment generalization for tabletop manipulation. We see our work as starting point for scalable reward specification from unlabeled videos that will benefit from the rapid advances in generative modeling. Source code and datasets are available on the project website: https://escontrela.me/viper, Comment: 22 pages, 18 figures, 4 tables. under review

Recent progress in scaling up large language models has shown impressive capabilities in performing few-shot learning across a wide range of text-based tasks. However, a key limitation is that these language models fundamentally lack visual perception - a crucial attribute needed to extend these models to be able to interact with the real world and solve vision tasks, such as in visual-question answering and robotics. Prior works have largely connected image to text through pretraining and/or fine-tuning on curated image-text datasets, which can be a costly and expensive process. In order to resolve this limitation, we propose a simple yet effective approach called Language-Quantized AutoEncoder (LQAE), a modification of VQ-VAE that learns to align text-image data in an unsupervised manner by leveraging pretrained language models (e.g., BERT, RoBERTa). Our main idea is to encode image as sequences of text tokens by directly quantizing image embeddings using a pretrained language codebook. We then apply random masking followed by a BERT model, and have the decoder reconstruct the original image from BERT predicted text token embeddings. By doing so, LQAE learns to represent similar images with similar clusters of text tokens, thereby aligning these two modalities without the use of aligned text-image pairs. This enables few-shot image classification with large language models (e.g., GPT-3) as well as linear classification of images based on BERT text features. To the best of our knowledge, our work is the first work that uses unaligned images for multimodal tasks by leveraging the power of pretrained language models., Comment: Fixed typos

To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. Current algorithms enable accurate predictions over short horizons but tend to suffer from temporal inconsistencies. When generated content goes out of view and is later revisited, the model invents different content instead. Despite this severe limitation, no established benchmarks on complex data exist for rigorously evaluating video generation with long temporal dependencies. In this paper, we curate 3 challenging video datasets with long-range dependencies by rendering walks through 3D scenes of procedural mazes, Minecraft worlds, and indoor scans. We perform a comprehensive evaluation of current models and observe their limitations in temporal consistency. Moreover, we introduce the Temporally Consistent Transformer (TECO), a generative model that substantially improves long-term consistency while also reducing sampling time. By compressing its input sequence into fewer embeddings, applying a temporal transformer, and expanding back using a spatial MaskGit, TECO outperforms existing models across many metrics. Videos are available on the website: https://wilson1yan.github.io/teco, Comment: Project website: https://wilson1yan.github.io/teco

In this work, we present Patch-based Object-centric Video Transformer (POVT), a novel region-based video generation architecture that leverages object-centric information to efficiently model temporal dynamics in videos. We build upon prior work in video prediction via an autoregressive transformer over the discrete latent space of compressed videos, with an added modification to model object-centric information via bounding boxes. Due to better compressibility of object-centric representations, we can improve training efficiency by allowing the model to only access object information for longer horizon temporal information. When evaluated on various difficult object-centric datasets, our method achieves better or equal performance to other video generation models, while remaining computationally more efficient and scalable. In addition, we show that our method is able to perform object-centric controllability through bounding box manipulation, which may aid downstream tasks such as video editing, or visual planning. Samples are available at https://sites.google.com/view/povt-public, Comment: Project Website: https://sites.google.com/view/povt-public

We present VideoGPT: a conceptually simple architecture for scaling likelihood based generative modeling to natural videos. VideoGPT uses VQ-VAE that learns downsampled discrete latent representations of a raw video by employing 3D convolutions and axial self-attention. A simple GPT-like architecture is then used to autoregressively model the discrete latents using spatio-temporal position encodings. Despite the simplicity in formulation and ease of training, our architecture is able to generate samples competitive with state-of-the-art GAN models for video generation on the BAIR Robot dataset, and generate high fidelity natural videos from UCF-101 and Tumbler GIF Dataset (TGIF). We hope our proposed architecture serves as a reproducible reference for a minimalistic implementation of transformer based video generation models. Samples and code are available at https://wilson1yan.github.io/videogpt/index.html, Comment: Project website: https://wilson1yan.github.io/videogpt/index.html

Using visual model-based learning for deformable object manipulation is challenging due to difficulties in learning plannable visual representations along with complex dynamic models. In this work, we propose a new learning framework that jointly optimizes both the visual representation model and the dynamics model using contrastive estimation. Using simulation data collected by randomly perturbing deformable objects on a table, we learn latent dynamics models for these objects in an offline fashion. Then, using the learned models, we use simple model-based planning to solve challenging deformable object manipulation tasks such as spreading ropes and cloths. Experimentally, we show substantial improvements in performance over standard model-based learning techniques across our rope and cloth manipulation suite. Finally, we transfer our visual manipulation policies trained on data purely collected in simulation to a real PR2 robot through domain randomization., Comment: Project website: https://sites.google.com/view/contrastive-predictive-model

Deep autoregressive models are one of the most powerful models that exist today which achieve state-of-the-art bits per dim. However, they lie at a strict disadvantage when it comes to controlled sample generation compared to latent variable models. Latent variable models such as VAEs and normalizing flows allow meaningful semantic manipulations in latent space, which autoregressive models do not have. In this paper, we propose using Fisher scores as a method to extract embeddings from an autoregressive model to use for interpolation and show that our method provides more meaningful sample manipulation compared to alternate embeddings such as network activations.

In this paper we tackle the problem of deformable object manipulation through model-free visual reinforcement learning (RL). In order to circumvent the sample inefficiency of RL, we propose two key ideas that accelerate learning. First, we propose an iterative pick-place action space that encodes the conditional relationship between picking and placing on deformable objects. The explicit structural encoding enables faster learning under complex object dynamics. Second, instead of jointly learning both the pick and the place locations, we only explicitly learn the placing policy conditioned on random pick points. Then, by selecting the pick point that has Maximal Value under Placing (MVP), we obtain our picking policy. This provides us with an informed picking policy during testing, while using only random pick points during training. Experimentally, this learning framework obtains an order of magnitude faster learning compared to independent action-spaces on our suite of deformable object manipulation tasks with visual RGB observations. Finally, using domain randomization, we transfer our policies to a real PR2 robot for challenging cloth and rope coverage tasks, and demonstrate significant improvements over standard RL techniques on average coverage., Comment: Project website: https://sites.google.com/view/alternating-pick-and-place