NVILA: Efficient Frontier Visual Language Models

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to optimize both efficiency and accuracy. Building on top of VILA, we improve its model architecture by first scaling up the spatial and temporal resolutions, and then compressing visual tokens. This "scale-then-compress" approach enables NVILA to efficiently process high-resolution images and long videos. We also conduct a systematic investigation to enhance the efficiency of NVILA throughout its entire lifecycle, from training and fine-tuning to deployment. NVILA matches or surpasses the accuracy of many leading open and proprietary VLMs across a wide range of image and video benchmarks. At the same time, it reduces training costs by 4.5X, fine-tuning memory usage by 3.4X, pre-filling latency by 1.6-2.2X, and decoding latency by 1.2-2.8X. We will soon make our code and models available to facilitate reproducibility.

LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning

In recent years, instruction-tuned Large Multimodal Models (LMMs) have been successful at several tasks, including image captioning and visual question answering; yet leveraging these models remains an open question for robotics. Prior LMMs for robotics applications have been extensively trained on language and action data, but their ability to generalize in different settings has often been less than desired. To address this, we introduce LLARVA, a model trained with a novel instruction tuning method that leverages structured prompts to unify a range of robotic learning tasks, scenarios, and environments. Additionally, we show that predicting intermediate 2-D representations, which we refer to as "visual traces", can help further align vision and action spaces for robot learning. We generate 8.5M image-visual trace pairs from the Open X-Embodiment dataset in order to pre-train our model, and we evaluate on 12 different tasks in the RLBench simulator as well as a physical Franka Emika Panda 7-DoF robot. Our experiments yield strong performance, demonstrating that LLARVA - using 2-D and language representations - performs well compared to several contemporary baselines, and can generalize across various robot environments and configurations.

When Do We Not Need Larger Vision Models?

Scaling up the size of vision models has been the de facto standard to obtain more powerful visual representations. In this work, we discuss the point beyond which larger vision models are not necessary. First, we demonstrate the power of Scaling on Scales (S$^2$), whereby a pre-trained and frozen smaller vision model (e.g., ViT-B or ViT-L), run over multiple image scales, can outperform larger models (e.g., ViT-H or ViT-G) on classification, segmentation, depth estimation, Multimodal LLM (MLLM) benchmarks, and robotic manipulation. Notably, S$^2$ achieves state-of-the-art performance in detailed understanding of MLLM on the V* benchmark, surpassing models such as GPT-4V. We examine the conditions under which S$^2$ is a preferred scaling approach compared to scaling on model size. While larger models have the advantage of better generalization on hard examples, we show that features of larger vision models can be well approximated by those of multi-scale smaller models. This suggests most, if not all, of the representations learned by current large pre-trained models can also be obtained from multi-scale smaller models. Our results show that a multi-scale smaller model has comparable learning capacity to a larger model, and pre-training smaller models with S$^2$ can match or even exceed the advantage of larger models. We release a Python package that can apply S$^2$ on any vision model with one line of code: https://github.com/bfshi/scaling_on_scales.

Humanoid Locomotion as Next Token Prediction

We cast real-world humanoid control as a next token prediction problem, akin to predicting the next word in language. Our model is a causal transformer trained via autoregressive prediction of sensorimotor trajectories. To account for the multi-modal nature of the data, we perform prediction in a modality-aligned way, and for each input token predict the next token from the same modality. This general formulation enables us to leverage data with missing modalities, like video trajectories without actions. We train our model on a collection of simulated trajectories coming from prior neural network policies, model-based controllers, motion capture data, and YouTube videos of humans. We show that our model enables a full-sized humanoid to walk in San Francisco zero-shot. Our model can transfer to the real world even when trained on only 27 hours of walking data, and can generalize to commands not seen during training like walking backward. These findings suggest a promising path toward learning challenging real-world control tasks by generative modeling of sensorimotor trajectories.

Rethinking Patch Dependence for Masked Autoencoders

In this work, we re-examine inter-patch dependencies in the decoding mechanism of masked autoencoders (MAE). We decompose this decoding mechanism for masked patch reconstruction in MAE into self-attention and cross-attention. Our investigations suggest that self-attention between mask patches is not essential for learning good representations. To this end, we propose a novel pretraining framework: Cross-Attention Masked Autoencoders (CrossMAE). CrossMAE's decoder leverages only cross-attention between masked and visible tokens, with no degradation in downstream performance. This design also enables decoding only a small subset of mask tokens, boosting efficiency. Furthermore, each decoder block can now leverage different encoder features, resulting in improved representation learning. CrossMAE matches MAE in performance with 2.5 to 3.7$\times$ less decoding compute. It also surpasses MAE on ImageNet classification and COCO instance segmentation under the same compute. Code and models: https://crossmae.github.io

Recursive Visual Programming

Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities, especially in few-shot and zero-shot scenarios. However, existing VP methods generate all code in a single function, resulting in code that is suboptimal in terms of both accuracy and interpretability. Inspired by human coding practices, we propose Recursive Visual Programming (RVP), which simplifies generated routines, provides more efficient problem solving, and can manage more complex data structures. RVP is inspired by human coding practices and approaches VQA tasks with an iterative recursive code generation approach, allowing decomposition of complicated problems into smaller parts. Notably, RVP is capable of dynamic type assignment, i.e., as the system recursively generates a new piece of code, it autonomously determines the appropriate return type and crafts the requisite code to generate that output. We show RVP's efficacy through extensive experiments on benchmarks including VSR, COVR, GQA, and NextQA, underscoring the value of adopting human-like recursive and modular programming techniques for solving VQA tasks through coding.

LLM-grounded Video Diffusion Models

Text-conditioned diffusion models have emerged as a promising tool for neural video generation. However, current models still struggle with intricate spatiotemporal prompts and often generate restricted or incorrect motion (e.g., even lacking the ability to be prompted for objects moving from left to right). To address these limitations, we introduce LLM-grounded Video Diffusion (LVD). Instead of directly generating videos from the text inputs, LVD first leverages a large language model (LLM) to generate dynamic scene layouts based on the text inputs and subsequently uses the generated layouts to guide a diffusion model for video generation. We show that LLMs are able to understand complex spatiotemporal dynamics from text alone and generate layouts that align closely with both the prompts and the object motion patterns typically observed in the real world. We then propose to guide video diffusion models with these layouts by adjusting the attention maps. Our approach is training-free and can be integrated into any video diffusion model that admits classifier guidance. Our results demonstrate that LVD significantly outperforms its base video diffusion model and several strong baseline methods in faithfully generating videos with the desired attributes and motion patterns.

Robot Learning with Sensorimotor Pre-training

We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. Given a sequence of camera images, proprioceptive robot states, and past actions, we encode the interleaved sequence into tokens, mask out a random subset, and train a model to predict the masked-out content. We hypothesize that if the robot can predict the missing content it has acquired a good model of the physical world that can enable it to act. RPT is designed to operate on latent visual representations which makes prediction tractable, enables scaling to 10x larger models, and 10 Hz inference on a real robot. To evaluate our approach, we collect a dataset of 20,000 real-world trajectories over 9 months using a combination of motion planning and model-based grasping algorithms. We find that pre-training on this data consistently outperforms training from scratch, leads to 2x improvements in the block stacking task, and has favorable scaling properties.

Refocusing Is Key to Transfer Learning

Transfer learning involves adapting a pre-trained model to novel downstream tasks. However, we observe that current transfer learning methods often fail to focus on task-relevant features. In this work, we emphasize the importance of refocusing the attention in transfer learning. We introduce Top-Down Attention Steering (TOAST), a novel transfer learning algorithm that keeps the pre-trained backbone frozen, while selecting the task-relevant elements in the output and feeding them back to the model to steer its attention to the task-specific features. By refocusing the attention only, TOAST achieves state-of-the-art results on a number of transfer learning benchmarks, while having a small portion of tunable parameters. Compared to fully fine-tuning, LoRA, and prompt tuning, TOAST substantially improves performance across a range of fine-grained visual classification datasets (e.g., 81.1% -> 86.2% on FGVC). TOAST also outperforms the fully fine-tuned Alpaca model on instruction-following language generation. Code is available at https://github.com/bfshi/TOAST.

Top-Down Visual Attention from Analysis by Synthesis

Current attention algorithms (e.g., self-attention) are stimulus-driven and highlight all the salient objects in an image. However, intelligent agents like humans often guide their attention based on the high-level task at hand, focusing only on task-related objects. This ability of task-guided top-down attention provides task-adaptive representation and helps the model generalize to various tasks. In this paper, we consider top-down attention from a classic Analysis-by-Synthesis (AbS) perspective of vision. Prior work indicates a functional equivalence between visual attention and sparse reconstruction; we show that an AbS visual system that optimizes a similar sparse reconstruction objective modulated by a goal-directed top-down signal naturally simulates top-down attention. We further propose Analysis-by-Synthesis Vision Transformer (AbSViT), which is a top-down modulated ViT model that variationally approximates AbS, and achieves controllable top-down attention. For real-world applications, AbSViT consistently improves over baselines on Vision-Language tasks such as VQA and zero-shot retrieval where language guides the top-down attention. AbSViT can also serve as a general backbone, improving performance on classification, semantic segmentation, and model robustness.