Vision Language Models (VLMs) have recently been leveraged to generate robotic actions, forming Vision-Language-Action (VLA) models. However, directly adapting a pretrained VLM for robotic control remains challenging, particularly when constrained by a limited number of robot demonstrations. In this work, we introduce LLaRA: Large Language and Robotics Assistant, a framework that formulates robot action policy as visuo-textual conversations and enables an efficient transfer of a pretrained VLM into a powerful VLA, motivated by the success of visual instruction tuning in Computer Vision. First, we present an automated pipeline to generate conversation-style instruction tuning data for robots from existing behavior cloning datasets, aligning robotic actions with image pixel coordinates. Further, we enhance this dataset in a self-supervised manner by defining six auxiliary tasks, without requiring any additional action annotations. We show that a VLM finetuned with a limited amount of such datasets can produce meaningful action decisions for robotic control. Through experiments across multiple simulated and real-world tasks, we demonstrate that LLaRA achieves state-of-the-art performance while preserving the generalization capabilities of large language models. The code, datasets, and pretrained models are available at https://github.com/LostXine/LLaRA.

Large Language Models (LLMs) have allowed recent LLM-based approaches to achieve excellent performance on long-video understanding benchmarks. We investigate how extensive world knowledge and strong reasoning skills of underlying LLMs influence this strong performance. Surprisingly, we discover that LLM-based approaches can yield surprisingly good accuracy on long-video tasks with limited video information, sometimes even with no video-specific information. Building on this, we explore injecting video-specific information into an LLM-based framework. We utilize off-the-shelf vision tools to extract three object-centric information modalities from videos, and then leverage natural language as a medium for fusing this information. Our resulting Multimodal Video Understanding (MVU) framework demonstrates state-of-the-art performance across multiple video understanding benchmarks. Strong performance also on robotics domain tasks establishes its strong generality. Code: github.com/kahnchana/mvu

Diffusion models have been adopted for behavioral cloning in a sequence modeling fashion, benefiting from their exceptional capabilities in modeling complex data distributions. The standard diffusion-based policy iteratively denoises action sequences from random noise conditioned on the input states and the model is typically trained with a singular diffusion loss. This paper explores the potential enhancements in such models when the denoising process is informed by a better visual representation. We study the scenario where the model is jointly optimized using the standard diffusion loss alongside an auxiliary objective based on self-supervised learning. After experimenting with various objectives, we introduce Crossway Diffusion, a simple yet effective way to enhance diffusion-based visuomotor policy learning via a state decoder and an auxiliary reconstruction objective. During training, the state decoder reconstructs raw image pixels and other states from the intermediate representations of the model. Experiments demonstrate the effectiveness of our method in various simulated and real-world tasks, confirming its consistent advantages over the standard diffusion-based policy and other baselines.

Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite their success, ViTs lack inductive biases, which can make it difficult to train them with limited data. To address this challenge, prior studies suggest training ViTs with self-supervised learning (SSL) and fine-tuning sequentially. However, we observe that jointly optimizing ViTs for the primary task and a Self-Supervised Auxiliary Task (SSAT) is surprisingly beneficial when the amount of training data is limited. We explore the appropriate SSL tasks that can be optimized alongside the primary task, the training schemes for these tasks, and the data scale at which they can be most effective. Our findings reveal that SSAT is a powerful technique that enables ViTs to leverage the unique characteristics of both the self-supervised and primary tasks, achieving better performance than typical ViTs pre-training with SSL and fine-tuning sequentially. Our experiments, conducted on 10 datasets, demonstrate that SSAT significantly improves ViT performance while reducing carbon footprint. We also confirm the effectiveness of SSAT in the video domain for deepfake detection, showcasing its generalizability. Our code is available at https://github.com/dominickrei/Limited-data-vits.

Reinforcement Learning (RL) can be considered as a sequence modeling task, where an agent employs a sequence of past state-action-reward experiences to predict a sequence of future actions. In this work, we propose State-Action-Reward Transformer (StARformer), a Transformer architecture for robot learning with image inputs, which explicitly models short-term state-action-reward representations (StAR-representations), essentially introducing a Markovian-like inductive bias to improve long-term modeling. StARformer first extracts StAR-representations using self-attending patches of image states, action, and reward tokens within a short temporal window. These StAR-representations are combined with pure image state representations, extracted as convolutional features, to perform self-attention over the whole sequence. Our experimental results show that StARformer outperforms the state-of-the-art Transformer-based method on image-based Atari and DeepMind Control Suite benchmarks, under both offline-RL and imitation learning settings. We find that models can benefit from our combination of patch-wise and convolutional image embeddings. StARformer is also more compliant with longer sequences of inputs than the baseline method. Finally, we demonstrate how StARformer can be successfully applied to a real-world robot imitation learning setting via a human-following task.

We investigate whether self-supervised learning (SSL) can improve online reinforcement learning (RL) from pixels. We extend the contrastive reinforcement learning framework (e.g., CURL) that jointly optimizes SSL and RL losses and conduct an extensive amount of experiments with various self-supervised losses. Our observations suggest that the existing SSL framework for RL fails to bring meaningful improvement over the baselines only taking advantage of image augmentation when the same amount of data and augmentation is used. We further perform evolutionary searches to find the optimal combination of multiple self-supervised losses for RL, but find that even such a loss combination fails to meaningfully outperform the methods that only utilize carefully designed image augmentations. After evaluating these approaches together in multiple different environments including a real-world robot environment, we confirm that no single self-supervised loss or image augmentation method can dominate all environments and that the current framework for joint optimization of SSL and RL is limited. Finally, we conduct the ablation study on multiple factors and demonstrate the properties of representations learned with different approaches.