Abstract:Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle images, text, video, and audio for various tasks such as image captioning, question answering, and image generation. In this work, we explore discrete diffusion models as a unified generative formulation in the joint text and image domain, building upon their recent success in text generation. Discrete diffusion models offer several advantages over AR models, including improved control over quality versus diversity of generated samples, the ability to perform joint multimodal inpainting (across both text and image domains), and greater controllability in generation through guidance. Leveraging these benefits, we present the first Unified Multimodal Discrete Diffusion (UniDisc) model which is capable of jointly understanding and generating text and images for a variety of downstream tasks. We compare UniDisc to multimodal AR models, performing a scaling analysis and demonstrating that UniDisc outperforms them in terms of both performance and inference-time compute, enhanced controllability, editability, inpainting, and flexible trade-off between inference time and generation quality. Code and additional visualizations are available at https://unidisc.github.io.
Abstract:Progress in 3D vision-language learning has been hindered by the scarcity of large-scale 3D datasets. We introduce UniVLG, a unified architecture for 2D and 3D vision-language understanding that bridges the gap between existing 2D-centric models and the rich 3D sensory data available in embodied systems. Our approach initializes most model weights from pre-trained 2D models and trains on both 2D and 3D vision-language data. We propose a novel language-conditioned mask decoder shared across 2D and 3D modalities to ground objects effectively in both RGB and RGB-D images, outperforming box-based approaches. To further reduce the domain gap between 2D and 3D, we incorporate 2D-to-3D lifting strategies, enabling UniVLG to utilize 2D data to enhance 3D performance. With these innovations, our model achieves state-of-the-art performance across multiple 3D vision-language grounding tasks, demonstrating the potential of transferring advances from 2D vision-language learning to the data-constrained 3D domain. Furthermore, co-training on both 2D and 3D data enhances performance across modalities without sacrificing 2D capabilities. By removing the reliance on 3D mesh reconstruction and ground-truth object proposals, UniVLG sets a new standard for realistic, embodied-aligned evaluation. Code and additional visualizations are available at $\href{https://univlg.github.io}{univlg.github.io}$.
Abstract:Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame. Recent advances in single-image depth estimation, brought about by the rise of large foundation models and the use of synthetic training data, have fueled a renewed interest in video depth. However, naively applying a single-image depth estimator to every frame of a video disregards temporal continuity, which not only leads to flickering but may also break when camera motion causes sudden changes in depth range. An obvious and principled solution would be to build on top of video foundation models, but these come with their own limitations; including expensive training and inference, imperfect 3D consistency, and stitching routines for the fixed-length (short) outputs. We take a step back and demonstrate how to turn a single-image latent diffusion model (LDM) into a state-of-the-art video depth estimator. Our model, which we call RollingDepth, has two main ingredients: (i) a multi-frame depth estimator that is derived from a single-image LDM and maps very short video snippets (typically frame triplets) to depth snippets. (ii) a robust, optimization-based registration algorithm that optimally assembles depth snippets sampled at various different frame rates back into a consistent video. RollingDepth is able to efficiently handle long videos with hundreds of frames and delivers more accurate depth videos than both dedicated video depth estimators and high-performing single-frame models. Project page: rollingdepth.github.io.
Abstract:Learning from Demonstrations, the field that proposes to learn robot behavior models from data, is gaining popularity with the emergence of deep generative models. Although the problem has been studied for years under names such as Imitation Learning, Behavioral Cloning, or Inverse Reinforcement Learning, classical methods have relied on models that don't capture complex data distributions well or don't scale well to large numbers of demonstrations. In recent years, the robot learning community has shown increasing interest in using deep generative models to capture the complexity of large datasets. In this survey, we aim to provide a unified and comprehensive review of the last year's progress in the use of deep generative models in robotics. We present the different types of models that the community has explored, such as energy-based models, diffusion models, action value maps, or generative adversarial networks. We also present the different types of applications in which deep generative models have been used, from grasp generation to trajectory generation or cost learning. One of the most important elements of generative models is the generalization out of distributions. In our survey, we review the different decisions the community has made to improve the generalization of the learned models. Finally, we highlight the research challenges and propose a number of future directions for learning deep generative models in robotics.
Abstract:We have made significant progress towards building foundational video diffusion models. As these models are trained using large-scale unsupervised data, it has become crucial to adapt these models to specific downstream tasks. Adapting these models via supervised fine-tuning requires collecting target datasets of videos, which is challenging and tedious. In this work, we utilize pre-trained reward models that are learned via preferences on top of powerful vision discriminative models to adapt video diffusion models. These models contain dense gradient information with respect to generated RGB pixels, which is critical to efficient learning in complex search spaces, such as videos. We show that backpropagating gradients from these reward models to a video diffusion model can allow for compute and sample efficient alignment of the video diffusion model. We show results across a variety of reward models and video diffusion models, demonstrating that our approach can learn much more efficiently in terms of reward queries and computation than prior gradient-free approaches. Our code, model weights,and more visualization are available at https://vader-vid.github.io.
Abstract:Large-scale generative language and vision-language models (LLMs and VLMs) excel in few-shot in-context learning for decision making and instruction following. However, they require high-quality exemplar demonstrations to be included in their context window. In this work, we ask: Can LLMs and VLMs generate their own prompt examples from generic, sub-optimal demonstrations? We propose In-Context Abstraction Learning (ICAL), a method that builds a memory of multimodal experience insights from sub-optimal demonstrations and human feedback. Given a noisy demonstration in a new domain, VLMs abstract the trajectory into a general program by fixing inefficient actions and annotating cognitive abstractions: task relationships, object state changes, temporal subgoals, and task construals. These abstractions are refined and adapted interactively through human feedback while the agent attempts to execute the trajectory in a similar environment. The resulting abstractions, when used as exemplars in the prompt, significantly improve decision-making in retrieval-augmented LLM and VLM agents. Our ICAL agent surpasses the state-of-the-art in dialogue-based instruction following in TEACh, multimodal web agents in VisualWebArena, and action anticipation in Ego4D. In TEACh, we achieve a 12.6% improvement in goal-condition success. In VisualWebArena, our task success rate improves over the SOTA from 14.3% to 22.7%. In Ego4D action forecasting, we improve over few-shot GPT-4V and remain competitive with supervised models. We show finetuning our retrieval-augmented in-context agent yields additional improvements. Our approach significantly reduces reliance on expert-crafted examples and consistently outperforms in-context learning from action plans that lack such insights.
Abstract:Existing VLMs can track in-the-wild 2D video objects while current generative models provide powerful visual priors for synthesizing novel views for the highly under-constrained 2D-to-3D object lifting. Building upon this exciting progress, we present DreamScene4D, the first approach that can generate three-dimensional dynamic scenes of multiple objects from monocular in-the-wild videos with large object motion across occlusions and novel viewpoints. Our key insight is to design a "decompose-then-recompose" scheme to factorize both the whole video scene and each object's 3D motion. We first decompose the video scene by using open-vocabulary mask trackers and an adapted image diffusion model to segment, track, and amodally complete the objects and background in the video. Each object track is mapped to a set of 3D Gaussians that deform and move in space and time. We also factorize the observed motion into multiple components to handle fast motion. The camera motion can be inferred by re-rendering the background to match the video frames. For the object motion, we first model the object-centric deformation of the objects by leveraging rendering losses and multi-view generative priors in an object-centric frame, then optimize object-centric to world-frame transformations by comparing the rendered outputs against the perceived pixel and optical flow. Finally, we recompose the background and objects and optimize for relative object scales using monocular depth prediction guidance. We show extensive results on the challenging DAVIS, Kubric, and self-captured videos, detail some limitations, and provide future directions. Besides 4D scene generation, our results show that DreamScene4D enables accurate 2D point motion tracking by projecting the inferred 3D trajectories to 2D, while never explicitly trained to do so.
Abstract:Recent research on instructable agents has used memory-augmented Large Language Models (LLMs) as task planners, a technique that retrieves language-program examples relevant to the input instruction and uses them as in-context examples in the LLM prompt to improve the performance of the LLM in inferring the correct action and task plans. In this technical report, we extend the capabilities of HELPER, by expanding its memory with a wider array of examples and prompts, and by integrating additional APIs for asking questions. This simple expansion of HELPER into a shared memory enables the agent to work across the domains of executing plans from dialogue, natural language instruction following, active question asking, and commonsense room reorganization. We evaluate the agent on four diverse interactive visual-language embodied agent benchmarks: ALFRED, TEACh, DialFRED, and the Tidy Task. HELPER-X achieves few-shot, state-of-the-art performance across these benchmarks using a single agent, without requiring in-domain training, and remains competitive with agents that have undergone in-domain training.
Abstract:Significant progress has been made in training multimodal trajectory forecasting models for autonomous driving. However, effectively integrating these models with downstream planners and model-based control approaches is still an open problem. Although these models have conventionally been evaluated for open-loop prediction, we show that they can be used to parameterize autoregressive closed-loop models without retraining. We consider recent trajectory prediction approaches which leverage learned anchor embeddings to predict multiple trajectories, finding that these anchor embeddings can parameterize discrete and distinct modes representing high-level driving behaviors. We propose to perform fully reactive closed-loop planning over these discrete latent modes, allowing us to tractably model the causal interactions between agents at each step. We validate our approach on a suite of more dynamic merging scenarios, finding that our approach avoids the $\textit{frozen robot problem}$ which is pervasive in conventional planners. Our approach also outperforms the previous state-of-the-art in CARLA on challenging dense traffic scenarios when evaluated at realistic speeds.
Abstract:We marry diffusion policies and 3D scene representations for robot manipulation. Diffusion policies learn the action distribution conditioned on the robot and environment state using conditional diffusion models. They have recently shown to outperform both deterministic and alternative state-conditioned action distribution learning methods. 3D robot policies use 3D scene feature representations aggregated from a single or multiple camera views using sensed depth. They have shown to generalize better than their 2D counterparts across camera viewpoints. We unify these two lines of work and present 3D Diffuser Actor, a neural policy architecture that, given a language instruction, builds a 3D representation of the visual scene and conditions on it to iteratively denoise 3D rotations and translations for the robot's end-effector. At each denoising iteration, our model represents end-effector pose estimates as 3D scene tokens and predicts the 3D translation and rotation error for each of them, by featurizing them using 3D relative attention to other 3D visual and language tokens. 3D Diffuser Actor sets a new state-of-the-art on RLBench with an absolute performance gain of 16.3% over the current SOTA on a multi-view setup and an absolute gain of 13.1% on a single-view setup. On the CALVIN benchmark, it outperforms the current SOTA in the setting of zero-shot unseen scene generalization by being able to successfully run 0.2 more tasks, a 7% relative increase. It also works in the real world from a handful of demonstrations. We ablate our model's architectural design choices, such as 3D scene featurization and 3D relative attentions, and show they all help generalization. Our results suggest that 3D scene representations and powerful generative modeling are keys to efficient robot learning from demonstrations.