In this paper, we focus on enhancing a diffusion-based text-to-video (T2V) model during the post-training phase by distilling a highly capable consistency model from a pretrained T2V model. Our proposed method, T2V-Turbo-v2, introduces a significant advancement by integrating various supervision signals, including high-quality training data, reward model feedback, and conditional guidance, into the consistency distillation process. Through comprehensive ablation studies, we highlight the crucial importance of tailoring datasets to specific learning objectives and the effectiveness of learning from diverse reward models for enhancing both the visual quality and text-video alignment. Additionally, we highlight the vast design space of conditional guidance strategies, which centers on designing an effective energy function to augment the teacher ODE solver. We demonstrate the potential of this approach by extracting motion guidance from the training datasets and incorporating it into the ODE solver, showcasing its effectiveness in improving the motion quality of the generated videos with the improved motion-related metrics from VBench and T2V-CompBench. Empirically, our T2V-Turbo-v2 establishes a new state-of-the-art result on VBench, **with a Total score of 85.13**, surpassing proprietary systems such as Gen-3 and Kling.

Most multimodal large language models (MLLMs) learn language-to-object grounding through causal language modeling where grounded objects are captured by bounding boxes as sequences of location tokens. This paradigm lacks pixel-level representations that are important for fine-grained visual understanding and diagnosis. In this work, we introduce Groundhog, an MLLM developed by grounding Large Language Models to holistic segmentation. GROUNDHOG incorporates a masked feature extractor and converts extracted features into visual entity tokens for the MLLM backbone, which then connects groundable phrases to unified grounding masks by retrieving and merging the entity masks. To train GROUNDHOG, we carefully curated M3G2, a grounded visual instruction tuning dataset with Multi-Modal Multi-Grained Grounding, by harvesting a collection of segmentation-grounded datasets with rich annotations. Our experimental results show that GROUNDHOG achieves superior performance on various language grounding tasks without task-specific fine-tuning, and significantly reduces object hallucination. GROUNDHOG also demonstrates better grounding towards complex forms of visual input and provides easy-to-understand diagnosis in failure cases.

Prompt-based learning has been demonstrated as a compelling paradigm contributing to large language models’ tremendous success (LLMs). Inspired by their success in language tasks, existing research has leveraged LLMs in embodied instruction following and task planning. In this work, we tackle the problem of training a robot to understand multimodal prompts, interleaving vision signals with text descriptions. This type of task poses a major challenge to robots’ capability to understand the interconnection and complementarity between vision and language signals. In this work, we introduce an effective framework that learns a policy to perform robot manipulation with multimodal prompts from multi-task expert trajectories. Our methods consist of a two-stage training pipeline that performs inverse dynamics pretraining and multi-task finetuning. To facilitate multimodal understanding, we design our multimodal prompt encoder by augmenting a pretrained LM with a residual connection to the visual input and model the dependencies among action dimensions. Empirically, we evaluate the efficacy of our method on the VIMA-BENCH and establish a new state-of-the-art (10% improvement in success rate). Moreover, we demonstrate that our model exhibits remarkable in-context learning ability.

Understanding the continuous states of objects is essential for task learning and planning in the real world. However, most existing task learning benchmarks assume discrete (e.g., binary) object goal states, which poses challenges for the learning of complex tasks and transferring learned policy from simulated environments to the real world. Furthermore, state discretization limits a robot’s ability to follow human instructions based on the grounding of actions and states. To tackle these challenges, we present ARNOLD, a benchmark that evaluates language-grounded task learning with continuous states in realistic 3D scenes. ARNOLD is comprised of 8 language-conditioned tasks that involve understanding object states and learning policies for continuous goals. To promote language-instructed learning, we provide expert demonstrations with template-generated language descriptions. We assess task performance by utilizing the latest language-conditioned policy learning models. Our results indicate that current models for language-conditioned manipulations continue to experience significant challenges in novel goal-state generalizations, scene generalizations, and object generalizations. These findings highlight the need to develop new algorithms that address this gap and underscore the potential for further research in this area. Project website: https://arnold-benchmark.github.io.

We introduce Alexa Arena, a user-centric simulation platform to facilitate research in building assistive conversational embodied agents. Alexa Arena features multi-room layouts and an abundance of interactable objects. With user-friendly graphics and control mechanisms, the platform supports the development of gamified robotic tasks readily accessible to general human users, allowing high-efficiency data collection and EAI system evaluation. Along with the platform, we introduce a dialog-enabled task completion benchmark with online human evaluations.

Although partially autonomous driving (AD) systems are already available in production vehicles, drivers are still required to maintain a sufficient level of situational awareness (SA) during driving. Previous studies have shown that providing information about the AD’s capability using user interfaces can improve the driver’s SA. However, displaying too much information increases the driver’s workload and can distract or overwhelm the driver. Therefore, to design an efficient user interface (UI), it is necessary to understand its effect under different circumstances. In this paper, we focus on a UI based on augmented reality (AR), which can highlight potential hazards on the road. To understand the effect of highlighting on drivers’ SA for objects with different types and locations under various traffic densities, we conducted an in-person experiment with 20 participants on a driving simulator. Our study results show that the effects of highlighting on drivers’ SA varied by traffic densities, object locations and object types. We believe our study can provide guidance in selecting which object to highlight for the AR-based driver-assistance interface to optimize SA for drivers driving and monitoring partially autonomous vehicles.

Task-free attention has gained intensive interest in the computer vision community while relatively few works focus on task-driven attention (TDAttention). Thus this paper handles the problem of TDAttention prediction in daily scenarios where a human is doing a task. Motivated by the cognition mechanism that human attention allocation is jointly controlled by the top-down guidance and bottom-up stimulus, this paper proposes a cognitively-explanatory deep neural network model to predict TDAttention. Given an image sequence, bottom-up features, such as human pose and motion, are firstly extracted. At the same time, the coarse-grained task information and fine-grained task information are embedded as a top-down feature. The bottom-up features are then fused with the top-down feature to guide the model to predict TDAttention. Two public datasets are re-annotated to make them qualified for TDAttention prediction, and our model is widely compared with other models on the two datasets. In addition, some ablation studies are conducted to evaluate the individual modules in our model. Experiment results demonstrate the effectiveness of our model.

Human collaborators can effectively communicate with their partners to finish a common task by inferring each other's mental states (e.g., goals, beliefs, and desires). Such mind-aware communication minimizes the discrepancy among collaborators' mental states, and is crucial to the success in human ad-hoc teaming. We believe that robots collaborating with human users should demonstrate similar pedagogic behavior. Thus, in this paper, we propose a novel explainable AI (XAI) framework for achieving human-like communication in human-robot collaborations, where the robot builds a hierarchical mind model of the human user and generates explanations of its own mind as a form of communications based on its online Bayesian inference of the user's mental state. To evaluate our framework, we conduct a user study on a real-time human-robot cooking task. Experimental results show that the generated explanations of our approach significantly improves the collaboration performance and user perception of the robot. Code and video demos are available on our project website: https://xfgao.github.io/xCookingWeb/.

In this paper, we present a general framework for learning social affordance grammar as a spatiotemporal AND-OR graph (ST-AOG) from RGB-D videos of human interactions, and transfer the grammar to humanoids to enable a real-time motion inference for human-robot interaction (HRI). Based on Gibbs sampling, our weakly supervised grammar learning can automatically construct a hierarchical representation of an interaction with long-term joint sub-tasks of both agents and short term atomic actions of individual agents. Based on a new RGB-D video dataset with rich instances of human interactions, our experiments of Baxter simulation, human evaluation, and real Baxter test demonstrate that the model learned from limited training data successfully generates human-like behaviors in unseen scenarios and outperforms both baselines.