Related papers: Action Agent: Agentic Video Generation Meets Flow-…
With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many…
In visual semantic navigation, the robot navigates to a target object with egocentric visual observations and the class label of the target is given. It is a meaningful task inspiring a surge of relevant research. However, most of the…
Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity…
The emergence of agent-to-agent communication protocols mirrors the early internet: powerful connectivity with minimal security infrastructure. When AI agents communicate on behalf of users, every message crosses a trust boundary where the…
Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large language models offer new avenues to support users with this task. While existing…
Simulation has become a key tool for training and evaluating home robots at scale, yet existing environments fail to capture the diversity and physical complexity of real indoor spaces. Current scene synthesis methods produce sparsely…
A unified video and action model holds significant promise for robotics, where videos provide rich scene information for action prediction, and actions provide dynamics information for video prediction. However, effectively combining video…
Generating instructional images of human daily actions from an egocentric viewpoint serves as a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to…
Realistic and interactive scene simulation is a key prerequisite for autonomous vehicle (AV) development. In this work, we present SceneDiffuser, a scene-level diffusion prior designed for traffic simulation. It offers a unified framework…
Generating programmatic animation using libraries such as Manim presents unique challenges for Large Language Models (LLMs), requiring spatial reasoning, temporal sequencing, and familiarity with domain-specific APIs that are…
Executing language-conditioned tasks in dynamic visual environments remains a central challenge in embodied AI. Existing Vision-Language-Action (VLA) models predominantly adopt reactive state-to-action mappings, often leading to…
Building general-purpose embodied agents across diverse hardware remains a central challenge in robotics, often framed as the ''one-brain, many-forms'' paradigm. Progress is hindered by fragmented data, inconsistent representations, and…
Owing to powerful natural language processing and generative capabilities, large language model (LLM) agents have emerged as a promising solution for enhancing recommendation systems via user simulation. However, in the realm of video…
Video understanding has seen significant progress in recent years, with models' performance on perception from short clips continuing to rise. Yet, multiple recent benchmarks, such as LVBench, Neptune, and ActivityNet-RTL, show performance…
Computer-aided design (CAD) is a promising application area for emerging artificial intelligence methods. Traditional workflows for cyberphysical systems create detailed digital models which can be evaluated by physics simulators in order…
With the advancement of Multimodal Large Language Models (MLLM), LLM-driven visual agents are increasingly impacting software interfaces, particularly those with graphical user interfaces. This work introduces a novel LLM-based multimodal…
While recent image-based human animation methods achieve realistic body and facial motion synthesis, critical gaps remain in fine-grained holistic controllability, multi-scale adaptability, and long-term temporal coherence, which leads to…
We present 3D FlowMatch Actor (3DFA), a 3D policy architecture for robot manipulation that combines flow matching for trajectory prediction with 3D pretrained visual scene representations for learning from demonstration. 3DFA leverages 3D…
Humanoid agents are expected to emulate the complex coordination inherent in human social behaviors. However, existing methods are largely confined to single-agent scenarios, overlooking the physically plausible interplay essential for…
Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for users to iteratively generate and manipulate videos. However,…