Related papers: OmniFysics: Towards Physical Intelligence Evolutio…
Understanding the dynamic physical world, characterized by its evolving 3D structure, real-world motion, and semantic content with textual descriptions, is crucial for human-agent interaction and enables embodied agents to perceive and act…
We introduce OmniSource, a novel framework for leveraging web data to train video recognition models. OmniSource overcomes the barriers between data formats, such as images, short videos, and long untrimmed videos for webly-supervised…
The convergence of cross-modal adversarial learning and physics-driven methods represents a cutting-edge direction for tackling challenges in complex multi-modal tasks and scientific computing. This review focuses on systematically…
The diversity and complementarity of sensors available for Earth Observations (EO) calls for developing bespoke self-supervised multimodal learning approaches. However, current multimodal EO datasets and models typically focus on a single…
Multimodal physiological signals, such as EEG, ECG, EOG, and EMG, are crucial for healthcare and brain-computer interfaces. While existing methods rely on specialized architectures and dataset-specific fusion strategies, they struggle to…
Omni-proactive streaming video understanding, i.e., autonomously deciding when to speak and what to say from continuous audio-visual streams, is an emerging capability of omni-modal large language models. Existing benchmarks fall short in…
The field of 4D world modeling - aiming to jointly capture spatial geometry and temporal dynamics - has witnessed remarkable progress in recent years, driven by advances in large-scale generative models and multimodal learning. However, the…
Recent advances in omni-modal large language models have enabled remarkable progress in joint vision-audio understanding. However, prevailing architectures rely on modality-specific encoders with a \emph{video-coarse, audio-dense} design --…
Autonomous driving has seen remarkable advancements, largely driven by extensive real-world data collection. However, acquiring diverse and corner-case data remains costly and inefficient. Generative models have emerged as a promising…
We are perceiving and communicating with the world in a multisensory manner, where different information sources are sophisticatedly processed and interpreted by separate parts of the human brain to constitute a complex, yet harmonious and…
Scalable and generalizable physics-aware deep learning has long been considered a significant challenge with various applications across diverse domains ranging from robotics to molecular dynamics. Central to almost all physical systems are…
Learning motion tracking from rich human motion data is a foundational task for achieving general control in humanoid robots, enabling them to perform diverse behaviors. However, discrepancies in morphology and dynamics between humans and…
Camera control, which achieves diverse visual effects by changing camera position and pose, has attracted widespread attention. However, existing methods face challenges such as complex interaction and limited control capabilities. To…
Scaling data and artificial neural networks has transformed AI, driving breakthroughs in language and vision. Whether similar principles apply to modeling brain activity remains unclear. Here we leveraged a dataset of 3.1 million neurons…
Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials. These networks harness the distinctive characteristics of physical systems to carry out computations effectively,…
Data centers (DCs) as mission-critical infrastructures are pivotal in powering the growth of artificial intelligence (AI) and the digital economy. The evolution from Internet DC to AI DC has introduced new challenges in operating and…
We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be…
Multimodal deepfakes are proliferating on social media and threaten authenticity, information integrity, and digital forensics. Existing benchmarks are constrained by their single-modality scope, simplified manipulations, or unrealistic…
We present OmniBooth, an image generation framework that enables spatial control with instance-level multi-modal customization. For all instances, the multimodal instruction can be described through text prompts or image references. Given a…
Whole-body humanoid teleoperation enables humans to remotely control humanoid robots, serving as both a real-time operational tool and a scalable engine for collecting demonstrations for autonomous learning. Despite recent advances,…