AI Applications

Optimus-1: Hybrid Multimodal Memory empowers AI agents to excel in complex, long-horizon tasks by integrating hierarchical knowledge graphs and multimodal experience for superior planning and reflecti…

This paper introduces a novel, robust online control framework for managing evolving populations, achieving near-optimal control even in complex, noisy systems.

New large-scale dataset and model boost on-road object importance estimation accuracy by 23.1%!

Omnigrasp: A novel RL-based method enables simulated humanoids to grasp diverse objects and precisely follow complex trajectories, advancing realistic human-object interaction in virtual environments.

First-Glance Off-Policy Selection (FPS) revolutionizes human-centric AI by enabling personalized policy selection for new participants without prior data, improving learning and healthcare outcomes.

Newton Informed Neural Operator efficiently solves nonlinear PDEs with multiple solutions by learning the Newton solver, enabling faster computation and the discovery of new solutions with limited dat…

NeuralSteiner uses deep learning to predict Steiner points for efficient, overflow-avoiding global routing in chip design, achieving up to a 99.8% overflow reduction on large benchmarks.

NeuralFluid: Design & control complex fluidic systems with dynamic boundaries using differentiable simulation, achieving superior results in benchmark tasks.

MotionTTT: Deep learning enables accurate 3D motion-corrected MRI by cleverly estimating motion parameters during test-time training, significantly improving image reconstruction.

RealMotion: a novel motion forecasting framework for continuous driving that outperforms existing methods by accumulating historical scene information and sequentially refining predictions, achieving …

Model-Based Transfer Learning (MBTL) boosts deep RL sample efficiency by strategically selecting training tasks, achieving up to 50x improvement over traditional methods.

Model-Based Diffusion (MBD) uses diffusion processes and model information for data-free trajectory optimization, outperforming existing methods on complex tasks.

MGF: Mixed Gaussian Flow enhances trajectory prediction by using a mixed Gaussian prior, achieving state-of-the-art diversity and alignment accuracy.

MeMo: a novel framework for pretraining meaningful, modular robot controllers via noise injection, enabling efficient transfer learning across different robot morphologies and tasks.

MeLLoC: Mechanism Learning for Lossless Compression, a novel approach that combines high-order mechanism learning with classical encoding, significantly improves lossless compression for scientific da…

Medformer: A novel multi-granularity patching transformer achieves state-of-the-art performance in medical time series classification, excelling in challenging subject-independent settings.

Med-Real2Sim uses physics-informed self-supervised learning to build non-invasive medical digital twins, enabling in-silico clinical trials and unsupervised disease detection.

Make-An-Agent generates high-performing robotic control policies from single behavioral demonstrations using behavior-prompted diffusion, showcasing impressive generalization and real-world applicabil…

ALTER, a novel brain graph transformer, leverages long-range dependencies to achieve state-of-the-art accuracy in neurological disease diagnosis.

LLaMAR: LM-based planner for multi-agent robots excels in long-horizon, partially observable tasks, achieving 30% higher success than existing methods.