AI Applications

SMART: a novel self-supervised model tackles missing EHR data, improving patient health status prediction via missing-aware attention and robust pre-training.

SMART: a scalable, real-time multi-agent driving simulator using next-token prediction, achieves state-of-the-art results and zero-shot generalization.

SmMIL enhances medical image classification by introducing a novel smooth operator to improve instance-level localization in multiple instance learning, achieving state-of-the-art results.

MeshRet: A novel retargeting framework that uses dense geometric interaction modeling for realistic, artifact-free skinned character animation.

SimGen: Simulator-conditioned driving scene generation, uses a novel cascade diffusion pipeline to generate diverse driving scenes by mixing real-world and simulator data, addressing Sim2Real gaps.

IDA, a novel intervention assistance, dynamically shares control between human and AI copilots by intervening only when the AI’s action is superior across all goals, maximizing performance and preserv…

Sequence-augmented SE(3)-Flow model, FOLDFLOW-2, excels at generating diverse, designable protein structures, surpassing existing methods in unconditional and conditional design tasks.

Learning-based semantic routing, a scalable approach to route planning using rich user queries, is introduced, accompanied by a large-scale public benchmark and a proof-of-concept model demonstrating …

Self-Calibrating Conformal Prediction (SC-CP) marries model calibration and conformal prediction for more efficient and interpretable prediction intervals with prediction-conditional validity.

SeeA* enhances A* search by selectively sampling promising nodes, improving exploration and efficiency, especially with less accurate heuristics.

SceneDiffuser: a scene-level diffusion model revolutionizes driving simulation by uniting scene initialization and rollout, enabling efficient and controllable closed-loop traffic generation.

SCaR refines skill chaining for long-horizon robotic manipulation via dual regularization, achieving higher success rates and robustness.

Heterogeneous Pre-trained Transformers (HPT) enables robots to learn generalizable policies from diverse data, drastically improving performance on unseen tasks.

Satformer: a novel neural network accurately estimates satellite network traffic using an adaptive sparse spatio-temporal attention mechanism, outperforming existing methods.

TVSAFEOPT: Safe time-varying optimization using spatio-temporal kernels ensures safety while tracking time-varying reward and safety functions, providing optimality guarantees in stationary settings.

RoME, a robust contextual bandit algorithm, leverages mixed-effects modeling and debiased machine learning to optimize personalized mobile health interventions, achieving superior performance in simul…

CIMSleepNet: a novel framework for robust sleep staging from incomplete multimodal physiological signals using contrastive imagination.

Garner, a novel framework, enhances road network representation learning by incorporating the Third Law of Geography, significantly boosting performance in downstream tasks.

RL-GPT seamlessly integrates Large Language Models (LLMs) and Reinforcement Learning (RL) to create highly efficient agents mastering complex tasks in open-world environments.

Reaction-GFlowNet (RGFN) revolutionizes small molecule discovery by generating synthesizable molecules directly within the chemical reaction space, dramatically expanding the search space for drug dis…