6 papers
Extrapolating escape dynamics from non-escaping trajectories in Hamiltonian systems
Jianming Liu, Zhicheng Tong
Hamiltonian systems exhibit rich dynamical behaviors, among which escape is a typical phenomenon. Below the escape threshold, trajectories initiated inside the central potential we…
Admissible Diffusion for Multimodal Interventional Trajectories
Xing Han, Shravan Chaudhari, Jiarui Shao +2
Generating a plausible clinical trajectory does not establish what would happen under a different treatment. We present ADMIT, a framework combining irregular multimodal representa…
FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
Xing Han, Shravan Chaudhari, Tanvi Ranade +2
Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, tasks are co-available at des…
Open-Set Domain Adaptation Under Background Distribution Shift: Challenges and A Provably Efficient Solution
Shravan Chaudhari, Yoav Wald, Suchi Saria
As we deploy machine learning systems in the real world, a core challenge is to maintain a model that is performant even as the data shifts. Such shifts can take many forms: new cl…
Between Linear and Sinusoidal: Rethinking the Time Encoder in Dynamic Graph Learning
Hsing-Huan Chung, Shravan Chaudhari, Xing Han +3
Dynamic graph learning is essential for applications involving temporal networks and requires effective modeling of temporal relationships. Seminal attention-based models like TGAT…
Novel Node Category Detection Under Subpopulation Shift
Hsing-Huan Chung, Shravan Chaudhari, Yoav Wald +2
In real-world graph data, distribution shifts can manifest in various ways, such as the emergence of new categories and changes in the relative proportions of existing categories.…