13 papers
End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers
Xingjian Li, Kelvin Kan, Deepanshu Verma +3
We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs). Incorporating CBFs…
Path Planning in Physically Viable World Models
Su Ann Low, Cheng-Hsi Hsiao, Xingjian Li +3
Robots deployed in unstructured outdoor environments often plan from scene reconstructions collected before deployment because operators cannot remap large or remote sites before e…
Physically Viable World Models: A Case for Query-Conditioned Embodied AI
Adam J. Thorpe, Stepan Tretiakov, Cheng-Hsi Hsiao +6
World models for embodied AI must be physically viable: constructed to answer intervention queries by representing the physical structure governing action outcomes, rather than mer…
Neural Operators for Multi-Task Control and Adaptation
David Sewell, Xingjian Li, Stepan Tretiakov +2
Neural operator methods have emerged as powerful tools for learning mappings between infinite-dimensional function spaces, yet their potential in optimal control remains largely un…
Learning Generalizable Neural Operators for Inverse Problems
Adam J. Thorpe, Stepan Tretiakov, Dibakar Roy Sarkar +2
Inverse problems challenge existing neural operator architectures because ill-posed inverse maps violate continuity, uniqueness, and stability assumptions. We introduce B2B${}^{-1}…
Zero-Shot Function Encoder-Based Differentiable Predictive Control
Hassan Iqbal, Xingjian Li, Tyler Ingebrand +4
We introduce a differentiable framework for zero-shot adaptive control over parametric families of nonlinear dynamical systems. Our approach integrates a function encoder-based neu…
Stability of Transformers under Layer Normalization
Kelvin Kan, Xingjian Li, Benjamin J. Zhang +4
Despite their widespread use, training deep Transformers can be unstable. Layer normalization, a standard component, improves training stability, but its placement has often been a…
Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems
Xingjian Li, Kelvin Kan, Deepanshu Verma +3
This paper presents a transferable solution method for optimal control problems with varying objectives using function encoder (FE) policies. Traditional optimization-based approac…
AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)
Danush Khanna, Gurucharan Marthi Krishna Kumar, Basab Ghosh +5
Adversarial threats against LLMs are escalating faster than current defenses can adapt. We expose a critical geometric blind spot in alignment: adversarial prompts exploit latent c…
SetONet: A Set-Based Operator Network for Solving PDEs with Variable-Input Sampling
Stepan Tretiakov, Xingjian Li, Krishna Kumar
Most neural-operator surrogates for PDEs inherit from DeepONet-style formulations the requirement that the input function be sampled at a fixed, ordered set of sensors. This assump…
MLPs and KANs for data-driven learning in physical problems: A performance comparison
Raghav Pant, Sikan Li, Xingjian Li +2
There is increasing interest in solving partial differential equations (PDEs) by casting them as machine learning problems. Recently, there has been a spike in exploring Kolmogorov…
Basis-to-Basis Operator Learning Using Function Encoders
Tyler Ingebrand, Adam J. Thorpe, Somdatta Goswami +2
We present Basis-to-Basis (B2B) operator learning, a novel approach for learning operators on Hilbert spaces of functions based on the foundational ideas of function encoders. We d…
3D Object Positioning Using Differentiable Multimodal Learning
Sean Zanyk-McLean, Krishna Kumar, Paul Navratil
This article describes a multi-modal method using simulated Lidar data via ray tracing and image pixel loss with differentiable rendering to optimize an object's position with resp…