24 papers
Tracking Is Not Permanence: What Video World Models Keep of a Hidden Object
Peng Xie, Amr Alanwar
Video world models track objects they can see; we ask what they keep of objects they cannot. We hide an object from a frozen V-JEPA 2 predictor and compare its prediction for the h…
JEPA Learns What the Mask Leaves Unrecoverable
Peng Xie, Amr Alanwar
Joint-embedding predictive architectures are unusually sensitive to how the input is masked: block masks work, scattered masks do not, and the explanations are empirical. We give a…
Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and Cognition
Peng Xie, Amr Alanwar
Language models compute over tokens: language is their input, their output, and increasingly their internal representation. Whether language should keep all of these positions depe…
Sampling-based Certified Planning with Graphs of Convex Sets
Peng Xie, Amr Alanwar
Planners on graphs of convex sets return trajectories that are collision-free by construction, provided the convex regions are collision-free. The region generator only promises th…
Margin-Drop Coordinates for Cross-Budget Robustness Evaluation
Yanliang Huang, Zhen Zhang, Peng Xie +4
Fixed-budget robustness evaluation can select the wrong frozen vision encoder. An encoder that survives a shallow attack may lose most of that robustness when the same evaluation i…
CompCPZ: Preserving Multi-Modal Intent in Language-Guided Robot Manipulation
Zhen Zhang, Ahmad Hafez, Peng Xie +3
A robot asked to "place the cup near the red plate or the blue plate" may reach the centroid between them and appear geometrically successful, while satisfying neither disjunct of…
Certified Mechanistic Interpretability: Lifting Single-Input Findings to Bounded Neighbourhoods
Zhen Zhang, Yanliang Huang, Peng Xie +2
Mechanistic interpretability reverse-engineers transformer circuits one input at a time, leaving observed mechanisms without guarantees over bounded input neighbourhoods. We addres…
Probabilistic Reachable-Action Verification of Visuomotor Policies via Set-Based Training
Yanliang Huang, Zhuocheng Zhang, Peng Xie +5
Reachability analysis for visuomotor policies is difficult because large visual encoders make end-to-end set propagation computationally expensive and excessively conservative. We…
Certifying Plans under Model Mismatch: A Trilemma for Reachability from Scarce Data
Yanliang Huang, Zhen Zhang, Ahmad Hafez +4
Sim-to-real policies are designed under nominal dynamics, but target-system trials may yield only a few isolated one-step transitions. We study pre-execution certification of a fix…
Data-Driven Reachability Analysis Using Matrix Perturbation Theory
Peng Xie, Abdulla Fawzy, Zhen Zhang +1
We propose a matrix zonotope perturbation framework that leverages matrix perturbation theory to characterize how noise-induced distortions alter the dynamics within sets of models…
Orthogonal Transformations for Efficient Data-Driven Reachability Analysis
Peng Xie, Amr Alanwar
Data-driven reachability analysis using matrix zonotopes faces a fundamental challenge: the number of generators in the reachable set grows exponentially during propagation, while…
From Points to Sets: Set-Based Safety Verification in the Latent Space
Wenyuan Wu, Peng Xie, Zhen Zhang +3
We extend latent representation methods for safety control design to set-valued states. Recent work has shown that barrier functions designed in a learned latent space can transfer…
Bridging Data-Driven Reachability Analysis and Statistical Estimation via Constrained Matrix Convex Generators
Peng Xie, Zhen Zhang, Rolf Findeisen +1
Data-driven reachability analysis enables safety verification when first-principles models are unavailable. This requires constructing sets of system models consistent with measure…
Data-Driven Reachability Analysis with Optimal Input Design
Peng Xie, Davide M. Raimondo, Rolf Findeisen +1
This paper addresses the conservatism in data-driven reachability analysis for discrete-time linear systems subject to bounded process noise, where the system matrices are unknown…
Transformer-Enhanced Data-Driven Output Reachability with Conformal Coverage Guarantees
Zhen Zhang, Peng Xie, Wenyuan Wu +2
This paper considers output reachability analysis for linear time-invariant systems with unknown state-space matrices and unknown observation map, given only noisy input-output mea…
Transformer-Accelerated Interpolated Data-Driven Reachability Analysis from Noisy Data
Zhen Zhang, Ahmad Hafez, Peng Xie +3
Data-driven reachability analysis provides guaranteed outer approximations of reachable sets from input-state measurements, yet each propagation step requires a matrix-zonotope mul…
Certified Set Convergence for Piecewise Affine Systems via Neural Lyapunov Functions
Yanliang Huang, Peng Xie, Zhen Zhang +3
Safety-critical control of piecewise affine (PWA) systems under bounded additive disturbances requires guarantees not for individual states but for entire state sets simultaneously…
Data-Driven Reachability Analysis via Diffusion Models with PAC Guarantees
Yanliang Huang, Peng Xie, Wenyuan Wu +2
We present a data-driven framework for reachability analysis of nonlinear dynamical systems that requires no explicit model. A denoising diffusion probabilistic model learns the ti…
Conformalized Data-Driven Reachability Analysis with PAC Guarantees
Yanliang Huang, Zhen Zhang, Peng Xie +2
Data-driven reachability analysis computes over-approximations of reachable sets directly from noisy data. Existing deterministic methods require either known noise bounds or syste…
GNN-DIP: Neural Corridor Selection for Decomposition-Based Motion Planning
Peng Xie, Yanliang Huang, Wenyuan Wu +1
Motion planning through narrow passages remains a core challenge: sampling-based planners rarely place samples inside these narrow but critical regions, and even when samples land…
Roundabout Constrained Convex Generators: A Unified Framework for Multiply-Connected Reachable Sets
Peng Xie, Sabin Diaconescu, Florin Stoican +1
This paper introduces Roundabout Constrained Convex Generators (RCGs), a set representation framework for modeling multiply connected regions in control and verification applicatio…
Hybrid Polynomial Zonotopes: A Set Representation for Reachability Analysis in Hybrid Nonaffine Systems
Peng Xie, Zhen Zhang, Amr Alanwar
Reachability analysis for hybrid nonaffine systems remains computationally challenging, as existing set representations--including constrained, polynomial, and hybrid zonotopes--ei…
Informed Hybrid Zonotope-based Motion Planning Algorithm
Peng Xie, Johannes Betz, Amr Alanwar
Optimal path planning in nonconvex free spaces poses substantial computational challenges. A common approach formulates such problems as mixed-integer linear programs (MILPs); howe…
Data-Driven Reachability Analysis for Piecewise Affine Systems
Peng Xie, Johannes Betz, Davide M. Raimondo +1
Hybrid systems play a crucial role in modeling real-world applications where discrete and continuous dynamics interact, including autonomous vehicles, power systems, and traffic ne…