23 papers
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…
Cross-View Correspondence Is a Measurement Intervention: Two-Sided Validation for Agent Evaluation and Credit Assignment
Zhen Zhang, Ahmad Hafez, Amr Alanwar
Agent evaluations and trace-based learning often compare outputs across transformed views through a post-response correspondence treated as neutral preprocessing. We show that this…
The Cost of Conservation: Coordination-Memory Laws for Exact-Support Generation
Zhen Zhang, Amr Alanwar
Many AI systems make decisions locally, even when every realized output must obey an additive conservation law, such as selecting exactly a fixed number of items. This constraint c…
Differentiable Fuzzy Inference Layer: A Monotone, Compositional Ordinal Reasoning Head for Large Language Models
Zhen Zhang, Amr Alanwar
A state-of-the-art language model asked to interpret "most of most students passed" typically answers "most," though composing two instances of "most" yields a proportion closer to…
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…
Matrix Zonotopic Attention: A Context-Adaptive Value Projection for Set Transformers
Zhen Zhang, Amr Alanwar
Multi-head attention combines an input-dependent softmax routing with an input-independent linear value projection, so the per-sample operator mapping aggregated values to outputs…
Hybrid Probabilistic Zonotopes for Identifiable and Refinable Predictive Uncertainty
Zhen Zhang, Amr Alanwar
Probabilistic prediction heads in neural networks typically output either a Gaussian mixture or a single conformal region. Neither separates the distinct sources of uncertainty oft…
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…
Reachability Analysis With Probabilistic Zonotopes: Learning Realized Disturbances and Refining Aleatory Uncertainty
Amir Modares, Zhen Zhang, Themistoklis Charalambous +2
This paper develops a data-driven reachability framework for linear systems whose disturbances are modeled by probabilistic zonotopes (PZs), combining bounded deterministic and Gau…
DiffSlack: Learning under Nonlinear Inequality Constraints via Learnable Slack Variables
Ziqian Wang, Chenxi Fang, Zhen Zhang
Enforcing nonlinear inequality constraints in neural networks remains challenging, especially when the output is subject to many coupled constraints. Existing hard constraint metho…
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…
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…
PINNs in PDE Constrained Optimal Control Problems: Direct vs Indirect Methods
Zhen Zhang, Shanqing Liu, Alessandro Alla +2
We study physics-informed neural networks (PINNs) as numerical tools for the optimal control of semilinear partial differential equations. We first recall the classical direct and…
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 Nonconvex Reachability Analysis using Exact Set Propagation
Zhen Zhang, M. Umar B. Niazi, Michelle S. Chong +2
This paper studies deterministic data-driven reachability analysis for dynamical systems with unknown dynamics and nonconvex reachable sets. Existing deterministic data-driven appr…
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…
Data-Driven Tube-Based Zonotopic Predictive Control With Nonconvex Layered Terminal Sets
Zhen Zhang, Bogdan Gheorghe, Florin Stoican +1
This paper presents a data-driven tube-based zonotopic predictive control (DTZPC) framework with nonconvex layered terminal sets. Existing DTZPC schemes with closed-loop guarantees…
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…
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…
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…
Data-Driven Nonconvex Reachability Analysis using Exact Multiplication
Zhen Zhang, M. Umar B. Niazi, Michelle S. Chong +2
This paper addresses a fundamental challenge in data-driven reachability analysis: accurately representing and propagating non-convex reachable sets. We propose a novel approach us…