Skip to content

Author

Peng Xie

We have 7 of 25 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

JEPA Learns What the Mask Leaves Unrecoverable

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 measurement account. A mask is a linear measurement, and in a compactly supported wavelet basis every atom whose support lies inside the hi...

Peng Xie, Amr Alanwar · 0 citations
#artificial intelligence Preprint Aug 2026

Certified Mechanistic Interpretability: Lifting Single-Input Findings to Bounded Neighbourhoods

Mechanistic interpretability reverse-engineers transformer circuits one input at a time, leaving observed mechanisms without guarantees over bounded input neighbourhoods. We address this gap with a framework based on constrained polynomial-zonotope (CPZ) propagation that lifts mechanistic-interpretability observations...

Zhen Zhang, Yan-Liang Huang, Peng Xie et al. · 0 citations
Preprint Aug 2026

Certifying Plans under Model Mismatch: A Trilemma for Reachability from Scarce Data

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 fixed control sequence, such as an action chunk produced by a learned policy. If the sequence reaches an unobserved state-input region, the obs...

Yanliang Huang, Zhen Zhang, Ahmad Hafez et al. · 0 citations
Preprint Aug 2026

Probabilistic Reachable-Action Verification of Visuomotor Policies via Set-Based Training

This work freezes the visual encoder and confine set propagation to a low-dimensional interface between it and the downstream policy, with the interface set calibrated from held-out camera-pose perturbations to achieve reachability analysis for visuomotor policies.

Yan-Liang Huang, Zhuo-Cheng Zhang, Peng Xie et al. · 0 citations
#artificial intelligence Review Jul 2026

Error Certificates for KV-Cache Eviction via Randomized Design

It is proved that no estimator computable from the information a deterministic scheme retains is consistent for its own eviction error: evicted values can be altered so that everything retained is unchanged while the true attention-output error grows without bound.

Peng Xie · 0 citations
Preprint Aug 2026

CompCPZ: Preserving Multi-Modal Intent in Language-Guided Robot Manipulation

CompCPZ, a sound algebraic layer that language-conditioned learning systems wrap to recover multi-modal disjunctive representation, recursively composing per-primitive constrained polynomial zonotope enclosures along the language parse tree with distribution-free conformal coverage and sub-millisecond runtime is presen...

Zhen Zhang, Ahmad Hafez, Peng Xie et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.