We have 12 of 81 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.
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...
This study presents a centralized safety aware M2M framework for cooperative goal-directed navigation in a heterogeneous mobile robot system composed of a vision-capable robot and a cameraless robotic vehicle that can approve safe motion, trigger conservative replanning or holding behavior, and preserve a strict separa...
The Differentiable Fuzzy Inference Layer (DFIL), a dual-path prediction head pairing a standard classifier with a scalar-bottlenecked branch grounded in a bank of ordered membership functions, is introduced.
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...
A per-layer critical update strength is derived, computed from the measured spectrum of $W$ alone through the rectangular spiked-deformation transform, together with an exact secular-equation characterization of the updated spectrum, with no fitted parameters.
The Hybrid Probabilistic Zonotope (HProbZ), an output head that represents these three sources as binary, bounded, and stochastic generators of a zonotope, and admits a closed-form likelihood by convolution is introduced.
Language models are the best current models of the human language network, and they have entered the human speech community, shifting word frequencies while alignment narrows their conceptual diversity.
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...
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.
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...
Scaling transformer language models creates an inherent tension between expressivity and memory efficiency. While unique weights across layers preserve functional specialization---from input-grounding to abstract refinement---they incur a substantial memory footprint. Conversely, standard depth-sharing enforces uniform...
A validity theory and audit with three components: two-sided validation of nuisance removal and response preservation, all-optima identification of downstream conclusions, and uncertainty propagation after validity is established is developed.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
