UCGP is a universal physical adversarial patch that compromises cross-modal semantic alignment in IR-VLMs through curved-grid parameterization and representation-space disruption.
u ger, Robert and Hellstr \
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
method 4
citation-polarity summary
fields
cs.NE 2 cs.RO 2 astro-ph.GA 1 cond-mat.mtrl-sci 1 cs.CV 1 math.OC 1 physics.chem-ph 1 quant-ph 1verdicts
UNVERDICTED 10roles
method 4polarities
use method 4representative citing papers
A methodology is proposed to integrate Life Cycle Assessment as an additional discipline in Multidisciplinary Design Analysis and Optimization frameworks for launch vehicle eco-design, demonstrated through multi-objective optimization on an expendable launcher.
MSC-CMA-ES makes CMA-ES restarts structure-aware via cyclic nearest-better basin discovery on Sobol pre-samples, achieving 2.7x higher target coverage than BIPOP-CMA-ES on composition functions across CEC suites.
Wiggle and Go! uses system identification from rope motion observations to predict parameters that enable zero-shot goal-conditioned dynamic manipulation, achieving 3.55 cm accuracy on 3D target striking versus 15.34 cm without parameter information.
CCV-QAOA is a new complex-valued continuous-variable variant of QAOA that solves real and complex multivariate optimization problems via a variational framework.
PhDLspec combines differential spectra from physical stellar models with a transformer to derive approximately 30 stellar parameters from low-resolution spectra hundreds of times faster than traditional calculations.
LUCID learns embodiment-agnostic intent models from unstructured human videos to train dexterous robot policies in simulation, enabling zero-shot transfer on real-world tasks like stirring and wiping.
Reactive MD simulations of mixed halide perovskites find that Br-induced strain propagates up to 2 nm and stabilizes the cubic phase at low Br concentrations by changing octahedra dynamics.
Empirical benchmarking shows tolfunhist and the full portfolio stop CMA-ES closest to the optimal evaluation count on BBOB, while tolfun and tolfunhist often trigger before full stagnation.
CovAngelo implements a QM/QM/MM embedding model using quantum-information metrics to compute reaction energy profiles and barriers for covalent drug binding at lower cost than conventional methods, demonstrated on zanubrutinib to BTK.
citing papers explorer
-
Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models
UCGP is a universal physical adversarial patch that compromises cross-modal semantic alignment in IR-VLMs through curved-grid parameterization and representation-space disruption.
-
A Methodology for Integrating Life Cycle Assessment into a Multidisciplinary Design Analysis and Optimization Framework for Sustainable Launcher Development
A methodology is proposed to integrate Life Cycle Assessment as an additional discipline in Multidisciplinary Design Analysis and Optimization frameworks for launch vehicle eco-design, demonstrated through multi-objective optimization on an expendable launcher.
-
MSC-CMA-ES: Structure-Aware Restarts for CMA-ES via Cyclic Nearest-Better Basin Discovery
MSC-CMA-ES makes CMA-ES restarts structure-aware via cyclic nearest-better basin discovery on Sobol pre-samples, achieving 2.7x higher target coverage than BIPOP-CMA-ES on composition functions across CEC suites.
-
Wiggle and Go! System Identification for Zero-Shot Dynamic Rope Manipulation
Wiggle and Go! uses system identification from rope motion observations to predict parameters that enable zero-shot goal-conditioned dynamic manipulation, achieving 3.55 cm accuracy on 3D target striking versus 15.34 cm without parameter information.
-
A Complex-Valued Continuous-Variable Quantum Approximation Optimization Algorithm (CCV-QAOA)
CCV-QAOA is a new complex-valued continuous-variable variant of QAOA that solves real and complex multivariate optimization problems via a variational framework.
-
PhDLspec: physical-prior embedded deep learning method for spectroscopic determination of stellar labels in high-dimensional parameter space
PhDLspec combines differential spectra from physical stellar models with a transformer to derive approximately 30 stellar parameters from low-resolution spectra hundreds of times faster than traditional calculations.
-
LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition
LUCID learns embodiment-agnostic intent models from unstructured human videos to train dexterous robot policies in simulation, enabling zero-shot transfer on real-world tasks like stirring and wiping.
-
Mixing I and Br in Inorganic Perovskites: Atomistic Insights from Reactive Molecular Dynamics Simulations
Reactive MD simulations of mixed halide perovskites find that Br-induced strain propagates up to 2 nm and stabilizes the cubic phase at low Br concentrations by changing octahedra dynamics.
-
Quantitative Performance Analysis of Stopping Criteria for CMA-ES
Empirical benchmarking shows tolfunhist and the full portfolio stop CMA-ES closest to the optimal evaluation count on BBOB, while tolfun and tolfunhist often trigger before full stagnation.
-
CovAngelo: A hybrid quantum-classical computing platform for accurate and scalable drug discovery
CovAngelo implements a QM/QM/MM embedding model using quantum-information metrics to compute reaction energy profiles and barriers for covalent drug binding at lower cost than conventional methods, demonstrated on zanubrutinib to BTK.