Queen's University

3 related articles

Subscribe to updates

arXiv Oct 12, 2026
Diffusion watermarks survive erasure: wavelet-domain replicas keep 88% bit accuracy under MarkNull
Provenance watermarks for diffusion-generated images were previously suppressed by removal attacks with little visible quality loss. WaveMark embeds the message in the initial noise's wavelet domain, using a key to spread replicas of each message bit across spatial positions, wavelet orientations, and scales, then encodes each bit in a carrier's projection magnitude. On SD2.1 it reaches 100.0% bit accuracy without attacks and retains 88.66% and 88.06% under MarkNull and MarkNull-A, above the compared baselines.
Provenance watermarks for diffusion-generated images were previously suppressed by removal attacks with little visible quality loss. WaveMark embeds the message in the initial noise's wavelet domain, using a key to spread replicas of each message bit across spatial positions, wavelet orientations, and scales, then encodes each bit in a carrier's projection magnitude. On SD2.1 it reaches 100.0% bit accuracy without attacks and retains 88.66% and 88.06% under MarkNull and MarkNull-A, above the compared baselines.
Nanjing University Queen's University
Jie Cao（First author）
WaveMark Watermarking Discrete Wavelet Transform DDIM
arXiv Oct 5, 2026
CSIR planning framework lets robots find target people under incomplete information, beating distance-only graph baselines while semantics alone destabilizes search
For the Person Goal Navigation (PersonNav) problem, the work proposes a planning framework that combines distance and semantic information about the recipient (habits and intent) weighted by the trust of user-provided information, and builds a synthetic benchmark of scenarios with actors, items, and requests to evaluate performance before real-world deployment while simulating natural-language human-robot interaction; results show the informed search outperforms classical distance-based graph baselines, semantics alone leads to ungrounded and sporadic search, an LLM-based variant performs comparably, and hardware tests show the method supports real-world embodiment.
For the Person Goal Navigation (PersonNav) problem, the work proposes a planning framework that combines distance and semantic information about the recipient (habits and intent) weighted by the trust of user-provided information, and builds a synthetic benchmark of scenarios with actors, items, and requests to evaluate performance before real-world deployment while simulating natural-language human-robot interaction; results show the informed search outperforms classical distance-based graph baselines, semantics alone leads to ungrounded and sporadic search, an LLM-based variant performs comparably, and hardware tests show the method supports real-world embodiment.
University of Waterloo Queen's University
Tyler Chung（First author）
CSIR Person Goal Navigation Informed search planning framework
arXiv Sep 17, 2026
Re-bounding the Human-Data Ratio Needed to Prevent Model Collapse via Fisher-Rao Geometry
This work models iterative generative-model training as a closed-loop stochastic process on the probability simplex and analyzes its dynamics under the Fisher-Rao metric instead of the Euclidean metric, deriving contraction and invariance bounds that remain meaningful as dimension grows and giving a human-to-synthetic data ratio threshold that guarantees convergence to a Fisher-Rao ball, concluding that the effective required human-data ratio is higher than previously implied.
This work models iterative generative-model training as a closed-loop stochastic process on the probability simplex and analyzes its dynamics under the Fisher-Rao metric instead of the Euclidean metric, deriving contraction and invariance bounds that remain meaningful as dimension grows and giving a human-to-synthetic data ratio threshold that guarantees convergence to a Fisher-Rao ball, concluding that the effective required human-data ratio is higher than previously implied.
Queen's University
Matteo Marchi（First author）
Model Collapse Fisher-Rao Metric Training with Synthetic Data

You’re all caught up

Diffusion watermarks survive erasure: wavelet-domain replicas keep 88% bit accuracy under MarkNull

CSIR planning framework lets robots find target people under incomplete information, beating distance-only graph baselines while semantics alone destabilizes search

Re-bounding the Human-Data Ratio Needed to Prevent Model Collapse via Fisher-Rao Geometry