ReTokSync resolves tokenization ambiguity in generative linguistic steganography via targeted self-synchronizing resets, achieving over 99.7% extraction accuracy and 100% recovery with an auxiliary channel while matching baseline security and quality.
& Sutskever, I.Consistency Models May 2023
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A closed-loop multi-agent LLM framework enables heterogeneous robots to collaboratively manipulate objects by decomposing tasks, grounding actions via visual tools, and recovering from execution failures hierarchically.
PACE selects execution horizons online via low-speed valleys in predicted action chunks, boosting task success by 6.4 points in simulation and 19.7 points on real robots.
A physics-constrained consistency model downscales Greenland SMB and surface temperature by a factor of 32 while preserving coarse-scale sums and outperforming interpolation on test metrics.
New energetic spectral-element time integrators for phase-field gradient systems that preserve discrete energy dissipation and mass conservation, with numerical tests showing better performance than BDF4 and ETDRK4 on Allen-Cahn problems.
Lightweight IIoT intrusion detection models exhibit poor cross-network generalization due to reliance on coarse port-category feature shortcuts, with evaluation outcomes sensitive to class imbalance.
SafeMoE isolates unsafe knowledge in domain-specific LoRA experts and routes them via a lightweight gate trained on safe responses to produce safer and more informative LLM outputs with zero-shot generalization.
citing papers explorer
-
ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography
ReTokSync resolves tokenization ambiguity in generative linguistic steganography via targeted self-synchronizing resets, achieving over 99.7% extraction accuracy and 100% recovery with an auxiliary channel while matching baseline security and quality.
-
A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation
A closed-loop multi-agent LLM framework enables heterogeneous robots to collaboratively manipulate objects by decomposing tasks, grounding actions via visual tools, and recovering from execution failures hierarchically.
-
PACE: Phase-Aware Chunk Execution for Robot Policies with Action Chunking
PACE selects execution horizons online via low-speed valleys in predicted action chunks, boosting task success by 6.4 points in simulation and 19.7 points on real robots.
-
Physics-constrained generative machine learning-based high-resolution downscaling of Greenland's surface mass balance and surface temperature
A physics-constrained consistency model downscales Greenland SMB and surface temperature by a factor of 32 while preserving coarse-scale sums and outperforming interpolation on test metrics.
-
Energetic Spectral-Element Time Marching Methods for Phase-Field Nonlinear Gradient Systems
New energetic spectral-element time integrators for phase-field gradient systems that preserve discrete energy dissipation and mass conservation, with numerical tests showing better performance than BDF4 and ETDRK4 on Allen-Cahn problems.
-
Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks
Lightweight IIoT intrusion detection models exhibit poor cross-network generalization due to reliance on coarse port-category feature shortcuts, with evaluation outcomes sensitive to class imbalance.
-
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
SafeMoE isolates unsafe knowledge in domain-specific LoRA experts and routes them via a lightweight gate trained on safe responses to produce safer and more informative LLM outputs with zero-shot generalization.