·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
DiScoFormer: Plug-In Density and Score Estimation with Transformers5h◆DCFO: Density-Based Counterfactuals for Outliers -- Additional Material5h◆Representation Unlearning: Forgetting through Information Compression5h◆Density-aware Sample-specific Attack5h◆TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation5h◆Temporal Stability and Few-Shot Prompting in Math Task Assessment5h◆Self-Trained Verification for Training- and Test-Time Self-Improvement5h◆DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories5h◆GRPO is Secretly a Process Reward Model5h◆Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms5h◆Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds5h◆Unlocking the Working Memory of Large Language Models for Latent Reasoning5h◆Gesture-Aware Indoor THz ISAC Systems for Adaptive Resource Allocation5h◆Neural Logistic Bandits5h◆EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance5h◆Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models5h◆ExCAM: Explainable Cultural Awareness Metrics5h◆A Survey on Recent Advances in Conversational Data Generation5h◆MediHive: A Decentralized Agent Collective for Medical Reasoning5h◆Taming Data Challenges in ML-based Security Tasks Using Generative AI5h◆DiScoFormer: Plug-In Density and Score Estimation with Transformers5h◆DCFO: Density-Based Counterfactuals for Outliers -- Additional Material5h◆Representation Unlearning: Forgetting through Information Compression5h◆Density-aware Sample-specific Attack5h◆TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation5h◆Temporal Stability and Few-Shot Prompting in Math Task Assessment5h◆Self-Trained Verification for Training- and Test-Time Self-Improvement5h◆DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories5h◆GRPO is Secretly a Process Reward Model5h◆Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms5h◆Modality Alignment across Trees on Heterogeneous Hyperbolic Manifolds5h◆Unlocking the Working Memory of Large Language Models for Latent Reasoning5h◆Gesture-Aware Indoor THz ISAC Systems for Adaptive Resource Allocation5h◆Neural Logistic Bandits5h◆EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance5h◆Reasoning that Travels: Dissecting How Chain-of-Thought Transfers Across Models5h◆ExCAM: Explainable Cultural Awareness Metrics5h◆A Survey on Recent Advances in Conversational Data Generation5h◆MediHive: A Decentralized Agent Collective for Medical Reasoning5h◆Taming Data Challenges in ML-based Security Tasks Using Generative AI5h◆
News/AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
arxiv
PublishedMay 29, 2026 at 4:00 AM

AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.29434v1 Announce Type: cross Abstract: Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and merging,

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivDiScoFormer: Plug-In Density and Score Estimation with Transformers5harxivDCFO: Density-Based Counterfactuals for Outliers -- Additional Material5harxivRepresentation Unlearning: Forgetting through Information Compression5harxivDensity-aware Sample-specific Attack5h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews