·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
MASPRM: Multi-Agent System Process Reward Model4h◆ELF: A Family of Encoder-Free ECG-Language Models4h◆Left-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence4h◆1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World4h◆A novel network for classification of cuneiform tablet metadata4h◆PC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner4h◆RADAR: Closed-Loop Robotic Data Generation via Semantic Planning and Autonomous Causal Environment Reset4h◆LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement4h◆Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion4h◆Research Novelty in Information Systems Journals After ChatGPT: Differences Across Institutional Language Contexts4h◆Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies4h◆Post-Deployment Accountability in AI Governance: A Cross-Regulatory Empirical Analysis of AI Incidents4h◆Fre-Res: Frequency-Residual Video Token Compression for Efficient Video MLLMs4h◆Piercing Gilbreath's Conjecture: From Deep Number Theory Insights to Fintech and Cybersecurity4h◆AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning4h◆An Explainable Agentic System for Detection of Conversational Scams with Summary-Based Memory4h◆Removable Defects: The Economics and Limits of Deliberate Deficiency4h◆Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs4h◆Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel4h◆Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation4h◆MASPRM: Multi-Agent System Process Reward Model4h◆ELF: A Family of Encoder-Free ECG-Language Models4h◆Left-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence4h◆1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World4h◆A novel network for classification of cuneiform tablet metadata4h◆PC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner4h◆RADAR: Closed-Loop Robotic Data Generation via Semantic Planning and Autonomous Causal Environment Reset4h◆LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement4h◆Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion4h◆Research Novelty in Information Systems Journals After ChatGPT: Differences Across Institutional Language Contexts4h◆Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies4h◆Post-Deployment Accountability in AI Governance: A Cross-Regulatory Empirical Analysis of AI Incidents4h◆Fre-Res: Frequency-Residual Video Token Compression for Efficient Video MLLMs4h◆Piercing Gilbreath's Conjecture: From Deep Number Theory Insights to Fintech and Cybersecurity4h◆AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning4h◆An Explainable Agentic System for Detection of Conversational Scams with Summary-Based Memory4h◆Removable Defects: The Economics and Limits of Deliberate Deficiency4h◆Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs4h◆Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel4h◆Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation4h◆
News/SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
arxiv
PublishedJune 16, 2026 at 4:00 AM

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness

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

arXiv:2605.25796v2 Announce Type: replace-cross Abstract: Semantic-level watermarking (SWM) improves robustness against text modifications by treating sentences as the basic unit. However, robustness to paragraph-level paraphrasing remains difficult because such attacks globally disrupt watermark si

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
arxivMASPRM: Multi-Agent System Process Reward Model4harxivELF: A Family of Encoder-Free ECG-Language Models4harxivLeft-right asymmetry in predicting brain activity from LLMs' representations emerges with their formal linguistic competence4harxiv1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World4h
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