·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Instagram’s Adam Mosseri: If you don’t like AI, ‘then you shouldn’t have it in your feed’2h◆Would you host part of an AI data center in your home?3h◆How Deutsche Telekom is rewiring telecommunications with AI9h◆Svarna: An Open Corpus Workbench for Modern Greek12h◆When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals12h◆PLURAL: A Global Dataset for Value Alignment12h◆BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression12h◆Robustness to Sparse Adversarial Corruption in Arbitrary Linear Measurements: Beyond Exact Recovery12h◆Infinity-Parser2 Technical Report12h◆Agentic Neural Architecture Search12h◆Leveraging Color Naming for Image Enhancement12h◆($\theta_l, \theta_u$)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces12h◆MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs12h◆Generalization Theory for Through-the-Wall Radar Human Activity Recognition12h◆ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification12h◆Improving Engine Sound Analysis in Hot-Test Environments via a RAB-U-Net (Residual Attention Block U-Net) Noise Removal Method12h◆Validating LLMs in social science: Epistemic threats and emerging norms12h◆Resolving Predictive Multiplicity for the Rashomon Set12h◆Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions12h◆Beyond Success Rates: Trainability and Extractability for Offline GCRL12h◆Instagram’s Adam Mosseri: If you don’t like AI, ‘then you shouldn’t have it in your feed’2h◆Would you host part of an AI data center in your home?3h◆How Deutsche Telekom is rewiring telecommunications with AI9h◆Svarna: An Open Corpus Workbench for Modern Greek12h◆When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals12h◆PLURAL: A Global Dataset for Value Alignment12h◆BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression12h◆Robustness to Sparse Adversarial Corruption in Arbitrary Linear Measurements: Beyond Exact Recovery12h◆Infinity-Parser2 Technical Report12h◆Agentic Neural Architecture Search12h◆Leveraging Color Naming for Image Enhancement12h◆($\theta_l, \theta_u$)-Parametric Multi-Task Optimization: Joint Search in Solution and Infinite Task Spaces12h◆MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs12h◆Generalization Theory for Through-the-Wall Radar Human Activity Recognition12h◆ProsMAE: Multi-Source MAE Pretraining for ISUP Grade Classification12h◆Improving Engine Sound Analysis in Hot-Test Environments via a RAB-U-Net (Residual Attention Block U-Net) Noise Removal Method12h◆Validating LLMs in social science: Epistemic threats and emerging norms12h◆Resolving Predictive Multiplicity for the Rashomon Set12h◆Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions12h◆Beyond Success Rates: Trainability and Extractability for Offline GCRL12h◆
News/WaterSearch: Exploring Seed Pooling for Improving the Quality-Detectability Trade-off in LLM Watermarking
arxiv
PublishedJune 2, 2026 at 4:00 AM

WaterSearch: Exploring Seed Pooling for Improving the Quality-Detectability Trade-off in LLM Watermarking

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

arXiv:2512.00837v3 Announce Type: replace Abstract: Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated content. Exi

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
arxivSvarna: An Open Corpus Workbench for Modern Greek12harxivWhen LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals12harxivPLURAL: A Global Dataset for Value Alignment12harxivBiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression12h
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