·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
MMGist: A Comprehensive Multimodal Benchmark for 20273h◆Visualizing "We the People": Bridging the Perception Gap through Pluralistic Data Storytelling3h◆Small edits, large models: How Wikipedia advocacy shapes LLM values3h◆Noise-Aware Boundary-Enhanced Generative Learning for Ultrasound Speckle Reduction3h◆Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models3h◆MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources3h◆HierBias: Context-Conditioned Hierarchical Media Bias Detection with Multi-Task Type Classification3h◆Where Larger Models Excel: The Primacy of Constraint-Guided Reasoning3h◆Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM3h◆Phonetic and semantic analyses of spoken corpora of Beijing and Taiwan Mandarin indicate that the neutral tone is a lexical tone3h◆ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent3h◆AnySimLite: A Lightweight Few-Shot Similarity Encoder for On-Device Speech-Adjacent Classification3h◆Extracting Problem and Method Sentence from Scientific Papers: A Context-enhanced Transformer Using Formulaic Expression Desensitization3h◆Utilizing Cognitive Signals Generated during Human Reading to Enhance Keyphrase Extraction from Microblogs3h◆Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News3h◆Nemotron-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context3h◆Assessing Post-Reform Changes in Risk Disclosure Quality with a Multidimensional Text Analysis Approach3h◆Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention3h◆Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning3h◆Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean3h◆MMGist: A Comprehensive Multimodal Benchmark for 20273h◆Visualizing "We the People": Bridging the Perception Gap through Pluralistic Data Storytelling3h◆Small edits, large models: How Wikipedia advocacy shapes LLM values3h◆Noise-Aware Boundary-Enhanced Generative Learning for Ultrasound Speckle Reduction3h◆Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models3h◆MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources3h◆HierBias: Context-Conditioned Hierarchical Media Bias Detection with Multi-Task Type Classification3h◆Where Larger Models Excel: The Primacy of Constraint-Guided Reasoning3h◆Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM3h◆Phonetic and semantic analyses of spoken corpora of Beijing and Taiwan Mandarin indicate that the neutral tone is a lexical tone3h◆ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent3h◆AnySimLite: A Lightweight Few-Shot Similarity Encoder for On-Device Speech-Adjacent Classification3h◆Extracting Problem and Method Sentence from Scientific Papers: A Context-enhanced Transformer Using Formulaic Expression Desensitization3h◆Utilizing Cognitive Signals Generated during Human Reading to Enhance Keyphrase Extraction from Microblogs3h◆Comparing BERT Sentence-Pair Classification and Few-Shot LLM Prompting for Detecting Threat and Solution Framing in German Climate News3h◆Nemotron-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context3h◆Assessing Post-Reform Changes in Risk Disclosure Quality with a Multidimensional Text Analysis Approach3h◆Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention3h◆Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning3h◆Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean3h◆
News/Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking
arxiv
PublishedJune 24, 2026 at 4:00 AM
—neutral

Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking

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

arXiv:2605.00348v2 Announce Type: replace-cross Abstract: Recent multi-bit watermarking methods for large language models (LLMs) prioritize capacity over reliability, often conflating decoding with detection. Our analysis reveals that existing ECC-based extractors suffer from catastrophic false posi

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
arxivMMGist: A Comprehensive Multimodal Benchmark for 20273harxivVisualizing "We the People": Bridging the Perception Gap through Pluralistic Data Storytelling3harxivSmall edits, large models: How Wikipedia advocacy shapes LLM values3harxivNoise-Aware Boundary-Enhanced Generative Learning for Ultrasound Speckle Reduction3h
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