·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
All the AI agents that can live in your text messages1h◆Sequential Capacity of Quantum Processes with Finite Memory11h◆Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study11h◆Q-MINO: A Minimal-Norm Method for Quantization-Aware Training11h◆SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing11h◆Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations11h◆Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions11h◆STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling11h◆A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform11h◆The Price of Correlated Tests: How Strict Should a Model Release Gate Be?11h◆Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening11h◆Open Vocabulary Word Recognition From Transcribed Bangla Texts11h◆Geometry-Dependent Bounds for Online Non-Monotone DR-Submodular Maximization11h◆Learning ab initio phase-field models11h◆Scaling Collider Event Generation with Residual-Quantized Tokens11h◆AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models11h◆TANGO: Treating Tokens as Operators11h◆Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization11h◆The hidden advantage of mask resampling: a theory of masked autoencoders11h◆Continual Reinforcement Learning with Neuroevolution11h◆All the AI agents that can live in your text messages1h◆Sequential Capacity of Quantum Processes with Finite Memory11h◆Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study11h◆Q-MINO: A Minimal-Norm Method for Quantization-Aware Training11h◆SmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing11h◆Continual Learning for 6-DoF Grasp Synthesis via Experience and Demonstrations11h◆Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions11h◆STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling11h◆A Survey on End-to-End Autonomous Driving Training from the Perspectives of Data, Strategy, and Platform11h◆The Price of Correlated Tests: How Strict Should a Model Release Gate Be?11h◆Tolerance-Based Fairness Auditing: Violation Certification and Sensitivity Screening11h◆Open Vocabulary Word Recognition From Transcribed Bangla Texts11h◆Geometry-Dependent Bounds for Online Non-Monotone DR-Submodular Maximization11h◆Learning ab initio phase-field models11h◆Scaling Collider Event Generation with Residual-Quantized Tokens11h◆AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models11h◆TANGO: Treating Tokens as Operators11h◆Optimal Momentum Methods for Stochastic Multilevel Compositional Optimization11h◆The hidden advantage of mask resampling: a theory of masked autoencoders11h◆Continual Reinforcement Learning with Neuroevolution11h◆
News/Attention Manifolds: Steering or Blocking Language Models by Editing Learned B-Spline Surfaces
arxiv
PublishedOctober 3, 2026 at 4:00 AM
—neutral

Attention Manifolds: Steering or Blocking Language Models by Editing Learned B-Spline Surfaces

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

arXiv:2610.00257v1 Announce Type: new Abstract: In standard transformer attention, a source token sends the same value vector to every receiver. The query determines \emph{how much} to attend but not \emph{what} to extract. This work introduces \textbf{attention manifolds}: learned 2D B-spline surfa

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
arxivSequential Capacity of Quantum Processes with Finite Memory11harxivSentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study11harxivQ-MINO: A Minimal-Norm Method for Quantization-Aware Training11harxivSmoothOperator: Enhancing Representations for Fine-grained Open-set Recognition via Modulated Label Smoothing11h
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 ↗
Built by Marouane Gazouzi
HomeModelsNews