·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
DiScoFormer: Plug-In Density and Score Estimation with Transformers2h◆DCFO: Density-Based Counterfactuals for Outliers -- Additional Material2h◆Representation Unlearning: Forgetting through Information Compression2h◆Density-aware Sample-specific Attack2h◆Calibrating Generative Models to Distributional Constraints2h◆Benchmarking at the Edge of Comprehension2h◆Recurrent Structural Policy Gradient for Partially Observable Mean Field Games2h◆Jailbreaking and Mitigation of Vulnerabilities in Large Language Models2h◆GRPO is Secretly a Process Reward Model2h◆AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning2h◆Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases2h◆RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models2h◆Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language Adaptation2h◆FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse Autoformalization2h◆CCS: Clinical Consensus Selection for Radiology Report Generation2h◆An End-to-End PyTorch Interface for Differentiable PDE Solvers: A RANS Model-Correction Study2h◆Gesture-Aware Indoor THz ISAC Systems for Adaptive Resource Allocation2h◆Neural Logistic Bandits2h◆Collaborative Threshold Watermarking2h◆Accelerating trajectory optimization with Sobolev-trained diffusion policies2h◆DiScoFormer: Plug-In Density and Score Estimation with Transformers2h◆DCFO: Density-Based Counterfactuals for Outliers -- Additional Material2h◆Representation Unlearning: Forgetting through Information Compression2h◆Density-aware Sample-specific Attack2h◆Calibrating Generative Models to Distributional Constraints2h◆Benchmarking at the Edge of Comprehension2h◆Recurrent Structural Policy Gradient for Partially Observable Mean Field Games2h◆Jailbreaking and Mitigation of Vulnerabilities in Large Language Models2h◆GRPO is Secretly a Process Reward Model2h◆AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning2h◆Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases2h◆RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models2h◆Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language Adaptation2h◆FormalEvolve: Neuro-Symbolic Evolutionary Search for Diverse Autoformalization2h◆CCS: Clinical Consensus Selection for Radiology Report Generation2h◆An End-to-End PyTorch Interface for Differentiable PDE Solvers: A RANS Model-Correction Study2h◆Gesture-Aware Indoor THz ISAC Systems for Adaptive Resource Allocation2h◆Neural Logistic Bandits2h◆Collaborative Threshold Watermarking2h◆Accelerating trajectory optimization with Sobolev-trained diffusion policies2h◆
News/Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
arxiv
PublishedMay 14, 2026 at 4:00 AM

Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models

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

arXiv:2605.11887v1 Announce Type: new Abstract: Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, limiting our ability to inspect, control, and systematically improve them. This opacity motivates a gr

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 Transformers2harxivDCFO: Density-Based Counterfactuals for Outliers -- Additional Material2harxivRepresentation Unlearning: Forgetting through Information Compression2harxivDensity-aware Sample-specific Attack2h
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