·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP Overrides18m◆Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation18m◆From Events to Reasoning: Hierarchical Rule Composition over Explicit States18m◆ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation18m◆Sensitivity Analysis of Decision Rules in an Agent-Based Agro-Ecological Model18m◆PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents18m◆From Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems18m◆Null Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and Interpretability18m◆Learnable Splines for Unstructured Neural Operators18m◆Functional Welfare for AI Safety18m◆Author-in-the-loop Agentic Reproducibility Auditing for a Machine Learning Conference18m◆Harness-Delta Attribution: Dissecting Gains From Harness Evolution18m◆Testing the Planning Claims of LLM-Based Agents against Formal Semantics18m◆Are Large Reasoning Models Good Everyday Reasoners? A Comparison with Non-Reasoning Models on Logical Reasoning Tasks18m◆FRACTAL: A Self-Similar Multi-Agent Orchestration Architecture with Formal Communication, Convergence, and Depth Bounds18m◆Repairing LLM-Generated Specifications with Deterministic Diagnosis18m◆At the Limits of Computability: Steps Towards Autonomous AI Discovery on the Busy Beaver Frontier18m◆From Relevant Memories to Sufficient Evidence: Rethinking Memory Utilization in LLM Agents18m◆Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation18m◆FlexUMM: Flexible Representation Learning for Unified Multimodal Models18m◆Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP Overrides18m◆Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation18m◆From Events to Reasoning: Hierarchical Rule Composition over Explicit States18m◆ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation18m◆Sensitivity Analysis of Decision Rules in an Agent-Based Agro-Ecological Model18m◆PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents18m◆From Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems18m◆Null Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and Interpretability18m◆Learnable Splines for Unstructured Neural Operators18m◆Functional Welfare for AI Safety18m◆Author-in-the-loop Agentic Reproducibility Auditing for a Machine Learning Conference18m◆Harness-Delta Attribution: Dissecting Gains From Harness Evolution18m◆Testing the Planning Claims of LLM-Based Agents against Formal Semantics18m◆Are Large Reasoning Models Good Everyday Reasoners? A Comparison with Non-Reasoning Models on Logical Reasoning Tasks18m◆FRACTAL: A Self-Similar Multi-Agent Orchestration Architecture with Formal Communication, Convergence, and Depth Bounds18m◆Repairing LLM-Generated Specifications with Deterministic Diagnosis18m◆At the Limits of Computability: Steps Towards Autonomous AI Discovery on the Busy Beaver Frontier18m◆From Relevant Memories to Sufficient Evidence: Rethinking Memory Utilization in LLM Agents18m◆Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation18m◆FlexUMM: Flexible Representation Learning for Unified Multimodal Models18m◆
News/From Llama to Cria: Scaling Down Neural Networks via Neuron-Level Spectral Structural Importance Evaluation
arxiv
PublishedMay 20, 2026 at 4:00 AM

From Llama to Cria: Scaling Down Neural Networks via Neuron-Level Spectral Structural Importance Evaluation

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

arXiv:2605.18860v1 Announce Type: new Abstract: This paper proposes a neuron pruning framework based on neuron-level spectral structural importance evaluation. Given a trained neural network, we record the hidden states of each hidden layer during inference and model neurons as graph nodes, with hid

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

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
arxivStructured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP Overrides18marxivRethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation18marxivFrom Events to Reasoning: Hierarchical Rule Composition over Explicit States18marxivECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation18m
The Bubble Brief
MON · WED · FRI

Read AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews