·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Opaque recurrence, and other AI terms that you should probably know7h◆Extremely Sparse Supervision Incentivizes Reasoning Ability23h◆Constructing and Evaluating Clinical Reasoning Trajectories for Medical Agent23h◆When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs23h◆Blockchain-Enabled Secure Logging for Fiscal Electronic Mechanisms: Evaluation of the Greek eSEND and myDATA Tax Systems23h◆Robust and Efficient Guardrails with Latent Reasoning23h◆NxN E-valuation: Hypothesis Certification via a Conformal CRT Null23h◆SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning23h◆Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection23h◆ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search23h◆Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts23h◆FVSpec: Real-World Property-Based Tests as Lean Challenges23h◆Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Construction23h◆Improving Energy Efficiency of Oil Platforms Through Optimal Loading of Diesel Generators Using Machine Learning and Search Algorithms23h◆Post-Training Language Models for Gold-Medal Performance in Coding Competitions23h◆Generating Constructive Feedback on Stories via Reinforcement Learning23h◆When LLM Decompilers Recompile More and Preserve Less23h◆Reflection-aware Generative Novel View Synthesis23h◆ConfRAG: Confidence-Guided Retrieval-Augmenting Generation23h◆Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One23h◆Opaque recurrence, and other AI terms that you should probably know7h◆Extremely Sparse Supervision Incentivizes Reasoning Ability23h◆Constructing and Evaluating Clinical Reasoning Trajectories for Medical Agent23h◆When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs23h◆Blockchain-Enabled Secure Logging for Fiscal Electronic Mechanisms: Evaluation of the Greek eSEND and myDATA Tax Systems23h◆Robust and Efficient Guardrails with Latent Reasoning23h◆NxN E-valuation: Hypothesis Certification via a Conformal CRT Null23h◆SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning23h◆Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection23h◆ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search23h◆Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts23h◆FVSpec: Real-World Property-Based Tests as Lean Challenges23h◆Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Construction23h◆Improving Energy Efficiency of Oil Platforms Through Optimal Loading of Diesel Generators Using Machine Learning and Search Algorithms23h◆Post-Training Language Models for Gold-Medal Performance in Coding Competitions23h◆Generating Constructive Feedback on Stories via Reinforcement Learning23h◆When LLM Decompilers Recompile More and Preserve Less23h◆Reflection-aware Generative Novel View Synthesis23h◆ConfRAG: Confidence-Guided Retrieval-Augmenting Generation23h◆Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One23h◆
News/When LLM Decompilers Recompile More and Preserve Less
arxiv
PublishedSeptember 7, 2026 at 4:00 AM
—neutral

When LLM Decompilers Recompile More and Preserve Less

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

arXiv:2609.05370v1 Announce Type: cross Abstract: Decompilation recovers high-level source from compiled machine code and serves as a foundation for security tasks such as vulnerability detection and malware analysis. Traditional decompilers like Ghidra and Hex-Rays expose whatever they cannot resol

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
arxivExtremely Sparse Supervision Incentivizes Reasoning Ability23harxivConstructing and Evaluating Clinical Reasoning Trajectories for Medical Agent23harxivWhen Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs23harxivBlockchain-Enabled Secure Logging for Fiscal Electronic Mechanisms: Evaluation of the Greek eSEND and myDATA Tax Systems23h
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