·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples39m◆Motif: Discovering and Automating Personal Web Workflows39m◆Tool-Adaptive LLM Reranker39m◆When Does Restricting a Coding Agent to execute_code Help? A Regime $\times$ Agent-Design Ablation39m◆Learning from Local Walks on Dynamic Graphs with Bandit Feedback39m◆DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoders39m◆MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference39m◆WasteAssistant: Regulation-Guided Visual Question Answering Framework for Intelligent Waste Segregation and Sustainable Managemen39m◆Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation39m◆World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning39m◆Auditing Construct Overlap in Explainable Machine Learning: Evidence from Burnout-Depression Prediction Across Student Cohorts39m◆Coverage Path Planning: Classical Foundations, Recent Advances, and Future Directions39m◆Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting39m◆Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Small VLMs39m◆Commenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications39m◆Learning to Fine-tune Foundation Models under Resource Limitations39m◆Action Map Policy: Learning 3D Closed-loop Manipulation via Pixel Classification39m◆MDQEC-QAS: Meta-Decoding for Quantum Error Correction with Hardware-Aware VQC Search and Confidence-Gated Recovery39m◆PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM Inference39m◆Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud39m◆ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples39m◆Motif: Discovering and Automating Personal Web Workflows39m◆Tool-Adaptive LLM Reranker39m◆When Does Restricting a Coding Agent to execute_code Help? A Regime $\times$ Agent-Design Ablation39m◆Learning from Local Walks on Dynamic Graphs with Bandit Feedback39m◆DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion Autoencoders39m◆MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference39m◆WasteAssistant: Regulation-Guided Visual Question Answering Framework for Intelligent Waste Segregation and Sustainable Managemen39m◆Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation39m◆World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning39m◆Auditing Construct Overlap in Explainable Machine Learning: Evidence from Burnout-Depression Prediction Across Student Cohorts39m◆Coverage Path Planning: Classical Foundations, Recent Advances, and Future Directions39m◆Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting39m◆Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Small VLMs39m◆Commenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications39m◆Learning to Fine-tune Foundation Models under Resource Limitations39m◆Action Map Policy: Learning 3D Closed-loop Manipulation via Pixel Classification39m◆MDQEC-QAS: Meta-Decoding for Quantum Error Correction with Hardware-Aware VQC Search and Confidence-Gated Recovery39m◆PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM Inference39m◆Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud39m◆
News/Region Seeding via Pre-Activation Regularization: A Geometric View from Piecewise Affine Nerual Networks
arxiv
PublishedMay 8, 2026 at 4:00 AM
—neutral

Region Seeding via Pre-Activation Regularization: A Geometric View from Piecewise Affine Nerual Networks

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

arXiv:2605.06300v1 Announce Type: new Abstract: Deep networks with continuous piecewise affine activations induce polyhedral partitions of the input space, making the number of realized affine regions a natural measure of expressive capacity and a key determinant of how well the model can approximat

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
arxivARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples39marxivMotif: Discovering and Automating Personal Web Workflows39marxivTool-Adaptive LLM Reranker39marxivWhen Does Restricting a Coding Agent to execute_code Help? A Regime $\times$ Agent-Design Ablation39m
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