·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
From Noise to Control: Parameterized Diffusion Policies1h◆Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics1h◆Drifting Preference Optimization for One-Step Generative Models1h◆Value-Free Policy Optimization via Reward Partitioning1h◆Semantic Retrieval for Product Search in E-Commerce1h◆Efficient Test-time Inference for Generative Planning Models1h◆ProbRes: Volatility Learning for Probabilistic Time-Series Forecasting1h◆Disentanglement-Based Equivariant Learning for Compositional VQA1h◆Large Electron Model: A Universal Ground State Predictor1h◆Nonlinear Equilibrium Transitions in a Potential Game Model for Federated Learning1h◆Geometry-Aware Probabilistic Circuits via Voronoi Tessellations1h◆Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs1h◆Incentives, Equilibria, and the Limits of Healthcare AI: A Game-Theoretic Perspective1h◆Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs1h◆ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment1h◆"Skill issues'': data-centric optimization of lakehouse agents1h◆The Case for Model Science: Verify, Explore, Steer, Refine1h◆Can LLM Agents Sustain Long-Horizon Organizational Dynamics?1h◆The Shape of Wisdom: Decision Trajectories in Language Models1h◆TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment1h◆From Noise to Control: Parameterized Diffusion Policies1h◆Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics1h◆Drifting Preference Optimization for One-Step Generative Models1h◆Value-Free Policy Optimization via Reward Partitioning1h◆Semantic Retrieval for Product Search in E-Commerce1h◆Efficient Test-time Inference for Generative Planning Models1h◆ProbRes: Volatility Learning for Probabilistic Time-Series Forecasting1h◆Disentanglement-Based Equivariant Learning for Compositional VQA1h◆Large Electron Model: A Universal Ground State Predictor1h◆Nonlinear Equilibrium Transitions in a Potential Game Model for Federated Learning1h◆Geometry-Aware Probabilistic Circuits via Voronoi Tessellations1h◆Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs1h◆Incentives, Equilibria, and the Limits of Healthcare AI: A Game-Theoretic Perspective1h◆Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs1h◆ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment1h◆"Skill issues'': data-centric optimization of lakehouse agents1h◆The Case for Model Science: Verify, Explore, Steer, Refine1h◆Can LLM Agents Sustain Long-Horizon Organizational Dynamics?1h◆The Shape of Wisdom: Decision Trajectories in Language Models1h◆TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment1h◆
News/Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation
arxiv
PublishedJune 2, 2026 at 4:00 AM

Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation

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

arXiv:2606.02552v1 Announce Type: cross Abstract: Despite advances in depth estimation, flying points remain a persistent failure mode: near object boundaries, depth estimators often predict spurious 3D points in the empty space between foreground and background surfaces. We trace this artifact to a

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
arxivFrom Noise to Control: Parameterized Diffusion Policies1harxivMesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics1harxivDrifting Preference Optimization for One-Step Generative Models1harxivValue-Free Policy Optimization via Reward Partitioning1h
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