·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation52m◆Counterfactual Model Testing Under Distribution Shift52m◆Centralized Critics for N-Agent Ad Hoc Teamwork52m◆Where and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning52m◆Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction52m◆Numina Fuse: Interactive Autoformalization in Lean 452m◆On the Limits of Sparse Linear Model with Shuffled Differential Privacy52m◆Video World Models Need Predictable Latents52m◆AutoPRL: Automated Path Representation Learning via a Learnable View Generator52m◆Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models52m◆Latent Goal Prediction from Language for Model-Based Planning52m◆Rectified Language Flow52m◆Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment52m◆Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila52m◆Estimating Long-term Heterogeneous Dose-response Curve: Generalization Bound Leveraging Optimal Transport Weights52m◆Intervention-Certified Amplification: A Validity Gate for $\sigma$-Weighted Post-Training52m◆Single-Cycle Battery Remaining Useful Life Prediction with Compressed Continuous Wavelet Features and Deep Neural Networks52m◆DoubleFree:Exploiting Exploration History for Rollout-Free Multi-Task LLMs Training52m◆Unbiased Alignment for Large Language Models with Noisy Preferences52m◆ExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess Calibration52m◆MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation52m◆Counterfactual Model Testing Under Distribution Shift52m◆Centralized Critics for N-Agent Ad Hoc Teamwork52m◆Where and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning52m◆Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction52m◆Numina Fuse: Interactive Autoformalization in Lean 452m◆On the Limits of Sparse Linear Model with Shuffled Differential Privacy52m◆Video World Models Need Predictable Latents52m◆AutoPRL: Automated Path Representation Learning via a Learnable View Generator52m◆Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models52m◆Latent Goal Prediction from Language for Model-Based Planning52m◆Rectified Language Flow52m◆Trainable Boundary-Keeping Where No Formal Answer Exists: A Controlled Knock-In Study of Reward Training in Evidence-Sufficiency Judgment52m◆Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila52m◆Estimating Long-term Heterogeneous Dose-response Curve: Generalization Bound Leveraging Optimal Transport Weights52m◆Intervention-Certified Amplification: A Validity Gate for $\sigma$-Weighted Post-Training52m◆Single-Cycle Battery Remaining Useful Life Prediction with Compressed Continuous Wavelet Features and Deep Neural Networks52m◆DoubleFree:Exploiting Exploration History for Rollout-Free Multi-Task LLMs Training52m◆Unbiased Alignment for Large Language Models with Noisy Preferences52m◆ExCal: Optimization-Free Multivariate Time Series Anomaly Detection via Excess Calibration52m◆
News/FVD: Inference-Time Alignment of Diffusion Models via Fleming-Viot Resampling
arxiv
PublishedApril 10, 2026 at 4:00 AM
▲bullish

FVD: Inference-Time Alignment of Diffusion Models via Fleming-Viot Resampling

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

arXiv:2604.06779v1 Announce Type: new Abstract: We introduce Fleming-Viot Diffusion (FVD), an inference-time alignment method that resolves the diversity collapse commonly observed in Sequential Monte Carlo (SMC) based diffusion samplers. Existing SMC-based diffusion samplers often rely on multinomi

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 →
Tags
04
#diffusion#monte-carlo#inference#optimization

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#diffusion#monte-carlo#inference#optimization

Related coverage

More from ARXIV
arxivMAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation52marxivCounterfactual Model Testing Under Distribution Shift52marxivCentralized Critics for N-Agent Ad Hoc Teamwork52marxivWhere and What to Reward? Understanding Generalization Between Verifiable and Open-Ended Domains in Reinforcement Learning52m
The Bubble Brief
MON · WED · FRI

Read diffusion 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