·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions31m◆Mapping Scientific Literature with Large Language Models and Topic Modeling31m◆Grounding Computer Use Agents on Human Demonstrations31m◆Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models31m◆LSTM based IoT Device Identification31m◆Breaking the Ice: Analyzing Cold Start Latency in vLLM31m◆Higher order PCA-like rotation-invariant features for detailed shape descriptors modulo rotation31m◆Minimal surfaces, Knots, and Neural Networks31m◆CCKS: Consensus-based Communication and Knowledge Sharing31m◆APPO: Agentic Procedural Policy Optimization31m◆Noise-Aware Framework for Correcting Corrupted Labels31m◆Using Explainability as a Training-Time Reliability Signal for Efficient ECG Classification31m◆Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity31m◆Measuring Semantic Progress in Multi-turn Dialogue via Information Gain31m◆Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems31m◆Persistent Homology as a Theory of Emergent Structure31m◆Bypassing Prompt Guards in Production with Controlled-Release Prompting31m◆Open Materials Generation with Inference-Time Reinforcement Learning31m◆Mechanisms of Introspective Awareness31m◆Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data31m◆Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions31m◆Mapping Scientific Literature with Large Language Models and Topic Modeling31m◆Grounding Computer Use Agents on Human Demonstrations31m◆Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models31m◆LSTM based IoT Device Identification31m◆Breaking the Ice: Analyzing Cold Start Latency in vLLM31m◆Higher order PCA-like rotation-invariant features for detailed shape descriptors modulo rotation31m◆Minimal surfaces, Knots, and Neural Networks31m◆CCKS: Consensus-based Communication and Knowledge Sharing31m◆APPO: Agentic Procedural Policy Optimization31m◆Noise-Aware Framework for Correcting Corrupted Labels31m◆Using Explainability as a Training-Time Reliability Signal for Efficient ECG Classification31m◆Synthetic Homes: A Multimodal Generative AI Pipeline for Residential Building Data Generation under Data Scarcity31m◆Measuring Semantic Progress in Multi-turn Dialogue via Information Gain31m◆Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems31m◆Persistent Homology as a Theory of Emergent Structure31m◆Bypassing Prompt Guards in Production with Controlled-Release Prompting31m◆Open Materials Generation with Inference-Time Reinforcement Learning31m◆Mechanisms of Introspective Awareness31m◆Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data31m◆
News/CLOVER: Closed-Loop Value Estimation \& Ranking for End-to-End Autonomous Driving Planning
arxiv
PublishedMay 16, 2026 at 4:00 AM
—neutral

CLOVER: Closed-Loop Value Estimation \& Ranking for End-to-End Autonomous Driving Planning

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

arXiv:2605.15120v1 Announce Type: cross Abstract: End-to-end autonomous driving planners are commonly trained by imitating a single logged trajectory, yet evaluated by rule-based planning metrics that measure safety, feasibility, progress, and comfort. This creates a training--evaluation mismatch: t

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
arxivGeneralizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions31marxivMapping Scientific Literature with Large Language Models and Topic Modeling31marxivGrounding Computer Use Agents on Human Demonstrations31marxivEmbodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models31m
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