·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
IMEX Interaction-Based Model Explanation45m◆DialogueVPR: Towards Conversational Visual Place Recognition45m◆Human AI Construction of Bayesian Networks for Operational Decision Support -- A Virtual Survey Approach45m◆Capability from Access Structure, Not Scale: Lower Bounds and Pre-Registered Tests for Hybrid Sequence Models45m◆Orchestrating Power Grid Studies with Multi-Agent AI and MCP Servers45m◆MemoHarness: Agent Harnesses That Learn from Experience45m◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models45m◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System45m◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination45m◆How Artificial Intelligence LLM Engines Shape the Global Conflict Information Environment45m◆Align AI to Dynamic Human-AI Workflows45m◆The Steering Budget: Examples beat Knobs45m◆Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation45m◆AI Agents Do Not Fail Alone:The Context Fails First45m◆Measuring How Students Rely on Generative AI in Academic Writing: Development and Multi-Source Validation of the Generative AI Reliance Types Scale (GenAI-RTS)45m◆Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions45m◆Traccia: An OpenTelemetry-Based Governance Platform for AI Systems45m◆CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents45m◆Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving45m◆A Comparative Analysis of Machine Learning Models for Long and Short-Term Forecasting of the Egyptian Stock Market: A Focus on EGX3045m◆IMEX Interaction-Based Model Explanation45m◆DialogueVPR: Towards Conversational Visual Place Recognition45m◆Human AI Construction of Bayesian Networks for Operational Decision Support -- A Virtual Survey Approach45m◆Capability from Access Structure, Not Scale: Lower Bounds and Pre-Registered Tests for Hybrid Sequence Models45m◆Orchestrating Power Grid Studies with Multi-Agent AI and MCP Servers45m◆MemoHarness: Agent Harnesses That Learn from Experience45m◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models45m◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System45m◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination45m◆How Artificial Intelligence LLM Engines Shape the Global Conflict Information Environment45m◆Align AI to Dynamic Human-AI Workflows45m◆The Steering Budget: Examples beat Knobs45m◆Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation45m◆AI Agents Do Not Fail Alone:The Context Fails First45m◆Measuring How Students Rely on Generative AI in Academic Writing: Development and Multi-Source Validation of the Generative AI Reliance Types Scale (GenAI-RTS)45m◆Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions45m◆Traccia: An OpenTelemetry-Based Governance Platform for AI Systems45m◆CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents45m◆Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving45m◆A Comparative Analysis of Machine Learning Models for Long and Short-Term Forecasting of the Egyptian Stock Market: A Focus on EGX3045m◆
News/LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models
arxiv
PublishedMarch 31, 2026 at 4:00 AM

LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA Models

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

arXiv:2603.28301v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models achieve strong performance in robotic manipulation by leveraging pre-trained vision-language backbones. However, in downstream robotic settings, they are typically fine-tuned with limited data, leading to overfitting

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
arxivIMEX Interaction-Based Model Explanation45marxivDialogueVPR: Towards Conversational Visual Place Recognition45marxivHuman AI Construction of Bayesian Networks for Operational Decision Support -- A Virtual Survey Approach45marxivCapability from Access Structure, Not Scale: Lower Bounds and Pre-Registered Tests for Hybrid Sequence Models45m
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