·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Squid: Long Context as a New Modality for Energy-Efficient On-Device Language Models2h◆GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification2h◆Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking2h◆OntoExtend: A Framework for Requirement-driven and Scalable Ontology Extension with LLMs2h◆Can Multimodal Large Language Models Understand OCT?2h◆FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications2h◆SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning2h◆Comparing Spectrogram Front-Ends for Abnormal Heart-Sound Detection with a Convolutional Neural Network2h◆Fully-sensorized smart-eyewear platform for on-device Machine Learning2h◆International Agreements to Limit Frontier AI: Objectives and Exit2h◆RouteCost: A Production-Inspired Multi-Stage Framework for Pre-Order Shipping Cost Estimation in E-Commerce2h◆Nonlinear Bandit2h◆From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language2h◆Intelligence-Guided Adaptive Purification for DDoS-Resilient Quantum Networks: A CUDA-Q based Study2h◆GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification2h◆Spectral Adaptive Conformal Prediction for Structured Non-Exchangeable Data2h◆PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation2h◆Reliable Remediation Impact Prediction for Black-Box Security Ratings2h◆Hierarchy-Aware and Anatomy-Guided Learning for Lung Ultrasound Video Classification2h◆COLIP-2: Olfaction-Vision-Language Embeddings2h◆Squid: Long Context as a New Modality for Energy-Efficient On-Device Language Models2h◆GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification2h◆Towards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking2h◆OntoExtend: A Framework for Requirement-driven and Scalable Ontology Extension with LLMs2h◆Can Multimodal Large Language Models Understand OCT?2h◆FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications2h◆SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning2h◆Comparing Spectrogram Front-Ends for Abnormal Heart-Sound Detection with a Convolutional Neural Network2h◆Fully-sensorized smart-eyewear platform for on-device Machine Learning2h◆International Agreements to Limit Frontier AI: Objectives and Exit2h◆RouteCost: A Production-Inspired Multi-Stage Framework for Pre-Order Shipping Cost Estimation in E-Commerce2h◆Nonlinear Bandit2h◆From Weights to Words: Expressing and Editing Preference Model Inferences in Natural Language2h◆Intelligence-Guided Adaptive Purification for DDoS-Resilient Quantum Networks: A CUDA-Q based Study2h◆GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification2h◆Spectral Adaptive Conformal Prediction for Structured Non-Exchangeable Data2h◆PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation2h◆Reliable Remediation Impact Prediction for Black-Box Security Ratings2h◆Hierarchy-Aware and Anatomy-Guided Learning for Lung Ultrasound Video Classification2h◆COLIP-2: Olfaction-Vision-Language Embeddings2h◆
News/Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs
arxiv
PublishedJuly 14, 2026 at 4:00 AM
—neutral

Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs

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

arXiv:2410.03565v4 Announce Type: replace-cross Abstract: In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (CMDP), agents train on a fixed, finite set of contexts and must generalize to new ones. Recent work has demonstrated that training on additional states,

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
arxivSquid: Long Context as a New Modality for Energy-Efficient On-Device Language Models2harxivGRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification2harxivTowards Agentic Agent-based Models: Feasibility, Performance, and Statistical Model Checking2harxivOntoExtend: A Framework for Requirement-driven and Scalable Ontology Extension with LLMs2h
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