·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades3h◆Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards3h◆CogDrift-4D: Hierarchical Multimodal Modeling of Temporal Behavioral Decay for MCI Detection3h◆Task-Centric Multimodal Learning for Cognitive Impairment Detection3h◆Bridging the Gap: Converting Read Text to Conversational Dialogue3h◆VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents3h◆Learning When to Think: Utility-Guided Adaptive Reasoning for Efficient Text Retrieval3h◆Sharp and Stable Label-Free Calibration Certificates from Logical Coherence3h◆INCONVENIENT: A Benchmark to Assess LLM Generalization Capabilities from Convenience Samples3h◆Isolating a Language Model's Judgment with a Label-Free Subspace3h◆Ranking and Partitioning of Attention Heads for Sparse and Continual Reinforcement Learning Fine-tuning3h◆Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation3h◆Backward Compatibility in Zero-Bit Neural Audio Watermarking3h◆Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration3h◆CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for Clustering3h◆RoleQ: Role-Aligned Scales for Converting Language Models to Ternary3h◆CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness3h◆Progress Reward Model for Reinforcement Learning via Large Language Models3h◆FAOPs: Normal Forms and an Algebra for AI Agent Workflows3h◆Prism-1: Position- and Rival-Independent Scoring for System One Models3h◆CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades3h◆Gibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards3h◆CogDrift-4D: Hierarchical Multimodal Modeling of Temporal Behavioral Decay for MCI Detection3h◆Task-Centric Multimodal Learning for Cognitive Impairment Detection3h◆Bridging the Gap: Converting Read Text to Conversational Dialogue3h◆VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents3h◆Learning When to Think: Utility-Guided Adaptive Reasoning for Efficient Text Retrieval3h◆Sharp and Stable Label-Free Calibration Certificates from Logical Coherence3h◆INCONVENIENT: A Benchmark to Assess LLM Generalization Capabilities from Convenience Samples3h◆Isolating a Language Model's Judgment with a Label-Free Subspace3h◆Ranking and Partitioning of Attention Heads for Sparse and Continual Reinforcement Learning Fine-tuning3h◆Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation3h◆Backward Compatibility in Zero-Bit Neural Audio Watermarking3h◆Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration3h◆CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for Clustering3h◆RoleQ: Role-Aligned Scales for Converting Language Models to Ternary3h◆CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness3h◆Progress Reward Model for Reinforcement Learning via Large Language Models3h◆FAOPs: Normal Forms and an Algebra for AI Agent Workflows3h◆Prism-1: Position- and Rival-Independent Scoring for System One Models3h◆
News/Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection
arxiv
PublishedJuly 31, 2026 at 4:00 AM
—neutral

Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection

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

arXiv:2607.26273v1 Announce Type: cross Abstract: We consider a stochastic multi-objective bandit problem where, at each round, the agent selects a slate of $k$ arms and observes their $d$-dimensional reward vectors under semi-bandit feedback. We do not aim at identifying a single optimal arm; inste

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 →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivCascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades3harxivGibbs-Gap Policy Optimization for Off-Policy RL with Verifiable Rewards3harxivCogDrift-4D: Hierarchical Multimodal Modeling of Temporal Behavioral Decay for MCI Detection3harxivTask-Centric Multimodal Learning for Cognitive Impairment Detection3h
The Bubble Brief
MON · WED · FRI

Read AI 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