·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
The sameness problem behind those unappetizing AI-generated menus40m◆ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval1h◆MasterControl Seventeen Every Time1h◆GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving1h◆PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing1h◆HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews1h◆The Attention Triangle in Audio-Video Models1h◆CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception1h◆Semantic Bayesian World Models1h◆Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations1h◆Bioinfoysis Technical Report1h◆STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation1h◆Xiaomi-TabLDM: A Tabular Foundation Model Technical Report1h◆Inferring Affective Consciousness in an Artificial Agent: A Case Study1h◆Lose the Order, Keep the Hierarchy: Deordering HTN Plans1h◆Value-Preserving Architectures for Agentic AI Systems1h◆Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting1h◆Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding1h◆FiMI Banking: A Sovereign Model for Indian Retail Banking1h◆Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning1h◆The sameness problem behind those unappetizing AI-generated menus40m◆ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval1h◆MasterControl Seventeen Every Time1h◆GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving1h◆PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing1h◆HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews1h◆The Attention Triangle in Audio-Video Models1h◆CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative Perception1h◆Semantic Bayesian World Models1h◆Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain Operations1h◆Bioinfoysis Technical Report1h◆STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation1h◆Xiaomi-TabLDM: A Tabular Foundation Model Technical Report1h◆Inferring Affective Consciousness in an Artificial Agent: A Case Study1h◆Lose the Order, Keep the Hierarchy: Deordering HTN Plans1h◆Value-Preserving Architectures for Agentic AI Systems1h◆Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting1h◆Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding1h◆FiMI Banking: A Sovereign Model for Indian Retail Banking1h◆Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated Graph Learning1h◆
News/CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO
arxiv
PublishedJune 2, 2026 at 4:00 AM

CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO

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

arXiv:2606.00172v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR), especially Group Relative Policy Optimization (GRPO), has been widely used to improve reasoning in large language models. However, outcome-level rewards provide only sparse supervision, and group-r

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
arxivExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval1harxivMasterControl Seventeen Every Time1harxivGrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving1harxivPPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing1h
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