·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models1h◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders1h◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA1h◆Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging1h◆Multi-Mask Diffusion Language Models for Few-Step Generation1h◆Solar Open 2 Technical Report1h◆The Geometry of Personality: Activation Steering with Jungian Cognitive Functions1h◆Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning1h◆H$^2$SD: Hybrid Hindsight Self-Distillation1h◆LunarFM: A Shared Multimodal Representation of the Moon's Surface1h◆Prior laundering: learned priors with inherited, undetectable overconfidence1h◆Deep Sigma Point Processes for RCS Modeling in Spaceborne SAR Imagery1h◆Prompt as a Data Type: In-Database LLM Prompt Management and Rewriting1h◆CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference1h◆Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support1h◆Spatially-Enhanced Temporal Fusion Transformer: Interpretable Multi-Output Prediction for Parametric Dynamical Systems with Time-Varying Inputs1h◆Meta-Learning Approaches for Speaker-Dependent Voice Fatigue Models1h◆A Comparative Benchmark of Federated Learning Strategies for Mortality Prediction on Heterogeneous and Imbalanced Clinical Data1h◆Simpson's Paradox in Behavioral Curves: How Aggregation Distorts Parametric Models of User Dynamics1h◆DriftXpress: Faster Drifting Models via Projected RKHS Fields1h◆A Consensus-Based Framework for Relative Preference Evaluation of Large Language Models1h◆Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders1h◆Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA1h◆Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging1h◆Multi-Mask Diffusion Language Models for Few-Step Generation1h◆Solar Open 2 Technical Report1h◆The Geometry of Personality: Activation Steering with Jungian Cognitive Functions1h◆Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning1h◆H$^2$SD: Hybrid Hindsight Self-Distillation1h◆LunarFM: A Shared Multimodal Representation of the Moon's Surface1h◆Prior laundering: learned priors with inherited, undetectable overconfidence1h◆Deep Sigma Point Processes for RCS Modeling in Spaceborne SAR Imagery1h◆Prompt as a Data Type: In-Database LLM Prompt Management and Rewriting1h◆CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference1h◆Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support1h◆Spatially-Enhanced Temporal Fusion Transformer: Interpretable Multi-Output Prediction for Parametric Dynamical Systems with Time-Varying Inputs1h◆Meta-Learning Approaches for Speaker-Dependent Voice Fatigue Models1h◆A Comparative Benchmark of Federated Learning Strategies for Mortality Prediction on Heterogeneous and Imbalanced Clinical Data1h◆Simpson's Paradox in Behavioral Curves: How Aggregation Distorts Parametric Models of User Dynamics1h◆DriftXpress: Faster Drifting Models via Projected RKHS Fields1h◆
News/MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation
arxiv
PublishedJuly 27, 2026 at 4:00 AM

MoE$^2$-LoRA: When MoE Models Meet MoE-style Low-Rank Adaptation

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

arXiv:2607.21978v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have been widely adopted in large language models, yet parameter-efficient fine-tuning (PEFT) for MoE models remains underexplored. Existing PEFT methods for MoE either ignore router priors with uniform adapters,

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
arxivA Consensus-Based Framework for Relative Preference Evaluation of Large Language Models1harxivProbing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders1harxivData Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA1harxivEnjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging1h
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