·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
AI music maker Suno now generates spoken words54m◆Don’t be fooled—LLMs don’t reason2h◆AutoSynthData: Generating Training Data for Enterprise Agents6h◆On the (In)effectiveness of AMR Augmentation for Large Language Models6h◆cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents6h◆Mitigating Memorization In Language Models6h◆MoEless: Efficient MoE LLM Serving with Serverless Experts6h◆Fork-Think with Confidence6h◆A Moving-Horizon Approximate Branch-and-Reduce Method for Deep Classification Trees6h◆Bongard: Training Machine Intuition6h◆Inference Auctions6h◆DEdit: Iterative Draft Editing for Speculative Decoding6h◆4MT-VLM: How Coarse Is a VLMs Cognitive Map?6h◆JuryFlow: Disagreement-Guided Human-in-the-Loop Multi-Agent Evaluation6h◆OverdoseMoE: A Multi-Expert Framework for Opioid Overdose Risk Prediction6h◆Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering6h◆OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation6h◆JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion6h◆Incident-Arena: Getting agents to the last nine of reliability6h◆Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard6h◆AI music maker Suno now generates spoken words54m◆Don’t be fooled—LLMs don’t reason2h◆AutoSynthData: Generating Training Data for Enterprise Agents6h◆On the (In)effectiveness of AMR Augmentation for Large Language Models6h◆cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents6h◆Mitigating Memorization In Language Models6h◆MoEless: Efficient MoE LLM Serving with Serverless Experts6h◆Fork-Think with Confidence6h◆A Moving-Horizon Approximate Branch-and-Reduce Method for Deep Classification Trees6h◆Bongard: Training Machine Intuition6h◆Inference Auctions6h◆DEdit: Iterative Draft Editing for Speculative Decoding6h◆4MT-VLM: How Coarse Is a VLMs Cognitive Map?6h◆JuryFlow: Disagreement-Guided Human-in-the-Loop Multi-Agent Evaluation6h◆OverdoseMoE: A Multi-Expert Framework for Opioid Overdose Risk Prediction6h◆Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering6h◆OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong Adaptation6h◆JusticeAxis: Benchmarking Legal Judgment between Rigid Rule Application and Ungrounded Discretion6h◆Incident-Arena: Getting agents to the last nine of reliability6h◆Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard6h◆
News/Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing
arxiv
PublishedSeptember 17, 2026 at 4:00 AM

Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing

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

arXiv:2609.18131v1 Announce Type: cross Abstract: In this paper, we present a Mixture-of-Experts (MoE) quantization method based on activation entropy. Although quantization reduces memory and computational costs, it can substantially degrade performance. In particular, performance decline is pronou

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
arxivOn the (In)effectiveness of AMR Augmentation for Large Language Models6harxivcua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents6harxivMitigating Memorization In Language Models6harxivMoEless: Efficient MoE LLM Serving with Serverless Experts6h
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 ↗
Built by Marouane Gazouzi
HomeModelsNews