·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Real-Time Intelligence with IBM Time Series Models on Confluent34m◆OpenAI faces 30 more lawsuits tied to Tumbler Ridge shooting2h◆The Curse of Multilinguality in Lexical Normalization10h◆A Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving Policies10h◆SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification10h◆Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs10h◆Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs10h◆ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents10h◆Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing Problems10h◆CWoMP: Morpheme Representation Learning for Interlinear Glossing10h◆TempCloze: Can Video-LLMs Identify the Missing Middle?10h◆Agentic Empirical Asset Pricing: Methodological Foundations10h◆Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?10h◆Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement10h◆Can LLMs Discover Scientific Laws in Real and Parallel Worlds?10h◆Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random10h◆TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories10h◆Automated Tree Knowledge Graph Construction using Ontology Expansion and Retrieval from Vietnamese History Textbooks10h◆Modelpedia: A Catalog of Model Findings for the Meta-Science of AI10h◆Workload Identification with Physical Side Channels for AI Governance10h◆Real-Time Intelligence with IBM Time Series Models on Confluent34m◆OpenAI faces 30 more lawsuits tied to Tumbler Ridge shooting2h◆The Curse of Multilinguality in Lexical Normalization10h◆A Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving Policies10h◆SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification10h◆Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs10h◆Escaping Redundant Reasoning: Structure-Aware Search for Inference-Time LLMs10h◆ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents10h◆Reinforcement Learning Enhanced LLM Agents for Complex Vehicle Routing Problems10h◆CWoMP: Morpheme Representation Learning for Interlinear Glossing10h◆TempCloze: Can Video-LLMs Identify the Missing Middle?10h◆Agentic Empirical Asset Pricing: Methodological Foundations10h◆Are Near-Tied LLM Rankings Robust to Family-DIF-Guided Benchmark Recomposition?10h◆Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement10h◆Can LLMs Discover Scientific Laws in Real and Parallel Worlds?10h◆Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable From Random10h◆TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories10h◆Automated Tree Knowledge Graph Construction using Ontology Expansion and Retrieval from Vietnamese History Textbooks10h◆Modelpedia: A Catalog of Model Findings for the Meta-Science of AI10h◆Workload Identification with Physical Side Channels for AI Governance10h◆
News/TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling
arxiv
PublishedMarch 30, 2026 at 4:00 AM

TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling

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

arXiv:2602.07374v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve remarkable performance but demand substantial computational resources, limiting deployment on edge devices and resource-constrained environments. We present TernaryLM, a 132M-parameter transformer trained

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
arxivThe Curse of Multilinguality in Lexical Normalization10harxivA Closed-Loop Evaluation of Capability Loss and Recovery in Compressed Driving Policies10harxivSOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification10harxivControl-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs10h
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