·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Opendoor’s India exit is fueling a bigger conversation about AI and outsourcing4h◆MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning4h◆Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!4h◆Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions4h◆The Impossibility of Eliciting Latent Knowledge4h◆Mapping Scientific Literature with Large Language Models and Topic Modeling4h◆Grounding Computer Use Agents on Human Demonstrations4h◆Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models4h◆Implicit Neural Representations of Individual Behavior4h◆LSTM based IoT Device Identification4h◆StanceNakba Shared Task: Actor and Topic-Aware Stance Detection in Public Discourse4h◆UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA4h◆Phi-Actor-Critic: Steering General-Sum Games to Pareto-Efficient Correlated Equilibria4h◆Composing Linear Layers from Irreducibles4h◆Visualizing LLM Latent Space Geometry Through Dimensionality Reduction4h◆Robustness of Mixtures of Experts to Feature Noise4h◆Breaking the Ice: Analyzing Cold Start Latency in vLLM4h◆MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation4h◆Pretrained self-supervised speech models can recognize unseen consonants4h◆BioMamba: Domain-Adaptive Biomedical Language Models4h◆Opendoor’s India exit is fueling a bigger conversation about AI and outsourcing4h◆MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning4h◆Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!4h◆Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions4h◆The Impossibility of Eliciting Latent Knowledge4h◆Mapping Scientific Literature with Large Language Models and Topic Modeling4h◆Grounding Computer Use Agents on Human Demonstrations4h◆Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models4h◆Implicit Neural Representations of Individual Behavior4h◆LSTM based IoT Device Identification4h◆StanceNakba Shared Task: Actor and Topic-Aware Stance Detection in Public Discourse4h◆UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA4h◆Phi-Actor-Critic: Steering General-Sum Games to Pareto-Efficient Correlated Equilibria4h◆Composing Linear Layers from Irreducibles4h◆Visualizing LLM Latent Space Geometry Through Dimensionality Reduction4h◆Robustness of Mixtures of Experts to Feature Noise4h◆Breaking the Ice: Analyzing Cold Start Latency in vLLM4h◆MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation4h◆Pretrained self-supervised speech models can recognize unseen consonants4h◆BioMamba: Domain-Adaptive Biomedical Language Models4h◆
News/Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation
arxiv
PublishedJune 10, 2026 at 4:00 AM
—neutral

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation

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

arXiv:2606.09864v1 Announce Type: cross Abstract: Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measuring perplexity and accuracy without assessing the safety impact. In this study, we explore alignmen

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Mentioned models
01
  • 01
    Mistral-7B
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
03
#quantization#safety#large-language-models
Mentioned companies
01
NVIDIA

No replies yet. Be first.

Mentioned models
01
  • 01
    Mistral-7B
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
03
#quantization#safety#large-language-models
Mentioned companies
01
NVIDIA

Related coverage

More from ARXIV
arxivMODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning4harxivPosition: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!4harxivGeneralizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions4harxivThe Impossibility of Eliciting Latent Knowledge4h
The Bubble Brief
WEEKLY

Read quantization insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews