·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
CaLR: Causal Latent Revision for Robust Diffusion Reasoning5h◆LoRA Enhanced Contrastive Learning with SAS Vision Transformers5h◆Can Agents Design Better Chips with a Higher Level Abstraction?5h◆SpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificity5h◆Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency5h◆Beyond Exact Match: Task-Aware GRPO for Cross-Domain PCBA Visual Question Answering5h◆Authorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution5h◆Co-Evolving Zero-Day Jamming: Adaptive Attack Synthesis and Graph Attention-Based Online Detection5h◆CESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT Devices5h◆From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers5h◆Knowledge-Graph-Augmented Chronos-2 for HEC-RAS Surrogate Forecasting5h◆AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents5h◆Consistent Relexicalization of Clinical Documents using Graph-Based Approach5h◆WS-NeRF: A Mamba-Driven World-State-Aware Adaptive Deblurring Neural Radiance Field5h◆HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference5h◆2nd Place Solution to the HANDS 2026 Workshop Challenge-Dexterous Grasp Motion Track: Single-Shot Trajectory Warping for Grasp Motion Generation5h◆VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration5h◆OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios5h◆On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation5h◆GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions5h◆CaLR: Causal Latent Revision for Robust Diffusion Reasoning5h◆LoRA Enhanced Contrastive Learning with SAS Vision Transformers5h◆Can Agents Design Better Chips with a Higher Level Abstraction?5h◆SpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificity5h◆Hallucination-R1: Robustness-Oriented Paraphrase Generation for Factual Consistency5h◆Beyond Exact Match: Task-Aware GRPO for Cross-Domain PCBA Visual Question Answering5h◆Authorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution5h◆Co-Evolving Zero-Day Jamming: Adaptive Attack Synthesis and Graph Attention-Based Online Detection5h◆CESBench: Benchmarking Large Language Models on Cryptographic Engineering Security for IoT Devices5h◆From Memory to Behavior: A Behavior-Aware Role-Playing Framework for Social Media Influencers5h◆Knowledge-Graph-Augmented Chronos-2 for HEC-RAS Surrogate Forecasting5h◆AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents5h◆Consistent Relexicalization of Clinical Documents using Graph-Based Approach5h◆WS-NeRF: A Mamba-Driven World-State-Aware Adaptive Deblurring Neural Radiance Field5h◆HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference5h◆2nd Place Solution to the HANDS 2026 Workshop Challenge-Dexterous Grasp Motion Track: Single-Shot Trajectory Warping for Grasp Motion Generation5h◆VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration5h◆OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios5h◆On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation5h◆GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions5h◆
News/TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching
arxiv
PublishedSeptember 21, 2026 at 4:00 AM

TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching

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

arXiv:2609.21172v1 Announce Type: new Abstract: Large language models (LLMs) are moving onto mobile devices for increasingly diverse workloads over text, images, video, and audio. These applications often require long contexts, making the Key-Value (KV) cache a dominant memory bottleneck because it

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
arxivCaLR: Causal Latent Revision for Robust Diffusion Reasoning5harxivLoRA Enhanced Contrastive Learning with SAS Vision Transformers5harxivCan Agents Design Better Chips with a Higher Level Abstraction?5harxivSpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificity5h
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