·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Sequential Capacity of Quantum Processes with Finite Memory8h◆Q-MINO: A Minimal-Norm Method for Quantization-Aware Training8h◆Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning8h◆Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits8h◆Aligning Inductive Bias for Data-Efficient Generalization in State Space Models8h◆Variability Aware Recursive Neural Network (VARNN): A Residual-Memory Model for Capturing Temporal Deviation in Sequence Regression Modeling8h◆The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models8h◆Poincar\'e Meets Bellman: Revisable Memory, Operational Quotients, and Evidence-Supported Learning in Changing Environments8h◆Evaluating Memory Structure in LLM Agents8h◆Multi-Task Anti-Causal Learning for Reconstructing Urban Events from Residents' Reports8h◆Model Merging via Data-Free Covariance Estimation8h◆Geometry-Dependent Bounds for Online Non-Monotone DR-Submodular Maximization8h◆AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning8h◆Retrieval from Within: An Intrinsic Capability of Attention-Based Models8h◆dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models8h◆Scaling Collider Event Generation with Residual-Quantized Tokens8h◆ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs8h◆PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks8h◆CASCADE Conformal Prediction: Uncertainty-Adaptive Prediction Intervals for Two-Stage Clinical Decision Support8h◆On Reliability of Membership Inference Vulnerability Evaluation8h◆Sequential Capacity of Quantum Processes with Finite Memory8h◆Q-MINO: A Minimal-Norm Method for Quantization-Aware Training8h◆Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning8h◆Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits8h◆Aligning Inductive Bias for Data-Efficient Generalization in State Space Models8h◆Variability Aware Recursive Neural Network (VARNN): A Residual-Memory Model for Capturing Temporal Deviation in Sequence Regression Modeling8h◆The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models8h◆Poincar\'e Meets Bellman: Revisable Memory, Operational Quotients, and Evidence-Supported Learning in Changing Environments8h◆Evaluating Memory Structure in LLM Agents8h◆Multi-Task Anti-Causal Learning for Reconstructing Urban Events from Residents' Reports8h◆Model Merging via Data-Free Covariance Estimation8h◆Geometry-Dependent Bounds for Online Non-Monotone DR-Submodular Maximization8h◆AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning8h◆Retrieval from Within: An Intrinsic Capability of Attention-Based Models8h◆dFlowGRPO: Rate-Aware Policy Optimization for Discrete Flow Models8h◆Scaling Collider Event Generation with Residual-Quantized Tokens8h◆ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs8h◆PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks8h◆CASCADE Conformal Prediction: Uncertainty-Adaptive Prediction Intervals for Two-Stage Clinical Decision Support8h◆On Reliability of Membership Inference Vulnerability Evaluation8h◆
News/EchoPress: Query-Agnostic KV Cache Pruning via Virtual Context Reconstruction
arxiv
PublishedOctober 3, 2026 at 4:00 AM
—neutral

EchoPress: Query-Agnostic KV Cache Pruning via Virtual Context Reconstruction

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

arXiv:2610.00412v1 Announce Type: new Abstract: KV cache pruning reduces long-context inference memory usage by evicting less important key-value pairs. KVzip estimates importance through context reconstruction: prompting a model to repeat the context chunk by chunk. This achieves strong compression

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
arxivSequential Capacity of Quantum Processes with Finite Memory8harxivQ-MINO: A Minimal-Norm Method for Quantization-Aware Training8harxivExploiting Exogenous Structure for Sample-Efficient Reinforcement Learning8harxivRethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits8h
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