Kv-Cache Steering

Ask about this topic

Recent momentum

+17%

7 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Also in Key-Value Cache

Neighbouring directions

CacheKey-Value CacheKey-Value Cache CompressionKey-ValueKey-Value Cache QuantizationKey-Value Cache EvictionEviction

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-14

6 new papers

A weekly snapshot of new work published in Kv-Cache Steering.

Period ending 2026-09-07

1 new paper

A weekly snapshot of new work published in Kv-Cache Steering.

48 papers

Latest in Kv-Cache Steering

Open your feed →
CardsList

  1. Shared KV Caching for Replicated 27B Inference: Correctness Failures and Performance Boundaries

    Sep 14, 2026Frank LiKv-Cache SteeringGraphics Processing Unit Memory

  2. K/V-Cache Interventions Dissociate Representation Alignment from Persona Expression in Decoder-Only Language Models

    Sep 11, 2026Yu Sun, Mengyin Lu, Cong Feng +2Kv-Cache SteeringPersonas

  3. Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs

    Sep 11, 2026Joseph Kanichai, Tiziano De Matteis, Animesh TrivediKv-Cache SteeringKey-Value Cache

  4. Composable CXL Memory as a Kubernetes-Native Shared Memory for LLM Serving

    Sep 9, 2026Hongjian Fan, Kevin Zhang, David Habinsky +1Kv-Cache SteeringKubernetes

  5. KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

    Sep 9, 2026Xi Shi, Qian LouKv-Cache SteeringRetrieval Benchmarks

  6. Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?

    Sep 9, 2026Fumihiko Tachibana, Daisuke Miyashita, Jun DeguchiKv-Cache SteeringKey-Value Cache

  7. BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents

    Sep 8, 2026Yanhong Qian, Xuanying He, Qingguo Meng +3Kv-Cache SteeringKey-Value Cache

  8. A Universal Context-Reuse Layer for Cross-Model KV Sharing

    Aug 31, 2026Yi Li, Dongming Jiang, Yi Zhao +1Kv-Cache SteeringKey-Value

  9. Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference

    Aug 10, 2026Tejasvi C. AddagadaKv-Cache SteeringKey-Value Cache

  10. KGCache: Amortized Subgraph Retrieval for KG Reasoning with LLMs

    Aug 8, 2026Uros Stanic, Changcheng Yuan, Sabuj Laskar +1Knowledge GraphsKv-Cache Steering

  11. Output-Aware Rotation for INT2 KV-Cache Quantization

    Aug 3, 2026Vincent-Daniel Yun, Woosang Lim, Minsoo Cheong +4Key-Value Cache QuantizationKv-Cache Steering

  12. Kalypso: Relational LLM Serving

    Jul 26, 2026Hojae Son, Md Ashraful Islam, Huy Gia Cao +2Large Language Model ServingLarge Language

  13. MoA-Structured Decode Attention DNF Derivation, KV-Cache Accumulation, GQA/MQA, and OpenACC Kernel

    Jul 21, 2026Lenore Mulin, Gaetan HainsTransformer AttentionKey-Value Cache Quantization

  14. SALT: Salience-Aware Lexical Trie for Long-Context Compression

    Jul 20, 2026Oteo Mamo, Hyunjin Yi, Joydhriti Choudhury +2Efficient Long-Context InferenceLarge Language Model Memory

  15. Regularize or Localize: When Training-Time KV-Cache Geometry Pays Under Quantization

    Jul 19, 2026Libo Sun, Po-Wei Harn, Zewei Zhang +2Key-Value Cache QuantizationKv-Cache Steering

  16. PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization

    Jul 17, 2026Yuchen Yang, Yifan Zhao, Anisha Dasgupta +1Mixture-Of-Expert Language ModelsKv-Cache Steering

  17. Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel

    Jul 15, 2026Sietse SchelpeFrozen ModelsKv-Cache Steering

  18. KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling

    Jul 10, 2026Peng Kuang, Haibo Jin, Xiaoyu Han +5Process Reward ModelingKv-Cache Steering

  19. Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference

    Jul 8, 2026Vladimir GusevKey-Value CacheKv-Cache Steering

  20. TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation

    Jul 7, 2026Andrii Balashov, Olena PonomarovaMixture-Of-Expert RoutingKey-Value Cache Quantization

  21. When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration

    Jun 27, 2026Luís Brito, Carlos BaqueroLarge Language Model AgentsAgent Memory

  22. ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory

    Jun 25, 2026Le Tu Ngoc Minh, Jinyeong Lim, Dongsu HanKv-Cache SteeringKey-Value Cache

  23. CrossPool: Efficient Multi-LLM Serving for Cold MoE Models through KV-Cache and Weight Disaggregation

    Jun 23, 2026Zhuoren Ye, Tianyu Wo, Dinghao Xue +4Kv-Cache SteeringLarge Language Model Serving

  24. Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving

    Jun 18, 2026Liang SuIntermediate CheckpointsKv-Cache Steering

  25. KVEraser: Learning to Steer KV Cache for Efficient Localized Context Erasing

    Jun 15, 2026Mufei Li, Shikun Liu, Dongqi Fu +5Kv-Cache SteeringKey-Value Cache

  26. See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents

    Jun 11, 2026Siyi Chen, Xiaoyan Zhang, Meng Wu +7Heterogeneous AgentsLatent Representation Alignment

  27. IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference

    Jun 6, 2026Junjie Li, Jiong Lou, Jie LiKv-Cache SteeringKey-Value Cache Eviction

  28. CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models

    May 27, 2026Fengze Yang, Bo Yu, Xuewen Luo +2Recent Vision-Language ModelsVision Encoders

  29. A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration

    May 25, 2026Lipeng Dai, Luping Xiang, Kun YangWireless Resource AllocationLow-Latency Systems

  30. ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning

    May 21, 2026Yeqiu Chen, Ziyan Liu, Zhenxin Huang +3Kv-Cache SteeringKey-Value Cache

  31. KVBuffer: IO-aware Serving for Linear Attention

    May 18, 2026Longwei Zou, Lin ZhongDynamic Sparse AttentionKv-Cache Steering

  32. VeriCache: Turning Lossy KV Cache into Lossless LLM Inference

    May 17, 2026Jiayi Yao, Samuel Shen, Kuntai Du +7Kv-Cache SteeringKey-Value Cache

  33. KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference

    May 12, 2026Alireza Nadali, Patrick Cooper, Ashutosh Trivedi +1Efficient Long-Context InferenceKv-Cache Steering

  34. Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing

    May 11, 2026Yunze Zhao, Yibo Zhao, Yuchen Zhang +2Vulnerability Detection & RepairLarge Language Model Serving

  35. Nectar: Neural Estimation of Cached-Token Attention via Regression

    May 10, 2026João Monteiro, Michal Klein, Pierre Ablin +1Softmax AttentionEfficient Long-Context Inference

  36. KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving

    May 10, 2026Zhiqing Zhong, Zhijing Ye, Jian Zhang +3Kv-Cache SteeringGraphics Processing Unit Memory

  37. PEEK: Predictive Queue-Informed KV Cache Management for LLM Serving

    May 10, 2026Bing Xie, Zhipeng Wang, Masahiro Tanaka +1Kv-Cache SteeringEviction

  38. ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference

    May 9, 2026Junjie Li, Jiong Lou, Jie LiLLM Inference EfficiencyEfficient Long-Context Inference

  39. Echo: KV-Cache-Free Associative Recall with Spectral Koopman Operators

    May 7, 2026Anupama Sridhar, Alexander JohansenKv-Cache SteeringMulti-Hop Retrieval

  40. Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management

    May 7, 2026Haoyu Zheng, Fangcheng Fu, Jia Wu +6Kv-Cache SteeringAgentic Workflows

  41. Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility

    May 7, 2026Jungsuk Oh, Hyeseo Jeon, Hyunjune Ji +2Efficient Long-Context InferenceLLM Inference Efficiency

  42. When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?

    Apr 29, 2026Tianyu Liu, Yuhao Shen, Xinyi Hu +8Speculative DecodingKv-Cache Steering

  43. Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache Steering

    Apr 20, 2026Manan Gupta, Dhruv KumarError CorrectionResidual Stream

  44. SLO-Guard: Crash-Aware, Budget-Consistent Autotuning for SLO-Constrained LLM Serving

    Apr 19, 2026Christian LysenstøenLarge Language Model ServingLow-Latency Systems

  45. Bit-Flip Vulnerability of Shared KV-Cache Blocks in LLM Serving Systems

    Apr 19, 2026Yuji Yamamoto, Satoshi MatsuuraKv-Cache SteeringLanguage Model Evasion Attacks

  46. Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation

    Apr 3, 2026Xingtong Ge, Yi Zhang, Yushi Huang +6Autoregressive Video GenerationDistributional Learning

  47. InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context

    Mar 5, 2026Xin Teng, Canyu Zhang, Shaoyi Zheng +3Kv-Cache SteeringRetrieval-Augmented Generation

  48. LLM Serving Optimization with Variable Prefill and Decode Lengths

    Aug 8, 2025Meixuan Wang, Yinyu Ye, Zijie ZhouLarge Language Model ServingAdaptive Scheduling