arXiv Machine Learning June 16, 2026 By Mufei Li, Shikun Liu, Dongqi Fu, Haoyu Wang, Yinglong Xia, Hong Li, Hong Yan, Pan Li

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

Read the original on arXiv Machine Learning →

arXiv:2606. 17034v1 Announce Type: cross Abstract: Post-hoc context erasing over the KV cache is challenging because a local edit has a global consequence: once a span has been processed, its influence propagates into the cached states of all subsequent tokens.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 30

Memory-Managed Long-Context Attention: A Preliminary Study of Editable Request-Local Memory

arXiv:2606. 28876v1 Announce Type: cross Abstract: Long-context language models often conflate two different goals: compressing history into an efficient state, and maintaining reliable long-term memory.

By Junyi Zou, Avrova Donz

llms benchmarks

arXiv Machine Learning

Aug 7

QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding

arXiv:2608. 05326v1 Announce Type: new Abstract: Autoregressive large language model inference is increasingly constrained by the memory footprint of the Key-Value (KV) cache.

By Ayushman Garg, Akshita Gupta, Shaswata Bhattacharya, Abhishek Gupta, Sandeep Kumar, Manoj Kumar

llms efficiency benchmarks

arXiv Machine Learning

Jul 13

Memory-Managed Long-Context Attention: Bounded Editable Memory with a Hard Lifecycle and Calibrated Sparse Fallback

arXiv:2606. 28876v2 Announce Type: replace-cross Abstract: We study memory-managed long-context attention: explicit bounded memory with a learned query-independent writer, lifecycle control, query-aware reading, calibrated sparse fallback, and frozen-LLM generation from raw evidence.

By Junyi Zou, Avrova Donz

llms

arXiv AI

Aug 11

SemPIC: Learning Semantic Position-Independent KV Caches

arXiv:2607. 28069v2 Announce Type: replace Abstract: Long-context retrieval and agentic workloads repeatedly reuse the same documents under changing instructions, histories, and document orders.

By Hui Xie, Peng Xiao, Yutong Deng, Shuoran Dou, Jian Yang, Jinyang Guo

agents fine-tuning efficiency

arXiv AI

Jul 7

IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference

arXiv:2605. 25475v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference.

By Xintong Yang, Hao Gu, Binxing Xu, Lujun Li, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Yike Guo, Sirui Han

llms efficiency

arXiv Machine Learning

Jul 31

Back from the Future: Key-Value Cache Management by Counter-Causal Surprise

arXiv:2607. 27600v1 Announce Type: new Abstract: Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years.

By Stephen Gould, Anton van den Hengel

llms efficiency multimodal benchmarks

Related stories

Memory-Managed Long-Context Attention: A Preliminary Study of Editable Request-Local Memory

QEvict: Recoverable Quantized KV Eviction for Attention-Drift-Robust Long-Context Decoding

Memory-Managed Long-Context Attention: Bounded Editable Memory with a Hard Lifecycle and Calibrated Sparse Fallback

SemPIC: Learning Semantic Position-Independent KV Caches

IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference

Back from the Future: Key-Value Cache Management by Counter-Causal Surprise