TwinKV is a training‑free, attention‑free repair pass that identifies and swaps orphaned and redundant tokens in a KV cache, improving long‑context inference for small models. It works by detecting near‑duplicate keys and can be composed with existing eviction policies without altering their scoring rules. Experiments on Qwen3‑4B and Llama‑3.2‑1B across LongBench, LooGLE, RULER, and MMLU‑Pro show that TwinKV consistently improves performance for most configurations, especially at tighter compression ratios.
arXiv:2607. 12204v1 Announce Type: new Abstract: Attention can be viewed as an online learner over context, yet existing test-time memories cannot certify that dropping a token leaves outputs unchanged or delete its influence outright.
arXiv:2608. 11231v1 Announce Type: new Abstract: LLM serving is increasingly accelerated by position-independent caching (PIC).
NestedKV is a training‑free key‑only KV cache compression technique for long‑context language models that uses global, block‑level, and sliding‑window key anchors to score tokens via multi‑time‑scale cosine anomaly. It combines these rankings with a head‑adaptive outer learner and surprise‑gated token routing, requiring no model modification or additional training. Experiments on Qwen3 and Llama‑3.2 across benchmarks such as RULER, LongBench, and MMLU‑Pro show that NestedKV outperforms existing methods when the retained cache is small, achieving up to 19‑point gains on RULER and LongBench at a 75% retention rate.
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.
The paper introduces GRKV, a training‑free method for compressing the key‑value cache in long‑context large language models. GRKV uses ridge‑regression to redistribute information from evicted tokens to retained ones, aiming to minimize the difference between compressed‑cache and full‑cache attention outputs. Experiments on LongBench and RULER show that GRKV improves overall performance with minimal overhead compared to other merging methods.
arXiv:2608. 01247v1 Announce Type: cross Abstract: Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets.
arXiv:2607. 27539v1 Announce Type: new Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record.
Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets. Existing methods primarily improve which original KV pairs are retained.
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs.
arXiv:2607.27836v2 Announce Type: replace Abstract: Large language model unlearning is consistently fragile under relearn attacks. On TOFU, fine-tuning on twenty forget examples substantially recover...
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.
arXiv:2607. 15498v1 Announce Type: cross Abstract: The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference.