arXiv:2605. 09778v2 Announce Type: replace Abstract: Evaluating softmax attention over a fixed long context requires reading every cached key-value pair for each new query token.
arXiv:2510. 07651v3 Announce Type: replace-cross Abstract: Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size.
arXiv:2604. 24432v2 Announce Type: replace-cross Abstract: Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system.
arXiv:2606. 18587v1 Announce Type: cross Abstract: Decoder-only Transformers compute attention over the KV cache of preceding tokens.
arXiv:2607. 16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck.
arXiv:2602. 03681v2 Announce Type: replace-cross Abstract: The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios.
arXiv:2606. 01294v1 Announce Type: cross Abstract: Linear attention reduces the quadratic cost of softmax attention by maintaining a recurrent fast-weight state, but it consistently lags on in-context retrieval and long-context tasks.
arXiv:2608. 06776v1 Announce Type: new Abstract: A standard self-attention layer consists of two interacting circuits: the query-key circuit that governs attention allocation, and the output-value circuit that maps attended representations to predictions.
arXiv:2607. 20524v1 Announce Type: new Abstract: Mean cross-positional attention degradation is widely reported in transformer interpretability, yet whether it causally limits contextual retrieval remains untested.
arXiv:2606. 09508v1 Announce Type: new Abstract: Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts.
arXiv:2604. 20920v2 Announce Type: replace Abstract: Sparse attention can reduce the cost of long-context inference, but most variants introduce new architectural components.
arXiv:2607. 18759v1 Announce Type: new Abstract: Transformers with relative positional encodings often extrapolate to sequences longer than those seen during training, whereas transformers with learned absolute encodings typically do not.
arXiv:2607. 27692v1 Announce Type: cross Abstract: Top-$K$ sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries.