arXiv:2608.30263v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) incur substantial inference costs due to their long and highly redundant visual-token sequences. Diversity-based...
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:2609.30738v1 Announce Type: new Abstract: KV cache eviction methods such as SnapKV and PyramidKV rank tokens solely by mean attention over a small observation window. We study a unified score,...
arXiv:2610.16615v1 Announce Type: new Abstract: Visual token compression has emerged as a critical technique for reducing the inference cost of Vision-Language Models. Existing methods select tokens...
arXiv:2607. 24331v1 Announce Type: new Abstract: As the inference phase of Large Language Models (LLMs) requires handling long context windows, the Key-Value (KV) cache initially appears to address this challenge but eventually becomes a significant bottleneck as the context window continues to grow.
arXiv:2607. 22586v1 Announce Type: new Abstract: Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with context length and becomes a major bottleneck due to the large number of visual tokens.
The paper proposes LaProx, a new KV cache eviction strategy for long‑context LLM inference that redefines the problem as an output‑aware, layer‑wise matrix multiplication approximation. Unlike prior methods that rely only on local attention weights, LaProx explicitly models the interaction between attention maps and projected value states, accounting for inter‑head dependencies to assign globally comparable token importance scores. Experiments on 19 datasets, including LongBench and Needle‑In‑A‑Haystack, show that LaProx retains model performance while using only 5% of the KV cache and reduces accuracy loss by up to 2× under extreme compression compared to state‑of‑the‑art baselines.
arXiv:2609.36916v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur high inference latency from long visual token sequences. Existing pruning methods commonly use attention...
arXiv:2606.14782v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong vision-language reasoning but incur large KV caches and high decoding latency with lo...
arXiv:2606. 26875v1 Announce Type: cross Abstract: Reasoning capability has advanced rapidly in large language models (LLMs), leading to an increasing size of key-value (KV) cache in both prefilling and decoding stages.
arXiv:2606. 29563v1 Announce Type: cross Abstract: Large language models (LLMs) excel at complex tasks like question answering and summarization, thanks to their ability to handle long-context inputs.
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.