arXiv:2605. 15913v4 Announce Type: replace-cross Abstract: Block attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios such as Retrieval-Augmented Generation (RAG).
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. 05305v3 Announce Type: replace-cross Abstract: Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models.
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:2607. 02980v1 Announce Type: cross Abstract: Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention.
arXiv:2607. 22663v1 Announce Type: new Abstract: Block diffusion has emerged as the dominant paradigm for scaling discrete diffusion language models (dLLMs), because decoding text in fixed-size blocks preserves parallel generation within each block while keeping the quadratic attention cost tractable.
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:2606. 04302v1 Announce Type: cross Abstract: Key-value (KV) caching accelerates inference of large language models (LLMs) by reusing past computations for generated tokens.
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:2601. 11667v2 Announce Type: replace-cross Abstract: Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment.
arXiv:2607. 09052v1 Announce Type: new Abstract: Block sparse attention is a hardware friendly way to alleviate the key-value (KV) cache read bottleneck in large language models (LLMs).
arXiv:2607. 19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context lengths under the test-time scaling paradigm.
arXiv:2502. 06818v4 Announce Type: replace Abstract: Recent works modify CLIP to perform open-vocabulary semantic segmentation in a training-free manner (TF-OVSS).