arXiv:2605. 08696v4 Announce Type: replace-cross Abstract: Over the last two decades, language modeling has experienced a shift from the use of predominantly recurrent architectures that process tokens sequentially during training and inference to non-recurrent models that process sequence elements in parallel during training, which results in greater training efficiency and stability at the expense of lower inference throughput.
By Benjamin L. Badger
arXiv:2606. 16093v1 Announce Type: cross Abstract: Modeling long-range dependencies remains a central challenge in natural language processing.
By Kuzey Torlak, H\"useyin Arda Arslan, An{\i}l Dervi\c{s}o\u{g}lu, Beyza Nur Deniz, Onur Boyar
arXiv:2606. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
By Ang Li, Sean McLeish, Haozhe Chen, Nimit Kalra, Zaiqian Chen, Artem Gazizov, Venkata Anoop Suhas Kumar Morisetty, Bhavya Kailkhura, Harshitha Menon, Zhuang Liu, Brian R. Bartoldson, Tom Goldstein, Sanae Lotfi, Micah Goldblum, Pavel Izmailov
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degrade model quality substantially or require considerable time and compute to compress a single long prompt.
arXiv:2609.25537v1 Announce Type: new
Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing laten...
By Md Mostafizer Rahman, Md Faizul Ibne Amin, Md Shahajada Mia, Yutaka Watanobe, Fang Liu
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.
By Yu Zhao, Zekun Zhang, Fan Jiang, Bo Zeng, Linlong Xu, Shimin Shan, Yu Liu, Longyue Wang, Weihua Luo
CompKV introduces a compensation‑aware sparse attention framework for long‑context LLM inference. It partitions tokens into blocks and optimizes token selection to minimize the error introduced by block‑level mean compensation, using compact block‑level statistics. Experiments on RULER and LongBench‑Pro show CompKV outperforms other sparse baselines and achieves up to a 6.85× speedup over full attention.
By Zhen Huang, Ruizhe Yao, Danyi Liu, Xinrui Chen, Shuwei Li, Siru Zhong, Zijian Cao, Yushan Lai, Mingming Guo, Weijie Zheng, Haohuan Fu
Elastic Threshold Attention (ETA) is a trainable attention mechanism that dynamically predicts contextual thresholds from query representations, enabling selective pruning of KV cache tokens during long‑context decoding. By multiplicatively suppressing sub‑threshold logits during training, ETA avoids representation collapse and eliminates localized attention sinks, allowing a 1.45B model to match dense attention performance at roughly 85% training sparsity and 38% active decode density. At inference, a custom Triton kernel achieves up to 2.5× faster decoding on sequences up to 512K tokens, and an offline calibration step can further reduce compute by 27% by freezing per‑head thresholds.
By Themistoklis Haris, Henry Li, Maryam Karimzadehgan
arXiv:2608. 08888v1 Announce Type: new Abstract: Autoregressive transformers compute along two axes: horizontally across generated tokens, and vertically through model depth.
By Xi Wang, Ziyang Cai, Zheng Zhan, Harry Dong, Ying Fan, Gustavo de Rosa, Tim Pearce, John Langford
The paper proposes a new architecture for masked language modeling that replaces the Transformer attention mechanism with a stack of low‑rank bottleneck autoencoders. Each autoencoder mixes information locally, across the full sequence, and across attention heads, compressing and reconstructing inputs without training‑dependent width. An iterative refinement process at masked positions pulls embeddings toward a weighted neighbor average and then projects them back onto the learned manifold, achieving comparable performance to BERT with roughly 1.9× fewer FLOPs and matching BERT on rare‑token performance through a frequency‑aware training schedule.
By Narges Mokhtari, Farzan Haddadi, Ebrahim Rezaii
arXiv:2607. 11614v1 Announce Type: cross Abstract: Extending the context length of large language models (LLMs) is critical for many real-world applications, yet standard transformers remain constrained by quadratic compute and linear memory scaling.
By Gleb Kuzmin, Ivan Rodkin, Aydar Bulatov, Yuri Kuratov, Lyudmila Rvanova, Mikhail Katkov, Ilia Sochenkov, Misha Tsodyks, Timothy Baldwin, Mikhail Burtsev, Artem Shelmanov
The quadratic growth of attention computation and key-value (KV) cache with respect to sequence length is a central bottleneck for ultra-long-context language models and high-resolution generative mod...