Rectified Sparse Attention for Efficient Long-Sequence Generation (2026.findings-acl)
Copied to clipboard
Yutao Sun, Tianzhu Ye, Li Dong, Yuqing Xia, Jian Chen, Yizhao Gao, Shijie Cao, Jianyong Wang, Furu Wei
| Challenge: | Recent sparse decoding methods improve efficiency but suffer from KV cache misalignment, resulting in performance degradation. |
| Approach: | They propose a method that combines block-sparse attention with periodic dense rectification to bound error accumulation and preserve alignment with the pretraining distribution. |
| Outcome: | Experiments on math reasoning, language modeling, and retrieval tasks show that ReSA achieves near-lossless generation quality with significantly improved efficiency. |
Similar Papers
RefreshKV: Updating Small KV Cache During Long-form Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for generating long sequences of tokens are expensive and require memory and computation resources. |
| Approach: | They propose a method that alternates between full context attention and attention over a subset of input tokens during generation. |
| Outcome: | The proposed method achieves comparable speedup to eviction-based methods while improving performance for various long-form generation tasks. |
Sparse Attention with Linear Units (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have suggested that sparse attention mechanisms can be made more interpretable by replacing the softmax activation with its sparser variants. |
| Approach: | They propose a method to replace softmax activation with a ReLU to achieve sparsity in attention by layer normalization with either a specialized initialization or an additional gating function. |
| Outcome: | The proposed model is easy to implement and more efficient than previously proposed sparse attention mechanisms. |
Latent-Condensed Transformer for Efficient Long Context Modeling (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches address these bottlenecks separately: Multi-head Latent Attention (MLA) reduces the KV cache by projecting tokens into a low-dimensional latent space, while sparse attention reduces computation. |
| Approach: | They propose a Latent-Condensed Attention mechanism that performs structured context condensation directly within MLA's latent space. |
| Outcome: | The proposed approach reduces KV cache size and attention cost without adding parameters. |
SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences (2026.findings-acl)
Copied to clipboard
| Challenge: | Speculative decoding performance degrades as input length increases, with significant drops even at moderate lengths. |
| Approach: | They propose a drop-in enhancement that improves speculative decoding on long sequences without additional training. |
| Outcome: | The proposed enhancement accelerates speculative decoding by up to 2.84 on 16K-token long document summarization and up to 3.86 on long-form reasoning while preserving the short-input performance of state-of-the-art frameworks. |
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs (2025.acl-short)
Copied to clipboard
| Challenge: | Recent advances in Video Large Language Models (Video-LLMs) have achieved exceptional performance on tasks like video question answering and captioning. |
| Approach: | They propose a decoding strategy that leverages sparse top-K attention and dense full attention to accelerate Video-LLMs without loss. |
| Outcome: | The proposed approach achieves a 1.94 walltime speedup in video processing. |
LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can process extremely long contexts, requiring efficient inference over extended inputs. |
| Approach: | They propose a model that uses a constant-sized key-value cache to train long-context models. |
| Outcome: | Experimental results show that LongSpec achieves 3.26x speedup over strong Flash Attention baselines and 2.34x wall clock time on four math reasoning tasks. |
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches (2024.findings-emnlp)
Copied to clipboard
Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu
| Challenge: | Long context capability is a crucial competency for large language models as it mitigates the human struggle to digest long-form texts. |
| Approach: | They propose to evaluate 10+ state-of-the-art approaches for long context-capable LLMs. |
| Outcome: | The proposed methods are compared against 10+ state-of-the-art approaches across seven categories of long context tasks. |
MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inference (2025.findings-acl)
Copied to clipboard
| Challenge: | State-of-the-art 2-bit KV cache quantization methods achieve excellent results in accelerating LLM inference while retaining accuracy on long context tasks. |
| Approach: | They propose a method based on 2-bit KV cache quantization with adaptive KV policies that retain LLM accuracy with only a subset of KV states. |
| Outcome: | The proposed method outperforms state-of-the-art methods on a wide range of long context tasks while retaining accuracy. |
ClusterAttn: KV Cache Compression under Intrinsic Attention Clustering (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for sparse attention apply the same pattern across different attention heads and inputs, but fail to capture the intrinsic attention clustering in large language models. |
| Approach: | They propose a training-free sparse attention method that provides an efficient prompt cache compression scheme under intrinsic attention clustering for efficient LLM inference. |
| Outcome: | The proposed method reduces memory usage by 10%–65% and increases throughput by 2.6–4.8 times with no accuracy loss. |
Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | a recent study explores efficient ultra-long context modeling. |
| Approach: | They propose to use Hierarchical Sparse Attention to achieve efficient ultra-long context modeling. |
| Outcome: | The proposed model performs comparable to full-attention baselines on in-domain and out-of-domain tasks. |