EQUIP: EQUivariant preserving In-Place updates for Efficient Token Pruning (2026.acl-long)
Copied to clipboard
| Challenge: | Token-pruning methods cause "holes" in KV tensors, posing major challenges . equip reduces recomputation of rotation operations through in-place update, caching and re-indexing . |
| Approach: | They propose an EQUIP-based in-place token update mechanism that preserves the equivariance property of the operations performed in the attention computation. |
| Outcome: | EQUIP reduces recomputation of rotation operations and reduces eviction overheads . it achieves geomean speedups of 1.62 (or 1.47) over StreamingLLM and 3.45 ( or 1.86) |
Similar Papers
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference (2026.findings-eacl)
Copied to clipboard
Krishna Teja Chitty-Venkata, Jie Ye, Siddhisanket Raskar, Anthony Kougkas, Xian Sun, Murali Emani, Venkatram Vishwanath, Bogdan Nicolae
| Challenge: | Large Language Models (LLMs) are exploding to large sizes, including GPT, LLaMA, and DeepSeek. |
| Approach: | They propose a fine-grained, structured KV cache pruning strategy that enhances the memory efficiency of vLLM’s PagedAttention. |
| Outcome: | The proposed method integrates seamlessly with PagedAttention without any modifications to its CUDA attention kernels. |
NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time (2024.acl-long)
Copied to clipboard
Yilong Chen, Guoxia Wang, Junyuan Shang, Shiyao Cui, Zhenyu Zhang, Tingwen Liu, Shuohuan Wang, Yu Sun, Dianhai Yu, Hua Wu
| Challenge: | Large Language Models (LLMs) with extended context windows are expensive and infeasible on fixed memory hardware due to the surprisingly large memory consumption of KV Cache. |
| Approach: | They propose a general framework for long-context KV cache eviction that achieves more optimal and efficient evict in a single operation during the encoding phase. |
| Outcome: | The proposed framework improves performance on short- and long-text tasks by 80% and 76% respectively, reducing KV Cache by up to 5 with over 95% performance maintenance. |
EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing semantic similarity methods struggle to accurately identify semantically equivalent steps in domain-specific contexts like mathematical reasoning. |
| Approach: | They propose a simple yet effective approach that identifies and prunes semantically equivalent actions during LLM reasoning search. |
| Outcome: | The proposed approach reduces token consumption while improving reasoning efficiency and accuracy on Qwen2.5-Math-7B-Instruct on GSM8K. |
RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evicting KV pairs rely on the "persistence of importance" hypothesis . visual tokens display "deferred importance" but become pivotal during later decoding, authors say . |
| Approach: | They propose an entropy-driven method that reformulates KV eviction from "discrete context truncation" to "continuous memory evolution" they propose to prune visual tokens with "deferred importance" visual token exhibiting low salience but becoming pivotal during later decoding . |
| Outcome: | The proposed method achieves 5.0 KV cache compression and 1.5 decoding acceleration. |
More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression (2025.findings-emnlp)
Copied to clipboard
Jiebin Zhang, Dawei Zhu, Yifan Song, Wenhao Wu, Chuqiao Kuang, Xiaoguang Li, Lifeng Shang, Qun Liu, Sujian Li
| Challenge: | storing more tokens in the KV cache at lower precision can enhance the long-context performance of large language models. |
| Approach: | They propose a token-precision trade-off strategy to optimize KV cache compression . they also propose storing more tokens in the KV at lower precision . |
| Outcome: | The proposed method achieves an optimal point within the Information Bottleneck compared to standalone KV pruning or KV quantization. |
LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing KV cache compression methods mitigate memory bottlenecks but struggle in long reasoning tasks. |
| Approach: | They propose a lagged eviction framework that prioritizes evicts based on tokens’ recurrence patterns to reduce KV cache by 50% and maintain comparable accuracy. |
| Outcome: | The proposed framework reduces KV cache by 50% 70% while maintaining comparable accuracy, outperforming existing KV baselines. |
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. |
KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Recent work shows that decoder-only LLMs can serve as strong embedding backbones when fine-tuned with contrastive objectives. |
| Approach: | They propose a framework that activates the latent representation power of frozen LLMs by rerouting the final token's KV states as a prepended prefix. |
| Outcome: | The proposed framework outperforms existing training-free baselines by 10% on MTEB and maintains robust performance on sequences up to 4,096 tokens. |
TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing token pruning methods rely on costly calibration or suboptimal importance metrics, leading to redundant retained tokens. |
| Approach: | They propose a token pruning strategy that preserves cross-modal alignment and informational diversity. |
| Outcome: | The proposed method maintains strong performance while reducing tokens by 88.9% on two models. |
PruneVid: Visual Token Pruning for Efficient Video Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to video token pruning face significant computational challenges due to the redundancy inherent in video data. |
| Approach: | They propose a training-free visual token pruning method that reduces the redundancy inherent in video data and leverages LLMs’ inherent ability to selectively prune visual tokens irrelevant to specific queries. |
| Outcome: | The proposed method can prune over 80% of tokens while maintaining competitive performance when combined with different video LLMs. |