LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering (2025.acl-short)
Copied to clipboard
Zhifan Ye, Zheng Wang, Kejing Xia, Jihoon Hong, Leshu Li, Lexington Whalen, Cheng Wan, Yonggan Fu, Yingyan Celine Lin, Souvik Kundu
| Challenge: | Recent work attributes performance degradation to an exponential decay in hidden-state memory. |
| Approach: | They propose a token filtering strategy that is training-free and attention-guided . they propose 'LAMB' to preserve critical tokens during inference . |
| Outcome: | The proposed token filtering improves long-context performance by 30.35% over state-of-the-art methods on benchmarks. |
Similar Papers
Rethinking Token Reduction for State Space Models (2024.emnlp-main)
Copied to clipboard
Zheng Zhan, Yushu Wu, Zhenglun Kong, Changdi Yang, Yifan Gong, Xuan Shen, Xue Lin, Pu Zhao, Yanzhi Wang
| Challenge: | Existing methods for token reduction for SSMs lead to performance drops . a recent study shows that Mamba-2 improves the accuracy of the model by 5.7% to 13.1% . |
| Approach: | They propose a token reduction method that integrates token importance and similarity into SSMs and takes advantage of pruning and merging. |
| Outcome: | The proposed method improves accuracy by 5.7% to 13.1% on six benchmarks with Mamba-2 compared to existing methods while reducing computational demands and memory requirements. |
Learning What to Remember: Adaptive Probabilistic Memory Retention for Memory-Efficient Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Adaptive Retention is a probabilistic, layer-wise token selection mechanism that learns which representations to keep under a strict global budget M. |
| Approach: | They propose a probabilistic token selection mechanism that learns which representations to keep under a strict global budget M. |
| Outcome: | The proposed method reduces memory usage by 35–45% while improving throughput by 1.8. |
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios. |
| Approach: | They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation . |
| Outcome: | The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead. |
DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large reasoning models generate long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire growing sequence. |
| Approach: | They propose a training-free sparse attention mechanism that reduces inference cost by evicting entries from the key-value cache. |
| Outcome: | The proposed model matches or surpasses full attention on reasoning benchmarks . it reduces the number of attended tokens by up to 4.25 and delivers 1.54 speedup . |
LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models (2025.acl-long)
Copied to clipboard
| Challenge: | State space models lack interpretability tools for long-context sequence modeling. |
| Approach: | They propose a token-level decomposition method for Mamba-1 and Mamba-2 that enables fine-grained interpretability. |
| Outcome: | The proposed method is able to reveal Mamba’s token-to-token interaction patterns across multiple tasks including translation, copying, and retrieval-based generation. |
Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for estimating attention importance for tokens are ineffective . dLLMs require bidirectional attention, which limits inference efficiency . |
| Approach: | They propose a training-free attention sparsification framework for efficient long-context inference . they propose 'sink-aware pruning strategy' to accurately estimate and remove redundant computation . |
| Outcome: | The proposed approach offers 29 lossless speedup under 32K context length. |
Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for full-attention dLLMs rely on random masking strategies that overlook intrinsic token dependencies. |
| Approach: | They propose an attention-guided denoising and optimization framework that aligns training and optimization with attention-derived dependencies. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on mathematical and coding benchmarks. |
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration (2025.findings-acl)
Copied to clipboard
| Challenge: | Long-context understanding is crucial for many NLP applications, but transformers struggle with efficiency due to quadratic complexity of self-attention. |
| Approach: | They propose a dynamic sparse attention mechanism that assigns adaptive masks at the attention-map level, preserving heterogeneous attention patterns. |
| Outcome: | The proposed method achieves high alignment with full-attention models while reducing memory and compute overhead. |
Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention (2026.acl-long)
Copied to clipboard
| Challenge: | Efficient long-context inference remains a major challenge for large language models (LLMs), as the cost of attention computation during auto-regressive decoding grows linearly with the context length. |
| Approach: | They propose to model token importance as a dynamic process that evolves over decoding steps and propagates through model layers. |
| Outcome: | The proposed method outperforms baseline sparse attention methods and achieves speedups of up to 5.36 for attention latency and 2.33 for end-to-end decoding. |
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. |