Papers with compression ratios
Comparing Text Compression Capabilities of Large Language Models with Traditional Compression Algorithms (2026.eacl-srw)
Copied to clipboard
| Challenge: | Experimental results show that large language models outperform baselines on non-English datasets . traditional methods remained dataset-agnostic, and the results suggest that current methods are impractical for the compression task. |
| Approach: | They evaluate the non-English and unstructured text compression performance of Large Language Models . they compare them with traditional baselines on datasets from eight most widely spoken languages . |
| Outcome: | The evaluated LLM outperformed baselines on non-English datasets . the results show that the current methods are highly impractical for the compression task . |
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are limited by context length when processing long videos. |
| Approach: | They propose a training-free method that flexibly reduces redundancy by allocating compression ratios among time and model layers with theoretical guarantees. |
| Outcome: | Experiments on videoMME, MLVU, LongVideoBench, and LVBench show that AdaRETAKE outperforms existing methods by 2.3% and 2.8% for 7B and 72B models. |
Efficient Learned Data Compression via Dual-Stream Feature Decoupling (2026.acl-long)
Copied to clipboard
| Challenge: | Learned data compression has achieved superior compression ratios, but balancing precise probability modeling with system efficiency remains challenging. |
| Approach: | They propose a Dual-Stream Multi-Scale Decoupler that disentangles local and global contexts to replace deep serial processing with shallow parallel streams. |
| Outcome: | The proposed method achieves state-of-the-art performance in both compression ratio and throughput while maintaining the lowest latency and memory usage. |
Tensorized Embedding Layers (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Using the Tensor Train decomposition, embeddings layers occupy large portion of model weights, preventing their deployment in limited resource settings. |
| Approach: | They propose a method for parameterizing embedding layers based on the Tensor Train decomposition, which allows compressing the model significantly at the cost of a negligible drop or even a slight gain in performance. |
| Outcome: | The proposed method can be plugged into any model and trained end-to-end. |
OjaKV: Context-Aware Online Low-Rank KV Cache Compression (2026.findings-acl)
Copied to clipboard
Yuxuan Zhu, David H. Yang, Mohammad Mohammadi Amiri, Keerthiram Murugesan, Tejaswini Pedapati, Pin-Yu Chen
| Challenge: | Existing methods for inference use static, offline-learned subspaces that perform poorly under distribution shifts. |
| Approach: | They propose a framework that integrates a storage policy with an online subspace adaptation to preserve key-value tokens in full rank as high-fidelity anchors. |
| Outcome: | Experiments show that OjaKV maintains or improves zero-shot accuracy at high compression ratios, achieving the strongest gains on long-context benchmarks requiring complex reasoning. |
Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation (2022.emnlp-main)
Copied to clipboard
| Challenge: | a new framework for sentence summarization is available that can be trained reference-free . a high-quality dataset of sentence-summary pairs with varying degrees of compression ratios is obtained . |
| Approach: | They propose a framework for sentence summarization that can be trained reference-free . they propose 'referee' that iteratively distills latent knowledge into better models . |
| Outcome: | The proposed framework outperforms existing models in the use of explicit examples from teacher models without compromising the quality of the summarization. |
Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to compress long contexts have degraded dramatically as compression ratios increase, sometimes even falling to the closed-book level. |
| Approach: | They propose a query-guided compression method that preserves key information within the compressed context. |
| Outcome: | The proposed method can consistently perform well even at high compression ratios, and offers significant benefits in terms of inference cost and throughput. |
LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly lengthy and require longer prompts . this paper presents a coarse-to-fine prompt compression method to reduce cost and increase performance. |
| Approach: | They propose a coarse-to-fine prompt compression method that maintains semantic integrity under high compression ratios and a token-level iterative compression algorithm to better model the interdependence between compressed contents. |
| Outcome: | The proposed method yields state-of-the-art performance and allows for up to 20x compression with little performance loss over four datasets from different scenarios. |
Sculpting the Vector Space: Towards Efficient Multi-Vector Visual Document Retrieval via Prune-then-Merge Framework (2026.findings-acl)
Copied to clipboard
| Challenge: | Visual Document Retrieval (VDR) is of importance in multimodal retrieval applications. |
| Approach: | They propose a two-stage pruning and merging frameworks that combine pruning and merge techniques to achieve higher compression rates. |
| Outcome: | The proposed framework outperforms existing methods on 29 visual document retrieval datasets. |
Automated Fine-Grained Mixture-of-Experts Quantization (2025.findings-acl)
Copied to clipboard
| Challenge: | specialized quantization framework for Mixture of Experts architectures is inadequate for model compression. |
| Approach: | They propose a specialized quantization framework for Mixture of Experts architectures . they find that expert networks exhibit distinctive channel-wise outlier distributions ." |
| Outcome: | The proposed framework improves on the Mixtral-8x7b-v0.1 architecture while maintaining minimal computational overhead. |