Arbitrary Ratio Feature Compression via Next Token Prediction

• URL: http://arxiv.org/abs/2602.11494v1
• Date: Thu, 12 Feb 2026 02:38:57 GMT
• Title: Arbitrary Ratio Feature Compression via Next Token Prediction
• Authors: Yufan Liu, Daoyuan Ren, Zhipeng Zhang, Wenyang Luo, Bing Li, Weiming Hu, Stephen Maybank,
• Abstract summary: Arbitrary Ratio Feature Compression (ARFC) framework supports any compression ratio with a single model.<n>ARC is an auto-regressive model that performs compression via next-gressive prediction.<n>MoS module refines the compressed tokens by utilizing multiple compression results.<n>ERGC is integrated into the training process to preserve semantic and structural relationships during compression.
• Score: 52.10426317889982
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Feature compression is increasingly important for improving the efficiency of downstream tasks, especially in applications involving large-scale or multi-modal data. While existing methods typically rely on dedicated models for achieving specific compression ratios, they are often limited in flexibility and generalization. In particular, retraining is necessary when adapting to a new compression ratio. To address this limitation, we propose a novel and flexible Arbitrary Ratio Feature Compression (ARFC) framework, which supports any compression ratio with a single model, eliminating the need for multiple specialized models. At its core, the Arbitrary Ratio Compressor (ARC) is an auto-regressive model that performs compression via next-token prediction. This allows the compression ratio to be controlled at inference simply by adjusting the number of generated tokens. To enhance the quality of the compressed features, two key modules are introduced. The Mixture of Solutions (MoS) module refines the compressed tokens by utilizing multiple compression results (solutions), reducing uncertainty and improving robustness. The Entity Relation Graph Constraint (ERGC) is integrated into the training process to preserve semantic and structural relationships during compression. Extensive experiments on cross-modal retrieval, image classification, and image retrieval tasks across multiple datasets demonstrate that our method consistently outperforms existing approaches at various compression ratios. Notably, in some cases, it even surpasses the performance of the original, uncompressed features. These results validate the effectiveness and versatility of ARFC for practical, resource-constrained scenarios.

Related papers

• Proxy Compression for Language Modeling [58.904023114033954]
  proxy compression is an alternative training scheme that preserves the efficiency benefits of compressed inputs.<n>Experiments on code language modeling demonstrate that proxy compression substantially improves training efficiency.<n>As model scale increases, proxy-trained models eventually match or rival tokenizer approaches.
  arXiv  Detail & Related papers  (2026-02-04T07:36:46Z)
• Simple Context Compression: Mean-Pooling and Multi-Ratio Training [12.049015994907629]
  We develop a lightweight and simple mean-pooling approach that consistently outperforms the widely used compression-tokens architecture.<n>We conduct extensive experiments across in-domain and out-of-domain QA datasets, as well as across model families, scales, and compression ratios.<n>Overall, our simple mean-pooling approach achieves the strongest performance, with a relatively small drop when training for multiple compression ratios.
  arXiv  Detail & Related papers  (2025-10-23T17:57:23Z)
• Compressing Many-Shots in In-Context Learning [61.231471139896506]
  We study an approach to improve the memory and computational efficiency of ICL inference by compressing the many-shot prompts.<n>We first show that existing prompt compression methods are ineffective for many-shot compression.<n>We propose MemCom, a layer-wise compression method.
  arXiv  Detail & Related papers  (2025-10-17T16:57:42Z)
• UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression [86.33995240043936]
  UniGist is a sequence-level long-context compression framework for large language models.<n>It efficiently preserves context information by replacing raw tokens with special compression tokens (gists) in a fine-grained manner.<n>Our scheme also supports flexible inference by allowing the actual removal of compressed tokens, resulting in real-time memory savings.
  arXiv  Detail & Related papers  (2025-09-19T08:47:37Z)
• Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation [10.376875638696504]
  This work presents Any Compression via Iterative Pruning (ACIP), a novel algorithmic approach to determine a compression-performance trade-off.<n>We use an SVD-reparametrization of linear layers and iteratively prune their singular values with a sparsity-inducing penalty.<n>We show that ACIP seamlessly complements common quantization-based compression techniques.
  arXiv  Detail & Related papers  (2025-02-03T18:40:58Z)
• UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation [59.3877309501938]
  Implicit Neural Representation (INR) networks have shown remarkable versatility due to their flexible compression ratios. We introduce a codebook containing frequency domain information as a prior input to the INR network. This enhances the representational power of INR and provides distinctive conditioning for different image blocks.
  arXiv  Detail & Related papers  (2024-05-27T05:52:13Z)
• Order of Compression: A Systematic and Optimal Sequence to Combinationally Compress CNN [5.25545980258284]
  We propose a systematic and optimal sequence to apply multiple compression techniques in the most effective order. Our proposed Order of Compression significantly reduces computational costs by up to 859 times on ResNet34, with negligible accuracy loss. We believe our simple yet effective exploration of the order of compression will shed light on the practice of model compression.
  arXiv  Detail & Related papers  (2024-03-26T07:26:00Z)
• You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient [88.58536093633167]
  Existing model compression approaches require re-compression or fine-tuning across diverse constraints to accommodate various hardware deployments. We propose a novel approach, YOCO-BERT, to achieve compress once and deploy everywhere. Compared with state-of-the-art algorithms, YOCO-BERT provides more compact models, yet achieving 2.1%-4.5% average accuracy improvement on the GLUE benchmark.
  arXiv  Detail & Related papers  (2021-06-04T12:17:44Z)
• Towards Compact CNNs via Collaborative Compression [166.86915086497433]
  We propose a Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models. We achieve 52.9% FLOPs reduction by removing 48.4% parameters on ResNet-50 with only a Top-1 accuracy drop of 0.56% on ImageNet 2012.
  arXiv  Detail & Related papers  (2021-05-24T12:07:38Z)
• Neural Network Compression Via Sparse Optimization [23.184290795230897]
  We propose a model compression framework based on the recent progress on sparse optimization. We achieve up to 7.2 and 2.9 times FLOPs reduction with the same level of evaluation of accuracy on VGG16 for CIFAR10 and ResNet50 for ImageNet.
  arXiv  Detail & Related papers  (2020-11-10T03:03:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.