The paper introduces V-CoLA, a training‑free token compression framework tailored for vision-language models that use linear attention. V-CoLA employs a uniqueness‑aware importance criterion to select critical vision tokens and an adaptive token merging strategy to compress them, all optimized to fit the chunk‑wise parallelism of linear attention. Experiments show that V‑CoLA retains 99.5% of the original performance with only half the vision tokens and achieves significant speedups during prefill.
By Hao Jiang, Yiru Mao, Tianpeng Bu, Hao Zhou, Hongtao Duan, Wang Jing, Bowen Xu, Xin Chen, Lulu Hu, Bin Yang, Yongliang Tao, Minying Zhang
Switching Linear Attention (SwiLA) is a new sequence layer that improves upon standard softmax attention by maintaining a fixed-size recurrent state while enhancing representational capacity. It derives its recurrence from a test-time regression framework, using online expectation-maximization in a mixture of linear regressions model. In various benchmarks—including associative recall, in-context language learning, and language modeling—SwiLA achieves strong performance, narrowing the gap to softmax attention and even surpassing it in some settings.
By Hyun Dong Lee, Xavier Gonzalez, Nicolas Zucchet, E. Kelly Buchanan, Emily B. Fox, Scott W. Linderman
Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models introduces the VIG‑Sampler, a method that prioritizes tokens for decoding based on their attention to image tokens and penalizes redundancy in image‑attention distributions. The approach aims to improve the quality of multimodal generation by selecting more informative tokens during diffusion decoding. Experiments on seven captioning and VQA benchmarks with three open‑source dMLLMs show that VIG‑Sampler outperforms the Info‑Gain Sampler by an average of 19.3 CIDEr points and achieves better COCO Caption results using only half as many decoding steps.
By Insu Lee, Wooje Park, Wonseok Shin, Jinwoo Son, Byonghyo Shim
arXiv:2606.14782v3 Announce Type: replace-cross
Abstract: Multimodal Large Language Models (MLLMs) achieve strong vision-language reasoning but incur large KV caches and high decoding latency with lo...
By Tianhao Chen, Yuheng Wu, Kelu Yao, Xiaogang Xu, Xiaobin Hu, Dongman Lee
arXiv:2608.06411v2 Announce Type: replace-cross
Abstract: Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by...
By Yuyao Sun, Tao Deng, Shuang Li, Deqing Wang, Hao Geng, Minjun Yu
arXiv:2608. 06411v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) achieve strong performance across diverse vision-language tasks, but their efficiency is limited by the cost of processing numerous visual tokens.
By Yuyao Sun, Tao Deng, Shuang Li, Deqing Wang, Hao Geng, Minjun Yu
arXiv:2609.35232v2 Announce Type: replace-cross
Abstract: Visual-token compression is effective for improving the efficiency of vision-language models, but under extreme compression budgets, token pr...
By Rui Zhong, Yu Li, Zheyu Yan, Cheng Zhuo
arXiv:2506. 05233v2 Announce Type: replace-cross Abstract: Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention.
By Johannes von Oswald, Nino Scherrer, Seijin Kobayashi, Luca Versari, Songlin Yang, Sarthak Mittal, Maximilian Schlegel, Kaitlin Maile, Yanick Schimpf, Oliver Sieberling, Alexander Meulemans, Rif A. Saurous, Guillaume Lajoie, Charlotte Frenkel, Razvan Pascanu, Blaise Ag\"uera y Arcas, Jo\~ao Sacramento
The paper introduces K-Token Merging, a latent-space compression method that merges each contiguous block of K token embeddings into a single embedding using a lightweight encoder. The compressed sequence is then processed by a LoRA-adapted large language model, while generation continues in the original vocabulary. Experiments on tasks such as structural reasoning, sentiment classification, and code editing demonstrate that K-Token Merging achieves up to 75% input length reduction with minimal performance loss, placing it on the Pareto frontier of performance versus compression.
By Zihao Xu, John Harvill, Ziwei Fan, Yizhou Sun, Hao Ding, Hao Wang
arXiv:2607. 16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck.
By Soumia Bouyahiaoui, Manel Kara laouar, Aicha Boutorh, Mohamed Hadj Ameur
Modern large language models are pretrained on massive datasets, making it difficult to prevent benchmark data from entering their training sets and undermining the reliability of evaluation results....
arXiv:2610.19210v1 Announce Type: new
Abstract: Transformers are efficient to pre-train at scale because attention permits parallel computation across sequence positions, but long-context inference r...
By Sarah Pan, Ali Behrouz