English
Related papers

Related papers: Probe and Skip: Self-Predictive Token Skipping for…

200 papers

Online video understanding is essential for applications like public surveillance and AI glasses. However, applying Multimodal Large Language Models (MLLMs) to this domain is challenging due to the large number of video frames, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xinqi Jin , Hanxun Yu , Bohan Yu , Kebin Liu , Jian Liu , Keda Tao , Yixuan Pei , Huan Wang , Fan Dang , Jiangchuan Liu , Weiqiang Wang

We introduce GateSkip, a simple residual-stream gating mechanism that enables token-wise layer skipping in decoder-only LMs. Each Attention/MLP branch is equipped with a sigmoid-linear gate that condenses the branch's output before it…

Computation and Language · Computer Science 2026-02-10 Filipe Laitenberger , Dawid Kopiczko , Cees G. M. Snoek , Yuki M. Asano

Whether Large Language Models (LLMs) develop coherent internal world models remains a core debate. While conventional Next-Token Prediction (NTP) focuses on one-step-ahead supervision, Multi-Token Prediction (MTP) has shown promise in…

Machine Learning · Computer Science 2026-04-21 Qimin Zhong , Hao Liao , Haiming Qin , Mingyang Zhou , Rui Mao , Wei Chen , Naipeng Chao

Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address this issue using single-layer Vision Transformer (ViT)…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Yunkai Dang , Yizhu Jiang , Yifan Jiang , Qi Fan , Yinghuan Shi , Wenbin Li , Yang Gao

In spite of strong performance achieved by LLMs, the costs of their deployment are unaffordable. For the compression of LLMs, gradient-based pruning methods present promising effectiveness. However, in these methods, the gradient…

Computation and Language · Computer Science 2025-06-16 Hourun Zhu , Chengchao Shen

Large Vision-Language Models (LVLMs) have advanced multimodal learning but face high computational costs due to the large number of visual tokens, motivating token pruning to improve inference efficiency. The key challenge lies in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Ao Li , Yuxiang Duan , Jinghui Zhang , Congbo Ma , Yutong Xie , Gustavo Carneiro , Mohammad Yaqub , Hu Wang

Large language models (LLMs) have demonstrated significant improvements in contextual understanding. However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace.…

Computation and Language · Computer Science 2025-10-27 Yiju Guo , Wenkai Yang , Zexu Sun , Ning Ding , Zhiyuan Liu , Yankai Lin

While 3D Multi-modal Large Language Models (MLLMs) demonstrate remarkable scene understanding capabilities, their practical deployment faces critical challenges due to computational inefficiency. The key bottleneck stems from processing…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Wencan Huang , Daizong Liu , Wei Hu

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Pu Zhang , Yuwei Li , Xingyuan Xian , Guoming Tang

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Computation and Language · Computer Science 2026-05-27 Kuan-Wei Lu , Ding-Yong Hong , Pangfeng Liu , Jan-Jan Wu

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the traditional self-attention mechanism, which processes both…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Tianyi Zhang , Baoxin Li , Jae-sun Seo , Yu Cao

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Yanshu Li , Jianjiang Yang , Zhennan Shen , Ligong Han , Haoyan Xu , Ruixiang Tang

This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's…

Computation and Language · Computer Science 2026-02-13 Florian Valade

Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs), typically by sampling multiple token-based chains-of-thought in parallel and aggregating outcomes through voting or search. Recent advances…

Computation and Language · Computer Science 2026-04-21 Runyang You , Yongqi Li , Meng Liu , Wenjie Wang , Liqiang Nie , Wenjie Li

Contextual sparsity is one of the approaches used to reduce computational complexity in the inference process of large language models (LLMs). Existing techniques for efficient LLM inference acceleration based on contextual sparsity with…

Machine Learning · Computer Science 2026-03-17 Georgii Serbin , Kirill Koshkin , Zhongao Sun , Anastasiya Bistrigova , C. C. Korikov

The quadratic computational complexity of self-attention remains a fundamental bottleneck for scaling Large Language Models (LLMs) to long contexts, particularly during the pre-filling phase. In this paper, we rethink the causal attention…

Machine Learning · Computer Science 2026-03-09 Lin Niu , Xin Luo , Linchuan Xie , Yifu Sun , Guanghua Yu , Jianchen Zhu , S Kevin Zhou

Large language models (LLMs) improve reasoning accuracy when generating multiple candidate solutions at test time, but standard methods like Best-of-N (BoN) incur high computational cost by fully generating all branches. Self-Truncation…

Machine Learning · Computer Science 2025-11-05 Sophie Li , Nicholas Huang , Nayan Saxena , Nina Luo , Vincent Lin , Kevin Zhu , Sunishchal Dev

Inference-time scaling has emerged as a powerful way to improve large language model (LLM) performance by generating multiple candidate responses and selecting among them. However, existing work on dynamic allocation for test-time compute…

Machine Learning · Computer Science 2025-09-15 Jenny Y. Huang , Mehul Damani , Yousef El-Kurdi , Ramon Astudillo , Wei Sun

Incremental text-to-speech (TTS) synthesis generates utterances in small linguistic units for the sake of real-time and low-latency applications. We previously proposed an incremental TTS method that leverages a large pre-trained language…

Sound · Computer Science 2021-09-23 Takaaki Saeki , Shinnosuke Takamichi , Hiroshi Saruwatari

The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively…

Computation and Language · Computer Science 2025-10-17 Chao Han , Yijuan Liang , Zihao Xuan , Daokuan Wu , Wei Zhang , Xiaoyu Shen