English
Related papers

Related papers: Wide-In, Narrow-Out: Revokable Decoding for Effici…

200 papers

Large Language Models (LLMs) enable various applications on edge devices such as smartphones, wearables, and embodied robots. However, their deployment often depends on expensive cloud-based APIs, creating high operational costs, which…

Robotics · Computer Science 2025-05-29 Yeshwanth Venkatesha , Souvik Kundu , Priyadarshini Panda

Unlike autoregressive language models, which terminate variable-length generation upon predicting an End-of-Sequence (EoS) token, Diffusion Language Models (DLMs) operate over a fixed maximum-length context window for a predetermined number…

Computation and Language · Computer Science 2026-03-09 Vittorio Rossi , Giacomo Cirò , Davide Beltrame , Luca Gandolfi , Paul Röttger , Dirk Hovy

Speculative decoding has emerged as a promising technique for large language model (LLM) inference by accelerating autoregressive decoding via draft-then-verify. This paper studies a new edge scenario with multi-user inference, where draft…

Information Theory · Computer Science 2026-04-24 Yaodan Xu , Sheng Zhou , Zhisheng Niu

Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation, alongside constraints from caption-derived vocabularies. To…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Yuchen Guan , Chong Sun , Canmiao Fu , Zhipeng Huang , Chun Yuan , Chen Li

Efficient inference in large language models (LLMs) has become a critical focus as their scale and complexity grow. Traditional autoregressive decoding, while effective, suffers from computational inefficiencies due to its sequential token…

Computation and Language · Computer Science 2024-11-28 Hyun Ryu , Eric Kim

Diffusion large language models (dLLMs) represent a significant advancement in text generation, offering parallel token decoding capabilities. However, existing open-source implementations suffer from quality-speed trade-offs that impede…

Computation and Language · Computer Science 2025-10-09 Fanheng Kong , Jingyuan Zhang , Yahui Liu , Zirui Wu , Yu Tian , Victoria W. , Guorui Zhou

We propose Windowed Inference for Non-blank Detection (WIND), a novel strategy that significantly accelerates RNN-T inference without compromising model accuracy. During model inference, instead of processing frames sequentially, WIND…

Machine Learning · Computer Science 2025-05-21 Hainan Xu , Vladimir Bataev , Lilit Grigoryan , Boris Ginsburg

Diffusion Large Language Models (dLLMs) enable breakthroughs in reasoning and parallel decoding but suffer from prohibitive quadratic computational complexity and memory overhead during inference. Current caching techniques accelerate…

Computation and Language · Computer Science 2025-11-06 Yuerong Song , Xiaoran Liu , Ruixiao Li , Zhigeng Liu , Zengfeng Huang , Qipeng Guo , Ziwei He , Xipeng Qiu

Beyond parallel generation and global context modeling, current masked diffusion large language models (masked dLLMs, i.e., LLaDA) suffer from a fundamental limitation: they require a predefined, fixed generation length, which lacks…

Computation and Language · Computer Science 2026-02-10 Jingyi Yang , Yuxian Jiang , Jing Shao

We present LayerSkip, an end-to-end solution to speed-up inference of large language models (LLMs). First, during training we apply layer dropout, with low dropout rates for earlier layers and higher dropout rates for later layers, and an…

Large vision-language models (LVLMs) excel at multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. We present DROPOUT DECODING, a novel inference-time approach that…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Yixiong Fang , Ziran Yang , Zhaorun Chen , Zhuokai Zhao , Jiawei Zhou

In this work, we present Xwin-LM, a comprehensive suite of alignment methodologies for large language models (LLMs). This suite encompasses several key techniques, including supervised finetuning (SFT), reward modeling (RM), rejection…

Computation and Language · Computer Science 2024-05-31 Bolin Ni , JingCheng Hu , Yixuan Wei , Houwen Peng , Zheng Zhang , Gaofeng Meng , Han Hu

In this work, we provide a systematic survey of Discrete Diffusion Language Models (dLLMs) and Discrete Diffusion Multimodal Language Models (dMLLMs). Unlike autoregressive (AR) models, dLLMs and dMLLMs adopt a multi-token, parallel…

Machine Learning · Computer Science 2025-09-22 Runpeng Yu , Qi Li , Xinchao Wang

Modern Vision-Language Models (VLMs) can solve a wide range of tasks requiring visual reasoning. In real-world scenarios, desirable properties for VLMs include fast inference and controllable generation (e.g., constraining outputs to adhere…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Shufan Li , Konstantinos Kallidromitis , Hritik Bansal , Akash Gokul , Yusuke Kato , Kazuki Kozuka , Jason Kuen , Zhe Lin , Kai-Wei Chang , Aditya Grover

Generative inference in Large Language Models (LLMs) is impeded by the growing memory demands of Key-Value (KV) cache, especially for longer sequences. Traditional KV cache eviction strategies, which discard less critical KV pairs based on…

Computation and Language · Computer Science 2025-03-14 Zhongwei Wan , Xinjian Wu , Yu Zhang , Yi Xin , Chaofan Tao , Zhihong Zhu , Xin Wang , Siqi Luo , Jing Xiong , Longyue Wang , Mi Zhang

Diffusion Large Language Models (DLLMs) promise fast non-autoregressive inference but suffer a severe quality-speed trade-off in parallel decoding. This stems from the ''combinatorial contradiction'' phenomenon, where parallel tokens form…

Computation and Language · Computer Science 2026-02-27 Yushi Ye , Feng Hong , Huangjie Zheng , Xu Chen , Zhiyong Chen , Yanfeng Wang , Jiangchao Yao

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Computation and Language · Computer Science 2025-06-12 Nadav Timor , Jonathan Mamou , Daniel Korat , Moshe Berchansky , Gaurav Jain , Oren Pereg , Moshe Wasserblat , David Harel

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…

Accelerating the inference of large language models (LLMs) has been a critical challenge in generative AI. Speculative decoding (SD) substantially improves LLM inference efficiency. However, its utility is limited by a fundamental…

Computation and Language · Computer Science 2026-05-05 Sibo Xiao , Jinyuan Fu , Zhongle Xie , Lidan Shou

Speculative decoding (SD) has emerged as a promising approach to accelerate LLM inference without sacrificing output quality. Existing SD methods tailored for video-LLMs primarily focus on pruning redundant visual tokens to mitigate the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-14 Qitan Lv , Tianyu Liu , Wen Wu , Xuenan Xu , Bowen Zhou , Feng Wu , Chao Zhang