English
Related papers

Related papers: When Latent Geometry Is Not Enough: Draft-Conditio…

200 papers

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face…

Computation and Language · Computer Science 2026-04-17 Zihong Zhang , Zuchao Li , Lefei Zhang , Ping Wang , Hai Zhao

Speculative decoding accelerates inference for Large Language Models by using a lightweight draft model to propose candidate tokens that are verified in parallel by a larger target model. Prior work shows that the draft model often…

Computation and Language · Computer Science 2026-03-06 Ofir Ben Shoham

Discrete Diffusion Language Models have emerged as a compelling paradigm for unified multimodal generation, yet their deployment is hindered by high inference latency arising from iterative decoding. Existing acceleration strategies often…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Chenglin Wang , Yucheng Zhou , Shawn Chen , Tao Wang , Kai Zhang

We investigate geometric regularization strategies for learned latent representations in encoder--decoder reduced-order models. In a fixed experimental setting for the advection--diffusion--reaction (ADR) equation, we model latent dynamics…

Machine Learning · Computer Science 2026-03-04 Mikhail Osipov

Large pre-trained language models have recently gained significant traction due to their improved performance on various down-stream tasks like text classification and question answering, requiring only few epochs of fine-tuning. However,…

Computation and Language · Computer Science 2023-09-01 Souvik Kundu , Sharath Nittur Sridhar , Maciej Szankin , Sairam Sundaresan

We consider the problem of ultra-low bit rate visual communication for remote vision analysis, human interactions and control in challenging scenarios with very low communication bandwidth, such as deep space exploration, battlefield…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Weiming Chen , Yijia Wang , Zhihan Zhu , Zhihai He

Generative receivers for wireless image transmission can improve reconstruction quality, but diffusion-based and flow-based decoding relies on iterative inference and therefore incurs substantial latency. In wireless image transmission,…

Image and Video Processing · Electrical Eng. & Systems 2026-05-05 Jingwen Fu , Ming Xiao , Mikael Skoglund

Snapshot compressive spectral imaging reconstruction aims to reconstruct three-dimensional spatial-spectral images from a single-shot two-dimensional compressed measurement. Existing state-of-the-art methods are mostly based on deep…

Image and Video Processing · Electrical Eng. & Systems 2024-08-27 Zongliang Wu , Ruiying Lu , Ying Fu , Xin Yuan

Latent diffusion models with Transformer architectures excel at generating high-fidelity images. However, recent studies reveal an optimization dilemma in this two-stage design: while increasing the per-token feature dimension in visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Jingfeng Yao , Bin Yang , Xinggang Wang

The performance of text-to-image diffusion models may be improved at test-time by scaling computation to search for a generated image that maximizes a given reward function. While existing trajectory level exploration methods improve the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Qingtao Yu , Changlin Song , Minghao Sun , Zhengyang Yu , Vinay Kumar Verma , Soumya Roy , Sumit Negi , Hongdong Li , Dylan Campbell

The steep computational cost of diffusion models at inference hinders their use as fast physics emulators. In the context of image and video generation, this computational drawback has been addressed by generating in the latent space of an…

Machine Learning · Computer Science 2025-11-04 François Rozet , Ruben Ohana , Michael McCabe , Gilles Louppe , François Lanusse , Shirley Ho

Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of…

Image and Video Processing · Electrical Eng. & Systems 2024-05-24 Marc Windsheimer , Fabian Brand , André Kaup

Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective -- reconstructing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Jiawei Yang , Tianhong Li , Lijie Fan , Yonglong Tian , Yue Wang

Open-ended text generation with autoregressive language models (LMs) is one of the core tasks in natural language processing. However, maximization-based decoding methods (e.g., greedy/beam search) often lead to the degeneration problem,…

Computation and Language · Computer Science 2022-12-06 Tian Lan , Yixuan Su , Shuhang Liu , Heyan Huang , Xian-Ling Mao

Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitation of AR models is their sequential nature, which processes…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Doohyuk Jang , Sihwan Park , June Yong Yang , Yeonsung Jung , Jihun Yun , Souvik Kundu , Sung-Yub Kim , Eunho Yang

Diffusion models have shown remarkable performance in image synthesis, but they demand extensive computational and memory resources for training, fine-tuning and inference. Although advanced quantization techniques have successfully…

Computer Vision and Pattern Recognition · Computer Science 2025-03-20 Hoigi Seo , Wongi Jeong , Kyungryeol Lee , Se Young Chun

We propose a novel class of language models, Latent Thought Models (LTMs), which incorporate explicit latent thought vectors that follow an explicit prior model in latent space. These latent thought vectors guide the autoregressive…

Computation and Language · Computer Science 2025-06-10 Deqian Kong , Minglu Zhao , Dehong Xu , Bo Pang , Shu Wang , Edouardo Honig , Zhangzhang Si , Chuan Li , Jianwen Xie , Sirui Xie , Ying Nian Wu

Diffusion language models generate text through iterative denoising under a uniform refinement rule applied to all tokens. However, tokens stabilize at different rates in practice, leading to substantial redundant refinement and motivating…

Artificial Intelligence · Computer Science 2026-03-06 Lipeng Wan , Jianhui Gu , Junjie Ma , Jianguo Huang , Shiguang Sun , Siyuan Li , Xuguang Lan

Identifying words that impact a task's performance more than others is a challenge in natural language processing. Transformers models have recently addressed this issue by incorporating an attention mechanism that assigns greater attention…

Computation and Language · Computer Science 2023-03-15 Neşet Özkan Tan , Alex Yuxuan Peng , Joshua Bensemann , Qiming Bao , Tim Hartill , Mark Gahegan , Michael Witbrock

The sequential nature of autoregressive next-token prediction imposes a fundamental speed limit on large language models. While continuous flow models offer a path to parallel generation, they traditionally demand expensive iterative…

‹ Prev 1 8 9 10 Next ›