English
Related papers

Related papers: D$^{3}$ToM: Decider-Guided Dynamic Token Merging f…

200 papers

Diffusion Language Models (DLMs) have shown strong potential for text generation and are becoming a competitive alternative to autoregressive models. The denoising strategy plays an important role in determining the quality of their…

Machine Learning · Computer Science 2026-03-03 Haojin Yang , Rui Hu , Zequn Sun , Rui Zhou , Yujun Cai , Yiwei Wang

Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve token merging by…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Jung Hwan Heo , Seyedarmin Azizi , Arash Fayyazi , Massoud Pedram

Diffusion transformers have shown exceptional performance in visual generation but incur high computational costs. Token reduction techniques that compress models by sharing the denoising process among similar tokens have been introduced.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Haipeng Fang , Sheng Tang , Juan Cao , Enshuo Zhang , Fan Tang , Tong-Yee Lee

Image tokenization plays a central role in modern generative modeling by mapping visual inputs into compact representations that serve as an intermediate signal between pixels and generative models. Diffusion-based decoders have recently…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Chuhan Wang , Hao Chen

Recent transformer-based models for 3D Human Mesh Recovery (HMR) have achieved strong performance but often suffer from high computational cost and complexity due to deep transformer architectures and redundant tokens. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Soroush Mehraban , Andrea Iaboni , Babak Taati

Towards more general and human-like intelligence, large language models should seamlessly integrate both multilingual and multimodal capabilities; however, extending an existing multimodal model to many languages typically requires…

Computation and Language · Computer Science 2026-05-21 Zijing Wang , Mingyang Wang , Ercong Nie , Yongkang Liu , Shi Feng , Mengjie Zhao , Daling Wang , Xiaocui Yang , Hinrich Schütze

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

Computation and Language · Computer Science 2025-10-06 Wenrui Bao , Zhiben Chen , Dan Xu , Yuzhang Shang

Stable diffusion is an outstanding image generation model for text-to-image, but its time-consuming generation process remains a challenge due to the quadratic complexity of attention operations. Recent token merging methods improve…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Min-Jeong Lee , Hee-Dong Kim , Seong-Whan Lee

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate…

Diffusion Language Models (DLMs) offer order-agnostic generation that can explore many possible decoding trajectories. However, current decoding methods commit to a single trajectory, limiting exploration in trajectory space. We introduce…

Computation and Language · Computer Science 2026-02-06 Yangyi Shen , Tianjian Feng , Jiaqi Han , Wen Wang , Tianlang Chen , Chunhua Shen , Jure Leskovec , Stefano Ermon

Due to the large number of parameters, the inference phase of Large Language Models (LLMs) is resource-intensive. Unlike traditional model compression, which needs retraining, recent dynamic computation methods show that not all components…

Computation and Language · Computer Science 2025-11-27 Siqi Fan , Xuezhi Fang , Xingrun Xing , Peng Han , Shuo Shang , Yequan Wang

Automatic speech recognition (ASR) systems based on large language models (LLMs) achieve superior performance by leveraging pretrained LLMs as decoders, but their token-by-token generation mechanism leads to inference latency that grows…

Sound · Computer Science 2026-01-27 Wenjie Tian , Bingshen Mu , Guobin Ma , Xuelong Geng , Zhixian Zhao , Lei Xie

While diffusion language models (DLMs) have achieved competitive performance in text generation, improving their reasoning ability with reinforcement learning remains an active research area. Here, we introduce d2, a reasoning framework…

Machine Learning · Computer Science 2026-02-10 Guanghan Wang , Gilad Turok , Yair Schiff , Marianne Arriola , Volodymyr Kuleshov

Diffusion models have emerged as a powerful class of generative models for molecular design, capable of capturing complex structural distributions and achieving high fidelity in 3D molecule generation. However, their widespread use remains…

Machine Learning · Computer Science 2026-01-15 Adrita Das , Peiran Jiang , Dantong Zhu , Barnabas Poczos , Jose Lugo-Martinez

Discrete diffusion language models (dLLMs) have recently emerged as a promising alternative to traditional autoregressive approaches, offering the flexibility to generate tokens in arbitrary orders and the potential of parallel decoding.…

Machine Learning · Computer Science 2026-04-28 Enshu Liu , Xuefei Ning , Yu Wang , Zinan Lin

While recent Multimodal Large Language Models (MLLMs) have attained significant strides in multimodal reasoning, their reasoning processes remain predominantly text-centric, leading to suboptimal performance in complex long-horizon,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Zefeng He , Xiaoye Qu , Yafu Li , Tong Zhu , Siyuan Huang , Yu Cheng

The landscape of image generation has been forever changed by open vocabulary diffusion models. However, at their core these models use transformers, which makes generation slow. Better implementations to increase the throughput of these…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Daniel Bolya , Judy Hoffman

Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their strengths, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Chenyang Gu , Mingyuan Zhang , Haozhe Xie , Zhongang Cai , Lei Yang , Ziwei Liu

Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While…

Machine Learning · Computer Science 2026-01-28 Zhongyu Xiao , Zhiwei Hao , Jianyuan Guo , Yong Luo , Jia Liu , Jie Xu , Han Hu

Recent progress in multimodal large language models (MLLMs) has highlighted the challenge of efficiently bridging pre-trained Vision-Language Models (VLMs) with Diffusion Models. While methods using a fixed number of learnable query tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Jian Yang , Dacheng Yin , Xiaoxuan He , Yong Li , Fengyun Rao , Jing Lyu , Wei Zhai , Yang Cao , Zheng-Jun Zha