English
Related papers

Related papers: V2Flow: Unifying Visual Tokenization and Large Lan…

200 papers

Large language models (LLMs) have enabled the creation of multi-modal LLMs that exhibit strong comprehension of visual data such as images and videos. However, these models usually rely on extensive visual tokens from visual encoders,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Yiwu Zhong , Zhuoming Liu , Yin Li , Liwei Wang

The remarkable success of Large Language Models (LLMs) has extended to the multimodal domain, achieving outstanding performance in image understanding and generation. Recent efforts to develop unified Multimodal Large Language Models…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Hao Li , Changyao Tian , Jie Shao , Xizhou Zhu , Zhaokai Wang , Jinguo Zhu , Wenhan Dou , Xiaogang Wang , Hongsheng Li , Lewei Lu , Jifeng Dai

Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose \textbf{VDLM}, a modular variable diffusion language model that separates semantic planning from…

Computation and Language · Computer Science 2026-02-19 Shuhui Qu

Large Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics. These visual tokens often outnumber their textual counterparts by a large margin, leading to substantial…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Rui Xu , Yunke Wang , Yong Luo , Bo Du

Most text-to-video(T2V) diffusion models depend on pre-trained text encoders for semantic alignment, yet they often fail to maintain video quality when provided with concise prompts rather than well-designed ones. The primary issue lies in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Xiangjun Zhang , Litong Gong , Yinglin Zheng , Yansong Liu , Wentao Jiang , Mingyi Xu , Biao Wang , Tiezheng Ge , Ming Zeng

Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generated by high-resolution images or multi-image inputs. Previous token compression techniques…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Jiaying Zhu , Yurui Zhu , Xin Lu , Wenrui Yan , Dong Li , Kunlin Liu , Xueyang Fu , Zheng-Jun Zha

Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Mude Hui , Rui-Jie Zhu , Songlin Yang , Yu Zhang , Zirui Wang , Yuyin Zhou , Jason Eshraghian , Cihang Xie

Large Language Model (LLM) based code generation is predominantly formulated as a strictly monotonic process, appending tokens linearly to an immutable prefix. This formulation contrasts to the cognitive process of programming, which is…

Software Engineering · Computer Science 2026-05-07 Chengran Yang , Zichao Wei , Heminghao Deng , Jinfeng Jiang , Zhensu Sun , Ting Zhang , Tianyi Wu , Ming Wen , David Lo

Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-10 Jusheng Zhang , Xiaoyang Guo , Kaitong Cai , Qinhan Lv , Yijia Fan , Wenhao Chai , Jian Wang , Keze Wang

Video large language models (VideoLLM) excel at video understanding, but face efficiency challenges due to the quadratic complexity of abundant visual tokens. Our systematic analysis of token compression methods for VideoLLMs reveals two…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Xuyang Liu , Yiyu Wang , Junpeng Ma , Linfeng Zhang

Large-scale Text-to-Video (T2V) diffusion models have recently demonstrated unprecedented capability to transform natural language descriptions into stunning and photorealistic videos. Despite the promising results, a significant challenge…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Xingyi Yang , Xinchao Wang

Video-based multimodal large language models (Video-LLMs) possess significant potential for video understanding tasks. However, most Video-LLMs treat videos as a sequential set of individual frames, which results in insufficient…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Xiaohan Lan , Yitian Yuan , Zequn Jie , Lin Ma

Autoregressive (AR) models have recently shown strong performance in image generation, where a critical component is the visual tokenizer (VT) that maps continuous pixel inputs to discrete token sequences. The quality of the VT largely…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Huawei Lin , Tong Geng , Zhaozhuo Xu , Weijie Zhao

Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches. However, existing…

Computation and Language · Computer Science 2025-10-14 Wenbin Guo , Xin Wang , Jiaoyan Chen , Lingbing Guo , Zhao Li , Zirui Chen

Recently, Vision Large Language Models (VLLMs) integrated with vision encoders have shown promising performance in vision understanding. The key of VLLMs is to encode visual content into sequences of visual tokens, enabling VLLMs to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Zhuqiang Lu , Zhenfei Yin , Mengwei He , Zhihui Wang , Zicheng Liu , Zhiyong Wang , Kun Hu

Video-conditioned audio generation, including Video-to-Sound (V2S) and Visual Text-to-Speech (VisualTTS), has traditionally been treated as distinct tasks, leaving the potential for a unified generative framework largely underexplored. In…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-23 Xin Cheng , Yuyue Wang , Xihua Wang , Yihan Wu , Kaisi Guan , Yijing Chen , Peng Zhang , Xiaojiang Liu , Meng Cao , Ruihua Song

Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens. In contrast, non-autoregressive seq2seq models generate all tokens in one pass, which leads to increased…

Computation and Language · Computer Science 2019-10-10 Xuezhe Ma , Chunting Zhou , Xian Li , Graham Neubig , Eduard Hovy

Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification. However, the annotation of concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Hangzhou He , Lei Zhu , Xinliang Zhang , Shuang Zeng , Qian Chen , Yanye Lu

Text-to-Image (T2I) generation has made significant advancements with diffusion models, yet challenges persist in handling complex instructions, ensuring fine-grained content control, and maintaining deep semantic consistency. Existing T2I…

Machine Learning · Computer Science 2025-08-08 Xiaoqi Dong , Xiangyu Zhou , Nicholas Evans , Yujia Lin

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Yuke Zhu , Chi Xie , Shuang Liang , Bo Zheng , Sheng Guo