3 citations · 6 across the 21 of their papers we have counts for
22 papers
Large Language Models are Universal Reasoners for Visual Generation
Sucheng Ren, Chen Chen, Zhenbang Wang +5
Text-to-image generation has advanced rapidly with diffusion models, progressing from CLIP and T5 conditioning to unified systems where a single LLM backbone handles both visual un…
Frequency-Aware Flow Matching for High-Quality Image Generation
Sucheng Ren, Qihang Yu, Ju He +3
Flow matching models have emerged as a powerful framework for realistic image generation by learning to reverse a corruption process that progressively adds Gaussian noise. However…
ViT-5: Vision Transformers for The Mid-2020s
Feng Wang, Sucheng Ren, Tiezheng Zhang +4
This work presents a systematic investigation into modernizing Vision Transformer backbones by leveraging architectural advancements from the past five years. While preserving the…
WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark
Wang Lin, Feng Wang, Majun Zhang +7
Recent advances in image editing models have demonstrated remarkable capabilities in executing explicit instructions, such as attribute manipulation, style transfer, and pose synth…
CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs
Haoran Li, Sucheng Ren, Alan Yuille +1
Rotary Positional Embedding (RoPE) is a key component of context scaling in Large Language Models (LLMs). While various methods have been proposed to adapt RoPE to longer contexts,…
Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
Haoyu Liu, Sucheng Ren, Tingyu Zhu +5
Rotary Position Embedding (RoPE) is the de facto positional encoding in large language models due to its ability to encode relative positions and support length extrapolation. When…
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
Letian Zhang, Sucheng Ren, Yanqing Liu +9
This paper presents a family of advanced vision encoder, named OpenVision 3, that learns a single, unified visual representation that can serve both image understanding and image g…
ViMix-14M: A Curated Multi-Source Video-Text Dataset with Long-Form, High-Quality Captions and Crawl-Free Access
Timing Yang, Sucheng Ren, Alan Yuille +1
Text-to-video generation has surged in interest since Sora, yet open-source models still face a data bottleneck: there is no large, high-quality, easily obtainable video-text corpu…
Autoregressive Video Generation beyond Next Frames Prediction
Sucheng Ren, Chen Chen, Zhenbang Wang +5
Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike wo…
Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers
Sucheng Ren, Qihang Yu, Ju He +2
Diffusion-based Transformers have demonstrated impressive generative capabilities, but their high computational costs hinder practical deployment, for example, generating an $8192\…
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
Sucheng Ren, Qihang Yu, Ju He +3
Autoregressive (AR) modeling, known for its next-token prediction paradigm, underpins state-of-the-art language and visual generative models. Traditionally, a ``token'' is treated…
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
Sucheng Ren, Qihang Yu, Ju He +3
Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through…
M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
Sucheng Ren, Yaodong Yu, Nataniel Ruiz +3
There exists recent work in computer vision, named VAR, that proposes a new autoregressive paradigm for image generation. Diverging from the vanilla next-token prediction, VAR stru…
Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
Feng Wang, Timing Yang, Yaodong Yu +7
In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representation…
What If We Recaption Billions of Web Images with LLaMA-3?
Xianhang Li, Haoqin Tu, Mude Hui +9
Web-crawled image-text pairs are inherently noisy. Prior studies demonstrate that semantically aligning and enriching textual descriptions of these pairs can significantly enhance…
Autoregressive Pretraining with Mamba in Vision
Sucheng Ren, Xianhang Li, Haoqin Tu +9
The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks. This paper shows that Mamba's visual capab…
Medical Vision Generalist: Unifying Medical Imaging Tasks in Context
Sucheng Ren, Xiaoke Huang, Xianhang Li +5
This study presents Medical Vision Generalist (MVG), the first foundation model capable of handling various medical imaging tasks -- such as cross-modal synthesis, image segmentati…
ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning
Sucheng Ren, Hongru Zhu, Chen Wei +3
This paper presents a new self-supervised video representation learning framework, ARVideo, which autoregressively predicts the next video token in a tailored sequence order. Two k…
Mamba-R: Vision Mamba ALSO Needs Registers
Feng Wang, Jiahao Wang, Sucheng Ren +6
Similar to Vision Transformers, this paper identifies artifacts also present within the feature maps of Vision Mamba. These artifacts, corresponding to high-norm tokens emerging in…
Beyond Finite Data: Towards Data-free Out-of-distribution Generalization via Extrapolation
Yijiang Li, Sucheng Ren, Weipeng Deng +4
Out-of-distribution (OOD) generalization is a favorable yet challenging property for deep neural networks. The core challenges lie in the limited availability of source domains tha…
Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data
Lei Zhang, Fangxun Shu, Tianyang Liu +3
The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably…
Rejuvenating image-GPT as Strong Visual Representation Learners
Sucheng Ren, Zeyu Wang, Hongru Zhu +3
This paper enhances image-GPT (iGPT), one of the pioneering works that introduce autoregressive pretraining to predict the next pixels for visual representation learning. Two simpl…