papers

Publications (49)

cs.CV2024

GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting

Hongyun Yu, Zhan Qu, Qihang Yu +8

Recent works on audio-driven talking head synthesis using Neural Radiance Fields (NeRF) have achieved impressive results. However, due to inadequate pose and expression control cau…

cs.CV2018

Recurrent Saliency Transformation Network: Incorporating Multi-Stage Visual Cues for Small Organ Segmentation

Qihang Yu, Lingxi Xie, Yan Wang +3

We aim at segmenting small organs (e.g., the pancreas) from abdominal CT scans. As the target often occupies a relatively small region in the input image, deep neural networks can…

cs.IR2026

ThinkRec: Thinking-based recommendation via LLM

Qihang Yu, Kairui Fu, Zheqi Lv +6

Recent advances in large language models (LLMs) have enabled more semantic-aware recommendations through natural language generation. Existing LLM for recommendation (LLM4Rec) meth…

cs.CV2023

Compositor: Bottom-up Clustering and Compositing for Robust Part and Object Segmentation

Ju He, Jieneng Chen, Ming-Xian Lin +2

In this work, we present a robust approach for joint part and object segmentation. Specifically, we reformulate object and part segmentation as an optimization problem and build a…

cs.CV2024

A Simple Video Segmenter by Tracking Objects Along Axial Trajectories

Ju He, Qihang Yu, Inkyu Shin +4

Video segmentation requires consistently segmenting and tracking objects over time. Due to the quadratic dependency on input size, directly applying self-attention to video segment…

cs.CV2020

When Radiology Report Generation Meets Knowledge Graph

Yixiao Zhang, Xiaosong Wang, Ziyue Xu +3

Automatic radiology report generation has been an attracting research problem towards computer-aided diagnosis to alleviate the workload of doctors in recent years. Deep learning t…

cs.CV2024

An Image is Worth 32 Tokens for Reconstruction and Generation

Qihang Yu, Mark Weber, Xueqing Deng +3

Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images. Tokenization, which transform…

cs.CV2025

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\…

cs.CV2025

Dictionary-based Framework for Interpretable and Consistent Object Parsing

Tiezheng Zhang, Qihang Yu, Alan Yuille +1

In this work, we present CoCal, an interpretable and consistent object parsing framework based on dictionary-based mask transformer. Designed around Contrastive Components and Logi…

cs.CV2026

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…

cs.CV2024

MaskBit: Embedding-free Image Generation via Bit Tokens

Mark Weber, Lijun Yu, Qihang Yu +4

Masked transformer models for class-conditional image generation have become a compelling alternative to diffusion models. Typically comprising two stages - an initial VQGAN model…

cs.CV2021

DeepLab2: A TensorFlow Library for Deep Labeling

Mark Weber, Huiyu Wang, Siyuan Qiao +12

DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer…

cs.CV2020

Can Temporal Information Help with Contrastive Self-Supervised Learning?

Yutong Bai, Haoqi Fan, Ishan Misra +6

Leveraging temporal information has been regarded as essential for developing video understanding models. However, how to properly incorporate temporal information into the recent…

cs.LG2026

ReCal: Reward Calibration for RL-based LLM Routing

Qihang Yu, Hanwen Tong, Zhengqi Zhang +5

Large language model (LLM) routing has emerged as an effective paradigm for leveraging the complementary strengths of multiple LLMs through dynamic model and reasoning-strategy sel…

cs.CV2022

PartImageNet: A Large, High-Quality Dataset of Parts

Ju He, Shuo Yang, Shaokang Yang +7

It is natural to represent objects in terms of their parts. This has the potential to improve the performance of algorithms for object recognition and segmentation but can also hel…

cs.CV2023

A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision

Lucas Beyer, Bo Wan, Gagan Madan +9

There has been a recent explosion of computer vision models which perform many tasks and are composed of an image encoder (usually a ViT) and an autoregressive decoder (usually a T…

cs.CV2022

CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation

Qihang Yu, Huiyu Wang, Dahun Kim +6

We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer archi…

cs.CV2024

ViTamin: Designing Scalable Vision Models in the Vision-Language Era

Jieneng Chen, Qihang Yu, Xiaohui Shen +2

Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to thos…

eess.IV2023

CancerUniT: Towards a Single Unified Model for Effective Detection, Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT Scans

Jieneng Chen, Yingda Xia, Jiawen Yao +22

Human readers or radiologists routinely perform full-body multi-organ multi-disease detection and diagnosis in clinical practice, while most medical AI systems are built to focus o…

cs.CV2019

Thickened 2D Networks for Efficient 3D Medical Image Segmentation

Qihang Yu, Yingda Xia, Lingxi Xie +2

There has been a debate in 3D medical image segmentation on whether to use 2D or 3D networks, where both pipelines have advantages and disadvantages. 2D methods enjoy a low inferen…

cs.CV2026

Autoregressive Image Generation with Masked Bit Modeling

Qihang Yu, Qihao Liu, Ju He +4

This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrar…

cs.CV2025

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

Dongwon Kim, Ju He, Qihang Yu +4

Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large…

cs.CV2025

Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting

Inkyu Shin, Qihang Yu, Xiaohui Shen +3

Recent advancements in zero-shot video diffusion models have shown promise for text-driven video editing, but challenges remain in achieving high temporal consistency. To address t…

cs.CV2025

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…

cs.CV2023

MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models

Chenglin Yang, Siyuan Qiao, Qihang Yu +5

This paper presents MOAT, a family of neural networks that build on top of MObile convolution (i.e., inverted residual blocks) and ATtention. Unlike the current works that stack se…

cs.CV2021

Glance-and-Gaze Vision Transformer

Qihang Yu, Yingda Xia, Yutong Bai +3

Recently, there emerges a series of vision Transformers, which show superior performance with a more compact model size than conventional convolutional neural networks, thanks to t…

cs.CV2024

Randomized Autoregressive Visual Generation

Qihang Yu, Ju He, Xueqing Deng +2

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining ful…

cs.CV2026

ReVision: Refining Video Diffusion with Explicit 3D Motion Modeling

Qihao Liu, Ju He, Qihang Yu +2

In recent years, video generation has seen significant advancements. However, challenges still persist in generating complex motions and interactions. To address these challenges,…

cs.CV2023

3D TransUNet: Advancing Medical Image Segmentation through Vision Transformers

Jieneng Chen, Jieru Mei, Xianhang Li +12

Medical image segmentation plays a crucial role in advancing healthcare systems for disease diagnosis and treatment planning. The u-shaped architecture, popularly known as U-Net, h…

cs.CV2026

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens

Tommie Kerssies, Gabriele Berton, Ju He +5

Anticipating diverse future states is a central challenge in video world modeling. Discriminative world models produce a deterministic prediction that implicitly averages over poss…

cs.IR2026

MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendation

Qihang Yu, Kairui Fu, Zhaocheng Du +10

The scaling law, which indicates that model performance improves with increasing dataset and model capacity, has fueled a growing trend in expanding recommendation models in both i…

cs.CV2023

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Qihang Yu, Ju He, Xueqing Deng +2

Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing objects from an open set of categories. One way to address this challenge is to leverage mul…

cs.CV2024

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…

cs.CV2020

CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks

Qihang Yu, Yingwei Li, Jieru Mei +2

3D Convolution Neural Networks (CNNs) have been widely applied to 3D scene understanding, such as video analysis and volumetric image recognition. However, 3D networks can easily l…

cs.CV2023

Towards Open-Ended Visual Recognition with Large Language Model

Qihang Yu, Xiaohui Shen, Liang-Chieh Chen

Localizing and recognizing objects in the open-ended physical world poses a long-standing challenge within the domain of machine perception. Recent methods have endeavored to addre…

cs.CV2020

Neural Architecture Search for Lightweight Non-Local Networks

Yingwei Li, Xiaojie Jin, Jieru Mei +7

Non-Local (NL) blocks have been widely studied in various vision tasks. However, it has been rarely explored to embed the NL blocks in mobile neural networks, mainly due to the fol…

cs.CV2023

kMaX-DeepLab: k-means Mask Transformer

Qihang Yu, Huiyu Wang, Siyuan Qiao +5

The rise of transformers in vision tasks not only advances network backbone designs, but also starts a brand-new page to achieve end-to-end image recognition (e.g., object detectio…

cs.CV2023

Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation

Inkyu Shin, Dahun Kim, Qihang Yu +6

Video Panoptic Segmentation (VPS) aims to achieve comprehensive pixel-level scene understanding by segmenting all pixels and associating objects in a video. Current solutions can b…

cs.CV2021

Mask Guided Matting via Progressive Refinement Network

Qihang Yu, Jianming Zhang, He Zhang +5

We propose Mask Guided (MG) Matting, a robust matting framework that takes a general coarse mask as guidance. MG Matting leverages a network (PRN) design which encourages the matti…

cs.CV2021

TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

Jieneng Chen, Yongyi Lu, Qihang Yu +6

Medical image segmentation is an essential prerequisite for developing healthcare systems, especially for disease diagnosis and treatment planning. On various medical image segment…

eess.IV2020

Detecting Pancreatic Ductal Adenocarcinoma in Multi-phase CT Scans via Alignment Ensemble

Yingda Xia, Qihang Yu, Wei Shen +3

Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers among the population. Screening for PDACs in dynamic contrast-enhanced CT is beneficial for early diagnosi…

cs.CV2025

COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation

Xueqing Deng, Qihang Yu, Ali Athar +5

This paper introduces the COCONut-PanCap dataset, created to enhance panoptic segmentation and grounded image captioning. Building upon the COCO dataset with advanced COCONut panop…

cs.CV2024

Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization

Qihao Liu, Zhanpeng Zeng, Ju He +3

This paper presents innovative enhancements to diffusion models by integrating a novel multi-resolution network and time-dependent layer normalization. Diffusion models have gained…

cs.CV2024

COCONut: Modernizing COCO Segmentation

Xueqing Deng, Qihang Yu, Peng Wang +2

In recent decades, the vision community has witnessed remarkable progress in visual recognition, partially owing to advancements in dataset benchmarks. Notably, the established COC…

cs.CV2023

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

Shuyang Sun, Weijun Wang, Qihang Yu +3

This paper presents a new mechanism to facilitate the training of mask transformers for efficient panoptic segmentation, democratizing its deployment. We observe that due to its hi…

cs.CV2023

TubeFormer-DeepLab: Video Mask Transformer

Dahun Kim, Jun Xie, Huiyu Wang +6

We present TubeFormer-DeepLab, the first attempt to tackle multiple core video segmentation tasks in a unified manner. Different video segmentation tasks (e.g., video semantic/inst…

cs.CV2025

FlowTok: Flowing Seamlessly Across Text and Image Tokens

Ju He, Qihang Yu, Qihao Liu +1

Bridging different modalities lies at the heart of cross-modality generation. While conventional approaches treat the text modality as a conditioning signal that gradually guides t…

cs.CV2021

Shape-Texture Debiased Neural Network Training

Yingwei Li, Qihang Yu, Mingxing Tan +5

Shape and texture are two prominent and complementary cues for recognizing objects. Nonetheless, Convolutional Neural Networks are often biased towards either texture or shape, dep…

cs.CV2020

C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation

Qihang Yu, Dong Yang, Holger Roth +4

3D convolution neural networks (CNN) have been proved very successful in parsing organs or tumours in 3D medical images, but it remains sophisticated and time-consuming to choose o…