1 citations · 2 across the 16 of their papers we have counts for
24 papers
EditAgent: Rethinking Agentic Image Editing
Haiyang Xu, Tianyu Wang, Jialu Li +5
Agentic image editors decompose complex requests into steps, but when a step fails, they mostly retry with the same narrow set of tools and a judge that scores each output by eye d…
Performance Portable Lattice Gauge Theory Simulation with Kokkos
Wei Sun
The increasing diversity of high performance computing systems makes separate, architecture specific implementations of lattice gauge theory algorithms costly to maintain. We prese…
OverLay++: Dense-Overlap Layout-to-Image Generation Dataset
Shivansh Aggarwal, Shresth Grover, Divyansh Srivastava +7
Layout-to-Image generation has made substantial progress in spatial and object-level control. However, existing methods still struggle with complex scenes containing many overlappi…
LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation
Shengxiang Ji, Boyang Wang, Haiyang Xu +9
We introduce LIFT, a unified image-to-video generation framework that complements camera control with Layout-In-FuTure control, enabling users to specify what should appear in a fu…
RECAP-Forcing: Retaining Content Appearances for Long Video Generation
Haiyang Xu, Zheng Ding, Zhuowen Tu
Long autoregressive video generation faces a fundamental memory challenge: with a finite attention window, a model must decide which information from an ever-expanding history to r…
SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons
Haiyang Xu, Ronghuan Wu, Li-Yi Wei +5
Graphic icons are a cornerstone of modern design workflows, yet they are often distributed as flattened single-path or compound-path graphics, where the original semantic layering…
CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation in Vision Foundation Models
Xiaojun Shan, Haoyu Shen, Yucheng Mao +5
We present CyCLeGen, a unified vision-language foundation model capable of both image understanding and image generation within a single autoregressive framework. Unlike existing v…
PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstruction
Xiang Zhang, Sohyun Yoo, Hongrui Wu +3
We introduce PixARMesh, a method to autoregressively reconstruct complete 3D indoor scene meshes directly from a single RGB image. Unlike prior methods that rely on implicit signed…
Soft Tail-dropping for Adaptive Visual Tokenization
Zeyuan Chen, Kai Zhang, Zhuowen Tu +1
We present Soft Tail-dropping Adaptive Tokenizer (STAT), a 1D discrete visual tokenizer that adaptively chooses the number of output tokens per image according to its structural co…
CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning
Zeyuan Chen, Xiang Zhang, Haiyang Xu +2
We present a central-peripheral vision-inspired framework (CVP), a simple yet effective multimodal model for spatial reasoning that draws inspiration from the two types of human vi…
Gaussian Swaying: Surface-Based Framework for Aerodynamic Simulation with 3D Gaussians
Hongru Yan, Xiang Zhang, Zeyuan Chen +2
Branches swaying in the breeze, flags rippling in the wind, and boats rocking on the water all show how aerodynamics shape natural motion -- an effect crucial for realism in vision…
C3Editor: Achieving Controllable Consistency in 2D Model for 3D Editing
Zeng Tao, Zheng Ding, Zeyuan Chen +3
Existing 2D-lifting-based 3D editing methods often encounter challenges related to inconsistency, stemming from the lack of view-consistent 2D editing models and the difficulty of…
VideoNSA: Native Sparse Attention Scales Video Understanding
Enxin Song, Wenhao Chai, Shusheng Yang +5
Video understanding in multimodal language models remains limited by context length: models often miss key transition frames and struggle to maintain coherence across long time sca…
OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
Bingnan Li, Chen-Yu Wang, Haiyang Xu +7
Despite steady progress in layout-to-image generation, current methods still struggle with layouts containing significant overlap between bounding boxes. We identify two primary ch…
Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification
Haowen Wang, Guowei Zhang, Xiang Zhang +4
In this paper, we address a key scientific problem in machine learning: Given a training set for an image classification task, can we train a generative model on this dataset to en…
YOLO-Count: Differentiable Object Counting for Text-to-Image Generation
Guanning Zeng, Xiang Zhang, Zirui Wang +4
We propose YOLO-Count, a differentiable open-vocabulary object counting model that tackles both general counting challenges and enables precise quantity control for text-to-image (…
DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion
Qingcheng Zhao, Xiang Zhang, Haiyang Xu +4
We propose DepR, a depth-guided single-view scene reconstruction framework that integrates instance-level diffusion within a compositional paradigm. Instead of reconstructing the e…
Lay-Your-Scene: Natural Scene Layout Generation with Diffusion Transformers
Divyansh Srivastava, Xiang Zhang, He Wen +2
We present Lay-Your-Scene (shorthand LayouSyn), a novel text-to-layout generation pipeline for natural scenes. Prior scene layout generation methods are either closed-vocabulary or…
OmniControlNet: Dual-stage Integration for Conditional Image Generation
Yilin Wang, Haiyang Xu, Xiang Zhang +4
We provide a two-way integration for the widely adopted ControlNet by integrating external condition generation algorithms into a single dense prediction method and incorporating i…
Bayesian Diffusion Models for 3D Shape Reconstruction
Haiyang Xu, Yu Lei, Zeyuan Chen +4
We present Bayesian Diffusion Models (BDM), a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-u…
HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data
Mengqi Zhang, Yang Fu, Zheng Ding +3
3D hand-object interaction data is scarce due to the hardware constraints in scaling up the data collection process. In this paper, we propose HOIDiffusion for generating realistic…
Restoration by Generation with Constrained Priors
Zheng Ding, Xuaner Zhang, Zhuowen Tu +1
The inherent generative power of denoising diffusion models makes them well-suited for image restoration tasks where the objective is to find the optimal high-quality image within…
TokenCompose: Text-to-Image Diffusion with Token-level Supervision
Zirui Wang, Zhizhou Sha, Zheng Ding +2
We present TokenCompose, a Latent Diffusion Model for text-to-image generation that achieves enhanced consistency between user-specified text prompts and model-generated images. De…
Dolfin: Diffusion Layout Transformers without Autoencoder
Yilin Wang, Zeyuan Chen, Liangjun Zhong +3
In this paper, we introduce a novel generative model, Diffusion Layout Transformers without Autoencoder (Dolfin), which significantly improves the modeling capability with reduced…