6 citations · 8 across the 37 of their papers we have counts for
23 papers · 1 filter
Focus Where It Counts: A Salience-Driven Vision-Language Model for Low Vision Assistance
Jiazhao Liang, Hao Huang, Shuaihang Yuan +8
Vision-language models (VLMs) are rapidly progressing and offer promising capabilities for assistive technologies supporting persons with blindness or low vision. However, existing…
StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization
Yuyang Yin, Zixiang Li, Longxuan Deng +11
Previsualization is an intermediate layer between ideas and production in film, games, architecture, and urban design. It lets creators iteratively refine scenes, actions, cameras,…
StructGen: Disambiguating Multi-Reference Image Generation via Structured Context Modeling
Jianing Peng, Mengyu Wang, Henghui Ding +6
Multi-reference image generation aims to synthesize images by integrating attributes from multiple reference images under textual instructions. As the number of references increase…
Rethinking One-Step Image Editing through ChordEdit: Reproduction, Simplification, and New Insights
Minghan Li, Jeremy Moebel, Mengyu Wang
One-step image editing is important for making text-guided editing fast, practical, and easy to deploy, but its underlying mechanism is still not fully understood. We revisit Chord…
GeoWorld-VLM: Geometry from World Models for Vision-Language Models
Renjie Gu, Kaichen Zhou, Yan Luo +1
Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between. One cause of…
Beyond Motion Primitives: Behavioral Activity Recognition from Head-Mounted IMU
Chung-Ta Huang, Leopold Das, Jeffrey Zhou +10
AR smart glasses need continuous behavioral context to offer proactive assistance, yet their most practical always-on sensor, the head-mounted Inertial Measurement Unit (IMU), dete…
VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation
Yan Luo, Ahmadou Aidara, Jingyi Lu +3
Classifier-free guidance (CFG) is the primary control over how strongly text semantics move a flow-based sampler, yet standard practice holds its scale fixed across the entire ODE…
GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
Kaichen Zhou, Yuzhen Chen, Fangneng Zhan +8
Video world models can generate realistic futures from a single instruction, but they often fail to track the same physical points consistently across time. As a result, the genera…
Stream3D: Sequential Multi-View 3D Generation via Evidential Memory
Kaichen Zhou, Zeyang Bai, Xinhai Chang +3
View-conditioned 3D generators such as SAM 3D, TRELLIS, and Hunyuan3D produce high-quality object reconstructions from a single view, but real-world visual observation often arrive…
Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
Advaith Ravishankar, Serena Liu, Mingyang Wang +11
State-of-the-art text-to-image models produce high-quality images, but inference remains expensive as generation requires several sequential ODE or denoising steps. Native one-step…
Single-Slice-to-3D Reconstruction in Medical Imaging and Natural Objects: A Comparative Benchmark with SAM 3D
Yan Luo, Advaith Ravishankar, Serena Liu +2
While three-dimensional imaging is essential for clinical diagnosis, its high cost and long wait times have motivated the use of image-to-3D foundation models to infer volume from…
Look-Ahead and Look-Back Flows: Training-Free Image Generation with Trajectory Smoothing
Yan Luo, Henry Huang, Todd Y. Zhou +1
Recent advances have reformulated diffusion models as deterministic ordinary differential equations (ODEs) through the framework of flow matching, providing a unified formulation f…
Memorization in 3D Shape Generation: An Empirical Study
Shu Pu, Boya Zeng, Kaichen Zhou +2
Generative models are increasingly used in 3D vision to synthesize novel shapes, yet it remains unclear whether their generation relies on memorizing training shapes. Understanding…
SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing
Sung-Hoon Yoon, Minghan Li, Gaspard Beaudouin +3
Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs. Despite their strong generative capab…
PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception
Kaichen Zhou, Yuhan Wang, Grace Chen +5
Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since the…
PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion
Yuyang Yin, HaoXiang Guo, Fangfu Liu +7
Generating a complete and explorable 360-degree visual world enables a wide range of downstream applications. While prior works have advanced the field, they remain constrained by…
Delta Rectified Flow Sampling for Text-to-Image Editing
Gaspard Beaudouin, Minghan Li, Jaeyeon Kim +2
We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image editing. DRFS is a distillation…
CurveFlow: Curvature-Guided Flow Matching for Image Generation
Yan Luo, Drake Du, Hao Huang +2
Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the imag…
All-in-One Slider for Attribute Manipulation in Diffusion Models
Weixin Ye, Hongguang Zhu, Wei Wang +3
Text-to-image (T2I) diffusion models have made significant strides in generating high-quality images. However, progressively manipulating certain attributes of generated images to…
CharaConsist: Fine-Grained Consistent Character Generation
Mengyu Wang, Henghui Ding, Jianing Peng +3
In text-to-image generation, producing a series of consistent contents that preserve the same identity is highly valuable for real-world applications. Although a few works have exp…
SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing
Hongguang Zhu, Yunchao Wei, Mengyu Wang +4
Diffusion models (DMs) have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety r…
FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models
Minghan Li, Chenxi Xie, Yichen Wu +2
Numerous text-to-video (T2V) editing methods have emerged recently, but the lack of a standardized benchmark for fair evaluation has led to inconsistent claims and an inability to…
SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process
Mengyu Wang, Henghui Ding, Jun Hao Liew +3
In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner,…