7 citations · 11 across the 11 of their papers we have counts for
11 papers
Echo-Memory: A Controlled Study of Memory in Action World Models
Wayne King, Zeyue Xue, Yuxuan Bian +13
We present \textbf{Echo-Memory}, a controlled study of memory mechanisms in action-conditioned world models. These models generate multi-segment videos from a first frame, text pro…
Recursive Flow Matching
Jiahe Huang, Sihan Xu, Sharvaree Vadgama +1
Generative models have emerged as a powerful paradigm for solving physics systems and modeling complex spatiotemporal dynamics. However, achieving high physical accuracy without in…
Next-Embedding Prediction Makes Strong Vision Learners
Sihan Xu, Ziqiao Ma, Wenhao Chai +5
Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training mode…
4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time
Ziqiao Ma, Xuweiyi Chen, Shoubin Yu +10
Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative…
SAB3R: Semantic-Augmented Backbone in 3D Reconstruction
Xuweiyi Chen, Tian Xia, Sihan Xu +3
We introduce a new task, Map and Locate, which unifies the traditionally distinct objectives of open-vocabulary segmentation - detecting and segmenting object instances based on na…
Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation
Ziqiao Ma, Jing Ding, Xuejun Zhang +6
Referring Expression Generation (REG) is a core task for evaluating the pragmatic competence of vision-language systems, requiring not only accurate semantic grounding but also adh…
Multi-Object Hallucination in Vision-Language Models
Xuweiyi Chen, Ziqiao Ma, Xuejun Zhang +5
Large vision language models (LVLMs) often suffer from object hallucination, producing objects not present in the given images. While current benchmarks for object hallucination pr…
UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control
Tian Xia, Xuweiyi Chen, Sihan Xu
Video Diffusion Models have been developed for video generation, usually integrating text and image conditioning to enhance control over the generated content. Despite the progress…
Inversion-Free Image Editing with Natural Language
Sihan Xu, Yidong Huang, Jiayi Pan +2
Despite recent advances in inversion-based editing, text-guided image manipulation remains challenging for diffusion models. The primary bottlenecks include 1) the time-consuming n…
CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
Sihan Xu, Ziqiao Ma, Yidong Huang +2
Diffusion models (DMs) have enabled breakthroughs in image synthesis tasks but lack an intuitive interface for consistent image-to-image (I2I) translation. Various methods have bee…
ACE: Zero-Shot Image to Image Translation via Pretrained Auto-Contrastive-Encoder
Sihan Xu, Zelong Jiang, Ruisi Liu +2
Image-to-image translation is a fundamental task in computer vision. It transforms images from one domain to images in another domain so that they have particular domain-specific c…