1 citations · 2 across the 22 of their papers we have counts for
23 papers
Figures as Programs: Recursive Generation of Editable Scientific Figures
Yepeng Liu, Dasen Dai, Chengzhi Liu +7
Scientific methodology figures are essential for communicating complex methods clearly, yet creating them remains labor-intensive and typically requires multiple rounds of refineme…
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Jiazheng Xing, Hangjie Yuan, Lingling Cai +9
Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelity generator into the unified t…
ActionMap: Robot Policy Learning via Voxel Action Heatmap
Pei Yang, Hai Ci, Yanzhe Chen +3
Vision-language-action (VLA) models have advanced rapidly across backbones, training recipes, and data scale, yet the action decoder, which converts the backbone's hidden state int…
UENR-600K: A Large-Scale Physically Grounded Dataset for Nighttime Video Deraining
Pei Yang, Hai Ci, Beibei Lin +2
Nighttime video deraining is uniquely challenging because raindrops interact with artificial lighting. Unlike daytime white rain, nighttime rain takes on various colors and appears…
LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation
Jiazheng Xing, Fei Du, Hangjie Yuan +7
Recent advances in diffusion models have significantly improved text-to-video generation, enabling personalized content creation with fine-grained control over both foreground and…
World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy
Xiaokang Liu, Zechen Bai, Hai Ci +2
Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervi…
H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos
Hai Ci, Xiaokang Liu, Pei Yang +2
Robots that learn manipulation skills from everyday human videos could acquire broad capabilities without tedious robot data collection. We propose a video-to-video translation fra…
X-Humanoid: Robotize Human Videos to Generate Humanoid Videos at Scale
Pei Yang, Hai Ci, Yiren Song +1
The advancement of embodied AI has unlocked significant potential for intelligent humanoid robots. However, progress in both Vision-Language-Action (VLA) models and world models is…
B2N3D: Progressive Learning from Binary to N-ary Relationships for 3D Object Grounding
Feng Xiao, Hongbin Xu, Hai Ci +1
Localizing 3D objects using natural language is essential for robotic scene understanding. The descriptions often involve multiple spatial relationships to distinguish similar obje…
DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection
Hai Ci, Ziheng Peng, Pei Yang +2
Diffusion-based editing enables realistic modification of local image regions, making AI-generated content harder to detect. Existing AIGC detection benchmarks focus on classifying…
RobotSeg: A Model and Dataset for Segmenting Robots in Image and Video
Haiyang Mei, Qiming Huang, Hai Ci +1
Accurate robot segmentation is a fundamental capability for robotic perception. It enables precise visual servoing for VLA systems, scalable robot-centric data augmentation, accura…
OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
Jiazheng Xing, Hai Ci, Hongbin Xu +3
Watermarking diffusion-generated images is crucial for copyright protection and user tracking. However, current diffusion watermarking methods face significant limitations: zero-bi…
macOSWorld: A Multilingual Interactive Benchmark for GUI Agents
Pei Yang, Hai Ci, Mike Zheng Shou
Graphical User Interface (GUI) agents show promising capabilities for automating computer-use tasks and facilitating accessibility, but existing interactive benchmarks are mostly E…
Cyc3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization
Hongbin Xu, Chaohui Yu, Feng Xiao +5
Despite the remarkable progress of 3D generation, achieving controllability, i.e., ensuring consistency between generated 3D content and input conditions like edge and depth, remai…
Impossible Videos
Zechen Bai, Hai Ci, Mike Zheng Shou
Synthetic videos nowadays is widely used to complement data scarcity and diversity of real-world videos. Current synthetic datasets primarily replicate real-world scenarios, leavin…
In-Context Defense in Computer Agents: An Empirical Study
Pei Yang, Hai Ci, Mike Zheng Shou
Computer agents powered by vision-language models (VLMs) have significantly advanced human-computer interaction, enabling users to perform complex tasks through natural language in…
Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation
Yiren Song, Shengtao Lou, Xiaokang Liu +4
Diffusion models have revolutionized generative modeling with their exceptional ability to produce high-fidelity images. However, misuse of such potent tools can lead to the creati…
IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation
Yiren Song, Pei Yang, Hai Ci +1
Recently, zero-shot methods like InstantID have revolutionized identity-preserving generation. Unlike multi-image finetuning approaches such as DreamBooth, these zero-shot methods…
Image Watermarks are Removable Using Controllable Regeneration from Clean Noise
Yepeng Liu, Yiren Song, Hai Ci +4
Image watermark techniques provide an effective way to assert ownership, deter misuse, and trace content sources, which has become increasingly essential in the era of large genera…
ProcessPainter: Learn Painting Process from Sequence Data
Yiren Song, Shijie Huang, Chen Yao +5
The painting process of artists is inherently stepwise and varies significantly among different painters and styles. Generating detailed, step-by-step painting processes is essenti…
Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?
Pei Yang, Hai Ci, Yiren Song +1
Digital watermarking techniques are crucial for copyright protection and source identification of images, especially in the era of generative AI models. However, many existing wate…
WMAdapter: Adding WaterMark Control to Latent Diffusion Models
Hai Ci, Yiren Song, Pei Yang +2
Watermarking is crucial for protecting the copyright of AI-generated images. We propose WMAdapter, a diffusion model watermark plugin that takes user-specified watermark informatio…
RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification
Hai Ci, Pei Yang, Yiren Song +1
We revisit Tree-Ring Watermarking, a recent diffusion model watermarking method that demonstrates great robustness to various attacks. We conduct an in-depth study on it and reveal…