YT
Yu-Wing Tai
cs.CVcs.LGcs.AIcs.GRAlgorithmseess.IVArtificial Intelligencecs.CLcs.ROcs.SD
On Valency
published · living versionsW_xz8na6nb·v1 · currentpublished
Revealing and Bridging the Physical Executability Gap in Vision-Language Navigation
with Gang He, Zhile Cheng, Kepeng Xu, Zhenyang Liu
1 version
Preprints & journals
162 papers in the corpus · 2006–2026Revealing and Bridging the Physical Executability Gap in Vision-Language Navigation2610.25687v1 · Gang He, Zhile Cheng, Kepeng Xu et al.2026 · 0 citationsarXivon Valency
RefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial Routing2610.07720v1 · Wanning He, Yuyao Zhang, Yu-Wing Tai2026 · 0 citationsarXiv
Just Align : Aligning Predictions, Not Representations2610.00600v1 · Yuyao Zhang, Yuwei Hu, Ziyang Mai et al.2026 · 0 citationsarXiv
When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution2608.09133v1 · Yu Shi, Yuyao Zhang, Yu-wing Tai2026 · 0 citationsarXiv
IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning2607.03614v1 · Yuening Cai, Junwei Zhou, Youran Qu et al.2026 · 0 citationsarXiv
Beyond MoCap: Scaling Motion Tokenizers with Synthetic Human Motion for Generative Modeling2606.27547v1 · Yiwen Yan, Wanning He, Yu-Wing Tai2026 · 0 citationsarXiv
Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation2605.25326v2 · Junwei Zhou, Yu-Wing Tai2026 · 0 citationsarXiv
Meta-Agent: From Task Descriptions to Verified Multi-Agent Systems2605.25233v1 · Andy Xu, Yu-Wing Tai2026 · 0 citationsarXiv
HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing2605.17294v1 · Yuyao Zhang, Alexander Huang-Menders, Yu-Wing Tai2026 · 0 citationsarXiv
AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling2605.16649v1 · Ziyang Mai, Yuyao Zhang, Yu-Wing Tai2026 · 0 citationsarXiv
ReasonNavi: Human-Inspired Global Map Reasoning for Zero-Shot Embodied Navigation2602.15864v1 · Yuzhuo Ao, Anbang Wang, Yu-Wing Tai et al.2026 · 0 citationsarXiv
CoT-Seg: Rethinking Segmentation with Chain-of-Thought Reasoning and Self-Correction2601.17420v1 · Shiu-hong Kao, Chak Ho Huang, Huaiqian Liu et al.2026 · 0 citationsarXiv
ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation2512.07328v2 · Ziyang Mai, Yu-Wing Tai2025 · 0 citationsarXiv
GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence2511.21945v3 · Junwei Zhou, Yu-Wing Tai2025 · 0 citationsarXiv
UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention2510.16325v4 · Yuyao Zhang, Yu-Wing Tai2025 · 0 citationsarXiv
Trace Anything: Representing Any Video in 4D via Trajectory Fields2510.13802v1 · Xinhang Liu, Yuxi Xiao, Donny Y. Chen et al.2025 · 0 citationsarXiv
SmartAvatar: Text- and Image-Guided Human Avatar Generation with VLM AI Agents2506.04606v1 · Alexander Huang-Menders, Xinhang Liu, Andy Xu et al.2025 · 0 citationsarXiv
MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning2505.20096v2 · Thang Nguyen, Peter Chin, Yu-Wing Tai2025 · 2 citationsarXiv
Agentic 3D Scene Generation with Spatially Contextualized VLMs2505.20129v3 · Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang2025 · 0 citationsarXiv
CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos2505.18561v4 · Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang2025 · 1 citationarXiv
RealRep: Generalized SDR-to-HDR Conversion via Attribute-Disentangled Representation Learning2505.07322v4 · Li Xu, Siqi Wang, Kepeng Xu et al.2025 · 3 citationsarXiv
PS-ReID: Advancing Person Re-Identification and Precise Segmentation with Multimodal Retrieval2503.21595v2 · Jincheng Yan, Yun Wang, Xiaoyan Luo et al.2025 · 0 citationsarXiv
LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration2504.00010v3 · Yuyao Zhang, Jinghao Li, Yu-Wing Tai2025 · 1 citationarXiv
Multimodal Generation of Animatable 3D Human Models with AvatarForge2503.08165v1 · Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang2025 · 0 citationsarXiv
ReelWave: Multi-Agentic Movie Sound Generation through Multimodal LLM Conversation2503.07217v3 · Zixuan Wang, Chi-Keung Tang, Yu-Wing Tai2025 · 0 citationsarXiv
Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning2503.07323v2 · Yubo Zhao, Qi Wu, Yifan Wang et al.2025 · 0 citationsarXiv
Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts2503.07503v4 · Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang2025 · 0 citationsarXiv
WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agents2502.15601v2 · Xinhang Liu, Chi-Keung Tang, Yu-Wing Tai2025 · 0 citationsarXiv
UVRM: A Scalable 3D Reconstruction Model from Unposed Videos2501.09347v2 · Shiu-hong Kao, Xiao Li, Jinglu Wang et al.2025 · 0 citationsarXiv
Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition2410.03335v2 · Zixuan Wang, Chi-Keung Tang, Yu-Wing Tai2024 · 0 citationsarXiv
Reward-RAG: Enhancing RAG with Reward Driven Supervision2410.03780v1 · Thang Nguyen, Peter Chin, Yu-Wing Tai2024 · 0 citationsarXiv
ChatCam: Empowering Camera Control through Conversational AI2409.17331v1 · Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang2024 · 4 citationsarXiv
VP-LLM: Text-Driven 3D Volume Completion with Large Language Models through Patchification2406.05543v1 · Jianmeng Liu, Yichen Liu, Yuyao Zhang et al.2024 · 0 citationsarXiv
Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling2406.03723v1 · Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang et al.2024 · 4 citationsarXiv
Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs2405.17013v3 · Qi Wu, Yubo Zhao, Yifan Wang et al.2024 · 1 citationarXiv
C3LLM: Conditional Multimodal Content Generation Using Large Language Models2405.16136v1 · Zixuan Wang, Qinkai Duan, Yu-Wing Tai et al.2024 · 0 citationsarXiv
FED-NeRF: Achieve High 3D Consistency and Temporal Coherence for Face Video Editing on Dynamic NeRF2401.02616v1 · Hao Zhang, Yu-Wing Tai, Chi-Keung Tang2024 · 0 citationsarXiv
Inpaint4DNeRF: Promptable Spatio-Temporal NeRF Inpainting with Generative Diffusion Models2401.00208v1 · Han Jiang, Haosen Sun, Ruoxuan Li et al.2023 · 2 citationsarXiv
Prompt2NeRF-PIL: Fast NeRF Generation via Pretrained Implicit Latent2312.02568v1 · Jianmeng Liu, Yuyao Zhang, Zeyuan Meng et al.2023 · 0 citationsarXiv
SANeRF-HQ: Segment Anything for NeRF in High Quality2312.01531v2 · Yichen Liu, Benran Hu, Chi-Keung Tang et al.2023 · 12 citationsarXiv
DragVideo: Interactive Drag-style Video Editing2312.02216v3 · Yufan Deng, Ruida Wang, Yuhao Zhang et al.2023 · 11 citationsarXiv
C3Net: Compound Conditioned ControlNet for Multimodal Content Generation2311.17951v1 · Juntao Zhang, Yuehuai Liu, Yu-Wing Tai et al.2023 · 6 citationsarXiv
Stable Segment Anything Model2311.15776v2 · Qi Fan, Xin Tao, Lei Ke et al.2023 · 2 citationsarXiv
InceptionHuman: Controllable Prompt-to-NeRF for Photorealistic 3D Human Generation2311.16499v2 · Shiu-hong Kao, Xinhang Liu, Yu-Wing Tai et al.2023 · 1 citationarXiv
EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding2309.02423v1 · Yue Xu, Yong-Lu Li, Zhemin Huang et al.2023 · 9 citationsarXiv
Scene-Generalizable Interactive Segmentation of Radiance Fields2308.05104v1 · Songlin Tang, Wenjie Pei, Xin Tao et al.2023 · 9 citationsarXiv
Feature Decoupling-Recycling Network for Fast Interactive Segmentation2308.03529v2 · Huimin Zeng, Weinong Wang, Xin Tao et al.2023 · 6 citationsarXiv
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector.37018107 · Zheng, Peng, Fu, Huazhu, Fan, Deng-Ping et al.2023 · 46 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(9):10929-10946
Cascade-DETR: Delving into High-Quality Universal Object Detection2307.11035v1 · Mingqiao Ye, Lei Ke, Siyuan Li et al.2023 · 64 citationsarXiv
Segment Anything Meets Point Tracking2307.01197v2 · Frano Rajic, Lei Ke, Yu-Wing Tai et al.2023 · 57 citationsarXiv
Career total: 290 works. 162 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.