LG
Leonidas Guibas
cs.CVcs.LGcs.GRcs.AIcs.ROcs.CGstat.MLcs.CLcs.NEeess.IV
On Valency
published · living versionsW_3dcebdb6·v1 · currentpublished
FluidGen: Physics-Aware Fluid Video Generation via Motion-Guided Post-Training
with Yang Zheng, Zizhang Li, Boyang Deng, Jan Ackermann +4
1 version
Preprints & journals
305 papers in the corpus · 2002–2026FluidGen: Physics-Aware Fluid Video Generation via Motion-Guided Post-Training2610.25660v1 · Yang Zheng, Zizhang Li, Boyang Deng et al.2026 · 0 citationsarXivon Valency
T2-z: Test-Time Optimization of Environment Latents for Robotic World Models2610.22364v1 · Chenyuan Zhou, Yining Hong, Huang Huang et al.2026 · 0 citationsarXiv
PCAsplat: Gaussian Splatting with Local PCA Regularization2610.11011v1 · Vitor Matias, Filipe Nascimento, Kiyohiro Nakayama et al.2026 · 0 citationsarXiv
Level-of-Token Diffusion2610.05816v1 · Kiyohiro Nakayama, Brian Chao, Jan Ackermann et al.2026 · 0 citationsarXiv
Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure Diagnosis2609.38851v1 · Xia Hu, Brian Potetz, Chun-Ta Lu et al.2026 · 0 citationsarXiv
Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulation2608.08559v1 · Lei Shu, Ying Jiang, Kui Wu et al.2026 · 0 citationsarXiv
SeeSE3: Emergence of 3D Space in Vision Features2607.14228v1 · Caroline Chen, Sayna Ebrahimi, Fedor Kitashov et al.2026 · 0 citationsarXiv
UniPose9D: Universal Category-Agnostic Object Pose Estimation2607.09985v2 · Yang You, Yi Du, Cole Harrison et al.2026 · 0 citationsarXiv
Geometry-Aware Motion Latents for Learning Robust Manipulation Policies2607.04714v1 · Yunchao Zhang, Yijia Weng, Ruizhe Liu et al.2026 · 0 citationsarXiv
SuperFlex: Deformable Superquadrics for Point Cloud Decomposition2607.01015v1 · Gabriel Tavernini, Elisabetta Fedele, Tiago Novello et al.2026 · 0 citationsarXiv
MeshFlow: Mesh Generation with Equivariant Flow Matching2606.23489v2 · Qi Sun, Kiyohiro Nakayama, Jing Nathan Yan et al.2026 · 0 citationsarXiv
Duet: Dual-Robot Understanding via Efficient Teaching2606.20990v2 · Yiqi Zhao, Ruohai Ge, Celina Shiyu Wang et al.2026 · 0 citationsarXiv
Functional Gradient Descent with Adaptive Representations2606.16926v1 · Daniel Csillag, Rodrigo Schuller, Pedro Dall'Antonia et al.2026 · 0 citationsarXiv
The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning2606.11918v2 · Theo Uscidda, Marta Tintore Gazulla, Maks Ovsjanikov et al.2026 · 0 citationsarXiv
Planning with the Views2605.29563v4 · Kangrui Wang, Linjie Li, Zhengyuan Yang et al.2026 · 0 citationsarXiv
Fishbone: From One 3D Asset to a Million Controllable Edits2605.24805v1 · Yumeng He, Xiaoying Wang, Peihao Li et al.2026 · 0 citationsarXiv
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop2605.18746v2 · Yining Hong, Jiageng Liu, Han Yin et al.2026 · 0 citationsarXiv
OCH3R: Object-Centric Holistic 3D Reconstruction2605.13018v2 · Yi Du, Yang You, Xiang Wan et al.2026 · 0 citationsarXiv
The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space2605.09883v3 · Xia Hu, Zhenrui Yue, Brian Potetz et al.2026 · 0 citationsarXiv
DOT-Sim: Differentiable Optical Tactile Simulation with Precise Real-to-Sim Physical Calibration2604.27367v1 · Yang You, Won Kyung Do, Aiden Swann et al.2026 · 0 citationsarXiv
FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos2604.05621v2 · Alexandros Delitzas, Chenyangguang Zhang, Alexey Gavryushin et al.2026 · 0 citationsarXiv
SceneTeract: Probing and Improving Agent-Aware Activity Reasoning in 3D Indoor Scenes2603.29798v2 · L'eopold Maillard, Francis Engelmann, Tom Durand et al.2026 · 0 citationsarXiv
RINO: Rotation-Invariant Non-Rigid Correspondences2603.27773v1 · Maolin Gao, Shao Jie Hu-Chen, Congyue Deng et al.2026 · 0 citationsComputer Vision and Pattern Recognition (CVPR) 2026
Mode Seeking meets Mean Seeking for Fast Long Video Generation2602.24289v3 · Shengqu Cai, Weili Nie, Chao Liu et al.2026 · 0 citationsarXiv
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs2602.21198v3 · Yining Hong, Huang Huang, Manling Li et al.2026 · 0 citationsarXiv
PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning2602.20323v6 · Haoyang Li, Yang You, Hao Su et al.2026 · 0 citationsarXiv
Learning Protein Structure Representation with Orientation-Aware Networks.41468157 · Li, Jiahan, Luo, Shitong, Deng, Congyue et al.2025 · 0 citationsJournal of computational biology : a journal of computational molecular cell biology. 2025
Mull-Tokens: Modality-Agnostic Latent Thinking2512.10941v2 · Arijit Ray, Ahmed Abdelkader, Chengzhi Mao et al.2025 · 0 citationsarXiv
SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling2512.05343v2 · Elisabetta Fedele, Francis Engelmann, Ian Huang et al.2025 · 0 citationsarXiv
SplatPainter: Interactive Authoring of 3D Gaussians from 2D Edits via Test-Time Training2512.05354v2 · Yang Zheng, Hao Tan, Kai Zhang et al.2025 · 0 citationsarXiv
HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild2512.02450v1 · Valentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno et al.2025 · 0 citationsarXiv
Robot Learning from a Physical World Model2511.07416v1 · Jiageng Mao, Sicheng He, Hao-Ning Wu et al.2025 · 0 citationsarXiv
Dynamic Reflections: Probing Video Representations with Text Alignment2511.02767v2 · Tyler Zhu, Tengda Han, Leonidas Guibas et al.2025 · 0 citationsarXiv
pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation2510.14974v3 · Hansheng Chen, Kai Zhang, Hao Tan et al.2025 · 0 citationsarXiv
MoMaps: Semantics-Aware Scene Motion Generation with Motion Maps2510.11107v1 · Jiahui Lei, Kyle Genova, George Kopanas et al.2025 · 1 citationarXiv
GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification2509.25603v1 · Yijia Weng, Zhicheng Wang, Songyou Peng et al.2025 · 0 citationsarXiv
Robot Learning from Any Images2509.22970v2 · Siheng Zhao, Jiageng Mao, Wei Chow et al.2025 · 0 citationsarXiv
Mixture of Contexts for Long Video Generation2508.21058v3 · Shengqu Cai, Ceyuan Yang, Lvmin Zhang et al.2025 · 1 citationarXiv
Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion2508.20136v1 · Junru Lin, Chirag Vashist, Mikaela Angelina Uy et al.2025 · 0 citationsarXiv
LookOut: Real-World Humanoid Egocentric Navigation2508.14466v1 · Boxiao Pan, Adam W. Harley, C. Karen Liu et al.2025 · 2 citationsarXiv
CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization2506.21117v2 · Jan Ackermann, Jonas Kulhanek, Shengqu Cai et al.2025 · 4 citationsarXiv
Video Perception Models for 3D Scene Synthesis2506.20601v1 · Rui Huang, Guangyao Zhai, Zuria Bauer et al.2025 · 0 citationsarXiv
SceneCrafter: Controllable Multi-View Driving Scene Editing2506.19488v1 · Zehao Zhu, Yuliang Zou, Chiyu Max Jiang et al.2025 · 5 citationsarXiv
AllTracker: Efficient Dense Point Tracking at High Resolution2506.07310v2 · Adam W. Harley, Yang You, Xinglong Sun et al.2025 · 11 citationsarXiv
Animal Pose Labeling Using General-Purpose Point Trackers2506.03868v1 · Zhuoyang Pan, Boxiao Pan, Guandao Yang et al.2025 · 0 citationsarXiv
Rodrigues Network for Learning Robot Actions2506.02618v2 · Jialiang Zhang, Haoran Geng, Yang You et al.2025 · 0 citationsarXiv
GARLIC: GAussian Representation LearnIng for spaCe partitioning2505.24608v2 · Panagiotis Rigas, Panagiotis Drivas, Charalambos Tzamos et al.2025 · 0 citationsarXiv
Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation2504.17207v1 · Phillip Y. Lee, Jihyeon Je, Chanho Park et al.2025 · 6 citationsarXiv
Visual Chronicles: Using Multimodal LLMs to Analyze Massive Collections of Images2504.08727v3 · Boyang Deng, Songyou Peng, Kyle Genova et al.2025 · 1 citationarXiv
Gaussian Mixture Flow Matching Models2504.05304v3 · Hansheng Chen, Kai Zhang, Hao Tan et al.2025 · 0 citationsarXiv
Career total: 976 works. 305 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.