Identifying Instabilities with Quantum Geometry in Flat Band Systems

Kavli Affiliate: Leon Balents | First 5 Authors: Jia-Xin Zhang, Wen O. Wang, Leon Balents, Lucile Savary, | Summary: The absence of a well-defined Fermi surface in flat-band systems challenges the conventional understanding of instabilities toward Landau order based on nesting. We investigate the existence of an intrinsic nesting structure encoded in the band geometry […]


Continue.. Identifying Instabilities with Quantum Geometry in Flat Band Systems

Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions

Kavli Affiliate: Yi Zhou | First 5 Authors: Ting-Hsuan Liao, Yi Zhou, Yu Shen, Chun-Hao Paul Huang, Saayan Mitra | Summary: We explore how body shapes influence human motion synthesis, an aspect often overlooked in existing text-to-motion generation methods due to the ease of learning a homogenized, canonical body shape. However, this homogenization can distort […]


Continue.. Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions

HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration

Kavli Affiliate: Zheng Zhu | First 5 Authors: Boyuan Wang, Runqi Ouyang, Xiaofeng Wang, Zheng Zhu, Guosheng Zhao | Summary: Single-image human reconstruction is vital for digital human modeling applications but remains an extremely challenging task. Current approaches rely on generative models to synthesize multi-view images for subsequent 3D reconstruction and animation. However, directly generating […]


Continue.. HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration

WonderTurbo: Generating Interactive 3D World in 0.72 Seconds

Kavli Affiliate: Zheng Zhu | First 5 Authors: Chaojun Ni, Xiaofeng Wang, Zheng Zhu, Weijie Wang, Haoyun Li | Summary: Interactive 3D generation is gaining momentum and capturing extensive attention for its potential to create immersive virtual experiences. However, a critical challenge in current 3D generation technologies lies in achieving real-time interactivity. To address this […]


Continue.. WonderTurbo: Generating Interactive 3D World in 0.72 Seconds

HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation

Kavli Affiliate: Zheng Zhu | First 5 Authors: Boyuan Wang, Xiaofeng Wang, Chaojun Ni, Guosheng Zhao, Zhiqin Yang | Summary: Human-motion video generation has been a challenging task, primarily due to the difficulty inherent in learning human body movements. While some approaches have attempted to drive human-centric video generation explicitly through pose control, these methods […]


Continue.. HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation

MAER-Nav: Bidirectional Motion Learning Through Mirror-Augmented Experience Replay for Robot Navigation

Kavli Affiliate: Biao Huang | First 5 Authors: Shanze Wang, Mingao Tan, Zhibo Yang, Biao Huang, Xiaoyu Shen | Summary: Deep Reinforcement Learning (DRL) based navigation methods have demonstrated promising results for mobile robots, but suffer from limited action flexibility in confined spaces. Conventional DRL approaches predominantly learn forward-motion policies, causing robots to become trapped […]


Continue.. MAER-Nav: Bidirectional Motion Learning Through Mirror-Augmented Experience Replay for Robot Navigation

StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion

Kavli Affiliate: Yi Zhou | First 5 Authors: , , , , | Summary: In the field of sketch generation, raster-format trained models often produce non-stroke artifacts, while vector-format trained models typically lack a holistic understanding of sketches, leading to compromised recognizability. Moreover, existing methods struggle to extract common features from similar elements (e.g., eyes […]


Continue.. StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion

StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion

Kavli Affiliate: Yi Zhou | First 5 Authors: Jin Zhou, Yi Zhou, Pengfei Xu, Hui Huang, | Summary: In the field of sketch generation, raster-format trained models often produce non-stroke artifacts, while vector-format trained models typically lack a holistic understanding of sketches, leading to compromised recognizability. Moreover, existing methods struggle to extract common features from […]


Continue.. StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusion

Giant Graviton Correlators as Defect Systems

Kavli Affiliate: Xinan Zhou | First 5 Authors: Junding Chen, Yunfeng Jiang, Xinan Zhou, , | Summary: We consider correlation functions of two maximal giant gravitons and two light $frac{1}{2}$-BPS operators in 4d $mathcal{N}=4$ SYM. Viewed as two-point correlators in the presence of a zero dimensional defect, they can be completely fixed at strong coupling […]


Continue.. Giant Graviton Correlators as Defect Systems

Emergent Hidden Multipolar State in the Triangular Lattice Magnet TmZn2GaO5

Kavli Affiliate: Leon Balents | First 5 Authors: Matthew Ennis, Rabindranath Bag, Tessa Cookmeyer, Matthew B. Stone, Alexander I. Kolesnikov | Summary: TmZn2GaO5 is a newly synthesized triangular lattice magnet that exhibits a unique quantum phase characterized by strong Ising anisotropy, a pseudo-doublet crystal electric field ground state, and a low-energy gapped excitation at the […]


Continue.. Emergent Hidden Multipolar State in the Triangular Lattice Magnet TmZn2GaO5