9 papers · 1 filter
AnaDiffusion: Anatomically Compositional Latent Diffusion for Controllable 3D Brain MRI Generation
Huiwen Han, Lulin Liu, Bangya Liu +8
3D brain MRI generation has made significant advances in medical imaging, simulation, and controllable anatomical analysis. However, existing generative models typically synthesize…
OpenLongTail: Generative Scaling of Long-Tail Driving Data
Lulin Liu, Nuo Chen, Yan Wang +15
Scaling robust driving policies is fundamentally bottlenecked by the scarcity of edge cases in curated datasets. While the real world continuously captures these critical events, s…
SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning
Jian Zhang, Shijie Zhou, Bangya Liu +2
Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their ina…
VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
Xiangbo Gao, Sicong Jiang, Bangya Liu +12
As AI-assisted video creation becomes increasingly practical, instruction-guided video editing has become essential for refining generated or captured footage to meet professional…
Accelerating Transformer-Based Monocular SLAM via Geometric Utility Scoring
Xinmiao Xiong, Bangya Liu, Hao Wang +7
Geometric Foundation Models (GFMs) have recently advanced monocular SLAM by providing robust, calibration-free 3D priors. However, deploying these models on dense video streams int…
Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis
Dayou Li, Lulin Liu, Bangya Liu +6
To serve as a scalable data source for embodied AI, world models should act as true simulators that infer interaction dynamics strictly from user actions, rather than mere conditio…
MV-S2V: Multi-View Subject-Consistent Video Generation
Ziyang Song, Xinyu Gong, Bangya Liu +1
Existing Subject-to-Video Generation (S2V) methods have achieved high-fidelity and subject-consistent video generation, yet remain constrained to single-view subject references. Th…
CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization
Zelin Zhao, Xinyu Gong, Bangya Liu +5
Achieving precise camera control in video generation remains challenging, as existing methods often rely on camera pose annotations that are difficult to scale to large and dynamic…
ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learning
Bangya Liu, Xinyu Gong, Zelin Zhao +6
Human-object interaction (HOI) video generation has garnered increasing attention due to its promising applications in digital humans, e-commerce, advertising, and robotics imitati…