3 citations · 3 across the 6 of their papers we have counts for
8 papers
IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies
Kian Hosseinkhani, Qinhe Peng, George Shramko +6
Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design couples this backbone with a dedic…
P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing
Yanshu Zhang, Shichong Peng, Mehran Aghabozorgi +2
Advances in neural rendering have enabled high-fidelity multi-view reconstruction of 3D scenes. However, free-form non-rigid shape editing remains a significant challenge. Point-ba…
WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control
Mehran Aghabozorgi, Alireza Moazeni, Yanshu Zhang +1
Model-based reinforcement learning promises strong sample efficiency but often underperforms in practice due to compounding model error, unimodal world models that average over mul…
Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering
Alireza Moazeni, Shichong Peng, Yanshu Zhang +2
Recent point-based intrinsic decomposition and inverse rendering methods have advanced the modelling of the shading and albedo of 3D scenes. However, we identify a fundamental limi…
How Good Are Deep Generative Models for Solving Inverse Problems?
Shichong Peng, Alireza Moazeni, Ke Li
Deep generative models, such as diffusion models, GANs, and IMLE, have shown impressive capability in tackling inverse problems. However, the validity of model-generated solutions…
PAPR: Proximity Attention Point Rendering
Yanshu Zhang, Shichong Peng, Alireza Moazeni +1
Learning accurate and parsimonious point cloud representations of scene surfaces from scratch remains a challenge in 3D representation learning. Existing point-based methods often…
CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis
Shichong Peng, Alireza Moazeni, Ke Li
A persistent challenge in conditional image synthesis has been to generate diverse output images from the same input image despite only one output image being observed per input im…
Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis
Shichong Peng, Alireza Moazeni, Ke Li
Deep generative models such as GANs have driven impressive advances in conditional image synthesis in recent years. A persistent challenge has been to generate diverse versions of…