activity
20242026
collaborators

6 papers

cs.RO2026

Generalizable Dense Reward for Long-Horizon Robotic Tasks

Silong Yong, Stephen Sheng, Carl Qi +6

Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilities, they often struggle with long-hori…

cs.CV2026

pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning

Zhanpeng Luo, Ce Zhang, Silong Yong +6

Multi-modal Large Language Models (MLLMs) have demonstrated strong capabilities in general-purpose perception and reasoning, but they still struggle with tasks that require spatial…

cs.CV2025

ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models

Zifu Wan, Ce Zhang, Silong Yong +6

Recent Large Vision-Language Models (LVLMs) have introduced a new paradigm for understanding and reasoning about image input through textual responses. Although they have achieved…

cs.CV2025

OMG: Opacity Matters in Material Modeling with Gaussian Splatting

Silong Yong, Venkata Nagarjun Pudureddiyur Manivannan, Bernhard Kerbl +4

Decomposing geometry, materials and lighting from a set of images, namely inverse rendering, has been a long-standing problem in computer vision and graphics. Recent advances in ne…

cs.CV2025

Aug3D: Augmenting large scale outdoor datasets for Generalizable Novel View Synthesis

Aditya Rauniyar, Omar Alama, Silong Yong +2

Recent photorealistic Novel View Synthesis (NVS) advances have increasingly gained attention. However, these approaches remain constrained to small indoor scenes. While optimizatio…

cs.CV2024

GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration

Silong Yong, Yaqi Xie, Simon Stepputtis +1

Volume rendering in neural radiance fields is inherently time-consuming due to the large number of MLP calls on the points sampled per ray. Previous works would address this issue…