activity
20242026
collaborators

8 papers

cs.LG2026

\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating

Jianghui Wang, Silong Yong, Francesco Orabona +3

Low-Rank Adaptation (LoRA) has become a widely adopted technique for efficient neural network fine-tuning, decomposing model updates into low-rank matrices. However, LoRA remains c…

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

Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation

Zifu Wan, Pingping Zhang, Yuhao Wang +4

Multi-modal semantic segmentation significantly enhances AI agents' perception and scene understanding, especially under adverse conditions like low-light or overexposed environmen…

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…