8 accepted papers
Despite the remarkable progress of 3D generation, achieving controllability, i.e., ensuring consistency between generated 3D content and input conditions like edge and depth, remains a significant challenge. Existing methods often struggle to maintain accurate alignment, leading to noticeable discre
Generative Reward Models (GRMs) have demonstrated strong performance in reward modeling, due to their interpretability and potential for refinement through reinforcement learning (RL). However, widely used pairwise GRMs create a computational bottleneck in reinforcement learning from human feedback …
Outlier rejection for correspondence-based point cloud registration confronts two fundamental challenges in real-world scenarios. First, low-overlap regions yield sparse and fragmented inlier distributions that are difficult to discover using conventional one-step global search strategies. Second, l
Robotic visual segmentation is essential for enabling robots to operate in complex environments. Although supervised methods have achieved remarkable progress, their dependence on dense annotations hinders scalability. Weakly supervised semantic segmentation (WSSS) alleviates this issue but suffers …
Mixture-of-Experts (MoE) models achieve a favorable trade-off between performance and inference efficiency by activating only a subset of experts. However, the memory overhead of storing all experts remains a major limitation, especially in large-scale MoE models such as DeepSeek-R1 (671B). In this…
Unsupervised anomaly detection is a critical task in many high-social-impact applications such as finance, healthcare, social media, and cybersecurity, where demographics involving age, gender, race, disease, etc. are used frequently. In these scenarios, possible bias from anomaly detection systems…
Anomaly detection methods typically require fully observed data for model training and inference and cannot handle incomplete data, while the missing data problem is pervasive in science and engineering, leading to challenges in many important applications such as abnormal user detection in recommen…
Optical flow sensors and optical flow divergence (OFD) have offered partial solutions for obstacle avoidance, landing, and perching with micro aerial vehicles. Theoretically, OFD can indicate the risk of collision, providing that the sensors' field of view is bounded within a single flat surface on