1 citations · 2 across the 10 of their papers we have counts for
10 papers
DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation
Yu Fang, Wanxi Dong, Jiaqi Liu +7
Reinforcement learning holds great promise for improving robot policies beyond the limits of imitation learning. However, its practical adoption remains bottlenecked by the lack of…
VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
Yixiao Wang, Mingxiao Huo, Zhixuan Liang +8
Pretrained vision foundation models (VFMs) advance robotic learning via rich visual representations, yet individual VFMs typically excel only in specific domains, limiting generali…
Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding
Mingxiao Huo, Jiayi Zhang, Hewei Wang +4
Vision-Language Models (VLMs) enable powerful multimodal reasoning but suffer from slow autoregressive inference, limiting their deployment in real-time applications. We introduce…
Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors
Wen-Hsuan Chu, Lei Ke, Jianmeng Liu +3
We tackle the challenge of generating dynamic 4D scenes from monocular, multi-object videos with heavy occlusions, and introduce GenMOJO, a novel approach that integrates rendering…
Multi-Cali Anything: Dense Feature Multi-Frame Structure-from-Motion for Large-Scale Camera Array Calibration
Jinjiang You, Hewei Wang, Yijie Li +8
Calibrating large-scale camera arrays, such as those in dome-based setups, is time-intensive and typically requires dedicated captures of known patterns. While extrinsics in such a…
Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning
Yixiao Wang, Yifei Zhang, Mingxiao Huo +8
The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all ta…
Composition Vision-Language Understanding via Segment and Depth Anything Model
Mingxiao Huo, Pengliang Ji, Haotian Lin +3
We introduce a pioneering unified library that leverages depth anything, segment anything models to augment neural comprehension in language-vision model zero-shot understanding. T…
Joint Pedestrian Trajectory Prediction through Posterior Sampling
Haotian Lin, Yixiao Wang, Mingxiao Huo +3
Joint pedestrian trajectory prediction has long grappled with the inherent unpredictability of human behaviors. Recent investigations employing variants of conditional diffusion mo…
Human-oriented Representation Learning for Robotic Manipulation
Mingxiao Huo, Mingyu Ding, Chenfeng Xu +6
Humans inherently possess generalizable visual representations that empower them to efficiently explore and interact with the environments in manipulation tasks. We advocate that s…
AbHE: All Attention-based Homography Estimation
Mingxiao Huo, Zhihao Zhang, Xinyang Ren +1
Homography estimation is a basic computer vision task, which aims to obtain the transformation from multi-view images for image alignment. Unsupervised learning homography estimati…