4 citations · 6 across the 23 of their papers we have counts for
28 papers
One-shot Human Video-Guided Adaptation for Vision-Language-Action Models
Qi Chen, Yuwei Wu, Quan Chen +5
Vision-language-action (VLA) models have recently achieved remarkable progress by leveraging large-scale robot datasets and foundation models for general-purpose robot manipulation…
Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents
Bingzhen Liu, Xiaomeng Fan, Yuwei Wu +4
Self-evolving methods improve the capabilities of LLM agents by sampling trajectories from the underlying LLMs and learning from these trajectories. However, these methods struggle…
Facial Expression Generation Aligned with Human Preference for Natural Dyadic Interaction
Xu Chen, Rui Gao, Xinjie Zhang +5
Achieving natural dyadic interaction requires generating facial expressions that are emotionally appropriate and socially aligned with human preference. Human feedback offers a com…
Morphology-Independent Facial Expression Imitation for Human-Face Robots
Xu Chen, Rui Gao, Che Sun +4
Accurate facial expression imitation on human-face robots is crucial for achieving natural human-robot interaction. Most existing methods have achieved photorealistic expression im…
Fine-Grained 3D Facial Reconstruction for Micro-Expressions
Che Sun, Xinjie Zhang, Rui Gao +3
Recent advances in 3D facial expression reconstruction have demonstrated remarkable performance in capturing macro-expressions, yet the reconstruction of micro-expressions remains…
Bridging Modality Disconnect in Self-Reflection via Closed-Loop Visually Grounded Verification
Haoyu Zhang, Yuwei Wu, Pengxiang Li +6
In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs,…
Rethinking the Encoding and Annotating of 3D Bounding Box: Corner-Aware 3D Object Detection from Point Clouds
Qinghao Meng, Junbo Yin, Jianbing Shen +1
Center-aligned regression remains dominant in LiDAR-based 3D object detection, yet it suffers from fundamental instability: object centers often fall in sparse or empty regions of…
Composition-Incremental Learning for Compositional Generalization
Zhen Li, Yuwei Wu, Chenchen Jing +3
Compositional generalization has achieved substantial progress in computer vision on pre-collected training data. Nonetheless, real-world data continually emerges, with possible co…
Multi-Step Reasoning for Embodied Question Answering via Tool Augmentation
Mingliang Zhai, Hansheng Liang, Xiaomeng Fan +6
Embodied Question Answering (EQA) requires agents to explore 3D environments to obtain observations and answer questions related to the scene. Existing methods leverage VLMs to dir…
Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
Xiaomeng Fan, Yuchuan Mao, Zhi Gao +3
Open-vocabulary learning requires modeling the data distribution in open environments, which consists of both seen-class and unseen-class data. Existing methods estimate the distri…
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
Pengxiang Li, Zechen Hu, Zirui Shang +15
Vision-language model (VLM) based GUI agents show promise for automating complex desktop and mobile tasks, but face significant challenges in applying reinforcement learning (RL):…
Adaptive Model Ensemble for Continual Learning
Yuchuan Mao, Zhi Gao, Xiaomeng Fan +3
Model ensemble is an effective strategy in continual learning, which alleviates catastrophic forgetting by interpolating model parameters, achieving knowledge fusion learned from d…
Long-Horizon Visual Imitation Learning via Plan and Code Reflection
Quan Chen, Chenrui Shi, Qi Chen +6
Learning from long-horizon demonstrations with complex action sequences presents significant challenges for visual imitation learning, particularly in understanding temporal relati…
Curvature Learning for Generalization of Hyperbolic Neural Networks
Xiaomeng Fan, Yuwei Wu, Zhi Gao +2
Hyperbolic neural networks (HNNs) have demonstrated notable efficacy in representing real-world data with hierarchical structures via exploiting the geometric properties of hyperbo…
LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images
Guichen Huang, Ruoyu Wang, Xiangjun Gao +4
3D Gaussian Splatting achieves high-fidelity novel view synthesis, but its application to online long-sequence scenarios is still limited. Existing methods either rely on slow per-…
Hyperbolic Dual Feature Augmentation for Open-Environment
Peilin Yu, Yuwei Wu, Zhi Gao +3
Feature augmentation generates novel samples in the feature space, providing an effective way to enhance the generalization ability of learning algorithms with hyperbolic geometry.…
Sekai: A Video Dataset towards World Exploration
Zhen Li, Chuanhao Li, Xiaofeng Mao +17
Video generation techniques have made remarkable progress, promising to be the foundation of interactive world exploration. However, existing video generation datasets are not well…
Multi-Label Stereo Matching for Transparent Scene Depth Estimation
Zhidan Liu, Chengtang Yao, Jiaxi Zeng +2
In this paper, we present a multi-label stereo matching method to simultaneously estimate the depth of the transparent objects and the occluded background in transparent scenes.Unl…
Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs
Xintong Zhang, Zhi Gao, Bofei Zhang +8
Vision language models (VLMs) have achieved impressive performance across a variety of computer vision tasks. However, the multimodal reasoning capability has not been fully explor…
Diving into the Fusion of Monocular Priors for Generalized Stereo Matching
Chengtang Yao, Lidong Yu, Zhidan Liu +3
The matching formulation makes it naturally hard for the stereo matching to handle ill-posed regions like occlusions and non-Lambertian surfaces. Fusing monocular priors has been p…
Memory-Centric Embodied Question Answering
Mingliang Zhai, Zhi Gao, Yuwei Wu +1
Embodied Question Answering (EQA) requires agents to autonomously explore and comprehend the environment to answer context-dependent questions. Typically, an EQA framework consists…
3D Visual Illusion Depth Estimation
Chengtang Yao, Zhidan Liu, Jiaxi Zeng +3
3D visual illusion is a perceptual phenomenon where a two-dimensional plane is manipulated to simulate three-dimensional spatial relationships, making a flat artwork or object look…
Large-Scale Riemannian Meta-Optimization via Subspace Adaptation
Peilin Yu, Yuwei Wu, Zhi Gao +2
Riemannian meta-optimization provides a promising approach to solving non-linear constrained optimization problems, which trains neural networks as optimizers to perform optimizati…
World knowledge-enhanced Reasoning Using Instruction-guided Interactor in Autonomous Driving
Mingliang Zhai, Cheng Li, Zengyuan Guo +7
The Multi-modal Large Language Models (MLLMs) with extensive world knowledge have revitalized autonomous driving, particularly in reasoning tasks within perceivable regions. Howeve…