12 citations · 31 across the 22 of their papers we have counts for
24 papers
Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models
Zhenghao Zhao, Gaowen Liu, Zhiling Lan +1
Data selection is already a central bottleneck in large-language-model training, where web-scale corpora are noisy and token budgets are finite. In continual pre-training (CPT), it…
Real-Time Robot Execution with Masked Action Chunking
Haoxuan Wang, Gengyu Zhang, Yan Yan +3
Real-time execution is essential for cyber-physical systems such as robots. These systems operate in dynamic real-world environments where even small delays can undermine responsiv…
Motion Marionette: Rethinking Rigid Motion Transfer via Prior Guidance
Haoxuan Wang, Jiachen Tao, Junyi Wu +3
We present Motion Marionette, a zero-shot framework for rigid motion transfer from monocular source videos to single-view target images. Previous works typically employ geometric,…
Efficient Multimodal Dataset Distillation via Generative Models
Zhenghao Zhao, Haoxuan Wang, Junyi Wu +3
Dataset distillation aims to synthesize a small dataset from a large dataset, enabling the model trained on it to perform well on the original dataset. With the blooming of large l…
GuirlVG: Incentivize GUI Visual Grounding via Empirical Exploration on Reinforcement Learning
Weitai Kang, Bin Lei, Gaowen Liu +2
Graphical user interface visual grounding (GUI-VG), a core capability for GUI agents, has primarily relied on supervised fine-tuning (SFT) of multimodal large language models (MLLM…
CaO: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation
Haoxuan Wang, Zhenghao Zhao, Junyi Wu +3
The recent introduction of diffusion models in dataset distillation has shown promising potential in creating compact surrogate datasets for large, high-resolution target datasets,…
Enhancing Dance-to-Music Generation via Negative Conditioning Latent Diffusion Model
Changchang Sun, Gaowen Liu, Charles Fleming +1
Conditional diffusion models have gained increasing attention since their impressive results for cross-modal synthesis, where the strong alignment between conditioning input and ge…
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
Changchang Sun, Ren Wang, Yihua Zhang +5
Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to…
SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding
Weitai Kang, Gaowen Liu, Mubarak Shah +1
Different from Object Detection, Visual Grounding deals with detecting a bounding box for each text-image pair. This one box for each text-image data provides sparse supervision si…
Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry
Ziheng Chen, Yue Song, Xiao-Jun Wu +2
Global Covariance Pooling (GCP) has been demonstrated to improve the performance of Deep Neural Networks (DNNs) by exploiting second-order statistics of high-level representations.…
Efficient Multitask Dense Predictor via Binarization
Yuzhang Shang, Dan Xu, Gaowen Liu +2
Multi-task learning for dense prediction has emerged as a pivotal area in computer vision, enabling simultaneous processing of diverse yet interrelated pixel-wise prediction tasks.…
Urban Scene Diffusion through Semantic Occupancy Map
Junge Zhang, Qihang Zhang, Li Zhang +3
Generating unbounded 3D scenes is crucial for large-scale scene understanding and simulation. Urban scenes, unlike natural landscapes, consist of various complex man-made objects a…
Causal-DFQ: Causality Guided Data-free Network Quantization
Yuzhang Shang, Bingxin Xu, Gaowen Liu +2
Model quantization, which aims to compress deep neural networks and accelerate inference speed, has greatly facilitated the development of cumbersome models on mobile and edge devi…
Nav: Action-Aware Zero-Shot Robot Navigation by Exploiting Vision-and-Language Ability of Foundation Models
Peihao Chen, Xinyu Sun, Hongyan Zhi +5
We study the task of zero-shot vision-and-language navigation (ZS-VLN), a practical yet challenging problem in which an agent learns to navigate following a path described by langu…
Physical-aware Cross-modal Adversarial Network for Wearable Sensor-based Human Action Recognition
Jianyuan Ni, Hao Tang, Anne H. H. Ngu +2
Wearable sensor-based Human Action Recognition (HAR) has made significant strides in recent times. However, the accuracy performance of wearable sensor-based HAR is currently still…
Riemannian Multinomial Logistics Regression for SPD Neural Networks
Ziheng Chen, Yue Song, Gaowen Liu +3
Deep neural networks for learning Symmetric Positive Definite (SPD) matrices are gaining increasing attention in machine learning. Despite the significant progress, most existing S…
Model Sparsity Can Simplify Machine Unlearning
Jinghan Jia, Jiancheng Liu, Parikshit Ram +5
In response to recent data regulation requirements, machine unlearning (MU) has emerged as a critical process to remove the influence of specific examples from a given model. Altho…
Optical Flow Estimation in 360 Videos: Dataset, Model and Application
Bin Duan, Keshav Bhandari, Gaowen Liu +1
Optical flow estimation has been a long-lasting and fundamental problem in the computer vision community. However, despite the advances of optical flow estimation in perspective vi…
Learning Omnidirectional Flow in 360-degree Video via Siamese Representation
Keshav Bhandari, Bin Duan, Gaowen Liu +3
Optical flow estimation in omnidirectional videos faces two significant issues: the lack of benchmark datasets and the challenge of adapting perspective video-based methods to acco…
Online Deep Metric Learning via Mutual Distillation
Gao-Dong Liu, Wan-Lei Zhao, Jie Zhao
Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samp…
Cross-View Exocentric to Egocentric Video Synthesis
Gaowen Liu, Hao Tang, Hugo Latapie +2
Cross-view video synthesis task seeks to generate video sequences of one view from another dramatically different view. In this paper, we investigate the exocentric (third-person)…
A Metamodel and Framework for Artificial General Intelligence From Theory to Practice
Hugo Latapie, Ozkan Kilic, Gaowen Liu +7
This paper introduces a new metamodel-based knowledge representation that significantly improves autonomous learning and adaptation. While interest in hybrid machine learning / sym…
Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network
Gaowen Liu, Hao Tang, Hugo Latapie +1
Cross-view image generation has been recently proposed to generate images of one view from another dramatically different view. In this paper, we investigate exocentric (third-pers…
Cycle In Cycle Generative Adversarial Networks for Keypoint-Guided Image Generation
Hao Tang, Dan Xu, Gaowen Liu +3
In this work, we propose a novel Cycle In Cycle Generative Adversarial Network (CGAN) for the task of keypoint-guided image generation. The proposed CGAN is a cross-modal f…