JL
Jiajun Liu
cs.CVcs.AIcs.LGcs.ROcs.IRcs.SIcs.CLcs.MMcs.DSphysics.soc-ph
On Valency
published · living versionsW_9dvv4xmd·v1 · currentpublished
Democratizing Robot-Use Agents: A Unified Harness with Open Models
with Jiarui Yuan, Yuxin Zuo, Xiaoyu Huang, Wenbo Zhang +23
1 version
Preprints & journals
51 papers in the corpus · 2013–2026NavHarness: Towards Lifelong Embodied Navigation2609.34276v1 · Xunyi Zhao, Jian Zhou, Sihao Lin et al.2026 · 0 citationsarXiv
Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents2609.29892v1 · Tingyu Qu, Weigao Sun, Yuecheng Liu et al.2026 · 0 citationsarXiv
Understanding the Effects of Projectors in Knowledge Distillation.41875002 · Chen, Yudong, Wang, Sen, Liu, Jiajun et al.2026 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(8):9078-9092
Embodied Agents Take Control: Minimal-Interface Zero-Shot Agents Rival Industrial-Scale Policies in Vision-and-Language Navigation2607.26148v4 · Jian Zhou, Xunyi Zhao, Gengze Zhou et al.2026 · 0 citationsarXiv
TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models2606.03127v1 · Wenbo Zhang, Jianxiong Li, Shuai Yang et al.2026 · 0 citationsarXiv
Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation2606.03175v2 · Xunyi Zhao, Sihao Lin, Gengze Zhou et al.2026 · 0 citationsarXiv
ReCoVR: Closing the Loop in Interactive Composed Video Retrieval2605.09836v2 · Bingqing Zhang, Yi Zhang, Zhuo Cao et al.2026 · 0 citationsarXiv
Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts2604.20851v1 · Bingqing Zhang, Zhuo Cao, Heming Du et al.2026 · 0 citationsarXiv
VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation2512.19021v1 · Sihao Lin, Zerui Li, Xunyi Zhao et al.2025 · 0 citationsarXiv
Estimating Pasture Biomass from Top-View Images: A Dataset for Precision Agriculture2510.22916v1 · Qiyu Liao, Dadong Wang, Rebecca Haling et al.2025 · 0 citationsarXiv
Beyond Static LLM Policies: Imitation-Enhanced Reinforcement Learning for Recommendation2510.13229v1 · Yi Zhang, Lili Xie, Ruihong Qiu et al.2025 · 0 citationsarXiv
MARCO: A Cooperative Knowledge Transfer Framework for Personalized Cross-domain Recommendations2510.04508v1 · Lili Xie, Yi Zhang, Ruihong Qiu et al.2025 · 0 citationsarXiv
Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning2509.20077v1 · Xun Li, Rodrigo Santa Cruz, Mingze Xi et al.2025 · 2 citationsMM '25: Proceedings of the 33rd ACM International Conference on Multimedia (2025) Pages 12492 - 12500
On-the-Fly Object-aware Representative Point Selection in Point Cloud2508.01980v1 · Xiaoyu Zhang, Ziwei Wang, Hai Dong et al.2025 · 0 citationsarXiv
Querying Autonomous Vehicle Point Clouds: Enhanced by 3D Object Counting with CounterNet2507.19209v2 · Xiaoyu Zhang, Zhifeng Bao, Hai Dong et al.2025 · 0 citationsarXiv
Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization2507.15504v2 · Bingqing Zhang, Zhuo Cao, Heming Du et al.2025 · 3 citationsarXiv
Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation2506.09990v2 · Wenbo Zhang, Tianrun Hu, Hanbo Zhang et al.2025 · 3 citationsarXiv
RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers2505.21847v2 · Xuwei Xu, Yang Li, Yudong Chen et al.2025 · 0 citationsarXiv
DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward2505.07257v1 · Yi Zhang, Ruihong Qiu, Xuwei Xu et al.2025 · 3 citationsarXiv
General Scene Adaptation for Vision-and-Language Navigation2501.17403v1 · Haodong Hong, Yanyuan Qiao, Sen Wang et al.2025 · 0 citationsarXiv
Effective Tuning Strategies for Generalist Robot Manipulation Policies2410.01220v1 · Wenbo Zhang, Yang Li, Yanyuan Qiao et al.2024 · 2 citationsarXiv
TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm2409.19865v1 · Bingqing Zhang, Zhuo Cao, Heming Du et al.2024 · 1 citationarXiv
Navigating Beyond Instructions: Vision-and-Language Navigation in Obstructed Environments2407.21452v1 · Haodong Hong, Sen Wang, Zi Huang et al.2024 · 6 citationsarXiv
ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems2407.13163v2 · Yi Zhang, Ruihong Qiu, Jiajun Liu et al.2024 · 9 citationsarXiv
Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts2406.02208v1 · Haodong Hong, Sen Wang, Zi Huang et al.2024 · 5 citationsarXiv
GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation2311.03035v2 · Xuwei Xu, Sen Wang, Yudong Chen et al.2023 · 18 citationsarXiv
Plug n' Play: Channel Shuffle Module for Enhancing Tiny Vision Transformers2310.05642v1 · Xuwei Xu, Sen Wang, Yudong Chen et al.2023 · 0 citationsarXiv
No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling2310.05654v2 · Xuwei Xu, Changlin Li, Yudong Chen et al.2023 · 7 citationsarXiv
Real-time Multi-modal Object Detection and Tracking on Edge for Regulatory Compliance Monitoring2310.03333v2 · Jia Syuen Lim, Ziwei Wang, Jiajun Liu et al.2023 · 2 citationsIJCAI (2024) 8725-8728
Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detection2308.11327v1 · Bingqing Zhang, Sen Wang, Yifan Liu et al.2023 · 3 citationsarXiv
OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision2308.10146v1 · Shujie Zhang, Tianyue Zheng, Zhe Chen et al.2023 · 13 citationsarXiv
Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation2308.01045v2 · Quan Tang, Bowen Zhang, Jiajun Liu et al.2023 · 51 citationsarXiv
Decoupled Graph Neural Networks for Large Dynamic Graphs2305.08273v1 · Yanping Zheng, Zhewei Wei, Jiajun Liu2023 · 20 citationsarXiv
Point-Syn2Real: Semi-Supervised Synthetic-to-Real Cross-Domain Learning for Object Classification in 3D Point Clouds2210.17009v1 · Ziwei Wang, Reza Arablouei, Jiajun Liu et al.2022 · 1 citationarXiv
InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee2208.06962v1 · Yaxian Li, Bingqing Zhang, Guoping Zhao et al.2022 · 1 citationarXiv
STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval2208.06966v1 · Guoping Zhao, Bingqing Zhang, Mingyu Zhang et al.2022 · 2 citationsarXiv
A Real-time Edge-AI System for Reef Surveys2208.00598v1 · Yang Li, Jiajun Liu, Brano Kusy et al.2022 · 12 citationsarXiv
Multimodal sensor data fusion for in-situ classification of animal behavior using accelerometry and GNSS data2206.12078v2 · Reza Arablouei, Ziwei Wang, Greg J. Bishop-Hurley et al.2022 · 54 citationsarXiv
Instant Graph Neural Networks for Dynamic Graphs2206.01379v1 · Yanping Zheng, Hanzhi Wang, Zhewei Wei et al.2022 · 22 citationsarXiv
The CSIRO Crown-of-Thorn Starfish Detection Dataset2111.14311v1 · Jiajun Liu, Brano Kusy, Ross Marchant et al.2021 · 12 citationsarXiv
A novel policy for pre-trained Deep Reinforcement Learning for Speech Emotion Recognition2101.00738v2 · Thejan Rajapakshe, Rajib Rana, Sara Khalifa et al.2021 · 14 citationsarXiv
Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN1907.05793v1 · Guoping Zhao, Mingyu Zhang, Jiajun Liu et al.2019 · 24 citationsarXiv
RUM: network Representation learning throUgh Multi-level structural information preservation1710.02836v1 · Yanlei Yu, Zhiwu Lu, Jiajun Liu et al.2017 · 1 citationarXiv
Learning in High-Dimensional Multimedia Data: The State of the Art1707.02683v1 · Lianli Gao, Jingkuan Song, Xingyi Liu et al.2017 · 128 citationsarXiv
A Novel Framework for Online Amnesic Trajectory Compression in Resource-constrained Environments1605.02337v1 · Jiajun Liu, Kun Zhao, Philipp Sommer et al.2016 · 62 citationsarXiv
Understanding Human Mobility from Twitter.26154597 · Jurdak, Raja, Zhao, Kun, Liu, Jiajun et al.2016 · 558 citationsPloS one. 2015;10(7):e0131469
Optimal Lévy-flight foraging in a finite landscape.25631566 · Zhao, Kun, Jurdak, Raja, Liu, Jiajun et al.2015 · 44 citationsJournal of the Royal Society, Interface. 2015;12(104):20141158
Temporal Embedding in Convolutional Neural Networks for Robust Learning of Abstract Snippets1502.05113v1 · Jiajun Liu, Kun Zhao, Brano Kusy et al.2015 · 6 citationsarXiv
Bounded Quadrant System: Error-bounded Trajectory Compression on the Go1412.0321v2 · Jiajun Liu, Kun Zhao, Philipp Sommer et al.2014 · 81 citationsarXiv
Multi-scale Population and Mobility Estimation with Geo-tagged Tweets1412.0327v1 · Jiajun Liu, Kun Zhao, Saeed Khan et al.2014 · 28 citationsarXiv
Career total: 116 works. 51 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.