Junliang Xing

Tsinghua University — China

Computer Science · Physical Sciences

52h-index16.8kcitations272works3.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Video Surveillance and Tracking Methods(91), Human Pose and Action Recognition(68), Face recognition and analysis(51), Anomaly Detection Techniques and Applications(33), Advanced Neural Network Applications(28)

Publications272 total

GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training
arXiv (Cornell University)·2025Open Access
Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generation
arXiv (Cornell University)·2025Open Access
Deep (Predictive) Discounted Counterfactual Regret Minimization
arXiv (Cornell University)·2025Open Access
Hierarchical Fusion of Local and Global Visual Features with Mixture-of-Experts for Remote Sensing Image Scene Classification
arXiv (Cornell University)·2025Open Access
Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation
arXiv (Cornell University)·2025Open Access
Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance
arXiv (Cornell University)·2025Open Access
Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance
arXiv (Cornell University)·2025Open Access
Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial Optimization
arXiv (Cornell University)·2025Open Access
StickMotion : Generating 3D Human Motions by Drawing a Stickman
2025· 1 cited
UBG: An Unreal BattleGround Benchmark With Object-Aware Hierarchical Proximal Policy Optimization
IEEE Transactions on Neural Networks and Learning Systems·2025Open Access
Asymmetric interaction preference induces cooperation in human-agent hybrid game
Science China Information Sciences·2025· 11 cited
Position-Aware Guided Point Cloud Completion with CLIP Model
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 1 citedOpen Access
An Open-Ended Learning Framework for Opponent Modeling
Proceedings of the AAAI Conference on Artificial Intelligence·2025Open Access
Multi-View 3D Human Pose Estimation with Weakly Synchronized Images
Proceedings of the AAAI Conference on Artificial Intelligence·2025· 1 citedOpen Access
Exploring Reliable PPG Authentication on Smartwatches in Daily Scenarios
arXiv (Cornell University)·2025Open Access
UV-Mamba: A DCN-Enhanced State Space Model for Urban Village Boundary Identification in High-Resolution Remote Sensing Images
2025· 7 cited
GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training
arXiv (Cornell University)·2025Open Access
BodyGen: Advancing Towards Efficient Embodiment Co-Design
arXiv (Cornell University)·2025Open Access
Leveraging Privileged Information for Partially Observable Reinforcement Learning
IEEE Transactions on Games·2025· 1 cited
page 1 of 14Next →

Frequent Co-authors

Cuiling Lan(12), Wenjun Zeng(12), Weiming Hu(12), Jin Gao(9), Qiang Wang(8), Shuicheng Yan(8), Mengdan Zhang(6), Jiashi Feng(6), Jiaying Liu(5), Jian Zhao(5), Yanghao Li(4), Sijie Song(4), Haizhou Ai(4), Matej Kristan(3), Jiřı́ Matas(3), Michael Felsberg(3), Roman Pflugfelder(3), Luka Čehovin Zajc(3), Gustavo J. Fernández(3), Alfredo Petrosino(3)