Junliang Xing

12

Papers

29

Total Citations

Papers (12)

Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Advancing Video Synchronization with Fractional Frame Analysis: Introducing a Novel Dataset and Model

StickMotion: Generating 3D Human Motions by Drawing a Stickman

Position-Aware Guided Point Cloud Completion with CLIP Model

DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving

SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement

Reflective Policy Optimization

Dynamic Dictionary Learning for Remote Sensing Image Segmentation

Entropy-Adaptive Diffusion Policy Optimization with Dynamic Step Alignment

Multi-View 3D Human Pose Estimation with Weakly Synchronized Images

An Open-Ended Learning Framework for Opponent Modeling