PPaperPicks

Jie Wang

27 papers at tracked venues · 17 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Adaptive Bounded-Rationality Modeling of Early-Stage Takeover in Shared-Control Driving
  2. CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables
  3. SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue
  4. A Multi-Style Chinese Characters Writing Intelligent Tool Based on Small-scale Training Data
  5. A Structure-Aware and Motion-Adaptive Framework for 3D Human Pose Estimation with Mamba
  6. AMQuestioner: Training Critical Thinking with Question-Driven Interactive Argument Maps in Online Discussion
  7. ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting
  8. Can Class-Priors Help Single-Positive Multi-Label Learning?
  9. DVAGen: Dynamic Vocabulary Augmented Generation
  10. Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-Learning
  11. From Gaze to Movement: Predicting Visual Attention for Autonomous Driving Human-Machine Interaction based on Programmatic Imitation Learning
  12. High-Fidelity Unified One-to-Many Medical Image Synthesis via Text-Conditioned Latent Diffusion
  13. MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
  14. Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training
  15. Real-World Reinforcement Learning of Active Perception Behaviors
  16. STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem
  17. Speaker Diarization with Overlapping Community Detection Using Graph Attention Networks and Label Propagation Algorithm
  18. StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion
  19. SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning
  20. VADIS: Investigating Inter-View Representation Biases for Multi-View Partial Multi-Label Learning
    UAI 2025 · Jie Wang
  21. VENUS: A VLLM-driven Video Content Discovery System for Real Application Scenarios
  22. ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos
  23. DSTCFuse: A Method based on Dual-cycled Cross-awareness of Structure Tensor for Semantic Segmentation via Infrared and Visible Image Fusion
  24. Efficient-PIP: Large-scale Pixel-level Aligned Image Pair Generation for Cross-time Infrared-RGB Translation
  25. Revisiting Interpolation Augmentation for Speech-to-Text Generation
  26. Serving Deep Learning Models from Relational Databases
  27. Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions