PPaperPicks

Zirui Zhuang

25 papers at tracked venues · 16 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning
  2. Example Quality Matters: Multi-Aspects Example Augmentation for Private Library Programming
  3. ModularMoE: Fast LLM Customization with Parameter-Sharing Mixture-of-Experts for Low-Resource Settings
  4. Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern
  5. ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
  6. ClusterAttn: KV Cache Compression under Intrinsic Attention Clustering
  7. Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns
  8. Evaluating and Mitigating Object Hallucination in Large Vision-Language Models: Can They Still See Removed Objects?
  9. Foresail: LLM Sensor Knowledge Empowered Status-guided Network for Multivariate Time-series Classification
  10. Generalizable Hand-Object Modeling from Monocular RGB Images via 3D Gaussians
  11. Pose-Guided Temporal Enhancement for Robust Low-Resolution Hand Reconstruction
  12. Robustness Verification of Deep Graph Neural Networks Tightened by Linear Approximation
  13. Towards Bare-Hand Interaction for Whiteboard Collaboration in Virtual Reality
  14. Unified 2D-3D Discrete Priors for Noise-Robust and Calibration-Free Multiview 3D Human Pose Estimation
  15. Unveiling Internal Reasoning Modes in LLMs: A Deep Dive into Latent Reasoning vs. Factual Shortcuts with Attribute Rate Ratio
  16. Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image
  17. HPipe: Large Language Model Pipeline Parallelism for Long Context on Heterogeneous Cost-effective Devices
  18. Interdependency Matters: Graph Alignment for Multivariate Time Series Anomaly Detection
  19. Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation
  20. Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning
  21. Pre-Tokenization of Numbers for Large Language Models
  22. Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective
  23. STAR-VP: Improving Long-term Viewport Prediction in 360° Videos via Space-aligned and Time-varying Fusion
  24. Safeguarding Sustainable Cities: Unsupervised Video Anomaly Detection through Diffusion-based Latent Pattern Learning
  25. Video Anomaly Detection via Progressive Learning of Multiple Proxy Tasks