PPaperPicks

Haifeng Sun

Beijing University of Posts and Telecommunications, State Key Laboratory of Networking and Switching Technology, Beijing, China

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

Venues

Frequent coauthors

Papers

  1. Balancing Flow and Collaboration: Exploring Visual Noise Cancellation in Mixed Reality Workspace
  2. Bridging the Tokenizer Gap: Semantics and Distribution-aware Knowledge Transfer for Unbiased Cross-Tokenizer Distillation
  3. DIVER: A Robust Text-to-SQL System with Dynamic Interactive Value Linking and Evidence Reasoning
  4. DiffNBR: Spatio-Temporal Diffusion with Information Bottleneck for Next-Basket Recommendation
  5. Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
  6. Example Quality Matters: Multi-Aspects Example Augmentation for Private Library Programming
  7. InkFlow: Connected Handwriting Recognition for Natural Mid-Air Input in Mixed Reality
  8. ModularMoE: Fast LLM Customization with Parameter-Sharing Mixture-of-Experts for Low-Resource Settings
  9. VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels
  10. A Dual-Branch 3D Spatial-Aware Latent Diffusion for Realistic Depth Image Synthesis
  11. A³-Net: Calibration-Free Multi-View 3D Hand Reconstruction for Enhanced Musical Instrument Learning
  12. Beyond Statistical Analysis: Multimodal Framework for Time Series Forecasting with LLM-Driven Temporal Pattern
  13. ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
  14. ClusterAttn: KV Cache Compression under Intrinsic Attention Clustering
  15. Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns
  16. Efficient Inter-Operator Scheduling for Concurrent Recommendation Model Inference on GPU
  17. Evaluating and Mitigating Object Hallucination in Large Vision-Language Models: Can They Still See Removed Objects?
  18. Foresail: LLM Sensor Knowledge Empowered Status-guided Network for Multivariate Time-series Classification
  19. Generalizable Hand-Object Modeling from Monocular RGB Images via 3D Gaussians
  20. Pose-Guided Temporal Enhancement for Robust Low-Resolution Hand Reconstruction
  21. Prior-Aware Dynamic Temporal Modeling Framework for Sequential 3D Hand Pose Estimation
  22. Rethinking Smoothness for Fast and Adaptable Entity Alignment Decoding
  23. Robustness Verification of Deep Graph Neural Networks Tightened by Linear Approximation
  24. Rule Meets Learning: Confidence-Aware Multi-View Fusion for Self-Supervised 3D Hand Pose Estimation
  25. The Threat of PROMPTS in Large Language Models: A System and User Prompt Perspective
  26. Towards Bare-Hand Interaction for Whiteboard Collaboration in Virtual Reality
  27. Unified 2D-3D Discrete Priors for Noise-Robust and Calibration-Free Multiview 3D Human Pose Estimation
  28. Unveiling Internal Reasoning Modes in LLMs: A Deep Dive into Latent Reasoning vs. Factual Shortcuts with Attribute Rate Ratio
  29. Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image
  30. Dynamic Support Information Mining for Category-Agnostic Pose Estimation
  31. FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models
  32. HPipe: Large Language Model Pipeline Parallelism for Long Context on Heterogeneous Cost-effective Devices
  33. Interdependency Matters: Graph Alignment for Multivariate Time Series Anomaly Detection
  34. Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation
  35. MDR: Model-Specific Demonstration Retrieval at Inference Time for In-Context Learning
  36. Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning
  37. Pre-Tokenization of Numbers for Large Language Models
  38. Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective
  39. SSS: Editing Factual Knowledge in Language Models towards Semantic Sparse Space
  40. Safeguarding Sustainable Cities: Unsupervised Video Anomaly Detection through Diffusion-based Latent Pattern Learning
  41. Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment
  42. Video Anomaly Detection via Progressive Learning of Multiple Proxy Tasks