PPaperPicks

Guiguang Ding

Tsinghua University, Beijing, China

38 papers at tracked venues · 22 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object Detection
  2. Tracking and Segmenting Anything in Any Modality
  3. AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
  4. Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations
  5. Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection
  6. CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts
  7. DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs
  8. DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup
  9. DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
  10. Exploiting Position Information in Convolutional Kernels for Structural Re-parameterization
  11. Extending LLM Context Window with Adaptive Grouped Positional Encoding: A Training-Free Method
  12. Fast Quiet-STaR: Thinking Without Thought Tokens
  13. FastVID: Dynamic Density Pruning for Fast Video Large Language Models
  14. HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator
  15. LSNet: See Large, Focus Small
  16. Mitigating Hallucinations in Multi-modal Large Language Models via Image Token Attention-Guided Decoding
  17. PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
  18. Promptable Anomaly Segmentation with SAM Through Self-Perception Tuning
  19. Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal
  20. TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
  21. Temporal Scaling Law for Large Language Models
  22. YOLOE: Real-Time Seeing Anythi
  23. Context Enhancement with Reconstruction as Sequence for Unified Unsupervised Anomaly Detection
  24. Debiased Novel Category Discovering and Localization
  25. Geometry-Guided Domain Generalization for Monocular 3D Object Detection
  26. JDRec: Practical Actor-Critic Framework for Online Combinatorial Recommender System
  27. Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence
  28. MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models
  29. More is Better: Deep Domain Adaptation with Multiple Sources
  30. Multi-Label Learning with Block Diagonal Labels
  31. One-dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applications
  32. PYRA: Parallel Yielding Re-activation for Training-Inference Efficient Task Adaptation
  33. Quantized Prompt for Efficient Generalization of Vision-Language Models
  34. Rep ViT: Revisiting Mobile CNN From ViT Perspective
  35. Revisiting motion information for RGB-Event tracking with MOT philosophy
  36. TaD: A Plug-and-Play Task-Aware Decoding Method to Better Adapt LLMs on Downstream Tasks
  37. VCP-CLIP: A Visual Context Prompting Model for Zero-Shot Anomaly Segmentation
  38. YOLOv10: Real-Time End-to-End Object Detection