PPaperPicks

Fei Chao

Xiamen University, Cognitive Science Department, School of Information Science and Engineering, China

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

Venues

Frequent coauthors

Papers

  1. Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation
  2. Automated Fine-Grained Mixture-of-Experts Quantization
  3. Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
  4. Discovering Important Experts for Mixture-of-Experts Models Pruning Through a Theoretical Perspective
  5. GS-Bias: Global-Spatial Bias Learner for Single-Image Test-Time Adaptation of Vision-Language Models
  6. Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing
  7. Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
  8. Spotlight Attention: Towards Efficient LLM Generation via Non-linear Hashing-based KV Cache Retrieval
  9. VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
  10. Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
  11. polybasic Speculative Decoding Through a Theoretical Perspective
  12. AffineQuant: Affine Transformation Quantization for Large Language Models
  13. Learning Image Demoiréing from Unpaired Real Data
  14. Multimodal Inplace Prompt Tuning for Open-set Object Detection
  15. Outlier-aware Slicing for Post-Training Quantization in Vision Transformer
  16. RepAn: Enhanced Annealing through Re-parameterization