PPaperPicks

Ping Wang

Wuhan University, School of Information Management, Centre for Studies of Information Resources, Hubei, China

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

Venues

Frequent coauthors

Papers

  1. BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores
  2. End-to-End Contrastive Language-Speech Pretraining Model for Long-Form Spoken Question Answering
  3. Faster MoE LLM Inference for Extremely Large Models
  4. RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding
  5. TRACE: Traversal Retrieval-Augmented Chain of Evidence for Document Understanding
  6. Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models
  7. Can Large Language Models Be Good Language Teachers?
  8. Dialogue-RAG: Enhancing Retrieval for LLMs via Node-Linking Utterance Rewriting
  9. Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding
  10. Label Drop for Multi-Aspect Relation Modeling in Universal Information Extraction
  11. NOTA: Multimodal Music Notation Understanding for Visual Large Language Model
  12. SongSong: A Time Phonograph for Chinese SongCi Music from Thousand of Years Away
  13. SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers
  14. Surprise Calibration for Better In-Context Learning
  15. What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning
  16. A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction
  17. A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis
  18. Hypergraph based Understanding for Document Semantic Entity Recognition
  19. Multi-Modal Latent Space Learning for Chain-of-Thought Reasoning in Language Models
  20. Multi-modal Auto-regressive Modeling via Visual Tokens
  21. N-gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understanding
  22. Selective Prefix Tuning for Pre-trained Language Models
  23. The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models
  24. VHASR: A Multimodal Speech Recognition System With Vision Hotwords