PPaperPicks

Lidan Shou

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

Venues

Frequent coauthors

Papers

  1. ChronosBI: Supercharging LLM-Powered Business Intelligence Pipelines with Semantic Caching and Cost Planning
  2. Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
  3. HybridKV: Hybrid KV Cache Compression for Efficient Multimodal Large Language Model Inference
  4. MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models
  5. REDPARROT: Accelerating NL-to-DSL for Business Analytics via Query Semantic Caching
  6. SVFusion: A CPU-GPU Co-Processing Architecture for Large-Scale Real-Time Vector Search
  7. See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs
  8. TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs
  9. A Comprehensive Study of Shapley Value in Data Analytics
  10. CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation
  11. FloE: On-the-Fly MoE Inference on Memory-constrained GPU
  12. HyperMR: Efficient Hypergraph-enhanced Matrix Storage on Compute-in-Memory Architecture
  13. SafeLoad: Efficient Admission Control Framework for Identifying Memory-Overloading Queries in Cloud Data Warehouses
  14. SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning
  15. TableCopilot: A Table Assistant Empowered by Natural Language Conditional Table Discovery
  16. Towards Automatic and Efficient Prediction Query Processing in Analytical Database
  17. Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
  18. Transfer-Aware Data Selection for Domain Adaptation in Text Retrieval
  19. T²DR: A Two-Tier Deficiency-Resistant Framework for Incomplete Multimodal Learning
  20. nlcTables: A Dataset for Marrying Natural Language Conditions with Table Discovery
  21. BoKA: Bayesian Optimization based Knowledge Amalgamation for Multi-unknown-domain Text Classification
  22. BushStore: Efficient B+Tree Group Indexing for LSM-Tree in Non-Volatile Memory
  23. CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition
  24. CoMAL: Contrastive Active Learning for Multi-Label Text Classification
  25. Draft& Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
  26. MCF-KV: Multi-Cuckoo-Filter Index based Key-Value Store with Persistent Memory
  27. Preventing the Popular Item Embedding Based Attack in Federated Recommendations
  28. Variational Hybrid-Attention Framework for Multi-Label Few-Shot Aspect Category Detection