PPaperPicks

Guihai Chen

Shanghai Jiao Tong University, China

41 papers at tracked venues · 35 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization
  2. Automated Annotation of Privacy Information in User Interactions with Large Language Models
  3. CMANNS: GPU-Accelerated Graph Index Construction for ANNS via Compute-Memory Disaggregation
  4. Channel-masked Asymmetric Distribution Matching for Cross-Domain Generalized Dataset Distillation
  5. CoDec: Prefix-Shared Decoding Kernel for LLMs
  6. ProCAST: A Projection Framework for Coupled Aggregation Constrained Multivariate Time Series Forecasting
  7. Prototype Augmentation-based Edge-end Heterogeneous Collaborative Learning
  8. Smaller but Better: Plasticity-Preserving Continual Learning for Embedded AI
  9. Vistar: Enhancing the Perception Capability of LLMs under Imprecise IMU-Text Alignment
  10. When Complex Event Recognition Meets Cloud-Native Architectures
  11. ABO: Abandon Bayer Filter for Adaptive Edge Offloading in Responsive Augmented Reality
  12. Adaptive Routing of Text-to-Image Generation Requests between Large Cloud Model and Light-Weight Edge Model
  13. Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data
  14. CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs
  15. CSR: Achieving 1 Bit Key-Value Cache via Sparse Representation
  16. DRNCS: Dual-Level Route Generation Model Based on Node Contraction and Shortcuts
  17. Gem: Scalable Monotonic Graph Processing Beyond Billion-Scale on a Single Machine
  18. HotPrefix: Hotness-Aware KV Cache Scheduling for Efficient Prefix Sharing in LLM Inference Systems
  19. Improving SAM for Camouflaged Object Detection via Dual Stream Adapters
  20. Personalized Language Model Learning on Text Data Without User Identifiers
  21. Pre³: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation
  22. Querier-Aware LLM: Generating Personalized Responses to the Same Query from Different Queriers
  23. RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
  24. Robust Data-Driven Auction Design
  25. Themis: Toward Stable Near-Zero Queuing Delay in Congestion Control for Low-Latency Interactive Video Streaming
  26. VEGA: An Active-tuning Learned Index with Group-Wise Learning Granularity
  27. VariGen: Controllable Image Generation Via Personalized Diffusion Framework
  28. 2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
  29. A Dual-Embedding Based DQN for Worker Recruitment in Spatial Crowdsourcing with Social Network
  30. ACER: Accelerating Complex Event Recognition via Two-Phase Filtering under Range Bitmap-Based Indexes
  31. Advancing Web 3.0: Making Smart Contracts Smarter on Blockchain
  32. BiKT: Enabling Bidirectional Knowledge Transfer Between Pretrained Models and Sequential Downstream Tasks
  33. Corruption Robust Dynamic Pricing in Liner Shipping under Capacity Constraint
  34. DISCO: A Dynamically Configurable Sketch Framework in Skewed Data Streams
  35. Enhancing On-Device LLM Inference with Historical Cloud-Based LLM Interactions
  36. GS2P: A Generative Pre-trained Learning to Rank Model with Over-parameterization for Web-Scale Search (Extended Abstract)
  37. Integrating System State into Spatio Temporal Graph Neural Network for Microservice Workload Prediction
  38. Lightweight GCN Encoder and Sequential Decoder for Multi-Candidate Carpooling Route Planning in Road Network
  39. MetaSTC: A Backbone Agnostic Spatio-Temporal Framework for Traffic Forecasting
  40. Temporal Interest Network for User Response Prediction
  41. Towards Resource Efficiency: Practical Insights into Large-Scale Spark Workloads at ByteDance