PPaperPicks

Haoyi Xiong

19 papers at tracked venues · 13 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating
  2. Probe-and-Fetch: Dynamic KV Cache Pruning for Accelerated Long-Context Inference in Web-Scale AI Search
  3. Retain to Refine: Adaptive Online Question Answering via Query Routing and Long-Short Memory
  4. FULTR: A Large-Scale Fusion Learning to Rank Dataset and Its Application for Satisfaction-Oriented Ranking
  5. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
  6. IV-mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
  7. Learning to Generate Vectorized Maps at Intersections with Multiple Roadside Cameras
  8. M2oERank: Multi-Objective Mixture-of-Experts Enhanced Ranking for Satisfaction-Oriented Web Search
  9. Multi-Agent Proactive Information Seeking with Adaptive LLM Orchestration for Non-Factoid Question Answering
  10. RankElectra: Semi-supervised Pre-training of Learning-to-Rank Electra for Web-scale Search
  11. RankExpert: A Mixture of Textual-and-Behavioral Experts for Multi-Objective Learning-to-Rank in Web Search
  12. SOLA-GCL: Subgraph-Oriented Learnable Augmentation Method for Graph Contrastive Learning
  13. Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection
  14. A Multi-Node Multi-GPU Distributed GNN Training Framework for Large-Scale Online Advertising
  15. G-LIME: Statistical Learning for Local Interpretations of Deep Neural Networks Using Global Priors (Abstract Reprint)
  16. GS2P: A Generative Pre-trained Learning to Rank Model with Over-parameterization for Web-Scale Search (Extended Abstract)
  17. Geometry-Guided Conditional Adaptation for Surrogate Models of Large-Scale 3D PDEs on Arbitrary Geometries
  18. GiLOT: Interpreting Generative Language Models via Optimal Transport
  19. MPGraf: a Modular and Pre-trained Graphformer for Learning to Rank at Web-scale (Extended Abstract)