PPaperPicks

Lei Liang

Ant Group, Hangzhou, China

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

Venues

Frequent coauthors

Papers

  1. C3Flow: SIMD-Style Concurrent Claude Code Workflow for Scaling Deep Research
  2. LookAhead Tuning: Safer Language Models via Partial Answer Previews
  3. Self-Correction Distillation for Structured Data Question Answering
  4. Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
  5. UniHR: Hierarchical Representation Learning for Unified Knowledge Graph Link Prediction
  6. Client-Server Co-design with Multi-modal Codebooks Makes Better and Faster Federate Knowledge Sharing
  7. Croppable Knowledge Graph Embedding
  8. EventRAG: Enhancing LLM Generation with Event Knowledge Graphs
  9. Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking
  10. HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts
  11. High Performance or Low Memory? An Updatable Learned Index Framework for Time-Space Tradeoff
  12. KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation
    WWW 2025 · Lei Liang
  13. KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
  14. MultiRAG: A Knowledge-Guided Framework for Mitigating Hallucination in Multi-Source Retrieval Augmented Generation
  15. OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System
  16. RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
  17. Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach
  18. SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMs
  19. ShapeShifter: Workload-Aware Adaptive Evolving Index Structures Based on Learned Models
  20. TrustUQA: A Trustful Framework for Unified Structured Data Question Answering
  21. AntDT: A Self-Adaptive Distributed Training Framework for Leader and Straggler Nodes
  22. Editing Conceptual Knowledge for Large Language Models
  23. Efficient and Effective Anchored Densest Subgraph Search: A Convex-programming based Approach
  24. IEPile: Unearthing Large Scale Schema-Conditioned Information Extraction Corpus
  25. InBox: Recommendation with Knowledge Graph using Interest Box Embedding
  26. InstructIE: A Bilingual Instruction-based Information Extraction Dataset
  27. KGFabric: A Scalable Knowledge Graph Warehouse for Enterprise Data Interconnection
  28. OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
  29. OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs
  30. Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language Models
  31. Unified Hallucination Detection for Multimodal Large Language Models