PPaperPicks

Xuebo Liu

Harbin Institute of Technology, School of Computer Science and Technology, Shenzhen, China

34 papers at tracked venues · 22 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation
  2. DeReA: Improving Idiom Translation with Detect-Retrieve-Arbitrate Reasoning
  3. Dynamic Sampling that Adapts: Self-Aware Iterative Data Persistent Optimization for Mathematical Reasoning
  4. Exposing the Cracks: Vulnerabilities of Retrieval-Augmented LLM-based Machine Translation
  5. APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training
  6. AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs
  7. AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration
  8. AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration
  9. CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task
  10. DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
  11. DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory
  12. DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
  13. Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
  14. Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments
  15. SGIC: A Self-Guided Iterative Calibration Framework for RAG
  16. SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models
  17. UnrealLLM: Towards Highly Controllable and Interactable 3D Scene Generation by LLM-powered Procedural Content Generation
  18. Weight-Aware Activation Sparsity with Constrained Bayesian Optimization Scheduling for Large Language Models
  19. Can LLMs Learn Uncertainty on Their Own? Expressing Uncertainty Effectively in A Self-Training Manner
  20. CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions
  21. Curriculum Consistency Learning for Conditional Sentence Generation
  22. DB-LLM: Accurate Dual-Binarization for Efficient LLMs
  23. Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine Translation
  24. EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
  25. Improving Attributed Text Generation of Large Language Models via Preference Learning
  26. LPZero: Language Model Zero-cost Proxy Search from Zero
  27. LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models
  28. NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
  29. Revisiting Demonstration Selection Strategies in In-Context Learning
  30. SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
  31. Self-Powered LLM Modality Expansion for Large Speech-Text Models
  32. Speech Sense Disambiguation: Tackling Homophone Ambiguity in End-to-End Speech Translation
  33. TasTe: Teaching Large Language Models to Translate through Self-Reflection
  34. Towards Demonstration-Aware Large Language Models for Machine Translation