PPaperPicks

Junbo Zhao

Zhejiang University, Zhejiang, China

38 papers at tracked venues · 27 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. An Invariant Latent Space Perspective on Language Model Inversion
  2. HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs
  3. KMLP: A Scalable Hybrid Architecture for Web-Scale Tabular Data Modeling
  4. Reinforcement Learning with Verbalized Probabilities for LLM Classification
  5. Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph
  6. ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models
  7. Bridging the Semantic Gap Between Text and Table: A Case Study on NL2SQL
  8. CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency
  9. CrowdAgent: Multi-Agent Managed Multi-Source Annotation System
  10. D.Va: Validate Your Demonstration First Before You Use It
  11. DataMan: Data Manager for Pre-training Large Language Models
  12. Ensembling Prompting Strategies for Zero-Shot Hierarchical Text Classification with Large Language Models
  13. Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
  14. Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
  15. Large Margin Representation Learning for Robust Cross-lingual Named Entity Recognition
  16. LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization
  17. LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains
  18. POLO: An LLM-Powered Project-Level Code Performance Optimization Framework
  19. Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation
  20. RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis
  21. Table as a Modality for Large Language Models
  22. Towards Reverse Engineering of Language Models: A Survey
  23. Towards Robust Incremental Learning Under Ambiguous Supervision
  24. A Separation and Alignment Framework for Black-Box Domain Adaptation
  25. CORAL: Collaborative Automatic Labeling System based on Large Language Models
  26. DORY: Deliberative Prompt Recovery for LLM
  27. Data Contamination Calibration for Black-box LLMs
  28. Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection
  29. Energy-based Automated Model Evaluation
  30. FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
  31. Learning Geometry-Aware Representations for New Intent Discovery
  32. Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild
  33. On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey
  34. Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation
  35. RECOST: External Knowledge Guided Data-efficient Instruction Tuning
  36. Targeted Representation Alignment for Open-World Semi-Supervised Learning
  37. Towards Cross-Table Masked Pretraining for Web Data Mining
  38. Unbiased Multi-Label Learning from Crowdsourced Annotations