PPaperPicks

Hai-Tao Zheng

Tsinghua University, Graduate School at Shenzhen, Shenzhen, China

30 papers at tracked venues · 20 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. CL²GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction
  2. GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment
  3. AdmTree: Compressing Lengthy Context with Adaptive Semantic Trees
  4. Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent
  5. CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction
  6. DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens
  7. Dual Denoising Diffusion Model for Session-based Social Recommendation
  8. EXCGEC: A Benchmark for Edit-Wise Explainable Chinese Grammatical Error Correction
  9. Frozen Language Models Are Gradient Coherence Rectifiers in Vision Transformers
  10. LexSemBridge: Fine-Grained Dense Representation Enhancement Through Token-Aware Embedding Augmentation
  11. MKT: A Multi-Stage Knowledge Transfer Framework to Mitigate Catastrophic Forgetting in Multi-Domain Chinese Spelling Correction
  12. One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs
  13. Position: LLMs Can be Good Tutors in English Education
  14. RAISE: Reinforced Adaptive Instruction Selection For Large Language Models
  15. ROMA: Recommendation-Oriented Language Model Adaptation Using Multi-Modal Multi-Domain Item Sequences
  16. Refine Knowledge of Large Language Models via Adaptive Contrastive Learning
  17. Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction
  18. UltraWiki: Ultra-Fine-Grained Entity Set Expansion with Negative Seed Entities
  19. VLM as Policy: Common-Law Content Moderation Framework for Short Video Platform
  20. EcomGPT: Instruction-Tuning Large Language Models with Chain-of-Task Tasks for E-commerce
  21. Empowering Private Tutoring by Chaining Large Language Models
  22. From Retrieval to Generation: Efficient and Effective Entity Set Expansion
  23. HyperLoRA: Efficient Cross-task Generalization via Constrained Low-Rank Adapters Generation
  24. MESED: A Multi-Modal Entity Set Expansion Dataset with Fine-Grained Semantic Classes and Hard Negative Entities
  25. MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension
  26. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-Grained Correctional Human Feedback
  27. SeqGPT: An Out-of-the-Box Large Language Model for Open Domain Sequence Understanding
  28. Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters
  29. UniEmbedding: Learning Universal Multi-Modal Multi-Domain Item Embeddings via User-View Contrastive Learning
  30. When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models