Lune

学者档案2020-2026ORCID 0000-0001-5128-5649

Hai-Tao Zheng

Tsinghua University

曾用署名:Haitao Zheng

40论文数
13末位作者
55合作者人数
0一作
0独著

一作与末位作者按论文署名顺序统计,部分顶会采用姓氏字母顺序署名。

近期论文40

  1. Read As Human: Compressing Context via Parallelizable Close Reading and Skimming第 10 位,共 12 位作者ACL 2026 · 10 次引用
  2. 3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language Models第 9 位,共 9 位作者ICML 2026 · 6 次引用
  3. Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction第 10 位,共 11 位作者AAAI 2026 · 2 次引用
  4. When Hard Negatives Hurt: Bridging the Generative Discriminative Gap in Hard Negative Synthesis for Retrieval第 7 位,共 8 位作者KDD 2026 · 1 次引用
  5. CL²GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction第 4 位,共 8 位作者ACL 2026
  6. CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation第 8 位,共 12 位作者ACL Findings 2026
  7. DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens第 11 位,共 11 位作者ACL Findings 2025 · 2 次引用
  8. UltraWiki: Ultra-Fine-Grained Entity Set Expansion with Negative Seed Entities第 7 位,共 9 位作者ICDE 2025 · 1 次引用
  9. CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error Correction第 6 位,共 12 位作者ACL 2025
  10. One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMs第 12 位,共 13 位作者ICML 2025
  11. RAISE: Reinforced Adaptive Instruction Selection For Large Language Models第 10 位,共 11 位作者EMNLP Findings 2025
  12. Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and Benchmarks第 8 位,共 8 位作者ICLR 2025
  13. MESED: A Multi-Modal Entity Set Expansion Dataset with Fine-Grained Semantic Classes and Hard Negative Entities第 6 位,共 11 位作者AAAI 2024 · 21 次引用
  14. Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters第 10 位,共 11 位作者ACL 2024 · 9 次引用
  15. MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension第 6 位,共 7 位作者EMNLP Findings 2024 · 6 次引用
  16. HyperLoRA: Efficient Cross-task Generalization via Constrained Low-Rank Adapters Generation第 7 位,共 7 位作者EMNLP Findings 2024 · 4 次引用
  17. AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation第 7 位,共 12 位作者NeurIPS 2023 · 170 次引用
  18. MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation第 9 位,共 10 位作者ACM MM 2023 · 62 次引用
  19. Few-shot Classification with Hypersphere Modeling of Prototypes第 5 位,共 7 位作者ACL Findings 2023 · 12 次引用
  20. Visually Grounded Commonsense Knowledge Acquisition第 8 位,共 11 位作者AAAI 2023 · 6 次引用
  21. A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check第 7 位,共 7 位作者EMNLP Findings 2023 · 5 次引用
  22. CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction第 6 位,共 7 位作者EMNLP 2023 · 5 次引用
  23. Global Mixup: Eliminating Ambiguity with Clustering第 6 位,共 6 位作者AAAI 2023 · 5 次引用
  24. Exploring Lottery Prompts for Pre-trained Language Models第 5 位,共 7 位作者ACL 2023 · 4 次引用
  25. Learning Semantic Alignment with Global Modality Reconstruction for Video-Language Pre-training towards Retrieval第 5 位,共 6 位作者AAAI 2023 · 4 次引用
  26. Fusion or Defusion? Flexible Vision-and-Language Pre-Training第 6 位,共 9 位作者ACL Findings 2023 · 2 次引用
  27. The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking第 10 位,共 10 位作者ACL Findings 2022 · 44 次引用
  28. Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking第 10 位,共 10 位作者EMNLP Findings 2022 · 29 次引用
  29. Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction第 11 位,共 12 位作者EMNLP Findings 2022 · 27 次引用
  30. Contrastive Learning with Hard Negative Entities for Entity Set Expansion第 5 位,共 5 位作者SIGIR 2022 · 22 次引用

展示最近收录的 30 篇论文。

黄昏的海面,两侧是细线勾勒的悬崖