Profiles2020-2026ORCID 0000-0001-5128-5649
Hai-Tao Zheng
Tsinghua University
Also published as Haitao Zheng
40Papers
13Last author
55Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers40
- Read As Human: Compressing Context via Parallelizable Close Reading and SkimmingAuthor 10 of 12ACL 2026 · 10 citations
- 3ViewSense: Spatial and Mental Perspective Reasoning from Orthographic Views in Vision-Language ModelsAuthor 9 of 9ICML 2026 · 6 citations
- Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR PredictionAuthor 10 of 11AAAI 2026 · 2 citations
- When Hard Negatives Hurt: Bridging the Generative Discriminative Gap in Hard Negative Synthesis for RetrievalAuthor 7 of 8KDD 2026 · 1 citation
- CL²GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error CorrectionAuthor 4 of 8ACL 2026
- CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal DistillationAuthor 8 of 12ACL Findings 2026
- DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft TokensAuthor 11 of 11ACL Findings 2025 · 2 citations
- UltraWiki: Ultra-Fine-Grained Entity Set Expansion with Negative Seed EntitiesAuthor 7 of 9ICDE 2025 · 1 citation
- CLEME2.0: Towards Interpretable Evaluation by Disentangling Edits for Grammatical Error CorrectionAuthor 6 of 12ACL 2025
- One Example Shown, Many Concepts Known! Counterexample-Driven Conceptual Reasoning in Mathematical LLMsAuthor 12 of 13ICML 2025
- RAISE: Reinforced Adaptive Instruction Selection For Large Language ModelsAuthor 10 of 11EMNLP Findings 2025
- Youku Dense Caption: A Large-scale Chinese Video Dense Caption Dataset and BenchmarksAuthor 8 of 8ICLR 2025
- MESED: A Multi-Modal Entity Set Expansion Dataset with Fine-Grained Semantic Classes and Hard Negative EntitiesAuthor 6 of 11AAAI 2024 · 21 citations
- Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled CharactersAuthor 10 of 11ACL 2024 · 9 citations
- MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular ComprehensionAuthor 6 of 7EMNLP Findings 2024 · 6 citations
- HyperLoRA: Efficient Cross-task Generalization via Constrained Low-Rank Adapters GenerationAuthor 7 of 7EMNLP Findings 2024 · 4 citations
- AR-Diffusion: Auto-Regressive Diffusion Model for Text GenerationAuthor 7 of 12NeurIPS 2023 · 170 citations
- MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for RecommendationAuthor 9 of 10ACM MM 2023 · 62 citations
- Few-shot Classification with Hypersphere Modeling of PrototypesAuthor 5 of 7ACL Findings 2023 · 12 citations
- Visually Grounded Commonsense Knowledge AcquisitionAuthor 8 of 11AAAI 2023 · 6 citations
- A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling CheckAuthor 7 of 7EMNLP Findings 2023 · 5 citations
- CLEME: Debiasing Multi-reference Evaluation for Grammatical Error CorrectionAuthor 6 of 7EMNLP 2023 · 5 citations
- Global Mixup: Eliminating Ambiguity with ClusteringAuthor 6 of 6AAAI 2023 · 5 citations
- Exploring Lottery Prompts for Pre-trained Language ModelsAuthor 5 of 7ACL 2023 · 4 citations
- Learning Semantic Alignment with Global Modality Reconstruction for Video-Language Pre-training towards RetrievalAuthor 5 of 6AAAI 2023 · 4 citations
- Fusion or Defusion? Flexible Vision-and-Language Pre-TrainingAuthor 6 of 9ACL Findings 2023 · 2 citations
- The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell CheckingAuthor 10 of 10ACL Findings 2022 · 44 citations
- Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell CheckingAuthor 10 of 10EMNLP Findings 2022 · 29 citations
- Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error CorrectionAuthor 11 of 12EMNLP Findings 2022 · 27 citations
- Contrastive Learning with Hard Negative Entities for Entity Set ExpansionAuthor 5 of 5SIGIR 2022 · 22 citations
Showing the 30 most recent indexed papers.
