Lune

Profiles2020-2025

Shaohan Huang

Peking University

30Papers
0Last author
34Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers30

  1. Rethinking DPO-Style Diffusion Aligning FrameworksAuthor 2 of 4ICCV 2025 · 4 citations
  2. GeAR: Generation Augmented RetrievalAuthor 2 of 9ACL Findings 2025
  3. NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement LearningAuthor 2 of 10EMNLP 2025
  4. Textual Aesthetics in Large Language ModelsAuthor 2 of 4EMNLP 2025
  5. Mixture of LoRA ExpertsAuthor 2 of 3ICLR 2024 · 174 citations
  6. Adapting Large Language Models via Reading ComprehensionAuthor 2 of 3ICLR 2024 · 146 citations
  7. Multi-Head Mixture-of-ExpertsAuthor 2 of 4NeurIPS 2024 · 42 citations
  8. Multimodal Large Language Models Make Text-to-Image Generative Models Align BetterAuthor 2 of 5NeurIPS 2024 · 26 citations
  9. Boosting Text-to-Video Generative Model with MLLMs FeedbackAuthor 2 of 5NeurIPS 2024 · 23 citations
  10. Instruction Pre-Training: Language Models are Supervised Multitask LearnersAuthor 3 of 6EMNLP 2024 · 13 citations
  11. ResLoRA: Identity Residual Mapping in Low-Rank AdaptionAuthor 2 of 10ACL Findings 2024 · 8 citations
  12. Se²: Sequential Example Selection for In-Context LearningAuthor 3 of 8ACL Findings 2024 · 3 citations
  13. HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria DecompositionAuthor 3 of 9ACL 2024 · 1 citation
  14. UPRISE: Universal Prompt Retrieval for Improving Zero-Shot EvaluationAuthor 2 of 10EMNLP 2023 · 28 citations
  15. MoEC: Mixture of Expert ClustersAuthor 2 of 4AAAI 2023 · 27 citations
  16. Beyond English-Centric Bitexts for Better Multilingual Language Representation LearningAuthor 3 of 8ACL 2023 · 8 citations
  17. Democratizing Reasoning Ability: Tailored Learning from Large Language ModelAuthor 2 of 11EMNLP 2023 · 8 citations
  18. GanLM: Encoder-Decoder Pre-training with an Auxiliary DiscriminatorAuthor 4 of 9ACL 2023 · 7 citations
  19. Dual-Alignment Pre-training for Cross-lingual Sentence EmbeddingAuthor 2 of 10ACL 2023 · 5 citations
  20. PromptBERT: Improving BERT Sentence Embeddings with PromptsAuthor 3 of 10EMNLP 2022 · 148 citations
  21. THE-X: Privacy-Preserving Transformer Inference with Homomorphic EncryptionAuthor 2 of 7ACL Findings 2022 · 86 citations
  22. CROP: Zero-shot Cross-lingual Named Entity Recognition with Multilingual Labeled Sequence TranslationAuthor 2 of 9EMNLP Findings 2022 · 21 citations
  23. Snapshot-Guided Domain Adaptation for ELECTRAAuthor 2 of 8EMNLP Findings 2022
  24. MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained TransformersAuthor 3 of 5ACL Findings 2021 · 260 citations
  25. mT6: Multilingual Pretrained Text-to-Text Transformer with Translation PairsAuthor 4 of 7EMNLP 2021 · 60 citations
  26. Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for DomainsAuthor 2 of 5ACL Findings 2021 · 25 citations
  27. Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-TrainingAuthor 3 of 8EMNLP 2021 · 15 citations
  28. Consistency Regularization for Cross-Lingual Fine-TuningAuthor 3 of 10ACL 2021
  29. Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word AlignmentAuthor 4 of 7ACL 2021
  30. Language Generation with Multi-Hop Reasoning on Commonsense Knowledge GraphAuthor 3 of 6EMNLP 2020 · 96 citations
Dusk over the sea between two cliffs drawn in fine vertical lines