Lune

Profiles2020-2026

Fei Huang

Alibaba Group

84Papers
16Last author
163Unique co-authors
0First author
0Solo

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

Recent papers84

  1. Reasoning-Guided Exploration for Online DPOAuthor 4 of 6ACL Findings 2026
  2. IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference OptimizationAuthor 4 of 5ACL 2025 · 29 citations
  3. DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point ThinkingAuthor 6 of 9ACL 2025 · 13 citations
  4. ExploraCoder: Advancing Code Generation for Multiple Unseen APIs via Planning and Chained ExplorationAuthor 6 of 8ACL 2025 · 13 citations
  5. DEMO: Reframing Dialogue Interaction with Fine-grained Element ModelingAuthor 6 of 8ACL Findings 2025 · 1 citation
  6. EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language ModelsAuthor 5 of 6EMNLP 2025 · 1 citation
  7. CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy OptimizationAuthor 6 of 7EMNLP Findings 2025
  8. CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer SynthesisAuthor 7 of 7EMNLP Findings 2025
  9. DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling CheckAuthor 9 of 9ACL 2025
  10. On the Role of Attention Heads in Large Language Model SafetyAuthor 5 of 9ICLR 2025
  11. StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information StructurizationAuthor 7 of 10ICLR 2025
  12. OMNIPARSER: A Unified Framework for Text Spotting, Key Information Extraction and Table RecognitionAuthor 6 of 9CVPR 2024 · 29 citations
  13. FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based AgentsAuthor 7 of 8EMNLP Findings 2024 · 15 citations
  14. TinyChart: Efficient Chart Understanding with Program-of-Thoughts Learning and Visual Token MergingAuthor 8 of 8EMNLP 2024 · 15 citations
  15. How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden StatesAuthor 5 of 6EMNLP Findings 2024 · 14 citations
  16. Self-Retrieval: End-to-End Information Retrieval with One Large Language ModelAuthor 9 of 13NeurIPS 2024 · 14 citations
  17. Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool UseAuthor 6 of 8ACL 2024 · 7 citations
  18. Improving Factual Consistency of News Summarization by Contrastive Preference OptimizationAuthor 7 of 9EMNLP Findings 2024 · 5 citations
  19. A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language ModelsAuthor 7 of 8EMNLP 2024 · 2 citations
  20. Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL ParsingAuthor 7 of 10AAAI 2023 · 164 citations
  21. Reasoning with Language Model Prompting: A SurveyAuthor 8 of 9ACL 2023 · 124 citations
  22. API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMsAuthor 8 of 9EMNLP 2023 · 72 citations
  23. RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-trainingAuthor 6 of 7ACM MM 2023 · 33 citations
  24. MGeo: Multi-Modal Geographic Language Model Pre-TrainingAuthor 4 of 8SIGIR 2023 · 29 citations
  25. Adversarial Self-Attention for Language UnderstandingAuthor 5 of 6AAAI 2023 · 19 citations
  26. Exploring Large Language Models for Multi-Modal Out-of-Distribution DetectionAuthor 4 of 5EMNLP Findings 2023 · 17 citations
  27. Improving Seq2Seq Grammatical Error Correction via Decoding InterventionsAuthor 9 of 9EMNLP Findings 2023 · 17 citations
  28. Unified Language Representation for Question Answering over Text, Tables, and ImagesAuthor 4 of 5ACL Findings 2023 · 17 citations
  29. NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker TextsAuthor 6 of 7ACL Findings 2023 · 11 citations
  30. COPA : Efficient Vision-Language Pre-training through Collaborative Object- and Patch-Text AlignmentAuthor 7 of 7ACM MM 2023 · 10 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines