Lune

Profiles2022-2026ORCID 0000-0003-3026-6347

Hao Fei

National University of Singapore

54Papers
4Last author
93Unique co-authors
5First author
0Solo

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

Recent papers54

  1. Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion ReasoningAuthor 9 of 11ICLR 2026 · 10 citations
  2. LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical SupervisionAuthor 2 of 10ICLR 2026 · 9 citations
  3. From Data Deluge to Data Curation: A Filtering-WoRA Paradigm for Efficient Text-based Person SearchAuthor 2 of 4WWW 2025 · 28 citations
  4. Towards Multimodal Empathetic Response Generation: A Rich Text-Speech-Vision Avatar-based BenchmarkAuthor 7 of 7WWW 2025 · 25 citations
  5. Combating Multimodal LLM Hallucination via Bottom-Up Holistic ReasoningAuthor 2 of 6AAAI 2025 · 24 citations
  6. Multi-Granular Multimodal Clue Fusion for Meme UnderstandingAuthor 2 of 8AAAI 2025 · 13 citations
  7. Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve FrameworkAuthor 2 of 9ACL 2025 · 11 citations
  8. Divide-Solve-Combine: An Interpretable and Accurate Prompting Framework for Zero-shot Multi-Intent DetectionAuthor 5 of 7AAAI 2025 · 9 citations
  9. VEGAS: Towards Visually Explainable and Grounded Artificial Social IntelligenceAuthor 2 of 5AAAI 2025 · 6 citations
  10. Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion KnowledgeAuthor 3 of 8ACL 2025 · 5 citations
  11. MuSLR: Multimodal Symbolic Logical ReasoningAuthor 2 of 11NeurIPS 2025 · 5 citations
  12. ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language ModelsAuthor 4 of 7ACM MM 2025 · 4 citations
  13. LEAF-Mamba: Local Emphatic and Adaptive Fusion State Space Model for RGB-D Salient Object DetectionAuthor 3 of 5ACM MM 2025 · 3 citations
  14. When Words Smile: Generating Diverse Emotional Facial Expressions from TextAuthor 7 of 7EMNLP 2025 · 2 citations
  15. CLEAR: A Framework Enabling Large Language Models to Discern Confusing Legal ParagraphsAuthor 4 of 6EMNLP Findings 2025 · 1 citation
  16. David vs. Goliath: Cost-Efficient Financial QA via Cascaded Multi-Agent ReasoningAuthor 4 of 5EMNLP Findings 2025
  17. Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual SceneAuthor 2 of 7CVPR 2025
  18. MCM-DPO: Multifaceted Cross-Modal Direct Preference Optimization for Alt-text GenerationAuthor 3 of 7ACM MM 2025
  19. On Path to Multimodal Generalist: General-Level and General-BenchAuthor 1 of 32ICML 2025
  20. Towards Semantic Equivalence of Tokenization in Multimodal LLMAuthor 2 of 7ICLR 2025
  21. Universal Scene Graph GenerationAuthor 2 of 3CVPR 2025
  22. VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video ModelsAuthor 8 of 8ICML 2025
  23. NExT-GPT: Any-to-Any Multimodal LLMAuthor 2 of 5ICML 2024 · 786 citations
  24. Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, EditingAuthor 1 of 7NeurIPS 2024 · 100 citations
  25. What Factors Affect Multi-Modal In-Context Learning? An In-Depth ExplorationAuthor 3 of 6NeurIPS 2024 · 37 citations
  26. Towards Unified Multimodal Editing with Enhanced Knowledge CollaborationAuthor 5 of 9NeurIPS 2024 · 27 citations
  27. PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment AnalysisAuthor 2 of 9ACM MM 2024 · 23 citations
  28. Harnessing Holistic Discourse Features and Triadic Interaction for Sentiment Quadruple Extraction in DialoguesAuthor 2 of 7AAAI 2024 · 22 citations
  29. Unified Generative and Discriminative Training for Multi-modal Large Language ModelsAuthor 5 of 10NeurIPS 2024 · 19 citations
  30. Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-ThoughtAuthor 2 of 7AAAI 2024 · 13 citations

Showing the 30 most recent indexed papers.

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