Lune

Profiles2020-2026

Furu Wei

Microsoft Corporation

94Papers
49Last author
141Unique co-authors
0First author
0Solo

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

Recent papers94

  1. MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal EmbeddingsAuthor 6 of 7ACL 2026 · 20 citations
  2. VibeVoice: Expressive Podcast Generation with Next-Token DiffusionAuthor 13 of 13ICLR 2026
  3. Towards Thinking-Optimal Scaling of Test-Time Compute for LLM ReasoningAuthor 4 of 4NeurIPS 2025 · 141 citations
  4. Autoregressive Speech Synthesis without Vector QuantizationAuthor 12 of 12ACL 2025 · 94 citations
  5. Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm PerspectiveAuthor 12 of 12ACL 2025 · 31 citations
  6. mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic DataAuthor 6 of 7ACL Findings 2025 · 6 citations
  7. Rethinking DPO-Style Diffusion Aligning FrameworksAuthor 4 of 4ICCV 2025 · 4 citations
  8. Examining False Positives under Inference Scaling for Mathematical ReasoningAuthor 4 of 5EMNLP 2025 · 1 citation
  9. GeAR: Generation Augmented RetrievalAuthor 8 of 9ACL Findings 2025
  10. PEACE: Empowering Geologic Map Holistic Understanding with MLLMsAuthor 11 of 11CVPR 2025
  11. Semi-Parametric Retrieval via Binary Bag-of-Tokens IndexAuthor 3 of 4ICLR 2025
  12. Textual Aesthetics in Large Language ModelsAuthor 4 of 4EMNLP 2025
  13. Mixture of LoRA ExpertsAuthor 3 of 3ICLR 2024 · 174 citations
  14. In-context Autoencoder for Context Compression in a Large Language ModelAuthor 6 of 6ICLR 2024 · 158 citations
  15. MiniLLM: Knowledge Distillation of Large Language ModelsAuthor 3 of 4ICLR 2024 · 95 citations
  16. Learning to Rank in Generative RetrievalAuthor 4 of 5AAAI 2024 · 83 citations
  17. Multimodal Large Language Models Make Text-to-Image Generative Models Align BetterAuthor 5 of 5NeurIPS 2024 · 26 citations
  18. Boosting Text-to-Video Generative Model with MLLMs FeedbackAuthor 5 of 5NeurIPS 2024 · 23 citations
  19. Instruction Pre-Training: Language Models are Supervised Multitask LearnersAuthor 6 of 6EMNLP 2024 · 13 citations
  20. Chain-of-Dictionary Prompting Elicits Translation in Large Language ModelsAuthor 6 of 6EMNLP 2024 · 9 citations
  21. ResLoRA: Identity Residual Mapping in Low-Rank AdaptionAuthor 7 of 10ACL Findings 2024 · 8 citations
  22. Se²: Sequential Example Selection for In-Context LearningAuthor 7 of 8ACL Findings 2024 · 3 citations
  23. HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria DecompositionAuthor 6 of 9ACL 2024 · 1 citation
  24. Improving Text Embeddings with Large Language ModelsAuthor 6 of 6ACL 2024
  25. Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language ModelsAuthor 7 of 8ACL 2024
  26. Respond in my Language: Mitigating Language Inconsistency in Response Generation based on Large Language ModelsAuthor 5 of 5ACL 2024
  27. TrOCR: Transformer-Based Optical Character Recognition with Pre-trained ModelsAuthor 9 of 9AAAI 2023 · 607 citations
  28. BEATs: Audio Pre-Training with Acoustic TokenizersAuthor 7 of 7ICML 2023 · 568 citations
  29. TextDiffuser: Diffusion Models as Text PaintersAuthor 6 of 7NeurIPS 2023 · 290 citations
  30. Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-OptimizersAuthor 7 of 7ACL Findings 2023 · 154 citations

Showing the 30 most recent indexed papers.

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