Profiles2021-2026
Fei Mi
Huawei Noah's Ark Lab
13Papers
0Last author
38Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers13
- Improved Policy Optimization for Mixture-of-Experts Models: Importance Sampling and Rewarding from an Expert-Centric PerspectiveAuthor 3 of 5ACL Findings 2026
- Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical ReasoningAuthor 10 of 12ACL 2026
- Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake AnalysisAuthor 6 of 14ICLR 2024 · 47 citations
- Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue GenerationAuthor 2 of 6ACL Findings 2024 · 2 citations
- A Synthetic Data Generation Framework for Grounded DialoguesAuthor 6 of 7ACL 2023 · 11 citations
- Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent VariablesAuthor 3 of 6AAAI 2023 · 8 citations
- KPT: Keyword-Guided Pre-training for Grounded Dialog GenerationAuthor 2 of 9AAAI 2023 · 5 citations
- ReSee: Responding through Seeing Fine-grained Visual Knowledge in Open-domain DialogueAuthor 3 of 4EMNLP 2023 · 4 citations
- DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question AnsweringAuthor 3 of 7ACL 2023 · 2 citations
- CINS: Comprehensive Instruction for Few-Shot Learning in Task-Oriented Dialog SystemsAuthor 1 of 5AAAI 2022 · 46 citations
- Towards Identifying Social Bias in Dialog Systems: Framework, Dataset, and BenchmarkAuthor 3 of 9EMNLP Findings 2022 · 31 citations
- Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-EncoderAuthor 5 of 7EMNLP Findings 2022 · 1 citation
- Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog SystemsAuthor 1 of 6EMNLP 2021 · 18 citations
