Fengqi Zhu
Fengqi Zhu has 2 papers in our library, in 2025–2026; often with Chongxuan Li, Ji-Rong Wen, Jun Zhou.
OpenAlex · h-index 2 · 8 works · 24 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 197 times in our library · ⭐ Paper Stars ranking: #5455
Affiliations
Fields, topics and concepts
📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 workInformation Systems · 1 work
Works by year
2020s
Papers
- Large Language Diffusion Models (2025 · 178 citations)
Modern LLMs almost all rely on autoregressive next-token prediction. Many assume that scaling, in-context learning and instruction-following depend on this design. The authors test that assumption with LLaDA, a masked diffusion language model trained from scratch. - LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models (2026 · 49 citations)
Masked diffusion models (MDMs) for language cannot compute exact log-likelihoods, so preference alignment methods such as DPO cannot be applied directly.
Co-authors here
- Chongxuan Li ×2
- Ji-Rong Wen ×2
- Jun Zhou ×2
- Shen Nie ×2
- Xiaolu Zhang ×2
- Yankai Lin ×2
- Jun Hu
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2025
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/fengqi-zhu/