Furu Wei

Microsoft (United States) — United States

Computer Science · Physical Sciences

81h-index31.8kcitations567works5.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(367), Natural Language Processing Techniques(334), Multimodal Machine Learning Applications(133), Advanced Text Analysis Techniques(70), Speech Recognition and Synthesis(64)

Publications567 total

Black-Box On-Policy Distillation of Large Language Models
arXiv (Cornell University)·2025Open Access
MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings
arXiv (Cornell University)·2025Open Access
PEACE: Empowering Geologic Map Holistic Understanding with MLLMs
2025· 3 cited
Reinforcement Pre-Training
arXiv (Cornell University)·2025Open Access
Think Only When You Need with Large Hybrid-Reasoning Models
arXiv (Cornell University)·2025Open Access
Efficient RL Training for Reasoning Models via Length-Aware Optimization
arXiv (Cornell University)·2025Open Access
BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
arXiv (Cornell University)·2025Open Access
Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipes
arXiv (Cornell University)·2025Open Access
BitNet b1.58 2B4T Technical Report
arXiv (Cornell University)·2025Open Access
Text to Image Generation with Bidirectional Multiway Transformers
Computational Visual Media·2025· 1 citedOpen Access
Model as a Game: On Numerical and Spatial Consistency for Generative Games
arXiv (Cornell University)·2025Open Access
Boosting Large Language Model for Speech Synthesis: An Empirical Study
2025· 4 cited
Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
arXiv (Cornell University)·2025Open Access
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
ArXiv.org·2025· 1 citedOpen Access
mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data
arXiv (Cornell University)·2025Open Access
Examining False Positives under Inference Scaling for Mathematical Reasoning
arXiv (Cornell University)·2025Open Access
Chain-of-Retrieval Augmented Generation
arXiv (Cornell University)·2025· 3 citedOpen Access
Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective
arXiv (Cornell University)·2025Open Access
GeAR: Generation Augmented Retrieval
2025Open Access
PEACE: Empowering Geologic Map Holistic Understanding with MLLMs
arXiv (Cornell University)·2025· 1 citedOpen Access
page 1 of 29Next →

Frequent Co-authors

Ming Zhou(22), Nan Yang(10), Li Dong(9), Hangbo Bao(8), Dong Li(6), Shaohan Huang(6), Duyu Tang(5), Tengchao Lv(5), Sujian Li(5), Bing Qin(4), Ke Xu(4), Wenhui Wang(4), Wenhui Wang(4), Lei Cui(4), Saksham Singhal(4), Ziqiang Cao(4), Shi‐Xia Liu(4), Ting Liu(3), Chuanqi Tan(3), Johan Björck(3)