Chenyan Xiong
Chenyan Xiong is an Associate Professor at Carnegie Mellon University's Language Technologies Institute, where he is also affiliated with the Machine Learning Department and the CMU Foundation and Language Model Center (FLAME). Before joining CMU as faculty in 2023, he was a Principal Researcher at Microsoft Research Redmond, where his work on dense retrieval and large-scale pretraining reached production systems at global scale. He is best known for advances in neural information retrieval and text representation learning, and more recently for EmbodiedMidtrain, a mid-training framework that bridges vision-language model pretraining and vision-language-action fine-tuning at a fraction of standard compute cost. He has accumulated over 10,600 scholarly citations across his career.
“EmbodiedMidtrain inserts a lightweight 'alignment' step between VLM pretraining and VLA fine-tuning that costs a fraction of normal training compute but consistently delivers performance competitive with models 3–8x larger.”
Source→“Chenyan Xiong — Language Technologies Institute, Carnegie Mellon University. Senior author. Known for work on information retrieval and representation learning. His involvement signals that the proximity estimation methodology draws on well-established principles from information retrieval and data selection for LLM pretraining — the paper explicitly cites the DSIR framework (Xie et al., 2023) from Percy Liang's group at Stanford.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.