Fanchao Chen

I am a final-year CS PhD student at the University of Wisconsin–Madison, advised by Prof. Shivaram Venkataraman. I am currently a research intern on the Nemotron Post-training Team at NVIDIA. Previously, I worked at ByteDance Seed, Moonshot AI (Kimi), and Microsoft Research Asia.

My research interests are about Efficient AI Systems and Continual Learning.

Fanchao Chen

Work Experience

Selected Publications

* indicates equal contribution.

arXiv 2026

Deriving a Quantization-Aware Distillation Recipe for NVFP4 Inference Accuracy Recovery

Fanchao Chen, Minghao Yan, Jiantao Jiao, Shivaram Venkataraman

We develop an NVFP4 quantization-aware distillation (QAD) recipe from open data, using domain-specific failure analysis and small-scale experiments to guide data selection and iteration. On Nemotron models, it uses up to 4.7× fewer training tokens than NVIDIA's official QAD recipe while recovering more of the quantization-induced accuracy loss.

arXiv 2026

Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards

Fanchao Chen*, Hengyu Fu*, Shivaram Venkataraman, Jiantao Jiao

HDL turns the hindsight signal from token-level supervision into trajectory branching: it uses hindsight-induced changes in token log-probabilities to pick branch points and samples new continuations from shared prefixes. Compared with GRPO, it speeds up rollouts by up to 1.8× while improving performance on math, code, and agentic tasks.

arXiv 2026

PipeTune: Tuning Pipeline Parallelism for Efficient Vision-Language Model Training

Fanchao Chen, Shivaram Venkataraman

Heterogeneous sequence lengths and modality mixes in VLM training data create pipeline bubbles. PipeTune jointly tunes micro-batch packing, ordering, and sizing, and moves vision-encoder computation into idle time, guided by a lightweight simulator that adapts as the data mix shifts. It speeds up training by up to 1.25× without changing training semantics.

Teaching & Service