2026
Implicit Neural Representations
Part III: faster radiance fields through hash encodings, tensor factorization, and explicit Gaussian primitives.
Authors
Xi Fang
2026
Building a Robot Learning Pipeline with SO-101
Part II: adapting GR00T N1.7 to the carrot-to-box dataset with a full-scope LoRA interface.
2026
Implicit Neural Representations
Part II: a neural radiance field turns calibrated images into a continuous scene that can render new views.
2026
VLA Post-Training
Part I: a controlled comparison of LoRA, QLoRA, and DoRA for post-training GR00T N1.7 on LIBERO-10 Long.
2026
VLA Robot Learning
Part II: why multi-robot data is difficult to pool, and how open generalist policies adapt across embodiments.
2026
Implicit Neural Representations
Part I: represent an image, shape, or scene as a continuous function that can be queried at any coordinate.
2026
Parameter-Efficient Fine-Tuning
Part I: LoRA, QLoRA, and DoRA—three ways to adapt a large frozen model without fully fine-tuning it.
2026
Multi-View Geometry
Part III turns the epipolar constraint into an algorithm: estimating a fundamental matrix from noisy point matches.
2026
VLA Robot Learning
Part I: the policy foundations beneath VLAs—from behavior cloning to action chunks, diffusion, and flow matching.
2026
Multi-View Geometry
Part II explains why a point in one image can correspond only to an epipolar line in another, and how the fundamental matrix expresses that constraint.
2026
Labor Day at Riverside House
A quiet Labor Day weekend by the river: a house, board games, and an unhurried afternoon outside.
2026
Multi-View Geometry
Part I builds the camera model from an intuitive idea of projection to the geometry that maps a 3D world point to a 2D pixel.
2026
Robot Kinematics
Part II of a technical note on robot kinematics, covering forward and inverse kinematics for serial robot arms.
2026
Robot Kinematics
Part I of a technical note on robot kinematics, covering coordinate frames, rotation, and rigid transforms.
2026
Building a Robot Learning Pipeline with SO-101
A practical build note on using SO-101 as a hardware platform for teleoperation, camera bring-up, and early dataset collection.
2026
Rethink Human Learning Through the Lens of Machine Learning
Machine learning offers a surprisingly useful vocabulary for thinking more systematically about how humans learn, adapt, and make decisions.
2025
Learning soft tissue deformation from incremental simulations
A data-driven framework that learns soft-tissue mechanics directly from incremental finite-element simulations, enabling more accurate CMF surgical planning.
2025
Cephalometric Landmark Detection Using Graph-and Image-Aware Network with Landmark Contrastive Regularization
A graph-and image-aware framework with contrastive regularization for robust cephalometric landmark detection under anatomical variability.
2024
Large language models diagnose facial deformity
We explore the potential of general-purpose large language models to interpret facial deformity descriptions and perform diagnostic reasoning in CMF.
2023
Spatiotemporal incremental mechanics modeling of facial tissue change
A spatiotemporal incremental mechanics model that captures continuous facial soft-tissue deformation for CMF surgical simulation.
2023
TriAxial Low-Rank Transformer for Efficient Medical Image Segmentation
A tri-axially factorized low-rank transformer that reduces computational cost while maintaining high segmentation accuracy. (Corresponding author: Xi Fang)
2021
Data augmentation for training deep neural networks
A comprehensive overview of data augmentation strategies tailored for medical image segmentation, radiotherapy, and robust deep learning.