Xia Li

Comparative evaluation of static and dynamic 4D dose recalculations in pencil beam scanning proton therapy for oesophageal cancer

Thu, 01 Jan 2026 00:00:00 +0000

Contour-informed inter-patient deformable registration for more reliable voxel-based analysis of Head-and-Neck cancer patients

Thu, 01 Jan 2026 00:00:00 +0000

Continuous sPatial-Temporal Deformable Image Registration (CPT-DIR) for motion modelling in radiotherapy: beyond classic voxel-based methods

Fri, 26 Dec 2025 00:00:00 +0000

I am serving as an Area Chair for ICML 2026

Thu, 20 Nov 2025 00:00:00 +0000

From ICML: We invite you to serve as an area chair (AC) for ICML 2026 based on your expertise in important sub-areas of machine learning and your prior experience in the peer review process. We sincerely hope you will accept this invitation and help us make ICML 2026 a success.

2 papers accepted to Medical Physics in 2025.

Tue, 18 Nov 2025 00:00:00 +0000

They are:

Continuous sPatial-Temporal Deformable Image Registration and 4D Frame Interpolation
Diffusion Schrödinger bridge models for high-quality MR-to-CT synthesis for proton treatment planning

3 papers accepted to phiRO in 2025.

Tue, 18 Nov 2025 00:00:00 +0000

They are:

Contour-informed inter-patient deformable registration for more reliable voxel-based analysis of Head-and-Neck Cancer patients
Gaussian primitives for deformable image registration
A proof-of-concept study of direct magnetic resonance imaging-based proton dose calculation for brain tumors via neural networks with Monte Carlo-comparable accuracy

Enhancing Brain MRI Super-Resolution Through Multi-Slice Aware Matching and Fusion

Wed, 01 Oct 2025 00:00:00 +0800

Gaussian Representation for Deformable Image Registration

Wed, 09 Jul 2025 00:00:00 +0000

A proof-of-concept study of direct magnetic resonance imaging-based proton dose calculation for brain tumors via neural networks with Monte Carlo-comparable accuracy

Sat, 05 Jul 2025 00:00:00 +0000

Exploring the effect of training set size and number of categories on ice crystal classification through a contrastive semi-supervised learning algorithm

Fri, 27 Jun 2025 00:00:00 +0800

Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation

Sun, 15 Jun 2025 00:00:00 +0000

MiLNet: Multiplex Interactive Learning Network for RGB-T Semantic Segmentation

Mon, 03 Mar 2025 00:00:00 +0800

1 paper accepted to TIP in 2025.

Sun, 09 Feb 2025 00:00:00 +0000

They are:

MiLNet: Multiplex Interactive Learning Network for RGB-T Semantic Segmentation

Diffusion Schrödinger bridge models for high-quality MR-to-CT synthesis for proton treatment planning

Wed, 01 Jan 2025 00:00:00 +0000

A Prior Causality‐Guided Multi‐View Diffusion Network for Brain Disorder Classification

Wed, 01 Jan 2025 00:00:00 +0800

HYRE: Hybrid Regressor for 3D Human Pose and Shape Estimation

Wed, 25 Dec 2024 00:00:00 +0800

IceDetectNet: a rotated object detection algorithm for classifying components of aggregated ice crystals with a multi-label classification scheme

Thu, 19 Dec 2024 00:00:00 +0800

High Performance Computing Framework for Variable Selection on Genome-wide Association Studies

Tue, 03 Dec 2024 00:00:00 +0800

UVMap-ID: A Controllable and Personalized UV Map Generative Model

Mon, 28 Oct 2024 00:00:00 +0800

Generating Synthetic Computed Tomography for Radiotherapy: SynthRAD2023 Challenge Report

Tue, 01 Oct 2024 00:00:00 +0800

Our work is reported by ESTRO Newletter

Tue, 20 Aug 2024 00:00:00 +0000

One of the 5 works appear in the official ESTRO 2024 Congress report.

With the title: Continuous Motion Modelling for Enhanced Deformable Image Registration in Radiotherapy

A Unified Generation-Registration Framework for Improved MR-based CT Synthesis in Proton Therapy

Tue, 13 Aug 2024 00:00:00 +0000

ICCR 2024 Rising Star Competition

Wed, 10 Jul 2024 09:41:00 +0200

I am awarded the 1st place in the ICCR Rising Star Competition (Oral Presentation)!

Wed, 10 Jul 2024 00:00:00 +0000

Detailed information:

Location: Palais de la Bourse de Lyon
Session: Gala Dinner
Date: 10 July, 19:00-24:00

Neural Graphics Primitives-based Deformable Image Registration for On-the-fly Motion Extraction

Mon, 08 Jul 2024 00:00:00 +0000

ModelNet-O: A large-scale synthetic dataset for occlusion-aware point cloud classification

Wed, 19 Jun 2024 00:00:00 +0800

Neural Clustering based Visual Representation Learning

Mon, 17 Jun 2024 00:00:00 +0800

Projects

Sun, 19 May 2024 00:00:00 +0000

VG4D: Vision-Language Model Goes 4D Video Recognition

Mon, 13 May 2024 00:00:00 +0800

ESTRO 2024 Proffered Paper

Sat, 04 May 2024 09:41:00 +0200

Our submission is selected as an Oral presentation by ICCR 2024!

Fri, 15 Mar 2024 00:00:00 +0000

From ICCR 2024: We are pleased to inform you that your submission “Neural Graphics Primitives-based Deformable Image Registration for On-the-fly Motion Extraction”, X. Li [et al.] (sciencesconf.org:iccr2024:525322) has been accepted for an oral presentation. The detailed program with the duration of each talk along with guidelines will be posted shortly.

Detailed information:

Location: Auditorium Lumière
Session: Rising Stars Competition
Date: 9 July, 09:45-10:00

Towards robust referring image segmentation

Tue, 05 Mar 2024 12:30:06 +0100

Towards open vocabulary learning: A survey

Mon, 05 Feb 2024 12:30:06 +0100

Uncertainty-aware MR-based CT synthesis for robust proton therapy planning of brain tumour

Thu, 01 Feb 2024 00:00:00 +0000

Audio–visual keyword transformer for unconstrained sentence‐level keyword spotting

Thu, 01 Feb 2024 00:00:00 +0800

Group

Mon, 01 Jan 2024 00:00:00 +0000

Students

Mon, 01 Jan 2024 00:00:00 +0000

FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation

Mon, 01 Jan 2024 00:00:00 +0800

Our abstract is selected as a Proffered Paper by ESTRO 2024!

Mon, 18 Dec 2023 00:00:00 +0000

From ESTRO: We are delighted to inform you that the Abstract Review Committee has selected your abstract E24-588 titled “Beyond Voxel-Based Methods: Continuous Motion Modeling for Enhanced Deformable Image Registration” for presentation as a Proffered Paper at ESTRO 2024.

Detailed information:

Track: Physics
Location: Hall 3
Session: Symposium - The art of morphing: Advancements and challenges in deformable image registration for radiotherapy
Date: 4 May 2024, 09:41-09:50

Skeleton-in-context: Unified skeleton sequence modeling with in-context learning

Fri, 15 Dec 2023 21:30:06 +0800

Explore In-Context Learning for 3D Point Cloud Understanding

Sun, 10 Dec 2023 12:30:06 +0100

Advanced Machine Learning

Tue, 24 Oct 2023 00:00:00 +0000

Hugo Blox Builder is designed to give technical content creators a seamless experience. You can focus on the content and the Hugo Blox Builder which this template is built upon handles the rest.

Embed videos, podcasts, code, LaTeX math, and even test students!

On this page, you’ll find some examples of the types of technical content that can be rendered with Hugo Blox.

Video

Teach your course by sharing videos with your students. Choose from one of the following approaches:

Youtube:

{{< youtube w7Ft2ymGmfc >}}

Bilibili:

{{< bilibili id="BV1WV4y1r7DF" >}}

Video file

Videos may be added to a page by either placing them in your assets/media/ media library or in your page’s folder, and then embedding them with the video shortcode:

{{< video src="my_video.mp4" controls="yes" >}}

Podcast

You can add a podcast or music to a page by placing the MP3 file in the page’s folder or the media library folder and then embedding the audio on your page with the audio shortcode:

{{< audio src="ambient-piano.mp3" >}}

Try it out:

Test students

Provide a simple yet fun self-assessment by revealing the solutions to challenges with the spoiler shortcode:

{{< spoiler text="👉 Click to view the solution" >}}
You found me!
{{< /spoiler >}}

renders as

👉 Click to view the solution

You found me 🎉

Math

Hugo Blox Builder supports a Markdown extension for $\LaTeX$ math. You can enable this feature by toggling the math option in your config/_default/params.yaml file.

To render inline or block math, wrap your LaTeX math with {{< math >}}$...${{< /math >}} or {{< math >}}$$...$${{< /math >}}, respectively.

We wrap the LaTeX math in the Hugo Blox math shortcode to prevent Hugo rendering our math as Markdown.

Example math block:

{{< math >}}
$$
\gamma_{n} = \frac{ \left | \left (\mathbf x_{n} - \mathbf x_{n-1} \right )^T \left [\nabla F (\mathbf x_{n}) - \nabla F (\mathbf x_{n-1}) \right ] \right |}{\left \|\nabla F(\mathbf{x}_{n}) - \nabla F(\mathbf{x}_{n-1}) \right \|^2}
$$
{{< /math >}}

renders as

$$\gamma_{n} = \frac{ \left | \left (\mathbf x_{n} - \mathbf x_{n-1} \right )^T \left [\nabla F (\mathbf x_{n}) - \nabla F (\mathbf x_{n-1}) \right ] \right |}{\left \|\nabla F(\mathbf{x}_{n}) - \nabla F(\mathbf{x}_{n-1}) \right \|^2}$$

Example inline math {{< math >}}$\nabla F(\mathbf{x}_{n})${{< /math >}} renders as $\nabla F(\mathbf{x}_{n})$ .

Example multi-line math using the math linebreak (\\):

{{< math >}}
$$f(k;p_{0}^{*}) = \begin{cases}p_{0}^{*} & \text{if }k=1, \\
1-p_{0}^{*} & \text{if }k=0.\end{cases}$$
{{< /math >}}

renders as

$$ f(k;p_{0}^{*}) = \begin{cases}p_{0}^{*} & \text{if }k=1, \\ 1-p_{0}^{*} & \text{if }k=0.\end{cases} $$

Code

Hugo Blox Builder utilises Hugo’s Markdown extension for highlighting code syntax. The code theme can be selected in the config/_default/params.yaml file.

```python
import pandas as pd
data = pd.read_csv("data.csv")
data.head()
```

renders as

import pandas as pd
data = pd.read_csv("data.csv")
data.head()

Inline Images

{{< icon name="python" >}} Python

renders as

Python

Experience

Tue, 24 Oct 2023 00:00:00 +0000

Learn JavaScript

Tue, 24 Oct 2023 00:00:00 +0000

Hugo Blox Builder is designed to give technical content creators a seamless experience. You can focus on the content and the Hugo Blox Builder which this template is built upon handles the rest.

Embed videos, podcasts, code, LaTeX math, and even test students!

On this page, you’ll find some examples of the types of technical content that can be rendered with Hugo Blox.

Video

Teach your course by sharing videos with your students. Choose from one of the following approaches:

Youtube:

{{< youtube w7Ft2ymGmfc >}}

Bilibili:

{{< bilibili id="BV1WV4y1r7DF" >}}

Video file

Videos may be added to a page by either placing them in your assets/media/ media library or in your page’s folder, and then embedding them with the video shortcode:

{{< video src="my_video.mp4" controls="yes" >}}

Podcast

You can add a podcast or music to a page by placing the MP3 file in the page’s folder or the media library folder and then embedding the audio on your page with the audio shortcode:

{{< audio src="ambient-piano.mp3" >}}

Try it out:

Test students

Provide a simple yet fun self-assessment by revealing the solutions to challenges with the spoiler shortcode:

{{< spoiler text="👉 Click to view the solution" >}}
You found me!
{{< /spoiler >}}

renders as

👉 Click to view the solution

You found me 🎉

Math

Hugo Blox Builder supports a Markdown extension for $\LaTeX$ math. You can enable this feature by toggling the math option in your config/_default/params.yaml file.

To render inline or block math, wrap your LaTeX math with {{< math >}}$...${{< /math >}} or {{< math >}}$$...$${{< /math >}}, respectively.

We wrap the LaTeX math in the Hugo Blox math shortcode to prevent Hugo rendering our math as Markdown.

Example math block:

{{< math >}}
$$
\gamma_{n} = \frac{ \left | \left (\mathbf x_{n} - \mathbf x_{n-1} \right )^T \left [\nabla F (\mathbf x_{n}) - \nabla F (\mathbf x_{n-1}) \right ] \right |}{\left \|\nabla F(\mathbf{x}_{n}) - \nabla F(\mathbf{x}_{n-1}) \right \|^2}
$$
{{< /math >}}

renders as

Example inline math {{< math >}}$\nabla F(\mathbf{x}_{n})${{< /math >}} renders as $\nabla F(\mathbf{x}_{n})$ .

Example multi-line math using the math linebreak (\\):

{{< math >}}
$$f(k;p_{0}^{*}) = \begin{cases}p_{0}^{*} & \text{if }k=1, \\
1-p_{0}^{*} & \text{if }k=0.\end{cases}$$
{{< /math >}}

renders as

$$ f(k;p_{0}^{*}) = \begin{cases}p_{0}^{*} & \text{if }k=1, \\ 1-p_{0}^{*} & \text{if }k=0.\end{cases} $$

Code

Hugo Blox Builder utilises Hugo’s Markdown extension for highlighting code syntax. The code theme can be selected in the config/_default/params.yaml file.

```python
import pandas as pd
data = pd.read_csv("data.csv")
data.head()
```

renders as

import pandas as pd
data = pd.read_csv("data.csv")
data.head()

Inline Images

{{< icon name="python" >}} Python

renders as

Python

Betrayed by captions: Joint caption grounding and generation for open vocabulary instance segmentation

Mon, 02 Oct 2023 21:30:06 +0800

Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video

Mon, 02 Oct 2023 21:30:06 +0800

Gator: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Pose

Sun, 04 Jun 2023 00:00:00 +0800

Interweaved Graph and Attention Network for 3D Human Pose Estimation

Sun, 04 Jun 2023 00:00:00 +0800

ESTRO 2023 Mini-Oral

Sat, 13 May 2023 15:15:00 +0200

Our abstract is selected as a Mini-Oral presentation by ESTRO 2023!

Tue, 20 Dec 2022 00:00:00 +0000

From ESTRO: We are delighted to inform you that the Abstract Review Committee has selected your abstract E23-0545 titled “Uncertainty-aware MR-base CT synthesis for robust proton planning of skull-based tumour” for presentation as a Mini-Oral at ESTRO 2023

Detailed information:

Track: Physics
Location: Stolz 2
Session: Image processing and treatment evaluation
Date: 13 May 2023, 15:15-16:15

Optimization induced equilibrium networks: An explicit optimization perspective for understanding equilibrium models

Fri, 10 Jun 2022 12:30:06 +0100

PCLoss: Fashion landmark estimation with position constraint loss

Fri, 01 Oct 2021 12:30:06 +0100

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

Sun, 12 Sep 2021 12:30:06 +0100

Towards efficient scene understanding via squeeze reasoning

Fri, 30 Jul 2021 00:00:00 +0800

Quasi-dense similarity learning for multiple object tracking

Sat, 20 Feb 2021 21:30:06 +0800

PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

Sat, 13 Feb 2021 00:00:00 +0800

Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification

Sat, 12 Dec 2020 12:30:06 +0100

Is Attention Better Than Matrix Decomposition?

Mon, 28 Sep 2020 21:30:06 +0800

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

Fri, 03 Jul 2020 00:00:00 +0800

Position Constraint Loss For Fashion Landmark Estimation

Mon, 04 May 2020 00:00:00 +0800

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

Mon, 24 Feb 2020 00:00:00 +0800

SOGNet: Scene Overlap Graph Network for Panoptic Segmentation

Fri, 07 Feb 2020 09:19:08 +0800

Dynamic System Inspired Adaptive Time Stepping Controller for Residual Networks Families

Fri, 07 Feb 2020 08:33:58 +0800

ICCV 2019 Oral

Fri, 01 Nov 2019 13:35:00 +0800

Self-Refining Deep Symmetry Enhanced Network for Rain Removal

Sun, 22 Sep 2019 00:00:00 +0800

Expectation Maximization Attention Networks for Semantic Segmentation

Mon, 22 Jul 2019 21:30:06 +0800

R^2 Net Recurrent and Recursive Network for Sparse View CT Artifacts Removal

Wed, 19 Jun 2019 21:02:38 +0800

Multi-label classification of PCB defects based on convolutional neural network

Mon, 22 Oct 2018 00:00:00 +0800

Recurrent Squeeze-and-Excitation Net for Single Image Deraining

Thu, 19 Jul 2018 19:54:59 +0800

Xia Li

Comparative evaluation of static and dynamic 4D dose recalculations in pencil beam scanning proton therapy for oesophageal cancer

Contour-informed inter-patient deformable registration for more reliable voxel-based analysis of Head-and-Neck cancer patients

Continuous sPatial-Temporal Deformable Image Registration (CPT-DIR) for motion modelling in radiotherapy: beyond classic voxel-based methods

I am serving as an Area Chair for ICML 2026

2 papers accepted to Medical Physics in 2025.

3 papers accepted to phiRO in 2025.

Enhancing Brain MRI Super-Resolution Through Multi-Slice Aware Matching and Fusion

Gaussian Representation for Deformable Image Registration

A proof-of-concept study of direct magnetic resonance imaging-based proton dose calculation for brain tumors via neural networks with Monte Carlo-comparable accuracy

Exploring the effect of training set size and number of categories on ice crystal classification through a contrastive semi-supervised learning algorithm

Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation

MiLNet: Multiplex Interactive Learning Network for RGB-T Semantic Segmentation

1 paper accepted to TIP in 2025.

Diffusion Schrödinger bridge models for high-quality MR-to-CT synthesis for proton treatment planning

A Prior Causality‐Guided Multi‐View Diffusion Network for Brain Disorder Classification

HYRE: Hybrid Regressor for 3D Human Pose and Shape Estimation

IceDetectNet: a rotated object detection algorithm for classifying components of aggregated ice crystals with a multi-label classification scheme

High Performance Computing Framework for Variable Selection on Genome-wide Association Studies

UVMap-ID: A Controllable and Personalized UV Map Generative Model

Generating Synthetic Computed Tomography for Radiotherapy: SynthRAD2023 Challenge Report

Our work is reported by ESTRO Newletter

A Unified Generation-Registration Framework for Improved MR-based CT Synthesis in Proton Therapy

ICCR 2024 Rising Star Competition

I am awarded the 1st place in the ICCR Rising Star Competition (Oral Presentation)!

Neural Graphics Primitives-based Deformable Image Registration for On-the-fly Motion Extraction

ModelNet-O: A large-scale synthetic dataset for occlusion-aware point cloud classification

Neural Clustering based Visual Representation Learning

Projects

VG4D: Vision-Language Model Goes 4D Video Recognition

ESTRO 2024 Proffered Paper

Our submission is selected as an Oral presentation by ICCR 2024!

Towards robust referring image segmentation

Towards open vocabulary learning: A survey

Uncertainty-aware MR-based CT synthesis for robust proton therapy planning of brain tumour

Audio–visual keyword transformer for unconstrained sentence‐level keyword spotting

Group

Students

FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation

Our abstract is selected as a Proffered Paper by ESTRO 2024!

Skeleton-in-context: Unified skeleton sequence modeling with in-context learning

Explore In-Context Learning for 3D Point Cloud Understanding

Advanced Machine Learning

Video

Podcast

Test students

Math

Code

Inline Images

Did you find this page helpful? Consider sharing it 🙌

Experience

Learn JavaScript

Video

Podcast

Test students

Math

Code

Inline Images

Did you find this page helpful? Consider sharing it 🙌

Betrayed by captions: Joint caption grounding and generation for open vocabulary instance segmentation

Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video

Gator: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Pose

Interweaved Graph and Attention Network for 3D Human Pose Estimation

ESTRO 2023 Mini-Oral

Our abstract is selected as a Mini-Oral presentation by ESTRO 2023!

Optimization induced equilibrium networks: An explicit optimization perspective for understanding equilibrium models

PCLoss: Fashion landmark estimation with position constraint loss

Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation

Towards efficient scene understanding via squeeze reasoning

Quasi-dense similarity learning for multiple object tracking

PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification

Is Attention Better Than Matrix Decomposition?

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

Position Constraint Loss For Fashion Landmark Estimation

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

SOGNet: Scene Overlap Graph Network for Panoptic Segmentation

Dynamic System Inspired Adaptive Time Stepping Controller for Residual Networks Families

ICCV 2019 Oral

Self-Refining Deep Symmetry Enhanced Network for Rain Removal