+
+
-If you like the template of this homepage, welcome to star and fork my open-sourced template version [AcadHomepage ](https://github.com/RayeRen/acad-homepage.github.io).
-
-{% include_relative includes/news.md %}
+
I'm always open to academic discussions, potential collaborations and interdisciplinary projects. Feel free to reach out at: yuhaoshen [at] link [dot] cuhk [dot] edu [dot] cn.
{% include_relative includes/pub.md %}
+{% include_relative includes/news.md %}
+
{% include_relative includes/honers.md %}
-{% include_relative includes/others.md %}
\ No newline at end of file
+{% include_relative includes/others.md %}
diff --git a/_pages/includes/homepage.md b/_pages/includes/homepage.md
index 33e459fe2a..f4c6dc9c07 100644
--- a/_pages/includes/homepage.md
+++ b/_pages/includes/homepage.md
@@ -1,5 +1,5 @@
# 📎 Homepages
-- Personal Pages: https://rayeren.github.io (updated recently🔥)
-- Linkedin: https://www.linkedin.com/in/rayeren
+- Personal Pages: https://yuhos16.github.io (updated recently🔥)
+- Linkedin: https://www.linkedin.com/in/yuhos16
- Google Scholar: https://scholar.google.com/citations?user=4FA6C0AAAAAJ
- DBLP: https://dblp.org/pid/75/6568-6.html
diff --git a/_pages/includes/honers.md b/_pages/includes/honers.md
index 29237503ef..8b13789179 100644
--- a/_pages/includes/honers.md
+++ b/_pages/includes/honers.md
@@ -1,10 +1 @@
-# 🎖 Honors and Awards
-- *2021.10* Tencent Scholarship (Top 1%)
-- *2021.10* National Scholarship (Top 1%)
-- *2020.12* [Baidu Scholarship](https://baike.baidu.com/item/%E7%99%BE%E5%BA%A6%E5%A5%96%E5%AD%A6%E9%87%91/9929412) (10 students in the world each year)
-- *2020.12* [AI Chinese new stars](https://mp.weixin.qq.com/s?__biz=MzA4NzQ5MTA2NA==&mid=2653639431&idx=1&sn=25b6368c1954419b9090840347d9a27d&chksm=8be75b90bc90d286a5af3ef8e610e822d705dc3cf4382b45e3f14489f3e7ec4fd8c95ed0eceb&mpshare=1&scene=2&srcid=0511LMlj9Qv9DeIZAjMjYAU9&sharer_sharetime=1620731348139&sharer_shareid=631c113940cb81f34895aa25ab14422a#rd) (100 worldwide each year)
-- *2020.12* [AI Chinese New Star Outstanding Scholar](https://mp.weixin.qq.com/s?__biz=MzA4NzQ5MTA2NA==&mid=2653639431&idx=1&sn=25b6368c1954419b9090840347d9a27d&chksm=8be75b90bc90d286a5af3ef8e610e822d705dc3cf4382b45e3f14489f3e7ec4fd8c95ed0eceb&mpshare=1&scene=2&srcid=0511LMlj9Qv9DeIZAjMjYAU9&sharer_sharetime=1620731348139&sharer_shareid=631c113940cb81f34895aa25ab14422a#rd) (10 candidates worldwide each year)
-- *2020.12* [ByteDance Scholars Program](https://ur.bytedance.com/scholarship) (10 students in China each year)
-- *2020.10* Tianzhou Chen Scholarship (Top 1%)
-- *2020.10* National Scholarship (Top 1%)
-- *2015.10* National Scholarship (Undergraduate) (Top 1%)
\ No newline at end of file
+
diff --git a/_pages/includes/intro.md b/_pages/includes/intro.md
index 59edbf7745..24a4ab2745 100644
--- a/_pages/includes/intro.md
+++ b/_pages/includes/intro.md
@@ -1,9 +1,22 @@
-I am now working on audio-driven video generation and text-to-speech research. If you are seeking any form of **academic cooperation**, please feel free to email me at [rayeren613@gmail.com](mailto:rayeren613@gmail.com). We are hiring interns!
-I graduated from [Chu Kochen Honors College](http://ckc.zju.edu.cn/ckcen/main.htm), Zhejiang University (浙江大学竺可桢学院) with a bachelor's degree and from the Department of Computer Science and Technology, Zhejiang University (浙江大学计算机科学与技术学院) with a master's degree, advised by [Zhou Zhao (赵洲)](https://person.zju.edu.cn/zhaozhou). I also collaborate with [Xu Tan (谭旭)](https://www.microsoft.com/en-us/research/people/xuta/), [Tao Qin (秦涛)](https://www.microsoft.com/en-us/research/people/taoqin/) and [Tie-yan Liu (刘铁岩)](https://www.microsoft.com/en-us/research/people/tyliu/) from [Microsoft Research Asia](https://www.microsoft.com/en-us/research/group/machine-learning-research-group/) closely.
+
M.Phil Student in Computer Science
+School of Data Science
+The Chinese University of Hong Kong, Shenzhen
-I won the [Baidu Scholarship](https://baike.baidu.com/item/%E7%99%BE%E5%BA%A6%E5%A5%96%E5%AD%A6%E9%87%91/9929412) (10 candidates worldwide each year) and [ByteDance Scholars Program](https://ur.bytedance.com/scholarship) (10 candidates worldwide each year) in 2020 and was selected as one of [the top 100 AI Chinese new stars](https://mp.weixin.qq.com/s?__biz=MzA4NzQ5MTA2NA==&mid=2653639431&idx=1&sn=25b6368c1954419b9090840347d9a27d&chksm=8be75b90bc90d286a5af3ef8e610e822d705dc3cf4382b45e3f14489f3e7ec4fd8c95ed0eceb&mpshare=1&scene=2&srcid=0511LMlj9Qv9DeIZAjMjYAU9&sharer_sharetime=1620731348139&sharer_shareid=631c113940cb81f34895aa25ab14422a#rd) and AI Chinese New Star Outstanding Scholar (10 candidates worldwide each year).
+
-My research interest includes speech synthesis, neural machine translation and automatic music generation. I have published 50+ papers at the top international AI conferences such as NeurIPS, ICML, ICLR, KDD.
-To promote the communication among the Chinese ML & NLP community, we (along with other 11 young scholars worldwide) founded the [MLNLP community](https://space.bilibili.com/168887299) in 2021. I am honored to be one of the chairs of the MLNLP committee.
+Hello! I’m Yuhao. My primary research interest is **AI for Healthcare**. As a member of the HEAL Group, I’m fortunate to work under the supervision of [Prof. Juexiao Zhou](https://www.joshuachou.ink/about/). My current work centers on the following three areas:
+
+
Medical LLMs & Agents
+
LLM Reasoning & Reinforcement learning
+
Medical Imaging & Computer Vision
+
+
diff --git a/_pages/includes/news.md b/_pages/includes/news.md
index 62d6068b15..d4040cde9f 100644
--- a/_pages/includes/news.md
+++ b/_pages/includes/news.md
@@ -1,6 +1,3 @@
# 🔥 News
-- *2024.03*: 🎉 Two papers are accepted by ICLR 2024
-- *2023.05*: 🎉 Five papers are accepted by ACL 2023
-- *2023.01*: DiffSinger was introduced in [a very popular video](https://www.bilibili.com/video/BV1uM411t7ZJ) (2000k+ views) in Bilibili!
-- *2023.01*: I join TikTok as a speech research scientist in Singapore!
-- *2022.02*: I release a modern and responsive academic personal [homepage template](https://github.com/RayeRen/acad-homepage.github.io). Welcome to STAR and FORK!
\ No newline at end of file
+- *2025.06*: I graduated from Hangzhou Dianzi University as an outstanding graduate.
+- *2025.05*: I officially joined the [HEAL Group](https://www.joshuachou.ink/about/) as an MPhil student.
diff --git a/_pages/includes/others.md b/_pages/includes/others.md
index 0d810f2353..b0f123164f 100644
--- a/_pages/includes/others.md
+++ b/_pages/includes/others.md
@@ -1,19 +1,9 @@
-# 📖 Educations
-- *2019.06 - 2022.04*, Master, Zhejiang University, Hangzhou.
-- *2015.09 - 2019.06*, Undergraduate, Chu Kochen Honors College, Zhejiang Univeristy, Hangzhou.
-- *2012.09 - 2015.06*, Luqiao Middle School, Taizhou.
+# 📖 Education
+- *2025.09 - Present:* M.Phil Student in Computer Science, School of Data Science, The Chinese University of Hong Kong, Shenzhen.
+- *2021.09 - 2025.06:* B.Eng. in Computer Science and Technology, School of Computer Science, Hangzhou Dianzi University, Hangzhou.
-# 💬 Invited Talks
-- *2022.02*, Hosted MLNLP seminar \| [\[Video\]](https://www.bilibili.com/video/BV1wF411x7qh)
-- *2021.06*, Audio & Speech Synthesis, Huawei internal talk
-- *2021.03*, Non-autoregressive Speech Synthesis, PaperWeekly & biendata \| [\[video\]](https://www.bilibili.com/video/BV1uf4y1t7Hr/)
-- *2020.12*, Non-autoregressive Speech Synthesis, Huawei Noah's Ark Lab internal talk
-
-# 💻 Internships
-- *2021.06 - 2021.09*, Alibaba, Hangzhou.
-- *2019.05 - 2020.02*, [EnjoyMusic](https://enjoymusic.ai/), Hangzhou.
-- *2019.02 - 2019.05*, [YiWise](https://www.yiwise.com/), Hangzhou.
-- *2018.08 - 2019.02*, [MSRA, machine learning Group](https://www.microsoft.com/en-us/research/group/machine-learning-research-group/), Beijing.
-- *2018.01 - 2018.06*, [NetEase, AI department](https://hr.163.com/zc/12-ai/index.html), Hangzhou.
-- *2017.08 - 2018.12*, DashBase (acquired by [Cisco](https://blogs.cisco.com/news/349511)), Hangzhou.
+# 💻 Internship
+- *2025.03 - 2025.05:* Reasearch Assistant, The Chinese University of Hong Kong, Shenzhen.
+- *2024.12 - 2025.02:* Algorithm Engineer, Hangzhou Huaxin Mechanical and Electrical Engineering Co., Ltd, Hangzhou.
+- *2023.07 - 2023.09:* Reasearch Assistant, Hangzhou Institute of Technology of Xidian University, Hangzhou.
diff --git a/_pages/includes/pub.md b/_pages/includes/pub.md
index e5c8f61622..bfb1f59f3e 100644
--- a/_pages/includes/pub.md
+++ b/_pages/includes/pub.md
@@ -1,136 +1,53 @@
-
-# 📝 Publications
-## 🎙 Speech Synthesis
-
-
-
NeurIPS 2019
+# 📚 Publication
+*# Equal Contribution*
+
+
Under Review
-[FastSpeech: Fast, Robust and Controllable Text to Speech](https://papers.nips.cc/paper/8580-fastspeech-fast-robust-and-controllable-text-to-speech.pdf) \\
-**Yi Ren**, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu
+[Trustworthy and Fair SkinGPT-R1 for Democratizing Dermatological Reasoning across Diverse Ethnicities](https://arxiv.org/abs/2511.15242) \\
+**Yuhao Shen**, Zhangtianyi Chen, Yuanhao He, Yan Xu, Shuping Zhang, Liyuan Sun, Zijian Wang, Yinghao Zhu, Yuyuan Yang, Jiahe Qian, Ziwen Wang, Xinyuan Zhang, Wenbin Liu, Zongyuan Ge, Tao Lu, Siyuan Yan, Juexiao Zhou
-[**Project**](https://speechresearch.github.io/fastspeech/)
-
-- FastSpeech is the first fully parallel end-to-end speech synthesis model.
-- **Academic Impact**: This work is included by many famous speech synthesis open-source projects, such as [ESPNet ](https://github.com/espnet/espnet). Our work are promoted by more than 20 media and forums, such as [机器之心](https://mp.weixin.qq.com/s/UkFadiUBy-Ymn-zhJ95JcQ)、[InfoQ](https://www.infoq.cn/article/tvy7hnin8bjvlm6g0myu).
-- **Industry Impact**: FastSpeech has been deployed in [Microsoft Azure TTS service](https://techcommunity.microsoft.com/t5/azure-ai/neural-text-to-speech-extends-support-to-15-more-languages-with/ba-p/1505911) and supports 49 more languages with state-of-the-art AI quality. It was also shown as a text-to-speech system acceleration example in [NVIDIA GTC2020](https://resources.nvidia.com/events/GTC2020s21420).
+- Introduce **SkinGPT-R1**, a dermatology VLM that achieves interpretable and equitable diagnosis across diverse ethnicities by performing explicit, step-by-step, and verifiable diagnostic chain-of-thought reasoning.
+
-
-
ICLR 2021
+
Under Review
-[FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://arxiv.org/abs/2006.04558) \\
-**Yi Ren**, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu
-
-[**Project**](https://speechresearch.github.io/fastspeech2/)
- - This work is included by many famous speech synthesis open-source projects, such as [PaddlePaddle/Parakeet ](https://github.com/PaddlePaddle/PaddleSpeech), [ESPNet ](https://github.com/espnet/espnet) and [fairseq ](https://github.com/pytorch/fairseq).
-
-
-
+[SkinCaRe: A Multimodal Dermatology Dataset Annotated with Medical Caption and Chain-of-Thought Reasoning](https://arxiv.org/abs/2405.18004) [Dataset] \\
+**Yuhao Shen#**, Liyuan Sun#, Yan Xu#, Wenbin Liu#, Shuping Zhang#, Shawn Afvari, Zhongyi Han, Jiaoyan Song, Yongzhi Ji, Tao Lu, Xiaonan He, Xin Gao, Juexiao Zhou
-
ICLR 2024
-
-
-[Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis](https://openreview.net/forum?id=mvMI3N4AvD) \\
-Ziyue Jiang, Jinglin Liu, **Yi Ren**, et al.
+
-[**Project**](https://boostprompt.github.io/boostprompt/)
- - This work has been deployed on many TikTok products.
- - Advandced zero-shot voice cloning model.
+- Release **SkinCaRe**, unifying SkinCAP (medical captions) and SkinCoT (clinician-verified chains-of-thought) for transparent dermatologic reasoning.
+
-
AAAI 2022
+
Under Review
-[DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://arxiv.org/abs/2105.02446) \\
-Jinglin Liu, Chengxi Li, **Yi Ren**, Feiyang Chen, Zhou Zhao
+[Towards Trustworthy Dermatology MLLMs: A Benchmark and Multimodal Evaluator for Diagnostic Narratives](https://arxiv.org/abs/2511.09195) \\
+**Yuhao Shen#**, Jiahe Qian#, Shuping Zhang#, Zhangtianyi Chen, Tao Lu, Juexiao Zhou*
-- Many [video demos](https://www.bilibili.com/video/BV1be411N7JA) created by the [DiffSinger community](https://github.com/openvpi) are released.
-- DiffSinger was introduced in [a very popular video](https://www.bilibili.com/video/BV1uM411t7ZJ) (1600k+ views) on Bilibili!
+
-- [**Project**](https://diffsinger.github.io/) \| [](https://github.com/NATSpeech/NATSpeech) \| [](https://github.com/MoonInTheRiver/DiffSinger) \| [](https://huggingface.co/spaces/NATSpeech/DiffSpeech)
+- Propose **DermBench** (six clinical dimensions) and **DermEval** (reference-free evaluator) for image–text dermatology reasoning aligned with physician scoring.
+
-
-
NeurIPS 2021
+
Under Review
-[PortaSpeech: Portable and High-Quality Generative Text-to-Speech](https://arxiv.org/abs/2109.15166) \\
-**Yi Ren**, Jinglin Liu, Zhou Zhao
+[CoTBox-TTT: Grounding Medical VQA with Visual Chain-of-Thought Boxes During Test-time Training](https://arxiv.org/abs/2511.12446) \\
+Jiahe Qian#, **Yuhao Shen#**, Zhangtianyi Chen, Juexiao Zhou, Peisong Wang
-[**Project**](https://portaspeech.github.io/) \| [](https://github.com/NATSpeech/NATSpeech) \| [](https://huggingface.co/spaces/NATSpeech/PortaSpeech)
-
-
-
-- `AAAI 2024` [Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling](https://arxiv.org/abs/2312.11947), Rui Liu, Yifan Hu, **Yi Ren**, et al. [](https://github.com/walker-hyf/ECSS)
-- ``ICML 2023`` [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://text-to-audio.github.io/paper.pdf), Rongjie Huang, Jiawei Huang, Dongchao Yang, **Yi Ren**, et al.
-- ``ACL 2023`` [CLAPSpeech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-Training](), Zhenhui Ye, Rongjie Huang, **Yi Ren**, et al.
-- ``ACL 2023`` [FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Models](), Ziyue Jiang, Qian Yang, Jialong Zuo, Zhenhui Ye, Rongjie Huang, **Yi Ren** and Zhou Zhao
-- ``ACL 2023`` [Revisiting and Incorporating GAN and Diffusion Models in High-Fidelity Speech Synthesis](), Rongjie Huang, **Yi Ren**, Ziyue Jiang, et al.
-- ``ACL 2023`` [Improving Prosody with Masked Autoencoder and Conditional Diffusion Model For Expressive Text-to-Speech](), Rongjie Huang, Chunlei Zhang, **Yi Ren**, et al.
-- `ICLR 2023` [Bag of Tricks for Unsupervised Text-to-Speech](https://openreview.net/forum?id=SbR9mpTuBn), **Yi Ren**, Chen Zhang, Shuicheng Yan
-- `INTERSPEECH 2023` [StyleS2ST: zero-shot style transfer for direct speech-to-speech translation](https://arxiv.org/abs/2305.17732), Kun Song, **Yi Ren**, Yi Lei, et al.
-- `INTERSPEECH 2023` [GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech](https://arxiv.org/abs/2306.15304), Yahuan Cong, Haoyu Zhang, Haopeng Lin, Shichao Liu, Chunfeng Wang, **Yi Ren**, et al.
-- `NeurIPS 2022` [Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech](), Ziyue Jiang, Zhe Su, Zhou Zhao, Qian Yang, **Yi Ren**, et al. [](https://github.com/Zain-Jiang/Dict-TTS)
-- `NeurIPS 2022` [GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech](), Rongjie Huang, **Yi Ren**, et al.
-- `NeurIPS 2022` [M4Singer: a Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus](), Lichao Zhang, Ruiqi Li, Shoutong Wang, Liqun Deng, Jinglin Liu, **Yi Ren**, et al. *(Datasets and Benchmarks Track)* [](https://github.com/M4Singer/M4Singer)
-- ``ACM-MM 2022`` [ProDiff: Progressive Fast Diffusion Model for High-Quality Text-to-Speech](), Rongjie Huang, Zhou Zhao, Huadai Liu, Jinglin Liu, Chenye Cui, **Yi Ren**, [](https://github.com/Rongjiehuang/ProDiff)
-- ``ACM-MM 2022`` [SingGAN: Generative Adversarial Network For High-Fidelity Singing Voice Generation](https://arxiv.org/abs/2110.07468), Rongjie Huang, Chenye Cui, Chen Feiayng, **Yi Ren**, et al.
-- ``IJCAI 2022`` [SyntaSpeech: Syntax-Aware Generative Adversarial Text-to-Speech](), Zhenhui Ye, Zhou Zhao, **Yi Ren**, et al. [](https://github.com/yerfor/SyntaSpeech)
-- ``IJCAI 2022`` (Oral) [EditSinger: Zero-Shot Text-Based Singing Voice Editing System with Diverse Prosody Modeling](), Lichao Zhang, Zhou Zhao, **Yi Ren**, et al.
-- ``IJCAI 2022`` [FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis](), Rongjie Huang, Max W. Y. Lam, Jun Wang, Dan Su, Dong Yu, **Yi Ren**, Zhou Zhao, (Oral), [](https://github.com/Rongjiehuang/FastDiff)
-- ``NAACL 2022`` [A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation](), Kexun Zhang, Rui Wang, Xu Tan, Junliang Guo, **Yi Ren**, et al.
-- ``ACL 2022`` [Revisiting Over-Smoothness in Text to Speech](https://arxiv.org/abs/2202.13066), **Yi Ren**, Xu Tan, Tao Qin, et al.
-- ``ACL 2022`` [Learning the Beauty in Songs: Neural Singing Voice Beautifier](https://arxiv.org/abs/2202.13277), Jinglin Liu, Chengxi Li, **Yi Ren**, et al. \| [](https://github.com/MoonInTheRiver/NeuralSVB)
-- ``ICASSP 2022`` [ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech](https://prosospeech.github.io/), **Yi Ren**, et al.
-- ``INTERSPEECH 2021`` [EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model](https://arxiv.org/abs/2106.09317), Chenye Cui, **Yi Ren**, et al.
-- ``INTERSPEECH 2021`` (best student paper award candidate) [WSRGlow: A Glow-based Waveform Generative Model for Audio Super-Resolution](https://arxiv.org/abs/2106.08507), Kexun Zhang, **Yi Ren**, Changliang Xu and Zhou Zhao
-- ``ICASSP 2021`` [Denoising Text to Speech with Frame-Level Noise Modeling](https://arxiv.org/abs/2012.09547), Chen Zhang, **Yi Ren**, Xu Tan, et al. \| [**Project**](https://speechresearch.github.io/denoispeech/)
-- ``ACM-MM 2021`` [Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus](https://arxiv.org/pdf/2112.10358), Rongjie Huang, Feiyang Chen, **Yi Ren**, et al. (Oral)
-- ``IJCAI 2021`` [FedSpeech: Federated Text-to-Speech with Continual Learning](https://www.ijcai.org/proceedings/2021/527), Ziyue Jiang, **Yi Ren**, et al.
-- ``KDD 2020`` [DeepSinger: Singing Voice Synthesis with Data Mined From the Web](https://dl.acm.org/doi/abs/10.1145/3394486.3403249), **Yi Ren**, Xu Tan, Tao Qin, et al. \| [**Project**](https://speechresearch.github.io/deepsinger/)
-- ``KDD 2020`` [LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition](https://dl.acm.org/doi/abs/10.1145/3394486.3403331), Jin Xu, Xu Tan, **Yi Ren**, et al. \| [**Project**](https://speechresearch.github.io/lrspeech/)
-- ``INTERSPEECH 2020`` [MultiSpeech: Multi-Speaker Text to Speech with Transformer](https://www.isca-speech.org/archive/Interspeech_2020/pdfs/3139.pdf), Mingjian Chen, Xu Tan, **Yi Ren**, et al. \| [**Project**](https://speechresearch.github.io/multispeech/)
-- ``ICML 2019`` (Oral) [Almost Unsupervised Text to Speech and Automatic Speech Recognition](https://pdfs.semanticscholar.org/9075/a3e6271e5ef4953491488d1776527e632408.pdf), **Yi Ren**, Xu Tan, Tao Qin, et al. \| [**Project**](https://speechresearch.github.io/unsuper/)
-
-## 👄 TalkingFace & Avatar
-
-
ICLR 2024
-
+
-[Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis](https://openreview.net/forum?id=7ERQPyR2eb), Zhenhui Ye, Tianyun Zhong, Yi Ren, et al. (Spotlight) [**Project**](https://real3dportrait.github.io/) | [**Code**](https://github.com/yerfor/Real3DPortrait)
+- Evidence-first **test-time training** with all backbones frozen; update a small set of continuous soft prompts guided by **visual chain-of-thought boxes**.
+