We are seeking self-motivated PhD students or outstanding master students for research internships focused on Foundation Model Architecture. Feel free to contact us.

About Me

I am an Artificial Intelligence Research Fellow with DeepLearning Lab at Ant Research Institute, which is under the leadership of CTO Zhengyu He. My research benefits from collaboration with esteemed colleagues including Dr. Jianguo Li, Dr. Yaohui Li, Dr. Zhangxuan Gu, Dr. Yan Hong, and Scientist Zhuoer Xu.

I pursued my M.E. in Automation and Artificial Intelligence Group at Nanjing University (NJU), where I was mentored by Prof. Chunlin Chen and Prof. Huaxiong Li. My B.E. was obtained at Southeast University (SEU). Currently, I focus on foundation model architecture and long-horizon multimodal agentic reasoning.

News

  • [Sep. 2026] We released our newest GUI agent model UIVenus2.0.
  • [Aug. 2026] One paper on "LLM upcycling" is accepted to EMNLP 2026 as Findings presentation.
  • [June 2026] One paper on "Parameter-efficient fine-tuning" is accepted to IJCV.
  • [April 2026] We released our first dLLM-based unify model LLaDA2.0-Uni.
  • [April 2026] One paper on "AI-Generated video detection" is accepted to SCIS.
  • [Mar. 2026] I am honored to be selected for the Doctoral/Master’s Thesis Incentive Program by the Chinese Institute of Electronics.
  • [Feb. 2026] One paper on "test-time scaling UniDLLM" is accepted to CVPR 2026.
  • [Jan. 2026] One paper on "Reasoning LLM" is accepted to ICLR 2026.
  • [Aug. 2025] One paper on "Test-time adaptation" is accepted to EMNLP 2025.
  • [July 2025] Two papers on "Human interaction animation / AI-Generated image detection " is accepted to ACM MM 2025.
  • [July 2025] One paper on "VLM adaptation" is accepted to IEEE TCSVT.
  • [May 2025] One paper on "Vision mamba" is accepted to ICML 2025.
  • [Mar. 2025] Joined the DeepLearning Lab at Ant Research Institute for AGI research.
  • [Feb. 2025] One paper on "VLM adaptation" is accepted to CVPR 2025.
  • [Dec. 2024] One paper on "AI-Generated image detection" is accepted to AAAI 2025 as Oral presentation.
  • [July 2024] One paper on "Multi-view clustering" is accepted to Pattern Recognition.
  • [July 2024] We showcased our achievements at WAIC.
  • [July 2024] One paper on "Diffusion models" is accepted to ECCV 2024.
  • [Dec. 2023] Two papers on "Image composition / Diffusion models" are accepted to ICASSP 2024.
  • [Sep. 2023] One paper on "Diffusion models" is accepted to NeurIPS 2023.
  • [Aug. 2023] Won 2nd place (2/717) in AFAC Competition.
  • [July 2023] One paper on "Image composition" is accepted to ACM MM 2023 as Oral presentation.
  • [April 2023] One paper on "Self-supervised learning" is accepted to ICML 2023.
  • [Mar. 2023] Won 3rd place (3/1267) in ICDAR Competition.
  • [Feb. 2023] One paper on "GUI element detection" is accepted to CVPR 2023.
  • [Jan. 2023] One paper on "Few-shot learning" is accepted to SCIS.
  • [July 2022] One paper on "Image aesthetics assessment" is accepted to ACM MM 2022.

Research Interest

I work in the field of Large Language Models (LLMs) and Unified Multimodal Large Models (UMMs). Currently, I focus on the following research topics:

Foundation Model Architecture

Exploring next-generation Large Language Models (LLMs) and Multimodal Large Models (MLLMs) with enhanced efficiency and unified architectures. My research focuses on architectural innovations to enable parameter-efficient scaling, dynamic computation, and cross-modal unification, supporting diverse real-world applications.

Long-Horizon Multimodal Agentic Reasoning

Focusing on long-horizon multimodal agents capable of sustained planning, reasoning, and interaction. My research centers on agentic design for robust multi-step decision-making, GUI Agents that perceive and operate in digital environments, and agentic image generation and editing through iterative visual understanding, tool use, and refinement.

Experiences

AI Researcher | AGI Center, Ant Research Institute

Mar 2025 – Present

AI Researcher | Tiansuan Lab, Ant Group

May 2022 – Mar 2025

Master Student | Nanjing University

Sep 2020 – June 2023. Advisor: Prof. Chunlin Chen and Prof. Huaxiong Li

Undergraduate Student | Southeast University

Sep 2016 – June 2020

Selected Publications Google Scholar DBLP

Tech Report Publications

LLaDA2Uni
UI-Venus-2 Technical Report
Zhuohan Cai, Haoxing Chen, Jiaxuan Chen, et al.
arXiv 2609.00028, 2026.
PaperModelsCode
LLaDA2Uni
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Haoxing Chen, Yi Xin, Qi Qin, et al.
arXiv 2604.20796, 2026.
PaperModelsCode
GroveMoE
Grove MoE: Towards Efficient and Superior MoE LLMs with Adjugate Experts
Haoyuan Wu#, Haoxing Chen#*, Xiaodong Chen#, Zhanchao Zhou#, Tieyuan Chen#, et al.
EMNLP 2026 CCF-B
PaperModelsCode
MultiEdit
MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks
Mingsong Li, Lin Liu, Hongjun Wang, Haoxing Chen, et al.
arXiv 2509.14638, 2025.
PaperDatasets
Lumina-DiMOO
Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
Yi Xin, Qi Qin, ... Haoxing Chen, ... et al.
arXiv 2510.06308, 2025.
PaperModelsCode

Top Conference / Journal Publications

demamba
Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark
Yi Xin, Jianjiang Yang, Siqi Luo, ... Haoxing Chen, et al.
International Journal of Computer Vision 2026 CCF-A IF: 9.7
PaperCodeBenchmark
demamba
DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark
Haoxing Chen, Yan Hong, Zizheng Huang, et al.
Sci. China Inf. Sci. 2026 CCF-A IF: 7.6
PaperCode
dMLLM-TTS
dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models
Yi Xin, Siqi Luo, Qi Qin, Haoxing Chen, et al.
CVPR 2026 CCF-A
Paper
DND
DND: Boosting Large Language Models with Dynamic Nested Depth
Tieyuan Chen, Xiaodong Chen, Haoxing Chen, Zhenzhong Lan, Weiyao Lin, Jianguo Li.
ICLR 2026CCF-A
Paper
EMNLP
Dynamic Model-bank Test-time Adaptation for Automatic Speech Recognition
Yanshuo Wang, Yanghao Zhou, Yukang Lin, Haoxing Chen, et al.
EMNLP 2025 CCF-B
Paper
Explainable AIGC
Towards Explainable Fake Image Detection with Multi-Modal Large Language Models
Yikun Ji, Yan Hong, Jiahui Zhan, Haoxing Chen, et al.
ACM MM 2025 CCF-A
Paper
InterAnimate
InterAnimate: Taming Region-aware Diffusion Model for Realistic Human Interaction Animation
Yukang Lin, Yan Hong, ... Haoxing Chen, et al.
ACM MM 2025 CCF-A
Paper
CPR
Conditional Prototype Rectification Prompt Learning
Haoxing Chen, Yaohui Li, Zizheng Huang, et al.
IEEE TCSVT 2025 CCF-B IF: 11.1
PaperCode
ShuffleMamba
Stochastic Layer-Wise Shuffle: A Good Practice to Improve Vision Mamba Training
Zizheng Huang, Haoxing Chen, et al.
ICML 2025 CCF-A
PaperCode
MSTA
Efficient Transfer Learning for Video-language Foundation Models
Haoxing Chen, Zizheng Huang, Yan Hong, et al.
CVPR 2025 CCF-A
Paper
WildFake
WildFake: A Large-scale Challenging Dataset for AI-Generated Images Detection
Yan Hong, Jianming Feng, Haoxing Chen, et al.
AAAI 2025 CCF-A Oral
Data
PR2024
Learning Latent Distangled Embeddings and Graphs for Multi-view Clustering
Chao Zhang, Haoxing Chen, Huaxiong Li, Chunlin Chen.
Pattern Recognition 2024 CCF-B IF: 7.5
Paper
ComFusion
ComFusion: Personalized Subject Generation in Multiple Specific Scenes From Single Image
Yan Hong, Yuxuan Duan, Bo Zhang, Haoxing Chen, et al.
ECCV 2024 CCF-B
SRIN
Segment Anything Model Meets Image Harmonization
Haoxing Chen, Yaohui Li, Zhangxuan Gu, et al.
ICASSP 2024 CCF-B
PaperarXivBibTeX
DiffusionInst
DiffusionInst: Diffusion Model for Instance Segmentation
Zhangxuan Gu, Haoxing Chen, et al.
ICASSP 2024 CCF-B Oral
PaperarXivCodeCode (Ant)
DiffUTE
DiffUTE: Universal Text Editing Diffusion Model
Haoxing Chen, Zhuoer Xu, Zhangxuan Gu, et al.
NeurIPS 2023 CCF-A
PaperarXivCodeVideo
HDNet
Hierarchical Dynamic Image Harmonization
Haoxing Chen, Zhangxuan Gu, Yaohui Li, et al.
ACM MM 2023 CCF-A Oral
PaperarXivCode
MACL
Model-Aware Contrastive Learning: Towards Escaping the Dilemmas
Zizheng Huang#, Haoxing Chen#*, et al.
ICML 2023 CCF-A
PaperarXivCode
SSFormer
Sparse Spatial Transformers for Few-Shot Learning
Haoxing Chen, Huaxiong Li, Yaohui Li, Chunlin Chen.
Sci. China Inf. Sci. 2023 CCF-A IF: 8.8
PaperSCIS LinkCode
APT
Mobile User Interface Element Detection Via Adaptively Prompt Tuning
Zhangxuan Gu, Zhuoer Xu, Haoxing Chen, et al.
CVPR 2023 CCF-A
PaperCode
TAPP
Transductive Aesthetic Preference Propagation for Personalized Image Aesthetics Assessment
Yaohui Li, Yuzhe Yang, Huaxiong Li, Haoxing Chen, et al.
ACM MM 2022 CCF-A
PaperBibTeX

Awards

Services

  • ICLR'25, ICCV'25, CVPR'25, ICME'25, ICML'24/25, NeurIPS'24, WACV'24, ACM MM'23/24, AAAI'23/25, PAKDD'22, ICPR'22, Reviewer
  • IEEE Trans on TIP/TCYB/TMM/TNNLS/TCSVT, Reviewer