| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Mon, 24 Nov 2025 20:28:59 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"6924c00b-b830"
expires: Mon, 29 Dec 2025 14:12:15 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 0C7A:292AC1:8E8EAC:9FF9F5:695289E7
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 16:03:36 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210072-BOM
x-cache: HIT
x-cache-hits: 0
x-timer: S1767024216.457741,VS0,VE202
vary: Accept-Encoding
x-fastly-request-id: 065ed6ed33838f51067d4bdbea82909d575c5e02
content-length: 10474
TACO-Group@TAMU
Faculty
Dr. Zhengzhong Tu is currently an Assistant Professor in the Department of Computer Science and Engineering at Texas A&M University, College Station, TX, USA.
He is the director of the Trustworthy, Autonomous, Human-Centered, and Embodied Intelligence Group (TACO-Group) at TAMU.
Contact: tzz [AT] tamu [.] edu
Headline
-
Prof. Tu has broad research interests spanning from trustworthy machine learning, multimodal and generative AI, autonomous driving systems, to embodied AI, machine learning system. We pick the following papers that represent our recent flavors. The list will change over time:
- [Multimodal Agents for Vision-Centric Tasks, NeurIPS 2025]
- [High-Res Video Generation, ICLR 2025]
- [Scalable & Secure V2X Systems, ICLR 2025]
- [VLM Post-Training Alignment, EMNLP 2025]
- [Trustworthy VLMs for Autonomous Driving, Arxiv 2024]
- [Language-driven Image Editing, ECCV 2024]
- [Conditional Diffusion Distillation, CVPR 2024]
Please check the Research tab for details of research in our lab.
Follow @TACO-Group
🚧 I am looking for highly motivated students, in terms of RA / TA / internship / visiting students. Interested candidates are strongly encouraged to contact me by email: tzzhire[AT]gmail[.]com or fill out the Google forms. Check out more detailed here.
Tweets
Tweets by _vztuPI & Research Interest
Dr. Tu received his Ph.D. degree under the supervision of Prof. Alan C. Bovik in Electrical and Computer Engineering from The University of Texas at Austin, Austin, TX, USA, in 2022 Summer. Afterward, he worked at Google Research on computational imaging and generative models. He has been involved in multiple product through interning at Google Research, Pixel Camera, and YouTube team. Dr. Tu has authored 30+ peer-reviewed international journal/conference papers in related areas. He has received Best Paper Nomination Award at CVPR 2022, won the First Place at the AI4Streaming Video Quality Challenge held at CVPR 2024, been acknowledged with highlights in Google Research's Annual Blog, and featuring in Google I/O media outlets. He served as technical reviewers for over 18+ international journals/conferences, such as IEEE TPAMI, IJCV, TIP, TCSVT, TMM, TCI, TSTSP, RA-Letters, IROS, ICRA, NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, WACV, ICIP, VCIP, ISCAS, etc.
Our group at Texas A&M University strives to explore cutting-edge generative and multimodal AI technologies, including core data generation, modeling, and alignment, as well as their domain-specific adaptations on real-world applications, such as autonomous vehicles/mobility, robotics, and healthcare.News
[Nov 2025]
- CyPortQA was selected as Oral Presentation. Cheers!
- 2x AAAI 2026 accepted. Cheers!
- （AISI Track) CyPortQA: Benchmarking Multimodal Large Language Models for Cyclone Preparedness in Port Operation
- （Demo Track) DreamLand: Real-Time Interactive 4D Scene Generation
- 1x TMLR'2025 accepted. Cheers!
- Dr. Tu gives keynote talks at 2COOOL and X-Sense workshop with ICCV 2025.
- Dr. Tu gave an invited talk at UC Merced.
- Dr. Tu was selected in the Stanford/Elsevier Top 2% Scientists List 2025!
- 2x NeurIPS'2025 accepted. Cheers!
- 4KAgent: agentic any image to 4K super-resolution
- DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
- Grateful to receive the 2025 Nvidia Academic Grant Award!
- Dr. Tu gave multiple invited talks at GMU, UMD, and UDel
- Dr. Tu will serve as Area Chair for ICLR 2026!
- 1x EMNLP'2025 (Main Track) accepted. Cheers!
- Dr. Tu gave an invited talk at Meta!
- Dr. Tu gave an invited talk at Berkeley Agentic AI Summit!
- Dr. Tu joins the Video Quality Expert Group (VQEG) board as a co-chair in Subjective and objective assessment of GenAI content (SOGAI)
- Dr. Tu starts to serve as Associate Editor for the prestigious IEEE Transactions on Image Processing!
- Dr. Tu will serve as AC for WACV 2026! See you again in Tuscon, AZ!
- 2x IROS'2025 accepted. Cheers!
- CoMamba: Real-time Cooperative Perception Unlocked with State Space Models
- CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perception
- Dr. Tu will attend CVPR 2025 in Nashville TN!
- Dr. Tu will co-organize the CVPR 2025 Workshop on Distillation of Foundation Models for Autonomous Driving
- Dr. Tu will co-organize the CVPR 2025 MetaFood Workshop.
- Dr. Tu will give an invited talk at Google XR at Mountain View, CA!
- Dr. Tu will attend ICRA 2025 in Atlanta, GA!
- Dr. Tu will attend VQEG 2025 Meeting hosted by Meta in Menlo Park, CA!
- Dr. Tu will give an invited talk at UC Davis!
- Dr. Tu gave an invited talk at Samsung Research America (SRA) in Dallas!
- 0x ICML'2025 accepted. No xixi :(
- Our team (TACO-SR) has won the 1st place on the NTIRE 2025 Challnege on Short-Form UGC Video Quality Assessment and Enhancement (Track 2: KwaiSR)!
- NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
- Dr. Tu will serve as an Area Chair for NeurIPS 2025, at your service!
- Dr. Tu will serve as an Area Chair for WDFM-AD workshop with CVPR 2025!
- Dr. Tu will co-organize the 2nd MetaFood Workshop with CVPR 2025! Welcome to participate our challenge:
- Dr. Tu gave an invited talk at Param-Intelligence (π) seminar talk at WPI.
- Dr. Tu attended WACV'2025 in Tuscon, AZ
- Dr. Tu gave an invited talk at AI Seminar at ASU.
- Dr. Tu attended WACV'2025 in Tuscon, AZ
- Dr. Tu co-organized the 3rd Workshop on Large Language and Vision Models for Autonomous Driving (LLVM-AD) with WACV'2025 in Tuscon, AZ.
- Dr. Tu gave an invited talk at Ethical and Explainable GeoAI Workshop held by TAMIDS.
- 3x CVPR'2025 (1x Highlight) accepted. Cheers!
- [Highlight] DPU: Dynamic prototype updating for multimodal out-of-distribution detection
- Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
- SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models
- 1x ICRA'2025 accepted. Cheers!
- We welcome Xiangbo Gao to join the TACO group!
- 2x ICLR'2025 (1x Spotlight) accepted. Cheers!
- [Spotlight] 4k4dgen: Panoramic 4d generation at 4k resolution
- STAMP: Scalable Task- And Model-agnostic Collaborative Perception
- 2x WACV'2025 workshop accepted. Cheers!
- OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Driving
- HFMF: Hierarchical Fusion Meets Multi-Stream Models for Deepfake Detection
- Dr. Tu attended Transportation Research Board (TRB) Annual Meeting at Washing D.C.
- Dr. Tu will serve as an Area Chair for ICCV2025, at your service!
- 1x IEEE TIP accepted. Cheers!
- 1x TMLR accepted. Cheers!
- Dr. Tu visited DARPA DSO Day, MIT, and Boston University.
- We welcome Xing Shuo and Renjie Li to join TACO group!
- 1x IEEE TPAMI accepted. Cheers!
- 1x NeurIPS'24 (DB& Track) accepted. Cheers!
- Dr. Tu, with his crew, visited Rice CS and gave an invited talk on diffusion models and generative AI.
- Dr. Tu gave an invited talk at SPS Webinar Series.
- We won the 3rd place in the AIM 2024 Challenge (Compressed Video Quality Assessment Track)
- Dr. Tu visited NYU, Columbia University.
- Dr. Tu was invited to an AI coffee chat by Dr. Zhang from Expresso Labs
- Our book chapter about Quality Assessment has been published.
- 1x ECCV'24 accepted. Cheers!
- Dr. Tu gave a talk on COVER (Slides) at Video Quality Expert Group (VQEG) Meeting
- 2x CVPR'24 accepted. Cheers!
- We won the 1st place in the AI4Streaming workshop (UGC Video Quality Assessment). [Challenge Report]
- Our book chapter Quality Assessment in Media and Entertainment: Challenges and Trends in Computer Vision: Challenges, Trends, and Opportunities has been Published.
Sponsor