# Sahand Sharifzadeh

> Sahand Sharifzadeh is a Staff Research Scientist on the Gemini team at Google DeepMind in London, working on mid-training, reasoning and multimodal models.

## Key facts
- Sahand Sharifzadeh (سهند شریف زاده) is a Staff Research Scientist on the Gemini Team at Google DeepMind in London, United Kingdom (at Google DeepMind since Aug 2022).
- Developed a key recipe used in Gemini 4 Argon as a core member of the Gemini Mid-Training team; contributed to the Gemini 2 and 3 model series.
- Contributed to Flamingo (NeurIPS 2022) as a DeepMind research scientist intern in 2021; first author and co-lead of Synth² (2024).
- Ph.D. in Computer Science, summa cum laude, LMU Munich (supervisor: Prof. Volker Tresp); M.Sc. TU Munich; B.Sc. Shahid Beheshti University.
- 17,000+ citations on Google Scholar. Languages: Persian, English, Azerbaijani, German, Turkish.
- Also known as: S. Sharifzadeh, S Sharifzadeh, سهند شریف زاده. Handles: @sharifza (GitHub), @sahandsharif (X).
- Research themes: RL & post-training; Multimodal & vision–language; Computer vision; Knowledge graph embeddings; AI for Science; Robotics.

## Profiles
- [Google Scholar](https://scholar.google.com/citations?user=frzfxXYAAAAJ)
- [LinkedIn](https://www.linkedin.com/in/sahandsharifzadeh)
- [GitHub](https://github.com/sharifza)
- [X](https://x.com/sahandsharif)
- [ORCID](https://orcid.org/0000-0002-5534-4017)
- [Website](https://sharifza.github.io/)

## In his own words
Items quoted from the site are in Sahand's own voice: "I" refers to Sahand Sharifzadeh.
Building frontier multimodal and reasoning models across 12+ years of research in foundation models, computer vision, deep RL, and robotics. I developed a key recipe used in Gemini 4 Argon and contributed to the Gemini 2 and 3 model series and Flamingo. Across the Gemini Mid-Training and Thinking areas, I drove research projects on reinforcement learning efficiency and scaling, inference-time scaling, quantization in post-training, and strategic reasoning in games, and co-led research on self-improving VLMs. Earlier, my research spanned looped graph transformers for iterative scene understanding (Classification by Attention, 2020), knowledge graph embeddings (PyKEEN), and deep inverse reinforcement learning for autonomous driving.

## News
- (2026-10) Gemini 4 Argon is now available to everyone, after its announcement on 30 September. I was a core member of the Gemini Mid-Training team and developed a key recipe used in the model. Source: https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-argon/
- (2026-09) Game Arena: strategic LLM evaluation in competitive environments (Kaggle). Technical report on arXiv. Source: https://arxiv.org/abs/2609.31473
- (2025-07) Gemini 2.5 technical report released. Source: https://arxiv.org/abs/2507.06261
- (2024-03) Synth²: self-improving VLMs with synthetic captions and image embeddings (co-lead). Source: https://arxiv.org/abs/2403.07750
- (2024) Ultra-high-granularity detector simulation published in Nature Communications. Source: https://www.nature.com/articles/s41467-024-49104-4

## Research trajectory
### RL & post-training
- (2014 – 2016, 2022) Inverse RL & Autonomous Driving: Motion planning with Inverse RL and Deep Q-Networks (NeurIPS 2016 Workshop, TUM CVG); Robotic pouring via curriculum RL (PourNet, IEEE/RSJ IROS 2022); 1st Place, ACM UIST 2013 Student Innovation Contest (Cool Print).
- (2024 – 2025) Gemini Thinking (2 & 3 Series): Contributor across the Gemini 2 and 3 series; Drove research explorations on Thinking: inference-time scaling and post-training quantization.
- (2025 – 2026) Gemini Games (Game Arena): Core contributor to Gemini Games: strategic reasoning and evaluation in games (Kaggle Game Arena).
- (2025 – 2026) Gemini Mid-Training: Core member of the Gemini Mid-Training team at Google DeepMind; developed a key recipe used in Gemini 4 Argon.
### Multimodal & vision–language
- (2007) GooyaSaz (Persian OCR & TTS): 1st Place Khwarizmi Youth Innovation Award (Tehran, Dec 2007): Farsi Optical Character Recognition (OCR) and Text-to-Speech software converting scanned documents into speech for blind people.
- (2019 – 2023) The Tensor Brain: The Tensor Brain: A Unified Theory of Perception, Memory, and Semantic Decoding (Neural Computation 2023 & CCN 2019).
- (2018 – 2023) Scene Graphs & Relationformer: Ph.D. at LMU Munich, thesis graded Summa Cum Laude: First-author AAAI (2021, 2022) and ICPR (2021) papers on scene graph generation & depth maps; Relationformer (ECCV 2022); InstanceFormer video segmentation (AAAI 2023); Prior-RadGraphFormer (MICCAIW 2023).
- (2021 – 2023) Flamingo VLM: Research Scientist Intern at DeepMind (Apr – Sep 2021): Flamingo visual language model for few-shot learning (NeurIPS 2022, 10,000+ citations); Do DALL-E and Flamingo Understand Each Other? (ICCV 2023).
- (2024) Synth² (Self-Improving VLMs): Co-lead & first author at Google DeepMind: self-improving VLMs trained with synthetic captions and image embeddings.
### Computer vision
- (2014 – 2017) Stereo 3D Reconstruction: Variational stereo image 3D reconstruction for automatic determination of pruning mass in grapevine management and breeding (Australian Journal of Grape and Wine Research, 2017; TUM Computer Vision Group with Prof. Daniel Cremers).
- (2015 – 2016) Medical Registration (MRFs): MRF-based image registration for intraoperative ultrasound brain-shift compensation towards robotic image-based neurosurgery (TUM CAMP, 2015–2016; 3rd HBP Workshop).
### Knowledge graph embeddings
- (2020 – 2021) Knowledge Graphs (PyKEEN): Co-author of: The PyKEEN knowledge graph embedding library (JMLR 2021); MemeGraphs (ICDAR 2023); Unsupervised KG-to-text generation (EMNLP 2020).
- (2020 – 2021) Large-scale KGE Evaluation (TPAMI): Co-author of “Bringing Light Into the Dark”, a large-scale evaluation of knowledge graph embedding models under a unified framework (IEEE TPAMI 2021).
### AI for Science
- (2020, 2024) Genomics & Protein QA: MutLX platform for clone-specific genomic mutation discovery (eLife 2020); PQA: Zero-Shot Protein Question Answering for Free-Form Scientific Enquiry with Large Language Models (2024).
- (2023 – 2024) Particle Detector Simulation: Ultra-High-Granularity Detector Simulation with Intra-Event Aware Generative Adversarial Network and Self-Supervised Relational Reasoning (Nature Communications 2024).
### Robotics
- (2006) Guard Robot (Safety Robotics): 1st Place Khwarizmi Youth Innovation Award (Tehran, Dec 2006): Design and build of an autonomous mobile robot for industrial safety applications.
- (2011 – 2013) @Home Service Robot & Kinect HCI: Technical Team Lead of the Sharif @Home RoboCup Team: 1st Place AUTCup 2012, RobX & SUT TDP papers, gesture & speech recognition; Research Assistant at the NUS HCI Lab (2011): 3D Kinect hand gesture alignment.

## Experience
- **Staff Research Scientist — Gemini Team, Google DeepMind, London, United Kingdom (Aug 2022 – Present)**
  - Gemini Mid-Training: Core member of the Gemini Mid-Training team; developed a key recipe used in Gemini 4 Argon.
  - Gemini Thinking: Contributor across the Gemini 2 and 3 series; drove research explorations on Thinking (inference-time scaling and post-training quantization).
  - Gemini Games: Core contributor; strategic reasoning and evaluation in games (Kaggle Game Arena).
  - Synth²: Co-lead; self-improving VLMs trained with synthetic captions and image embeddings.
- **Research Scientist Intern, DeepMind, London, United Kingdom (Apr 2021 – Sep 2021)**
  - Contributed to Flamingo, a visual language model for few-shot multimodal learning (NeurIPS 2022, 10,000+ citations).
- **Doctoral Researcher, LMU Munich, Munich, Germany (2018 – 2022)**
  - Scene graph generation, Relationformer, The Tensor Brain, and co-author of the PyKEEN knowledge graph embedding library—with publications in Nature Communications, NeurIPS, ICCV, ECCV, AAAI, IEEE TPAMI, JMLR, eLife, EMNLP, and Neural Computation.
- **Research and Teaching Assistant, Technical University of Munich (TUM), Munich, Germany (Oct 2013 – Apr 2017)**
  - Autonomous Driving & Computer Vision (Computer Vision Group, Oct 2013 – Apr 2017): Motion planning with inverse RL and deep Q-networks; stereo 3D reconstruction for grapevine management; CUDA Programming TA (“GPU Programming for Computer Vision”, Sep 2014).
  - Medical Imaging (Computer Aided Medical Procedures Lab — CAMP, May 2015 – Mar 2016): MRF-based image registration for ultrasound brain-shift compensation in neurosurgery.
- **Technical Team Lead — @Home RoboCup Team, Sharif University of Technology, Tehran, Iran (2012 – 2013)**
  - Design and build of a service robot; gesture and speech recognition.
- **Research Assistant — HCI Lab, National University of Singapore (NUS), Singapore (2011)**
  - Hand gesture recognition from Kinect data using sequence alignment.

## Education
- Ph.D. in Computer Science (Artificial Intelligence), Ludwig Maximilian University of Munich (LMU), Germany (2018 – 2022). Thesis: Summa Cum Laude (0.7 — The Highest Distinction). Thesis: On the Importance of Symbol Grounding and Top-Down Processes in Computer Vision;  Supervisor: Prof. Volker Tresp
- M.Sc. in Computer Science, Technical University of Munich (TUM), Germany (2013 – 2016). Thesis: High Distinction (1.1). Major: Computer Vision, Robotics & AI;  Supervisors: Prof. Daniel Cremers, Prof. Rudolph Triebel
- B.Sc. in Computer Science, Shahid Beheshti University, Iran (2008 – 2012). Thesis: High Distinction (20/20); Top 3 of Class. Thesis Supervisor: Prof. Shengdong Zhao (National University of Singapore)

## Talks
- [Transformers — Mediterranean Machine Learning (M2L) Summer School](https://www.youtube.com/watch?v=IvWHJvasGb0) (2023 · Google DeepMind): Invited summer school lecture covering Transformer architectures, attention mechanisms, and multimodal foundation models.
- [Classification by Attention: Scene Graph Classification with Prior Knowledge](https://www.youtube.com/watch?v=X48xcWHj6xo) (2021 · LMU Munich): Advanced School of Computing (ASoC 2021, IPM) — talk on symbol grounding, attention mechanisms, and prior-knowledge scene graph generation (AAAI 2021).
- [Learning to Drive using Deep Inverse Reinforcement Learning](https://www.youtube.com/watch?v=1aYnr6Ea-2E) (2016 · TUM Computer Vision Group): Human Brain Project School of Future Computing — presentation on deep inverse RL and Deep Q-Networks for autonomous driving.
- [Intra-operative Ultrasound-Based Brain-Shift Compensation Towards Robotic Neurosurgery](https://www.youtube.com/watch?v=4P1vUrSMRJg) (2016 · TUM CAMP Lab): 3rd Human Brain Project Education Workshop on Future Computing (Manchester) — MRF-based medical image registration.

## Publications
- (2026) B Doerschuk-Tiberi, Y Yan, …, S Sharifzadeh, …, O Firat, M Chen. [Game Arena: Strategic LLM Evaluation in Competitive Environments](https://arxiv.org/abs/2609.31473). Technical Report · arXiv.
- (2025) Gemini Team (incl. S Sharifzadeh). [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://arxiv.org/abs/2507.06261). Technical Report.
- (2024) S Sharifzadeh, C Kaplanis, S Pathak, D Kumaran, A Ilic, J Mitrovic, C Blundell, A Banino. [Synth²: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings](https://arxiv.org/abs/2403.07750). arXiv preprint. Role: First Author & Co-Lead.
- (2024) B Hashemi, N Hartmann, S Sharifzadeh, J Kahn, T Kuhr. [Ultra-High-Granularity Detector Simulation with Intra-Event Aware Generative Adversarial Network and Self-Supervised Relational Reasoning](https://www.nature.com/articles/s41467-024-49104-4). Nature Communications.
- (2024) EM Carrami, S Sharifzadeh. [PQA: Zero-Shot Protein Question Answering for Free-Form Scientific Enquiry with Large Language Models](https://arxiv.org/abs/2402.13653). arXiv preprint.
- (2023) R Koner, T Hannan, S Shit, S Sharifzadeh, M Schubert, T Seidl, V Tresp. [InstanceFormer: An Online Video Instance Segmentation Framework](https://arxiv.org/abs/2208.10547). AAAI.
- (2023) H Li, J Gu, R Koner, S Sharifzadeh, V Tresp. [Do DALL-E and Flamingo Understand Each Other?](https://arxiv.org/abs/2212.12249). ICCV.
- (2023) V Tresp, S Sharifzadeh, H Li, D Konopatzki, Y Ma. [The Tensor Brain: A Unified Theory of Perception, Memory, and Semantic Decoding](https://arxiv.org/abs/2109.13323). Neural Computation.
- (2023) V Kougia, S Fetzel, T Kirchmair, E Çano, SM Baharlou, S Sharifzadeh, B Roth. [MemeGraphs: Linking Memes to Knowledge Graphs](https://arxiv.org/abs/2305.18391). ICDAR.
- (2023) Y Xiong, J Liu, K Zaripova, S Sharifzadeh, M Keicher, N Navab. [Prior-RadGraphFormer: A Prior-Knowledge-Enhanced Transformer for Generating Radiology Graphs from X-Rays](https://arxiv.org/abs/2303.13818). MICCAI Workshop (GRAIL).
- (2022) JB Alayrac, J Donahue, P Luc, A Miech, …, S Sharifzadeh, et al.. [Flamingo: A Visual Language Model for Few-Shot Learning](https://arxiv.org/abs/2204.14198). NeurIPS. Role: 10,000+ Citations.
- (2022) S Shit, R Koner, B Wittmann, J Paetzold, I Ezhov, H Li, J Pan, S Sharifzadeh, et al.. [Relationformer: A Unified Framework for Image-to-Graph Generation](https://arxiv.org/abs/2203.10202). ECCV.
- (2022) S Sharifzadeh, SM Baharlou, M Schmitt, H Schütze, V Tresp. [Improving Scene Graph Classification by Exploiting Knowledge from Texts](https://arxiv.org/abs/2110.02586). AAAI. Role: First Author.
- (2022) E Babaians, T Sharma, M Karimi, S Sharifzadeh, E Steinbach. [PourNet: Robust Robotic Pouring Through Curriculum and Curiosity-Based Reinforcement Learning](https://doi.org/10.1109/IROS47612.2022.9981195). IEEE/RSJ IROS.
- (2022) S Sharifzadeh. [On the Importance of Symbol Grounding and Top-Down Processes in Computer Vision](https://edoc.ub.uni-muenchen.de/33176/). Ph.D. Dissertation · LMU Munich. Role: Summa Cum Laude.
- (2021) S Sharifzadeh, SM Baharlou, V Tresp. [Classification by Attention: Scene Graph Classification with Prior Knowledge](https://arxiv.org/abs/2011.10084). AAAI. Role: First Author.
- (2021) S Sharifzadeh, SM Baharlou, M Berrendorf, R Koner, V Tresp. [Improving Visual Relation Detection using Depth Maps](https://arxiv.org/abs/1911.09428). ICPR. Role: First Author.
- (2021) M Ali, M Berrendorf, CT Hoyt, L Vermue, M Galkin, S Sharifzadeh, et al.. [Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework](https://arxiv.org/abs/2006.13365). IEEE TPAMI.
- (2021) M Ali, M Berrendorf, CT Hoyt, L Vermue, S Sharifzadeh, et al.. [PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings](https://jmlr.org/papers/v22/20-825.html). JMLR.
- (2020) M Schmitt, S Sharifzadeh, V Tresp, H Schütze. [An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing](https://aclanthology.org/2020.emnlp-main.577/). EMNLP.
- (2020) M KaramiNejadRanjbar, S Sharifzadeh, et al.. [A Highly Accurate Platform for Clone-Specific Mutation Discovery Enables the Study of Active Mutational Processes](https://elifesciences.org/articles/55215). eLife.
- (2019) V Tresp, S Sharifzadeh, D Konopatzki. [A Model for Perception and Memory](https://doi.org/10.32470/CCN.2019.1264-0). CCN.
- (2017) A Kicherer, M Klodt, S Sharifzadeh, D Cremers, R Töpfer, K Herzog. [Automatic Image-Based Determination of Pruning Mass as a Determinant for Yield Potential in Grapevine Management and Breeding](https://doi.org/10.1111/ajgw.12243). Australian Journal of Grape and Wine Research. Role: Stereo 3D Reconstruction.
- (2016) S Sharifzadeh, I Chiotellis, R Triebel, D Cremers. [Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks](https://arxiv.org/abs/1612.03653). NeurIPS Workshop on Deep Learning for Action and Interaction. Role: First Author.
- (2016) S Sharifzadeh, SA Ahmadi, F Milletari, N Navab. Intra-operative Ultrasound-Based Brain-Shift Compensation Towards Robotic Image-Based Neurosurgery. 3rd Human Brain Project Education Workshop on Future Computing. Role: First Author.
- (2012–2013) A Keipour, S Sharifzadeh, E Babaians, et al.. RobX & SUT Service Delivery Robots League Team Description Papers. AUTCup & Khwarizmi International Robotic Competitions (@Home League).

## Honors & awards
- (2016) Human Brain Project Workshop on Future Computing: European Commission Certification & Speaker (Manchester & Graz).
- (2013 – 2016) TUM Scholarship for International Students (Merit-Based): Awarded three times by Technische Universität München based on academic achievement.
- (2013) 1st Place — ACM UIST Student Innovation Contest: Ranked 1st in the Usefulness Category (Team TUM IN), Cool Print Project.
- (2012) 1st Place — International AUTCup Robotic Competition (@Home League): Team Sharif University of Technology (SUT).
- (2009) 12th Place — ACM ICPC Asia Regional Contest: ACM International Collegiate Programming Contest, Asia Regional, Tehran.
- (2006 – 2007) 1st Place — Khwarizmi Youth Innovation Award (Tehran): 2007: 1st Place for the GooyaSaz Project — Persian OCR and text-to-speech software for blind people. 2006: 1st Place for the Guard Robot Project — mobile robot for industrial safety applications.

Last updated: 2026-10-24