Adobe Research · San Jose, CA

Ryan A. Rossi

Senior Staff Research Scientist

Product-oriented AI research leader building and shipping agentic AI systems, multimodal & LLM generative AI, and foundation-model applications across Adobe products — from Adobe Analytics and Customer Journey Analytics to Firefly. Leads large cross-functional AI initiatives from architecture through customer-facing release, with 15+ technology transfers into products.

I am continuously looking for outstanding and highly motivated Ph.D. students for spring, fall, or summer research positions. If you're interested, please send me your CV and research interests.

Personalized AIAgentic SystemsReasoning Model RoutingMultimodal & VLMsVideo & Image Generation Scalable InferenceRAGGraph Neural Networks Knowledge GraphsTrust & Privacy
200+Publications
100+Patents
20,000+Citations
57h-index
Research

Areas of focus

Theory, algorithms, and large-scale systems at the intersection of personalization, model routing, agents, multimodal models, and graphs. Erdős number: 3.

AI Personalization

Personalized text generation, graph-based retrieval, and multimodal personalization — leading personalization of AI systems at Adobe.

Agentic AI

LLM agents beyond predefined actions, reward-weighted conversation optimization, and preference-guided code generation.

Multimodal & Vision-Language

Image and video generation and editing, judge and reward modeling, post-training, and multimodal RAG.

User Simulation

Formal taxonomies and methods for high-fidelity LLM-based conversational user simulation and evaluation.

Graph Representation Learning

Foundational work on GNNs, knowledge graphs, roles, temporal embeddings, and network analysis.

Scalable AI Systems

Model routing, efficient algorithms, scalable inference and training, and production LLM platforms.

Scholarship

Publications

32 journal articles and 230 peer-reviewed conference papers. Every title links to the paper on Google Scholar.

Innovation & IP

Patents

Inventor on 100+ patents spanning AI personalization, agents, RAG, AI fairness, AI-as-a-judge, simulation, graph learning, knowledge graphs, recommendation, and scalable AI. Adobe Distinguished Inventor. Each entry links to a Google Patents search.

Browse all 105 patents
Open Source

Software, benchmarks & datasets

Widely used open-source frameworks, benchmarks, and data resources — including the Network Repository, the largest network data repository with 250M+ downloads.

Fair LLM Benchmark

GitHub

A comprehensive benchmark compiling over 20 publicly available bias and fairness evaluation datasets for LLMs, enabling standardized evaluation across diverse dimensions.

1,700+ citations 160 stars 16 forks
2023–present

Orthrus

GitHub

A dual-architecture framework that unifies the exact generation fidelity of autoregressive large language models with the high-speed parallel token generation of diffusion models, sharing one key-value cache across both views for lossless, memory-efficient inference.

353 stars 13 forks
2026–present

CulturaX

Hugging Face

A cleaned, multilingual dataset of 6.3 trillion tokens spanning 167 languages for large language model development, fully released on Hugging Face.

596 likes 26K+ downloads/month
2024–present

DynaSaur

GitHub

An LLM agent framework that generates and executes Python programs as a universal action representation, creating and accumulating reusable actions for open-ended tasks.

358 stars 28 forks
2025–present

NoLiMa

GitHub

A long-context evaluation benchmark that minimizes lexical overlap between questions and target content, requiring models to infer latent assoc. rather than rely on literal matching.

195 stars 17 forks
2025–present

PGraphRAG

GitHub

Framework & benchmark for personalized graph-based retrieval-augmented generation that integrates user-centric knowledge graphs to enrich personalization under sparse user history.

34 stars 3 forks
2025–present

LongLaMP

GitHub

A benchmark for personalized long-form text generation, providing a diverse evaluation framework across long-text tasks such as personalized email writing, review generation, and topic writing.

9 stars 2 forks
2024–present

AD-LLM

GitHub

The first benchmark evaluating large language models for anomaly detection, spanning zero-shot detection, data augmentation, and model selection.

44 stars 9 forks
2025–present

VisDoM

GitHub

A benchmark and multimodal retrieval-augmented generation approach for multi-document question answering over visually rich elements such as tables, charts, and slides.

43 stars 6 forks
2025–present

LGGM

GitHub

A large-scale training paradigm for graph generative models, pretrained over thousands of graphs, with zero-shot, fine-tuning, and text-to-graph generation capabilities.

29 stars 10 forks
2025–present

KGP

GitHub

A knowledge graph prompting method for multi-document question answering that pairs graph construction over documents with an LLM-guided graph traversal agent.

324 stars 33 forks
2024–present

GLEMOS

GitHub

A comprehensive benchmark for instantaneous graph learning model selection, providing extensive performance records, evaluation testbeds, and meta-graph features.

6 stars
2023–present

FigCaps-HF

GitHub

A figure-to-caption generative framework and benchmark that incorporates human feedback to optimize generated captions for reader preferences.

3 stars 1 fork
2023–present

Okapi

GitHub

A framework and resources for instruction tuning large language models in 26 languages using reinforcement learning from human feedback.

96 stars 3 forks
2023–present

CyCLIP

GitHub

A contrastive vision-language pretraining framework that enforces geometric consistency in the image and text representation spaces.

125 stars 16 forks
2022–present

CPGNN

GitHub

A graph neural network framework that learns an interpretable compatibility matrix, generalizing message passing to graphs with either homophily or heterophily.

31 stars 3 forks
2021–present

node2bits

GitHub

An efficient framework for user stitching that encodes multi-dimensional node context from feature-based temporal walks into compact binary hashcodes.

7 stars 6 forks
2019–present

role2vec

GitHub

A widely used community implementation of our popular role2vec role-based network embedding method.

169 stars 33 forks
2019–present

Parameterized Graphlet Decomposition Library (PGD)

Website

A fast parallel high-performance parameterized graphlet decomposition library for massive networks. Code at .

90 stars 31 forks
2015–present

Network Repository (NR)

Website

The first interactive data repository that integrates visualization with state-of-the-art statistical methods and analytic techniques to support discovery and exploration of data in real-time. NR is the largest network data repository, with over 6,000 donations across 30+ collections and growing.

4,000+ citations 250 million downloads
2012–present

GraphVIS

Website

Interactive visual graph mining and machine learning on the web. Visualize and explore network data easily. GraphVIS is the result of years of research in relational machine learning and graph mining. A free demo version is available at http://networkrepository.com/graphvis

2014–present

Parallel Maximum Clique Library (PMC)

GitHub

A parallel high-performance library for solving the maximum clique problem on dense graphs and large sparse networks.

120 stars 51 forks
2013

MLVis

Website

An interactive data repository that makes it easy to find, explore, and understand machine learning data, providing researchers with open, persistent, and accessible data alongside web-based visual analytic tools

2013–present

Dynamic PageRank

GitHub

A package for modeling the importance and influence of nodes in dynamic networks with external interest and attributes.

16 stars 4 forks
2012
Career

Experience

2017–present

Senior Staff Research Scientist

Adobe Research
  • Leading technical strategy and architecture for large-scale AI systems that translate frontier models into scalable product capabilities, spanning agentic AI, production multimodal and LLM platforms, model orchestration, personalization, recommendation, evaluation, and scalable inference.
  • Led a large-scale agentic data intelligence platform for Adobe Analytics, Customer Journey Analytics, and Adobe Experience Platform. Lead 30+ cross-functional contributors across research, engineering, product, UI, legal, and business stakeholders.
  • Led and contributed to Firefly multimodal generative AI systems, including agentic systems and judge models for image and video generation and editing.
  • Architected and delivered production-grade multimodal & LLM data-agent capabilities.
  • Developed and adapted architectures, LLMs, multimodal foundation models, fine-tuned models, retrieval-augmented systems, structured-output pipelines, judge models, and task-specialized model workflows to solve Adobe-specific product problems and support customer-facing releases.
  • Improved product quality, latency, scalability, and cost through production-aligned model design, efficient data structures, parallelization, and rigorous offline and continuous evaluation pipelines.
  • Led 15+ technology transfers of AI research into Adobe products across Experience Cloud, Creative Cloud, Document Cloud, and Commerce spanning Analytics, CJA, Experience Platform, Photoshop, Firefly, Real-Time CDP, Campaign, Acrobat Assistant, among others.
2015–2017

Member of Research Staff

Palo Alto Research Center (PARC, a Xerox company)

Machine Learning group

2013–2015

Visiting Researcher

Palo Alto Research Center (PARC)

Palo Alto, CA USA Research focused on theory, algorithms & applications of relational (graph-based) machine learning

Summer 2013

Research Intern

Palo Alto Research Center (PARC)

Palo Alto, CA USA Developed recommendation systems via collective matrix-tensor factorization

2009–2015

Research Assistant

Purdue University

USA Research: Machine Learning, Statistical Relational Learning Proposed methods for role discovery in large dynamic graphs and dynamic relational classification

Summer 2011–2012

Research Assistant

Lawrence Livermore National Laboratory (ISCR)

USA Research focused on developing ML algorithms to characterize and model user behavior for detecting malicious intent/intrusions in real-time. Invited back for second year. Resulted in two papers on modeling dynamic roles in large networks

Summer 2010

Research Assistant

Naval Research Laboratory (Artificial Intelligence Center)

USA Advisor: David Aha, Co-advisor: Luke McDowell (U.S. Naval Academy), NREIP Resulted in the JAIR paper "Transformation of Graph Data for Statistical Relational Learning"

Summer 2009

Research Assistant

California Institute of Technology (NASA JPL)

USA Advisor: Mark W. Powell, Summer Research Fellowship (returned to continue my research)

Spring 2009

Research Assistant

NASA Jet Propulsion Laboratory

USA Advisor: Mark W. Powell, Spring USRP Fellowship

Summer 2008

Research Assistant

University of Massachusetts at Amherst

USA Advisor: David Jensen, Co-advisor: Brian Taylor. REU NSF Fellowship. "Experimental Methods for Improving the Design of Participatory Sensing Systems"

Summer 2007

Research Assistant

New Mexico Institute of Technology, ICASA

USA Advisor: Srinivas Mukkamala, Senior Research Scientist, ICASA

2005–2009

Research Assistant

Coastal Carolina University

USA Advisor: Jean-Louis Lassez, Retired IBM T.J. Watson Research Center

Foundations

Education

2009–2015

Ph.D., Computer Science

Purdue University

Title: "Improving Relational Machine Learning by Modeling Temporal Dependencies" Recipient of Four Ph.D. Fellowships: – National Science Foundation Graduate Fellowship (NSF GRFP) – DoD: National Defense Science and Engineering Graduate Fellowship (NDSEG) – Bilsland Dissertation Fellowship Awarded to Outstanding Ph.D. candidates – Purdue University Fredrick N. Andrews Doctoral Fellowship

2013

MS in Computer Science

Purdue University

Concentrate in Machine Learning

2005–2009

Bachelor of Science in Computer Science

Coastal Carolina University (CCU)

Valedictorian class of 2009. GPA: 4.0., Summa Cum Laude Advisor: Jean-Louis Lassez (Retired IBM T.J. Watson Research Center)

Research fellowships: LLNL Scholar, Lawrence Livermore National Laboratory (Summer 11–12) · NREIP, Naval Research Laboratory (AI Center) (Summer 2010) · NASA Fellow, California Institute of Technology, JPL (2009) · USRP Fellow, Jet Propulsion Laboratory (2009) · NSF REU Fellow, University of Massachusetts at Amherst (Summer 2008) · Research Fellow, New Mexico Institute of Technology (Summer 2007)

Recognition

Honors & awards

Funding

Research awards & grants

Community

Selected talks & outreach

Mentorship

Students & committees

Supervised and mentored 100+ students from Stanford, CMU, Berkeley, Michigan, Georgia Tech, KAIST, and many more — most resulting in top-tier publications.

Ph.D. dissertation committees

Students supervised (100)
  • Bo NiVanderbilt University · Ph.D. Student2024–2026
  • Wang WeiVirginia Tech · Ph.D. Candidate2024–2026
  • Reuben LueraUC Berkeley · GEM Fellow, M.S. Student2024–2026
  • Deonna M. OwensStanford University · GEM Fellow, M.S. Student2024–2026
  • Yu XiaUC San Diego · Ph.D. Student2024–2025
  • Dang NguyenUniversity of Oregon · Ph.D. Student2024–2025
  • Yongjia Lei · Ph.D. Student2024–2025
  • Tiankai YangTexas A&M University · Ph.D. Student2024–2025
  • Zhehao ZhangDartmouth College · M.S. Student2024–2025
  • Yeonjun InKAIST · Ph.D. Student2024–2025
  • Ashish SinghUMass · Ph.D. Student2024–2025
  • Songwen HuUniversity of Georgia · Ph.D. Student2024–2025
  • Isabel O. GallegosStanford University · Ph.D. Student2023–2024
  • Shanyun GaoPurdue University · Ph.D. Student2023–2024
  • Xinyu ShiUniversity of Waterloo · Ph.D. Student2023–2024
  • Yoonjoo LeeKAIST · Ph.D. Student2023–2024
  • Puja TrivediUniversity of Michigan · Ph.D. Student2023–2024
  • Mehrnoosh MirtaheriUSC · Ph.D. Student2023–2024
  • Jian ChenUniversity at Buffalo · Ph.D. Student2023–2024
  • Fayokemi Ojo · Ph.D. Student2022–2023
  • Enyu Cai · Ph.D. Student2022–2023
  • Namyong ParkCMU · Meta Research2020-2022
  • Sudhanshu ChanpuriyaUMass Amherst · Ph.D. Student2020-2022
  • Hyeok KimNorthwestern · Ph.D. Student2020-2022
  • Arpit NarechaniaGeorgia Tech · Ph.D. Student2021-2022
  • Mustafa AbdallahPurdue University · Assistant Professor at IUPUI2021-2022
  • Gaurav VermaGeorgia Tech · Ph.D. Student2021-2022
  • Mohammad MehrabiUSC · Assistant Professor at IUPUI2021-2022
  • Shravika MittalGeorgia Tech · Ph.D. Student2022
  • April ChenHarvard University · Ph.D. Student2022
  • Xinyu ShiUniv. of Waterloo · Ph.D. Student2022
  • Tingyao HsuPenn. State · Ph.D. Student2022
  • Yuhang YaoCMU · Ph.D. Student2022
  • Carol (Xinyi) ZhengCMU · Ph.D. Student2022
  • Shanyun GaoPurdue University · Ph.D. Student2022
  • Rashmi Ranjan BhuyanUSC · Ph.D. Student2022
  • Luke SnyderUniversity of Washington · Ph.D. Student2022
  • Guande WuNYU · Ph.D. Student2022
  • Ryan AponteCMU · Ph.D. Student2022
  • Chen ChenUMD · Ph.D. Student2022
  • Alex TangNorthwestern · Ph.D. Student2022
  • Jean-Peic ChouStanford University · Ph.D. Student2022
  • Melanie BancilhonWashington University in St. Louis · Ph.D. Student2022
  • Jianna Audrey SoStanford University · Ph.D. Student2022
  • Jaeho BangGeorgia Tech · Ph.D. Student2022
  • Dario GarigliottiAalborg University · Ph.D. Student2022
  • Princess SampsonUniversity of Pennsylvania · Ph.D. Student2022
  • Enyu CaiPurdue University · Ph.D. Student2022
  • Dongliang GuoUniversity of Virginia · Ph.D. Student2022
  • Songwen HuShanghai Jiao Tong University · Ph.D. Student2022
  • Gaurav GuptaRice University · Ph.D. Student2021
  • Yang LiUNC · Ph.D. Student2021
  • Nathan NgUMass Amherst · Ph.D. Student2021
  • Bingjie (Jenny) XuNorthwestern · Ph.D. Student2021
  • Beleicia BullockStanford University · Ph.D. Student2021
  • Md Main Uddin RonyUMD · Ph.D. Student2021
  • Fayokemi OjoJohn Hopkins University · Ph.D. Student2021
  • Can QinNortheastern · Ph.D. Student2021
  • Shivam SrivastavaUMass Amherst · Ph.D. Student2021
  • Abhraneel SarmaNorthwestern · Ph.D. Student2021
  • Weixin JiangNorthwestern · Ph.D. Student2021
  • Duc HoangUniversity of Texas at Austin · Ph.D. Student2021
  • Benjamin ColemanRice University · Ph.D. Student2021
  • Pattara SukprasertNorthwestern · Ph.D. Student2021
  • Jiong ZhuUniversity of Michigan · Ph.D. Student2020
  • Xin QianUniversity of Maryland · Ph.D. Student2019-2021
  • Yue ZhaoCMU · Ph.D. Student2020
  • Sejoon OhGeorgia Tech · Ph.D. Student2020-2021
  • Mojtaba Sahraee-ArdakanUSC · Ph.D. Student2020
  • Enayat UllahJohn Hopkins University · Ph.D. Student2020
  • Jun YanUSC · Ph.D. Student2019-2020
  • Shenyu XuGeorgia Tech · Ph.D. Student2020
  • Zening QuUniversity of Washington · Ph.D. Student2020
  • Ihudiya Finda Ogbonnaya-OgburuUniversity of Michigan · Ph.D. Student2020
  • Zhuohao ZhangUniversity of Illinois at Urbana-Champaign · Ph.D. Student2020
  • Galen WeldUniversity of Washington · Ph.D. Student2020
  • Chenhan YuanVirginia Tech · Ph.D. Student2020-2021
  • Camille HarrisGeorgia Tech · Ph.D. Student2020
  • Mrigank RamanUSC · Ph.D. Student2020
  • Zihao ZhouUCSD · Ph.D. Student2020
  • Alireza FarhadiUniversity of Maryland (UMD) · Ph.D. Candidate2019-2022
  • Hongjie ChenVirginia Tech · Dolby Labs2019-2022
  • Youngsuk ParkStanford University · Ph.D. Candidate2019
  • Yikun XianRutgers University · Ph.D. Candidate2019
  • Saed RezayiUniversity of Georgia (UGA) · Ph.D. Candidate2019-2020
  • Gromit Yeuk-Yin ChanNew York University (NYU) · Ph.D. Candidate2019-2020
  • Kirankumar ShiragurStanford University · Ph.D. Candidate2019
  • Hongchang GaoUniversity of Pittsburgh · Ph.D. Candidate2019
  • He JiaGeorgia Institute of Technology · Ph.D. Candidate2019
  • Di JinUniversity of Michigan · Ph.D. Candidate2018-2021
  • Mark HeimannUniversity of Michigan · Ph.D. Candidate2018-2019
  • Aldo CarranzaStanford University · Ph.D. Student2018
  • Zahra ShakeriRutgers University · Ph.D. Candidate2018
  • Donghyun KimPOSTECH · Graduated @ Oath/Yahoo Research2018
  • Jianjun LuoWorcester Polytechnic Institute (WPI) · Ph.D. Candidate2018-2019
  • Charles ChenOhio State University · Ph.D. Candidate2018-2019
  • Tung MaiGeorgia Institute of Technology · Ph.D. Candidate2018
  • Jungho ParkSeoul National University · Ph.D Candidate2017
  • John Boaz LeeWorcester Polytechnic Institute (WPI) · Ph.D. Candidate2017-2021
  • Giang Hoang NguyenWorcester Polytechnic Institute (WPI) · Masters Student2017-2018