Divyanshu Goyal
Applied Scientist at Adobe
AI researcher and engineering leader with 8+ years at Adobe, specializing in agentic AI and multimodal LLMs. I led the technical strategy that took Adobe GenStudio for Performance Marketing from 0 to 1, driving multi-million-dollar adoption across the Fortune 500. Today I am tech lead for a 7-person team building VLMs, judge models, and retouchers. My work includes 6 patents and publications at CVPR, ICML, and AAAI workshops.
About Me
Education
M.S. in Computer Science
Georgia Institute of Technology
Machine Learning
B.E. in Computer Science
Birla Institute of Technology and Science, Pilani
M.Sc. in Mathematics
Birla Institute of Technology and Science, Pilani
Expertise
Tools & Languages
Publications & Patents
ATune: Unsupervised Photo Retouching Through Image-Editor Controls
Divyanshu Goyal*, Gabriel Ruiz*, Amir Meisami (*equal contribution)
DistortBench: Benchmarking Vision Language Models on Image Distortion Identification
Divyanshu Goyal, Akhil Eppa, Vanya Bannihatti Kumar
JudgeBreak: Is Taste Hidden in the Layers? Stress-Testing Reward Models and LLM Judges with Representation-Based Subjective Evaluation
Vanya Bannihatti Kumar, Anish Narang, Mayank Anand, Akhil Eppa, Divyanshu Goyal
Curiosity-Driven LLM-as-a-judge for Personalized Creative Judgment
Vanya Bannihatti Kumar, Divyanshu Goyal, Akhil Eppa, Neel Bhandari
Cultural Adaptation of Images Using Generative Artificial Intelligence
Akhil Eppa, Mayank Anand, Divyanshu Goyal
Guiding Language Translation with Translation Documents Using Machine Learning
Divyanshu Goyal, Akhil Eppa, Mayank Anand
Video-to-Video Culturalization Using Generative AI
Akhil Eppa, Divyanshu Goyal
Learning to Be Surprised: A Curiosity-Driven Framework for Creative Judgment
Divyanshu Goyal, Vanya Bannihatti Kumar, Akhil Eppa, Neel Bhandari
Systems and Methods to Provide Parameter-Efficient Fine-Tuned Models
Yuanyou Wang, Naveen Vangala, Mayank Anand, Kunal Kumar Jain, Jose Mathew, Eapen Jose, Divyanshu Goyal, Asmita Chihnara, Arif Abdullah, Anand Dantu
Brand-Aligned Marketing Content Generation Using Structured Brand Data and Generative Models
Divyanshu Goyal, Mayank Anand, Jose Mathew
Experience
Applied Scientist
/Adobe, San Jose, CAJune 2021 – Present
GenStudio for Performance Marketing · Tech Lead
- Led technical strategy and the production LLM API layer, taking GenStudio from prototype to multi-million-dollar Fortune 500 adoption.
- Co-invented brand-guideline extraction and compliance scoring, the engine behind Adobe Brand Intelligence.
Marketing VLM · Gemma-3-12B, SFT + GRPO
- Optimized distributed SFT and multi-round GRPO on 8× H100s, cutting training from 6 days to 24 hours.
- Diagnosed reward hacking (84% middle-rating collapse vs. 56% human) and redesigned the reward to bring it to 64%.
- Extended the VLM into a Photoshop agent that plans edits toward marketing appeal, now used by millions.
ATune · Co-Lead with Adobe Research
- A 54M-parameter retoucher that drives real image editors, trained on 10M unedited photos with no expert targets.
- Beat GPT-6 Astra (54.3% of decisive votes) and matched Claude Opus 5 in a 157-rater human preference study.
JEV-Style Marketing Judge
- Qwen3.5-4B judge trained on 1.1M human ratings; +57% SRCC on KonIQ, now integrated into Lightroom, Adobe Stock, and Firefly AI Assistant.
- Caught a silent vision-encoder collapse that loss curves missed, and built automated vision-health monitoring.
DistortBench · First Author
- 13.5K-question benchmark for fine-grained visual quality across 27 distortion types, adopted at Adobe to evaluate Photoshop-agent models.
Machine Learning Engineer
/Adobe, Bangalore, IndiaJuly 2016 – August 2019
ML Serving Platform
- Joined Adobe's ML serving platform at inception; scaled inference to 3,500 QPS per node at 0.3–0.6 ms p99 with a GC-free LMAX Disruptor pipeline.
Projects
VibeNanoChat: GPT-2 Scale LLM Pretraining from Scratch
A from-scratch framework for pretraining, scaling, and evaluating GPT-2 scale language models, featuring depth-parameterized scaling laws, a custom distributed Muon optimizer, and a 35+ benchmark evaluation suite.
Marketing Quality Vision-Language Models
Fine-tuned Gemma-3-12B with SFT and multi-round GRPO, then trained Qwen3.5-4B judges for marketing attributes, checked on a leak-checked benchmark suite.
Adobe GenStudio for Performance Marketing
Built the founding prototype and pitched it to Adobe leadership, leading to the launch of a generative-AI platform for creating on-brand marketing content at scale.