Some personal updates:
- I've completed my PhD at @unccs.bsky.social! 🎓
- Starting Fall 2026, I'll be joining the CS dept. at Johns Hopkins University @jhucompsci.bsky.social as an Assistant Professor 💙
- Currently exploring options for my gap year (Aug 2025 - Jul 2026), so feel free to reach out! 🔎

3️⃣ Evaluation & Refinement

🌟 Fine-grained evaluation 👉 Assess generation skills across dimensions
e.g., DALL-Eval (ICCV ’23), VPEval (NeurIPS ’23), DSG (ICLR ’24)

🌟 Automatic refinement 👉 Use the evaluations to refine
e.g., EnvGen (COLM ’24), DataEnvGym (’24), SELMA (NeurIPS ’24), VideoRepair (’24)

2️⃣ Faithful Reasoning

🌟 Planning-based visual generation 👉 Decompose problems into interpretable steps
e.g., VPGen (NeurIPS ’23), VideoDirectorGPT (COLM ’24), DiagrammerGPT (COLM ’24)

🌟 Multimodal RAG 👉 Boost factuality/efficiency via multimodal retrieval
e.g., M3DocRAG (’24), HiREST (CVPR ’23)

1️⃣ Scalable Frameworks

🌟Unified frameworks 👉 Handle all tasks w/ a single generative model
e.g., VL-T5 (ICML ’21), X-LXMERT (EMNLP ’20), TVLT (NeurIPS ’22 Oral)

🌟 Efficient finetuning 👉 Reduce computation for task-specific models
e.g., VL-Adapter (CVPR ’22), LST (NeurIPS ’22), Ctrl-Adapter (’24)

🚨 I’m on the academic job market!
j-min.io

I work on ✨Multimodal AI✨, advancing reasoning in understanding & generation by:
1⃣ Making it scalable
2⃣ Making it faithful
3⃣ Evaluating + refining it

Completing my PhD at UNC (w/ @mohitbansal.bsky.social).
Happy to connect (will be at #NeurIPS2024)!

👇🧵