Jindong Jiang

Research Scientist · NVIDIA Research

Email: jindongj at nvidia.com · Google Scholar · LinkedIn

About

I am a Research Scientist at NVIDIA Research. I received my Ph.D. in Computer Science from Rutgers University in April 2025, advised by Prof. Sungjin Ahn.

My current research focuses on two directions. One is efficient LLMs, including speculative decoding and diffusion LLMs. The other is agentic AI, focusing on improving AI on edge devices and edge cloud collaboration.

News

Oct 2026: We released EdgeWise, enabling agents on local devices to solve long-horizon tasks with selective cloud assistance at lower inference cost.
Oct 2026: Our on-policy distillation study shows that reusing offline student rollouts often improves accuracy and training efficiency.
Sep 2026: We released Mid-Harness, improving terminal-agent reliability by sampling and verifying candidate actions before execution.
May 2026: We released Nemotron-Labs-Diffusion, a tri-mode LM unifying autoregressive, diffusion, and self-speculation decoding in a single architecture.
Apr 2026: We released Recursive Multi-Agent Systems, a framework for recursive agent collaboration in latent space.
Mar 2026: We released Stateful Token Reduction for hybrid VLMs: 75% fewer tokens and 4.2× faster prefilling with the same or better long-video accuracy.
Feb 2026: Our 4DP-QA, a geometry-grounded VLM training recipe for 4D spatiotemporal understanding, was accepted to CVPR 2026.
Sep 2025: Our Eagle 2.5, an 8B VLM that matches GPT-4o and models 10× larger on long-video understanding, was accepted to NeurIPS 2025.
May 2025: I joined Learning and Perception Research Group as a Research Scientist.
Apr 2025: I successfully completed my Ph.D. defense at Rutgers University.
Mar 2025: Preprint of our new work, Token-Efficient Long Video Understanding for Multimodal LLMs, for long-video Multimodal LLMs, is out on arXiv.
Sep 2024: Our Slot State Space Models is accepted to NeurIPS 2024.
Jun 2024: Preprint of our new work, Slot State Space Models, for modular sequence modeling, is out on arXiv.
Jun 2024: I joined Learning and Perception Research Group as a Research Intern in the Summer of 2024.
Feb 2024: Our Layout-Agnostic Scene Text Image Synthesis with Diffusion Models is accepted to CVPR 2024.
Sep 2023: Our Object-Centric Slot Diffusion is accepted to NeurIPS 2023 as a 🌟Spotlight🌟 paper.
Feb 2023: I will be joining Adobe Research as a Research Scientist Intern in the Summer of 2023.

Publications

Agentic AI

2026

EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation

Zeru Shi*, Jindong Jiang*, Ryo Hachiuma, Yonggan Fu, Byung-Kwan Lee, Peter Belcak, Saurav Muralidharan, Ayush Agarwal, Ruixiang Tang, Ambrish Dantrey, Pavlo Molchanov, Anjul Patney, Subhashree Radhakrishnan

arXiv 2026 paper project
2026

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Minki Kang, Ryo Hachiuma, Shaokun Zhang, Subhashree Radhakrishnan, Yonggan Fu, Jindong Jiang, Mingjie Liu, Ehsan Hosseini-Asl, Yi Dong, Yu-Chiang Frank Wang, Byung-Kwan Lee

arXiv 2026 paper project
2026

Recursive Multi-Agent Systems

Jiaru Zou, Rui Pan, Ruizhong Qiu, Pan Lu, Shizhe Diao, Jindong Jiang, Hanghang Tong, Tong Zhang, Markus J. Buehler, Jingrui He, James Zou

arXiv 2026 paper project

Large Language Models

2026

When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better

Siyan Zhao, Yonggan Fu, Jindong Jiang, Shih-Yang Liu, Song Bian, Byung-Kwan Lee, Sharath Turuvekere Sreenivas, Wenliang Dai, Hanrong Ye, Aditya Grover, Pavlo Molchanov

arXiv 2026 paper
2026

Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding

Yonggan Fu, Lexington Whalen, Abhinav Garg, Chengyue Wu, Maksim Khadkevich, Nicolai Oswald, Enze Xie, Daniel Egert, Sharath Turuvekere Sreenivas, Shizhe Diao, Chenhan Yu, Ye Yu, Weijia Chen, Sajad Norouzi, Jingyu Liu, Shiyi Lan, Ligeng Zhu, Jin Wang, Jindong Jiang, Morteza Mardani, Mehran Maghoumi, Song Han, Ante Jukić, Nima Tajbakhsh, Jan Kautz, Pavlo Molchanov

arXiv 2026 paper

Vision-Language Models

2026

4DP-QA: Scalable QA for 4D Perception in Vision Language Models

Seokju Cho, Abhishek Badki, Hang Su, Jindong Jiang, Ziyao Zeng, Seungryong Kim, Sifei Liu, Orazio Gallo

CVPR 2026paper project
2026

Stateful Token Reduction for Long-Video Hybrid VLMs

Jindong Jiang*, Amala Sanjay Deshmukh, Kateryna Chumachenko, Karan Sapra, Zhiding Yu, Guilin Liu, Andrew Tao, Pavlo Molchanov, Jan Kautz, Wonmin Byeon*

arXiv 2026paper
2025

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

Guo Chen, Zhiqi Li, Shihao Wang, Jindong Jiang, Yicheng Liu, Lidong Lu, De-An Huang, Wonmin Byeon, Matthieu Le, Max Ehrlich, Tong Lu, Limin Wang, Bryan Catanzaro, Jan Kautz, Andrew Tao, Zhiding Yu, Guilin Liu

NeurIPS 2025paper
2025

STORM: Token-Efficient Long Video Understanding for Multimodal LLMs

Jindong Jiang*, Xiuyu Li*, Zhijian Liu, Muyang Li, Guo Chen, Zhiqi Li, De-An Huang, Guilin Liu, Zhiding Yu, Kurt Keutzer, Sungjin Ahn, Jan Kautz, Hongxu Yin, Yao Lu, Song Han, Wonmin Byeon

ICCV Workshops 2025paper project

Computer Vision

2024

SceneTextGen: Layout-Agnostic Scene Text Image Synthesis with Diffusion Models

Qilong Zhangli, Jindong Jiang, Di Liu, Licheng Yu, Xiaoliang Dai, Ankit Ramchandani, Guan Pang, Dimitris N. Metaxas, Praveen Krishnan

CVPR 2024paper
2024

ProxEdit: Improving Tuning-Free Real Image Editing With Proximal Guidance

Ligong Han, Song Wen, Qi Chen, Zhixing Zhang, Kunpeng Song, Mengwei Ren, Ruijiang Gao, Anastasis Stathopoulos, Xiaoxiao He, Yuxiao Chen, Di Liu, Qilong Zhangli, Jindong Jiang, Zhaoyang Xia, Akash Srivastava, Dimitris Metaxas

WACV 2024paper
2018

RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation

Jindong Jiang, Lunan Zheng, Fei Luo, Zhijun Zhang

arXiv 2018paper code

Structured Representation Learning & World Models

2024

Slot State Space Models

Jindong Jiang, Fei Deng, Gautam Singh, Minseung Lee, Sungjin Ahn

NeurIPS 2024paper project
2023

Object-Centric Slot Diffusion

Jindong Jiang, Fei Deng, Gautam Singh, Sungjin Ahn

NeurIPS 2023Spotlight · top 3%paper project
2020

Generative Neurosymbolic Machines

Jindong Jiang, Sungjin Ahn

NeurIPS 2020Spotlight · top 4%paper code
2020

Improving Generative Imagination in Object-Centric World Models

Zhixuan Lin, Yi-Fu Wu, Skand Peri, Bofeng Fu, Jindong Jiang, Sungjin Ahn

ICML 2020paper project
2020

SCALOR: Generative World Models with Scalable Object Representations

Jindong Jiang*, Sepehr Janghorbani*, Gerard de Melo, Sungjin Ahn

ICLR 2020paper project
2020

SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition

Zhixuan Lin*, Yi-Fu Wu*, Skand Vishwanath Peri*, Weihao Sun, Gautam Singh, Fei Deng, Jindong Jiang, Sungjin Ahn

ICLR 2020paper project

* Equal contribution