Publications

Jaemin Cho, Debanjan Mahata, Ozan İrsoy, Yujie He, Mohit Bansal (2024). M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding.

Preprint Cite Project

Jialu Li, Jaemin Cho, Yi-Lin Sung, Jaehong Yoon, Mohit Bansal (2024). SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data. In NeurIPS.

Preprint Cite Code Project

Zaid Khan, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal (2024). DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback.

Preprint Cite Code Project

Han Lin, Abhay Zala, Jaemin Cho, Mohit Bansal (2024). VideoDirectorGPT: Consistent Multi-Scene Video Generation via LLM-Guided Planning. In COLM.

Preprint Cite Code Project

Abhay Zala, Jaemin Cho, Han Lin, Jaehong Yoon, Mohit Bansal (2024). EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents. In COLM.

Preprint Cite Code Project

Abhay Zala, Han Lin, Jaemin Cho, Mohit Bansal (2024). DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning. In COLM.

Preprint Cite Code Project

Heesoo Jang, Jaemin Cho (2024). An Assessment of Reported Biases and Harms of Large Language Models. In ICA 2024 (Top Paper Award).

Cite

Yasumasa Onoe, Sunayana Rane, Zachary Berger, Yonatan Bitton, Jaemin Cho, Roopal Garg, Alexander Ku, Zarana Parekh, Jordi Pont-Tuset, Garrett Tanzer, Su Wang, Jason Baldridge (2024). DOCCI: Descriptions of Connected and Contrasting Images. In ECCV.

Preprint Cite Dataset Project

Han Lin, Jaemin Cho, Abhay Zala, Mohit Bansal (2024). Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model.

Preprint Cite Code Project

Jaemin Cho, Linjie Li, Zhengyuan Yang, Zhe Gan, Lijuan Wang, Mohit Bansal (2024). Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generation. In CVPR Workshop (Oral).

Preprint Cite Code Dataset Project

Qin Liu, Jaemin Cho, Mohit Bansal, Marc Niethammer (2024). Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts. In CVPR.

Preprint Cite Code Project

David Wan, Jaemin Cho, Elias Stengel-Eskin, Mohit Bansal (2024). Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training. In ECCV.

Preprint Cite Code Project

Jaemin Cho, Yushi Hu, Roopal Garg, Peter Anderson, Ranjay Krishna, Jason Baldridge, Mohit Bansal, Jordi Pont-Tuset, Su Wang (2023). Davidsonian Scene Graph: Improving Reliability in Fine-Grained Evaluation for Text-to-Image Generation. In ICLR.

Preprint Cite Code Project

Jaemin Cho, Abhay Zala, Mohit Bansal (2023). Visual Programming for Text-to-Image Generation and Evaluation. In NeurIPS.

Preprint Cite Code Project

Shoubin Yu, Jaemin Cho, Prateek Yadav, Mohit Bansal (2023). Self-Chained Image-Language Model for Video Localization and Question Answering. In NeurIPS.

Preprint Cite Code

Zhenhailong Wang, Ansel Blume, Sha Li, Genglin Liu, Jaemin Cho, Zineng Tang, Mohit Bansal, Heng Ji (2023). Paxion: Patching Action Knowledge in Video-Language Foundation Models. In NeurIPS.

Preprint Cite Code

Jaemin Cho, Abhay Zala, Mohit Bansal (2023). DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models. In ICCV.

Preprint Cite Code

Abhay Zala, Jaemin Cho, Satwik Kottur, Xilun Chen, Barlas Oğuz, Yasahar Mehdad, Mohit Bansal (2023). Hierarchical Video-Moment Retrieval and Step-Captioning. In CVPR.

Preprint Cite Code Project

Zineng Tang, Jaemin Cho, Jie Lei, Mohit Bansal (2023). Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention. In WACV.

Preprint Cite Code

Zineng Tang, Jaemin Cho, Yixin Nie, Mohit Bansal (2022). TVLT: Textless Vision-Language Transformer. In NeurIPS.

Preprint Cite Code

Yi-Lin Sung, Jaemin Cho, Mohit Bansal (2022). LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning. In NeurIPS.

Preprint Cite Code

Jaemin Cho, Seunghyun Yoon, Ajinkya Kale, Franck Dernoncourt, Trung Bui, Mohit Bansal (2022). Fine-grained Image Captioning with CLIP Reward. In Findings of NAACL.

Preprint Cite Code

Yi-Lin Sung, Jaemin Cho, Mohit Bansal (2022). VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks. In CVPR.

Preprint Cite Code

Revanth Gangi Reddy, Xilin Rui, Manling Li, Xudong Lin, Haoyang Wen, Jaemin Cho, Lifu Huang, Mohit Bansal, Avi Sil, Shih-Fu Chang, Alexander Schiwing, Heng Ji (2021). MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding. In AAAI.

Preprint Cite

Zineng Tang, Jaemin Cho, Hao Tan, Mohit Bansal (2021). VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer. In NeurIPS.

Preprint Cite Code

Jaemin Cho, Jie Lei, Hao Tan, Mohit Bansal (2021). Unifying Vision-and-Language Tasks via Text Generation. In ICML.

Preprint Cite Code

Jaemin Cho, Jiasen Lu, Dustin Schwenk, Hannaneh Hajishirzi, Aniruddha Kembhavi (2020). X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers. In EMNLP.

Preprint Cite Code Project

Jaemin Cho, Minjoon Seo, Hannaneh Hajishirzi (2019). Mixture Content Selection for Diverse Sequence Generation. In EMNLP.

Preprint Cite Code

Yookoon Park, Jaemin Cho, Gunhee Kim (2018). A Hierarchical Latent Structure for Variational Conversation Modeling. In NAACL (Oral).

Preprint Cite Code Video