Latest News

• [July, 2026] I am serving as an Action Editor for TMLR.
• [June, 2026] I am serving as an Area Chair for WACV 2027.
• [May, 2026] Survey paper on Multimodal Agentic Frameworks is accepted at TMLR.
• [May, 2026] Recognized as an Outstanding Reviewer (top 5%) for CVPR 2026.
• [March, 2026] Started a new chapter at Adobe Research.
• [July, 2025] Defended Ph.D. thesis, and joined FAIR, Meta as a Postdoctoral Researcher (with Christoph and Pengchuan).
• [June, 2025] ED-VTG is accepted in ICCV 2025 as a Highlights.
• [Dec, 2024] Invited talk on SPIQA at Voxel51 NeurIPS 2024 Preshow. Recording can be found here.
• [Oct, 2024] Invited lecture on Introduction to Transformers in EN.520.665 Machine Perception at Johns Hopkins. Recording can be found here.
• [Sep, 2024] SPIQA is accepted in NeurIPS 2024 D&B.
• [Jul, 2024] Joined FAIR, Meta as a returning research scientist intern. Working with Daffy, Efi, Yale and Lorenzo on fine-grained video temporal grounding.
• [Jun, 2024] EgoVLPv2 is awarded as an EgoVis 2022/2023 Distinguished Paper.
• [Jun, 2024] Received Spot Bonus from Google for exceptional contributions while being a student researcher.
• [Apr, 2024] VistaLLM is selected as a Highlight (Top 2.8%) and Ego-Exo4D is selected as an Oral (Top 0.8%) in CVPR 2024.
• [Mar, 2024] Selected to participate in Doctoral Consortium at CVPR 2024.
• [Feb, 2024] VistaLLM and Ego-Exo4D are accepted in CVPR 2024.
• [Feb, 2024] Invited talk at CCVL on EgoVLPv2 and VistaLLM. Recording can be found here.
• [Dec, 2023] Successfully passed the Graduate Board Oral (GBO) examination. Officially a Ph.D. candidate now.
• [Oct, 2023] Joined Google Research as a student researcher. Working with Subhashini on AI for Science.
• [Aug, 2023] VoLTA is accepted in TMLR 2023.
• [Jul, 2023] EgoVLPv2 and UniVTG are accepted in ICCV 2023.
• [Jun, 2023] Received student researcher offer from Google Research for Fall 2023.
• [Jun, 2023] Joined Meta AI as a returning research scientist intern. Working with Nicolas, Amjad, Guangxing, Qifan and Rui.
• [Feb, 2023] 1 paper accepted in Biomedical Signal Processing and Control, Elsevier.
• [Jan, 2023] Received research internship offers from Meta AI (return), Microsoft Research, Adobe Research, Salesforce Research, and Samsung Research America for Summer 2023.
• [Oct, 2022] Attended ECCV 2022, and presented our work Where in the World is this Image?
• [Jul, 2022] 1 paper accepted in ECCV 2022.
• [May, 2022] Joined Meta AI as a research scientist intern. Working with Pengchuan, Li, Yale, and Yann.
• [Jan, 2022] Attended WACV 2022 in person at Waikoloa, Hawaii, and presented our work Multimodal Learning using Optimal Transport.
• [Nov, 2021] Received research internship offers from Meta AI, AWS AI, and Adobe Research for Summer 2022.
• [Oct, 2021] Received EMNLP volunteer fellowship and free registration in EMNLP 2021.
• [Oct, 2021] 1 paper accepted in WACV 2022.
• [Aug, 2021] 1 paper accepted in Findings of EMNLP 2021.
• [Jul, 2021] Received ACL volunteer fellowship and free registration in ACL 2021.
• [May, 2021] 1 paper accepted in Knowledge-based Systems, Elsevier.
• [May, 2021] 1 paper accepted in Findings of ACL 2021.
• [Mar, 2021] 1 paper accepted in ICWSM 2021.
• [Jan, 2021] Joined Johns Hopkins University for my Ph.D. with ECE departmental fellowship, under the supervision of Professor Rama Chellappa.
• [Jun, 2020] Joined Qatar Computing Research Institute (QCRI), Doha as a Research Associate.
• [Apr, 2020] Received Ph.D. admission offers from 7 US Universities – JHU, GaTech, Purdue, UCR, Penn State, WashU St. Louis, and Yale.
• [Jan, 2019] Selected as one of the Mitacs Globalink Research Interns 2019.

Selected Publications

2026

Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards

Wenbo Hu, Shraman Pramanick, Krishna Kumar Singh, Nanyun Peng, Kai-Wei Chang, Yong Jae Lee

arXiv 2026

Paper Project

A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications

Neel Mokaria*, Rishie Raj*, Dheeraj Baiju*, Xiaoqian Shen, Shraman Pramanick, Kevin Qinghong Lin, Arda Senocak, Mike Zheng Shou, Philip Torr, Mohamed Elhoseiny, Yapeng Tian, Ruohan Gao, Salman Khan, Sayan Nag, Sanjoy Chowdhury, Dinesh Manocha

TMLR 2026

Paper arXiv

2025

SciFig: Towards Automating Scientific Figure Generation

Siyuan Huang, Yifan Zhou, Yutong Gao, Zi Yin, Juyang Bai, Xinxin Liu, Rama Chellappa, Chun Pong Lau, Cheng Peng, Sayan Nag, Shraman Pramanick

arXiv 2025

Paper Project Code Dataset

Enrich and Detect: Video Temporal Grounding with Multimodal LLMs

Shraman Pramanick, Effrosyni Mavroudi, Yale Song, Rama Chellappa, Lorenzo Torresani, Triantafyllos Afouras

ICCV 2025 (Highlights, Top 2.4%)

Paper Project

2024

SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers

Shraman Pramanick*, Rama Chellappa, Subhashini Venugopalan*

NeurIPS 2024 D&B

Paper Code Dataset Poster

Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model

Shraman Pramanick*, Guangxing Han*, Rui Hou, Sayan Nag, Ser-Nam Lim, Nicolas Ballas, Qifan Wang, Rama Chellappa, Amjad Almahairi

CVPR 2024 (Highlights, Top 2.8%)

Paper Project Poster

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

Kristen Grauman et al.

CVPR 2024 (Oral, Top 0.8%)

Paper Project Blog Video

2023

EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone

Shraman Pramanick, Yale Song, Sayan Nag, Kevin Qinghong Lin, Hardik Shah, Mike Z. Shou, Rama Chellappa, Pengchuan Zhang

ICCV 2023

Paper Code Project Poster

UniVTG: Towards Unified Video-Language Temporal Grounding

Kevin Qinghong Lin, Pengchuan Zhang, Joya Chen, Shraman Pramanick, Difei Gao, Alex JP. Wang, Rui Yan, Mike Z. Shou

ICCV 2023

Paper Code

VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment

Shraman Pramanick*, Li Jing*, Sayan Nag*, Jiachen Zhu, Hardik Shah, Yann LeCun, Rama Chellappa

TMLR 2023

Paper Code Project

Localizing and Grasping of 3-D Objects by a Vision-Actuated Robot Arm using Brain-Computer Interface

Arnab Rakshit, Shraman Pramanick, Anurag Bagchi, Saugat Bhattacharyya

Biomedical Signal Processing and Control, Elsevier, 2023

Paper

2022

Where in the World is this Image? Transformer-based Geo-localization in the Wild

Shraman Pramanick, Ewa Nowara, Joshua Gleason, Carlos D. Castillo, Rama Chellappa

ECCV 2022

Paper Code + Data Slides Poster Video

Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection

Shraman Pramanick*, Aniket Roy*, Vishal M. Patel

WACV 2022

Paper Slides Poster Video

2021

MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets

Shraman Pramanick*, Shivam Sharma*, Dimitar Dimitrov, Shad Aktar, Preslav Nakov, Tanmoy Chakraborty

Findings of EMNLP 2021

Paper Code + Data Poster Slides

Detecting Harmful Memes and Their Targets

Shraman Pramanick, Dimitar Dimitrov, Rituparna Mukherjee, Shivam Sharma, Shad Aktar, Preslav Nakov, Tanmoy Chakraborty

Findings of ACL 2021

Paper Code + Data Slides Video

See, Hear, Read: Leveraging Multimodality with Guided Attention for Abstractive Text Summarization

Yash Atri*, Shraman Pramanick*, Vikram Goyal, Tanmoy Chakraborty

Knowledge-Based Systems, Elsevier, 2021

Paper Code + Data

Exercise? I thought you said 'Extra Fries': Leveraging Sentence Demarcations and Multi-hop Attention for Meme Affect Analysis

Shraman Pramanick, Shad Aktar, Tanmoy Chakraborty

ICWSM 2021

Paper Code Slides Poster