Publications
2024
Compare without Despair: Reliable Preference Evaluation with Generation Separability
Sayan Ghosh, Tejas Srinivasan, Swabha Swayamdipta
arXiV Preprint
Selective “Selective Prediction”: Reducing Unnecessary Abstention in Vision-Language Reasoning
Tejas Srinivasan, Jack Hessel, Tanmay Gupta, Bill Yuchen Lin, Yejin Choi, Jesse Thomason, Khyathi Raghavi Chandu
ACL Findings 2024
WinoViz: Probing Visual Properties of Objects Under Different States
Woojeong Jin, Tejas Srinivasan, Jesse Thomason, Xiang Ren
arXiV Preprint
2023
Exploring Strategies for Modeling Sign Language Phonology
Lee Kezar, Riley Carlin, Tejas Srinivasan, Zed Sehyr, Naomi Caselli, Jesse Thomason
European Symposium on Artificial Neural Networks (ESANN) 2023
I2I: Initializing Adapters with Improvised Knowledge
Tejas Srinivasan, Furong Jia, Mohammad Rostami, Jesse Thomason
Conference on Lifelong Learning Agents (CoLLAs) 2023
Multimodal Speech Recognition for Language-Guided Embodied Agents
Allen Chang, Xiaoyuan Zhu, Aarav Monga, Seoho Ahn, Tejas Srinivasan, Jesse Thomason
Interspeech 2023
Curriculum Learning for Data-Efficient Vision-Language Alignment
Tejas Srinivasan, Xiang Ren, Jesse Thomason
O-DRUM Workshop, CVPR 2023
2022
CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks
Tejas Srinivasan, Ting-Yun Chang, Leticia Pinto Alva, Georgios Chochlakis, Mohammad Rostami, Jesse Thomason
NeurIPS 2022 Datasets and Benchmarks Track
Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models
Tejas Srinivasan, Yonatan Bisk
4th Workshop on Gender Bias in Natural Language Processing, NAACL 2022
2020
Fine-Grained Grounding for Multimodal Speech Recognition
Tejas Srinivasan, Ramon Sanabria, Florian Metze, Desmond Elliott
Findings of Emperical Methods in Natural Language Processing (EMNLP) 2020
Multimodal Speech Recognition with Unstructured Audio Masking
Tejas Srinivasan, Ramon Sanabria, Florian Metze, Desmond Elliott
Workshop on Natural Language Processing Beyond Text, EMNLP 2020
Reasoning Over History: Context-Aware Visual Dialog
Muhammad Shah*, Shikib Mehri*, Tejas Srinivasan*
Workshop on Natural Language Processing Beyond Text, EMNLP 2020
Looking Enhances Listening: Recovering Missing Speech Using Images
Tejas Srinivasan, Ramon Sanabria, Florian Metze
International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2020
2019
Multitask Learning For Different Subword Segmentations In Neural Machine Translation
Tejas Srinivasan, Ramon Sanabria, Florian Metze
International Workshop on Spoken Language Translation (IWSLT) 2019
Structured Fusion Networks for Dialog
Shikib Mehri*, Tejas Srinivasan*, Maxine Eskenazi
Special Interest Group on Discourse and Dialogue (SIGDIAL) 2019
Best Paper Award
Analyzing Utility of Visual Context in Multimodal Speech Recognition Under Noisy Conditions
Tejas Srinivasan, Ramon Sanabria, Florian Metze
The How2 Challenge: New Tasks for Vision & Language, ICML 2019
* denotes equal contribution