Tejas Srinivasan

10 papers · 2020–2025 · 5 conferences · across top CS/AI conferences

Achievements

🗺️ Taxonomy Completionist (27) 🧭 Keyword Pioneer 🌈 Renaissance Researcher (7) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (5) 🏃 Academic Marathon (5) 🐝 Cross-Pollinator (14) 💎 Century Club (10) ❓ The Questioner

Conferences

EMNLP (4) ACL (2) NAACL (2) INTERSPEECH (1) NIPS (1)

Top co-authors

Jesse Thomason (4) Desmond Elliott (2) Florian Metze (2) Ramon Sanabria (2) Hyundong Justin Cho (1) Tanmay Gupta (1) Michael Saxon (1) Spencer Lin (1) Yejin Choi (1) Seoho Ahn (1)

Keywords

multimodal learning (6) vision-language model (4) automatic speech recognition (3) visual context (2) visual reasoning (2) attention mechanism (2) speech enhancement (1) visual question answering (1) action recognition (1) coreference resolution (1) visual grounding (1) visual dialog (1) object detection (1) pragmatic reasoning (1) selective prediction (1) elo rating (1) transfer learning (1) noise robustness (1) pairwise comparison (1) catastrophic forgetting (1)

Papers

Can Vision Language Models Understand Mimed Actions? ACL 2025

Compare without Despair: Reliable Preference Evaluation with Generation Separability EMNLP 2024

Selective “Selective Prediction”: Reducing Unnecessary Abstention in Vision-Language Reasoning ACL 2024

WINOVIZ: Probing Visual Properties of Objects Under Different States NAACL 2024

Multimodal Speech Recognition for Language-Guided Embodied Agents INTERSPEECH 2023

CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks NIPS 2022

Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models NAACL 2022

Multimodal Speech Recognition with Unstructured Audio Masking EMNLP 2020

Fine-Grained Grounding for Multimodal Speech Recognition EMNLP 2020

Reasoning Over History: Context Aware Visual Dialog EMNLP 2020