Deepanway Ghosal

Researcher, Google DeepMind

Joined

July 2019

Names

Deepanway Ghosal (Preferred)

Emails

****@gmail.com (Confirmed)

****@mymail.sutd.edu.sg (Confirmed)

Personal Links

Career & Education History

Researcher

Google DeepMind (google.com)

2024 – Present

PhD student

Singapore University of Technology and Design (sutd.edu.sg)

2019 – 2024

Undergrad student

Indian Institute of Technology Patna (iitp.ac.in)

2014 – 2018

Advisors, Relations & Conflicts

PhD Advisor

Soujanya Poria

2019 – 2024

Expertise

commonsense reasoning

inference

implicit reasoning

logical reasoning

Present

emotion recognition in conversations

graph neural networks

Present

dialogue reasoning

dialogue explanation

sentence ordering

Present

Publications

Tracking the Evolution of Multimodal Reasoning on Visual Puzzles
Vernon Toh, Yew Ken Chia, Deepanway Ghosal, Soujanya Poria
- AAAI 2026 Bridge LMReasoning Oral
- Readers: Everyone
Not All Votes Count! Translated Program for Verification Improves Self-Consistency of Language Models for Math Reasoning
Vernon Toh, Deepanway Ghosal, Soujanya Poria
- AI4Math@ICML25 Poster
- Readers: Everyone
MixEval-X: Any-to-any Evaluations from Real-world Data Mixture
Jinjie Ni, Yifan Song, Deepanway Ghosal, Bo Li, David Junhao Zhang, Xiang Yue, Fuzhao Xue, Yuntian Deng, Zian Zheng, Kaichen Zhang, Mahir Shah, Kabir Jain, Yang You, Michael Shieh
- ICLR 2025 Spotlight
- Readers: Everyone
Tango 2: Aligning Diffusion-based Text-to-Audio Generative Models through Direct Preference Optimization
Navonil Majumder, Chia-Yu Hung, Deepanway Ghosal, Wei-Ning Hsu, Rada Mihalcea, Soujanya Poria
- MM2024 Oral
- Readers: Everyone
Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts
Deepanway Ghosal, Navonil Majumder, Roy Ka-Wei Lee, Rada Mihalcea, Soujanya Poria
- EMNLP 2023 Findings
- Readers: Everyone
ReTAG: Reasoning Aware Table to Analytic Text Generation
Deepanway Ghosal, Preksha Nema, Aravindan Raghuveer
- EMNLP 2023 Main
- Readers: Everyone
Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model
Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Soujanya Poria
- 25 Apr 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication
Navonil Majumder, Deepanway Ghosal, Devamanyu Hazarika, Alexander F. Gelbukh, Rada Mihalcea, Soujanya Poria
- 2021 (modified: 13 Jul 2021)
- CoRR 2021
- Readers: Everyone
Persuasive dialogue understanding: The baselines and negative results
Hui Chen, Deepanway Ghosal, Navonil Majumder, Amir Hussain, Soujanya Poria
- 2021 (modified: 13 Nov 2021)
- Neurocomputing 2021
- Readers: Everyone
Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical Study
Deepanway Ghosal, Navonil Majumder, Rada Mihalcea, Soujanya Poria
- 2021 (modified: 13 Nov 2021)
- ACL/IJCNLP (Findings) 2021
- Readers: Everyone

View all 29 publications

Co-Authors

View all 45 co-authors