নমস্কার — I am Soujanya Poria (সৌজন্য পড়িয়া)
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore
My group studies how AI can reason, explain itself, and act safely across language, vision, and audio. I'm an Associate Professor at EEE, NTU, leading the DeCLaRe Lab. Before NTU, I was at SUTD.
Research Focus
My research focuses on language and multimodal intelligence, with emphasis on systems that reason, explain, align with human values, and operate robustly across modalities. My recent work spans LLM evaluation, safety and alignment, multimodal reasoning, text-to-audio generation, embodied AI, and affective computing.
Open to Collaboration
Prospective students and collaborators should first review the lab research slides and current publications before reaching out.
Research slidesAward Highly Cited Researcher 2026
Recognized by Web of Science.
AAAI 2026 Two papers accepted
ICLR 2026 Four papers accepted
ICML 2026 Two papers accepted
2025 Joined EEE, NTU
Moved to the School of Electrical and Electronic Engineering at NTU.
ACL 2025 Four papers accepted
EMNLP 2025 Five papers accepted
DeCLaRe Lab
Much of this work grows out of the DeCLaRe Lab, where we study dependable, communicative, and reasoning-capable AI systems across language, vision, audio, and embodied interaction. The group brings together students and collaborators working on multimodal learning, affective computing, trustworthy LLMs, and agents that can act with better grounding.
Selected Publications
A small set of representative papers, grouped by research direction.
Representation Learning & Fusion
MISA was one of the early works to use attention for fusing multimodalities.
- MISAACM MM
- Tensor Fusion NetworkEMNLP
- Memory Fusion NetworkAAAI
- Multimodal InfoMaxNAACL
Emotion, Sentiment & Dialogue
MELD is used as a benchmark in Qwen-Audio, Qwen2-Audio, Audio-Flamingo, SALMONN, MiniCPM-o-4.5, and Phi-4.
- MELDACL
- DialogueRNNAAAI
- DialogueGCNEMNLP
- BC-LSTMACL
- MIMEEMNLP
- CICEROACL
Text-to-Audio Generation
LLM Evaluation & Reasoning
- InstructEvalarXiv
- Mathematical and Coding CompetencyACL Findings
- PuzzleVQA / AlgoPuzzleVQAACL / NAACL
- Reasoning Paths OptimizationEMNLP Findings
Data-Efficient ML, Attention & Memory
- Data-AgentICML
- EFLAarXiv
- Delta-MemarXiv
AI Safety, Alignment & Trustworthiness
- Red Teaming LLMsArxiv
- Safety ArithmeticEMNLP
- Trustworthy RAGICLR
- FerretEMNLP Findings
Retrieval-Augmented Generation
- Chain-of-KnowledgeICLR
- Consistency Guided RetrievalWWW
- M-LongDocEMNLP
Agents, Planning & Robotics
- Emma-XACL
- NORAProject
- From Grounding to ManipulationEMNLP Findings
- Can-Do!arXiv