Soujanya Poria

91 papers · 2015–2026 · 11 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (13) 🐝 Cross-Pollinator (13) 🏃 Academic Marathon (10) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (11) 🗺️ Taxonomy Completionist (10) 🧭 Keyword Pioneer 🌟 Keyword Trendsetter Combo (3) 🏠 Conference Loyalist (30) 🔬 Deep Specialist (27) 🧬 Topic Evolution 🏆 Keyword Champion (5) 👥 Mega-Team (35) 🤝 Dynamic Duo (25) ❓ The Questioner (2) 🗃️ Keyword Collector (369) 💎 Century Club (89) 📈 Trend Setter 🚀 Conference Pioneer 🔥 Unstoppable (11) ⚡ Prolific Year (11)

Conferences

EMNLP (30) ACL (23) NAACL (13) COLING (7) AAAI (4) EACL (4) ICLR (3) IJCNLP (3) INTERSPEECH (2) ECCV (1) SEMEVAL (1)

Top co-authors

Navonil Majumder (26) Rada Mihalcea (18) Deepanway Ghosal (18) Erik Cambria (17) Rishabh Bhardwaj (14) Devamanyu Hazarika (13) Lidong Bing (10) Yew Ken Chia (9) Wei Han (8) Hui Chen (8)

Research topics

Applications (1)

Keywords

multimodal learning (13) large language model (12) sentiment analysis (12) text classification (11) emotion recognition (10) language model (9) conversation analysis (6) sentiment classification (6) commonsense knowledge (6) domain adaptation (5) attention mechanism (5) multimodal sentiment analysis (5) knowledge distillation (4) emotion classification (4) dialogue system (4) data augmentation (3) representation learning (3) recurrent neural network (3) video understanding (3) benchmark evaluation (3)

Papers

DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM Priors AAAI 2026

10 Open Challenges Steering the Future of Vision-Language-Action Models AAAI 2026

Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse ICLR 2025

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning ACL 2025

Pixel-Level Reasoning Segmentation via Multi-turn Conversations ACL 2025

DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models ACL 2025

Evaluating LLMs’ Mathematical and Coding Competency through Ontology-guided Interventions ACL 2025

Why AI Is WEIRD and Shouldn't Be This Way: Towards AI for Everyone, with Everyone, by Everyone AAAI 2025

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision EMNLP 2025

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique EMNLP 2025

From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems EMNLP 2025

Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk Appetite? EMNLP 2025

M-LongDoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework EMNLP 2025

PREMISE: Matching-based Prediction for Accurate Review Recommendation NAACL 2025

Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability NAACL 2025

AlgoPuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Algorithmic Multimodal Puzzles NAACL 2025

Reward-Guided Tree Search for Inference Time Alignment of Large Language Models NAACL 2025

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses ICLR 2025

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic ACL 2024

InstructEval: Towards Holistic Evaluation of Instruction-Tuned Large Language Models EACL 2024

Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction EMNLP 2024

Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths EMNLP 2024

WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models EMNLP 2024

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations EMNLP 2024

CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models NAACL 2024

Self-Adaptive Sampling for Accurate Video Question Answering on Image Text Models NAACL 2024

Mustango: Toward Controllable Text-to-Music Generation NAACL 2024

Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense NAACL 2024

A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the CHATGPT Era and Beyond EACL 2024

Large Language Models for Automated Open-domain Scientific Hypotheses Discovery ACL 2024

Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models ACL 2024

PuzzleVQA: Diagnosing Multimodal Reasoning Challenges of Language Models with Abstract Visual Patterns ACL 2024

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources ICLR 2024

HYPERTTS: Parameter Efficient Adaptation in Text to Speech Using Hypernetworks COLING 2024

Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts EMNLP 2023

Uncertainty Guided Label Denoising for Document-level Distant Relation Extraction ACL 2023

A Robust Information-Masking Approach for Domain Counterfactual Generation ACL 2023

Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt ACL 2023

UDAPTER - Efficient Domain Adaptation Using Adapters EACL 2023

Lightweight Spatial Modeling for Combinatorial Information Extraction From Documents EACL 2023

LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models EMNLP 2023

Adapter Pruning using Tropical Characterization EMNLP 2023

kNN-CM: A Non-parametric Inference-Phase Adaptation of Parametric Text Classifiers EMNLP 2023

Sentence Embedder Guided Utterance Encoder (SEGUE) for Spoken Language Understanding INTERSPEECH 2023

ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation INTERSPEECH 2023

CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues ACL 2022

So Different Yet So Alike! Constrained Unsupervised Text Style Transfer ACL 2022

Knowledge Enhanced Reflection Generation for Counseling Dialogues ACL 2022

Analyzing Modality Robustness in Multimodal Sentiment Analysis NAACL 2022

PIP: Physical Interaction Prediction via Mental Simulation with Span Selection ECCV 2022

SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning COLING 2022

KNOT: Knowledge Distillation Using Optimal Transport for Solving NLP Tasks COLING 2022

DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification COLING 2022

RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction ACL 2022

Vector-Quantized Input-Contextualized Soft Prompts for Natural Language Understanding EMNLP 2022

A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach EMNLP 2022

Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering EMNLP 2022

MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences EMNLP 2022

SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training EMNLP 2022

STaCK: Sentence Ordering with Temporal Commonsense Knowledge EMNLP 2021

Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis EMNLP 2021

Causal Augmentation for Causal Sentence Classification EMNLP 2021

More Identifiable yet Equally Performant Transformers for Text Classification ACL 2021

Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical Study ACL 2021

MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences NAACL 2021

Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical Study IJCNLP 2021

More Identifiable yet Equally Performant Transformers for Text Classification IJCNLP 2021

MIME: MIMicking Emotions for Empathetic Response Generation EMNLP 2020

KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis ACL 2020

CMU-MOSEAS: A Multimodal Language Dataset for Spanish, Portuguese, German and French EMNLP 2020

COSMIC: COmmonSense knowledge for eMotion Identification in Conversations EMNLP 2020

DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation IJCNLP 2019

Multi-task Learning for Multi-modal Emotion Recognition and Sentiment Analysis NAACL 2019

DialogueRNN: An Attentive RNN for Emotion Detection in Conversations AAAI 2019

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations ACL 2019

DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation EMNLP 2019

Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper) ACL 2019

IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis EMNLP 2018

Contextual Inter-modal Attention for Multi-modal Sentiment Analysis EMNLP 2018

Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph ACL 2018

CASCADE: Contextual Sarcasm Detection in Online Discussion Forums COLING 2018

Proceedings of Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML) ACL 2018

Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos NAACL 2018

Modeling Inter-Aspect Dependencies for Aspect-Based Sentiment Analysis NAACL 2018

ICON: Interactive Conversational Memory Network for Multimodal Emotion Detection EMNLP 2018

Tensor Fusion Network for Multimodal Sentiment Analysis EMNLP 2017

Context-Dependent Sentiment Analysis in User-Generated Videos ACL 2017

SenticNet 4: A Semantic Resource for Sentiment Analysis Based on Conceptual Primitives COLING 2016

A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks COLING 2016

SeNTU: Sentiment Analysis of Tweets by Combining a Rule-based Classifier with Supervised Learning SEMEVAL 2015

Deep Convolutional Neural Network Textual Features and Multiple Kernel Learning for Utterance-level Multimodal Sentiment Analysis EMNLP 2015