Deep Cognition and Language Research (DeCLaRe) Lab

This repository contains the source codes for the paper: "Aspect Sentiment Triplet Extraction using Reinforcement Learning" published at CIKM 2021.

JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment

Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards

Codes and datasets for the paper Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

This repo contains implementation of different architectures for emotion recognition in conversations.

This repository contains various models targetting multimodal representation learning, multimodal fusion for downstream tasks such as multimodal sentiment analysis.

NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks

MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis

This repository contains the dataset and baselines explained in the paper: M2H2: A Multimodal Multiparty Hindi Dataset For HumorRecognition in Conversations

This repository is maintained to release dataset and models for multimodal puzzle reasoning.

No description provided.

This repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study

Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions

[ICLR 2026] TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching

Official Repo for Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

[ICLR 2026] KAIROS: An LLM Eval Technique to Evaluate Multi-Agent Social Interactions

A family of diffusion models for text-to-audio generation.

This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.

This repository contains PyTorch implementations of the models from the paper An Empirical Study MIME: MIMicking Emotions for Empathetic Response Generation.

No description provided.

Codebase for ProactiveAI in conversations

This repository contains code for extending the Stanford Alpaca synthetic instruction tuning to existing instruction-tuned models such as Flan-T5.

Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding

Reading list for Awesome Sentiment Analysis papers

Codes and Checkpoints of the Interspeech paper "Sentence Embedder Guided Utterance Encoder (SEGUE) for Spoken Language Understanding"

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

This repository contains the dataset and the PyTorch implementations of the models from the paper Recognizing Emotion Cause in Conversations.

This repository implements our ACL Findings 2022 research paper RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction. The goal of Zero-Shot Relation Triplet Extraction (ZeroRTE) is to extract relation triplets of the format (head entity, tail entity, relation), despite not having annotated data for the test relation labels.