Skip to content
@declare-lab

Deep Cognition and Language Research (DeCLaRe) Lab

Hi! 👋👋

Welcome fellow researchers to the DeCLaRe Lab! We are a small academic research group working on interesting and challenging AI problems. To know more about our work, please browse our catalog of publications. Want to be part of the team? Please drop us an email.

And here is our Team Declare! 😃

Pinned Loading

  1. conv-emotion Public

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

    Python 1.5k 337

  2. MELD Public

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

    Python 935 220

  3. tango Public

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

    Python 1.2k 103

  4. instruct-eval Public

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

    Python 546 45

  5. TangoFlux Public

    TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching

    Jupyter Notebook 763 66

  6. nora Public

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

    Python 159 8

Repositories

Showing 10 of 70 repositories
  • Auto-Scaling Public

    [Arxiv 2024] Official Implementation of the paper: "Towards Robust Instruction Tuning on Multimodal Large Language Models"

    Jupyter Notebook 9 MIT 1 0 0 Updated Aug 2, 2025
  • jamify Public

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

    Python 47 5 3 0 Updated Aug 1, 2025
  • nora Public

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

    Python 159 8 3 0 Updated Jul 29, 2025
  • TangoFlux Public

    TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching

    Jupyter Notebook 763 66 6 1 Updated Jul 29, 2025
  • tango Public

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

    Python 1,182 103 26 0 Updated Jul 29, 2025
  • HTML 0 MIT 0 0 8 Updated Jul 29, 2025
  • PathFinder-PRM Public

    This repository contains the official implementation of Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision.

    Jupyter Notebook 6 1 0 0 Updated May 27, 2025
  • dialogxpert Public

    Codebase for ProactiveAI in conversations

    Python 1 0 0 0 Updated May 22, 2025
  • Emma-X Public

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

    Python 68 6 5 0 Updated May 17, 2025
  • LLM-ReasoningTest Public

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

    Python 10 Apache-2.0 1 0 0 Updated Apr 21, 2025