Deep Cognition and Language Research (DeCLaRe) Lab

All

71 repositories

KAIROS
Public
KAIROS: An LLM Eval Technique to Evaluate Multi-Agent Social Interactions
Python
•
Apache License 2.0
•0•1•0•0•Updated Aug 24, 2025Aug 24, 2025
.github
Public
0•0•0•0•Updated Aug 19, 2025Aug 19, 2025
declare-lab.github.io
Public
HTML
•
MIT License
•0•0•0•8•Updated Aug 19, 2025Aug 19, 2025
jamify
Public
JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment
tts ai-song song-generation ai-song-generator
Python
•
Other
•7•83•5•0•Updated Aug 7, 2025Aug 7, 2025
Auto-Scaling
Public
[Arxiv 2024] Official Implementation of the paper: "Towards Robust Instruction Tuning on Multimodal Large Language Models"
instruction-following large-language-models llm multimodal-instruction-tuning multimodal-large-language-models llm-robustness
Jupyter Notebook
•
MIT License
•1•9•0•0•Updated Aug 2, 2025Aug 2, 2025
nora
Public
NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
vision-language-action-model
Python
•9•167•7•0•Updated Jul 29, 2025Jul 29, 2025
TangoFlux
Public
TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching
tta text-to-audio generative-ai text-to-audio-ai flow-matching
Jupyter Notebook
•
Other
•66•772•6•1•Updated Jul 29, 2025Jul 29, 2025
tango
Public
A family of diffusion models for text-to-audio generation.
language-models diffusion diffusion-models text-to-audio audio-generation large-language-models
Python
•
Other
•104•1.2k•26•0•Updated Jul 29, 2025Jul 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.
reinforcement-learning reasoning process-reward-model
Jupyter Notebook
•1•6•0•0•Updated May 27, 2025May 27, 2025
dialogxpert
Public
Codebase for ProactiveAI in conversations
Python
•0•2•0•0•Updated May 22, 2025May 22, 2025
Emma-X
Public
Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
robotics agents vla vlm embodied-artificial-intelligence embodied-agent embodied-ai llm chain-of-thought embodied-intelligence
Python
•6•72•5•0•Updated May 17, 2025May 17, 2025
LLM-ReasoningTest
Public
Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions
reasoning humaneval gsm8k
Python
•
Apache License 2.0
•1•10•0•0•Updated Apr 21, 2025Apr 21, 2025
PromptDistill
Public
Python
•0•5•0•0•Updated Apr 2, 2025Apr 2, 2025
MM-InstructEval
Public
This repository contains code to evaluate various multimodal large language models using different instructions across multiple multimodal content comprehension tasks.
multimodal-large-language-models multimodal-content-comprehension-tasks
Python
•1•29•2•0•Updated Mar 9, 2025Mar 9, 2025
trust-align
Public
Codes and datasets for the paper Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse
rag retrieval-augmented-generation
Python
•4•63•0•0•Updated Mar 3, 2025Mar 3, 2025
LLM-PuzzleTest
Public
This repository is maintained to release dataset and models for multimodal puzzle reasoning.
gemini language-model multimodal-learning multimodal-deep-learning gpt-4 large-language-models llm llms gemini-pro
Python
•
MIT License
•7•101•0•0•Updated Feb 26, 2025Feb 26, 2025
darwin
Public
Python
•0•3•0•0•Updated Jan 24, 2025Jan 24, 2025
safety-arithmetic
Public
Jupyter Notebook
•5•12•0•0•Updated Jan 14, 2025Jan 14, 2025
PROVE
Public
Python
•0•4•0•0•Updated Dec 18, 2024Dec 18, 2024
ferret
Public
Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique
red-teaming llm safety-alignment
Python
•
Other
•3•18•1•0•Updated Aug 22, 2024Aug 22, 2024
Sealing
Public
[NAACL 2024] Official Implementation of paper "Self-Adaptive Sampling for Efficient Video Question Answering on Image--Text Models"
video-understanding visual-language-models naacl2024 multimodal-rag video-rag
Python
•
MIT License
•3•12•0•0•Updated Jul 25, 2024Jul 25, 2024
della
Public
DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
transformer huggingface llm llms model-merging
Python
•3•35•2•0•Updated Jul 12, 2024Jul 12, 2024
HyperTTS
Public
Python
•
MIT License
•2•37•1•0•Updated Apr 15, 2024Apr 15, 2024
resta
Public
Restore safety in fine-tuned language models through task arithmetic
alignment safety alignment-algorithm llm llms llm-safety llms-benchmarking llm-safety-benchmark
Python
•1•28•1•0•Updated Mar 28, 2024Mar 28, 2024
adapter-mix
Public
Python
•4•16•2•0•Updated Mar 14, 2024Mar 14, 2024
MM-Align
Public
[EMNLP 2022] This repository contains the official implementation of the paper "MM-Align: Learning Optimal Transport-based Alignment Dynamics for Fast and Accurate Inference on Missing Modality Sequences"
machine-learning natural-language-processing optimal-transport multimodal-sentiment-analysis multimodal-deep-learning
Python
•
MIT License
•2•30•0•0•Updated Mar 10, 2024Mar 10, 2024
MELD
Public
MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation
sentiment-analysis chatbot dialogue-systems personality-profiling personality-traits conversational-ai multimodal-interactions multimodal-sentiment-analysis emotion-recognition-in-conversation dialogue
Python
•
GNU General Public License v3.0
•221•943•31•1•Updated Mar 10, 2024Mar 10, 2024
instruct-eval
Public
This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.
llm instruct-tuning
Python
•
Apache License 2.0
•45•547•22•2•Updated Mar 10, 2024Mar 10, 2024
conv-emotion
Public
This repo contains implementation of different architectures for emotion recognition in conversations.
natural-language-processing sentiment-analysis memory-network pretrained-models emotion-analysis dialogue-systems conversational-agents natural-language-understanding conversational-ai emotion-recognition-in-conversation
Python
•
MIT License
•336•1.5k•7•1•Updated Mar 10, 2024Mar 10, 2024
red-instruct
Public
Codes and datasets of the paper Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
llama huggingface-transformers llm llms llama2
Python
•
Apache License 2.0
•13•103•1•0•Updated Mar 8, 2024Mar 8, 2024