Research

Safety

Trustworthiness

Multimodality

Multimodal representation learning

TFN, MISA and Multimodal-InfoMax study how to combine language, vision and audio: by modelling their interactions, separating shared and modality-specific information, or preserving information during fusion.

AI for Science

Efficiency

Embodied AI

Code, models and data

  • Audio and music generation · Model · ICLR 2026

    TangoFlux

    Text-to-audio with flow matching and CRPO preference training. Makes 30 seconds of 44.1 kHz audio in a few seconds on one A40.

    885 stars 1,424/mo

  • Audio and music generation · Model · ACM MM 2023

    Tango

    Latent-diffusion text-to-audio model that reads the prompt with an instruction-tuned LLM (FLAN-T5).

    1,243 stars 71/mo

  • Audio and music generation · Model · NAACL 2024

    Mustango

    Text-to-music that follows chords, beats, tempo and key named in the prompt.

    396 stars 4,943/mo

  • Audio and music generation · Model · 2025

    JAM

    Small flow-matching song generator. You can set when each lyric word is sung.

    174 stars 183/mo

  • Audio and music generation · Dataset · 2023

    TangoPromptBank

    The text-audio caption corpus Tango was pretrained on.

    326/mo

  • Embodied AI and robotics · Model · 2025

    NORA

    3B-parameter vision-language-action model trained on 970k real-robot demonstrations. Small enough to run cheaply.

    225 stars 191/mo

  • Embodied AI and robotics · Model · 2025

    NORA-1.5

    NORA plus a flow-matching action expert, post-trained on action pairs ranked by a world model.

    110 stars 34/mo

  • Embodied AI and robotics · Model · 2025

    Emma-X

    An embodied multimodal action model that plans with grounded chain-of-thought and look-ahead spatial reasoning.

    85 stars 104/mo

  • Trustworthiness and safety · Model + data · ICLR 2025

    Trust-Align

    Scores whether RAG answers are supported and cited, and trains models to refuse when the documents don't contain the answer.

    75 stars 282/mo

  • Trustworthiness and safety · Code · ACL 2024

    RESTA

    Restores safety in a fine-tuned model by adding a safety vector back to its weights.

    33 stars

  • Trustworthiness and safety · Code + data · 2023

    Red-Instruct

    Chain-of-Utterances red-teaming: the RED-EVAL benchmark and the HarmfulQA dataset.

    111 stars 3,040/mo

  • Trustworthiness and safety · Benchmark · ICLR 2026

    OffTopicEval

    Tests whether an agent built for one task answers in-scope requests and declines the rest.

    12 stars 136/mo

  • Efficiency, memory and agents · Code · ICML 2026

    Data Agent

    Picks training examples during training, using the model's current difficulty and uncertainty as feedback.

    14 stars

  • Efficiency, memory and agents · Model · 2026

    δ-mem

    Online memory for a frozen LLM. Adds 0.12% parameters and steers attention through a low-rank interface.

    269 stars

  • Efficiency, memory and agents · Code · 2026

    IDEAgent

    Searches for a set of research ideas that meet quality thresholds without repeating one another.

    21 stars

  • Efficiency, memory and agents · Code · 2026

    EFLA

    Linear attention derived as the exact solution of its continuous-time dynamics.

    80 stars

  • Efficiency, memory and agents · Model · 2023

    Flan-Alpaca

    Alpaca-style instruction tuning applied to Flan-T5, released with the Flan-mini instruction set.

    355 stars 323/mo

  • Efficiency, memory and agents · Benchmark · 2023

    InstructEval

    Evaluates instruction-tuned models on problem solving, writing and alignment with human values.

    551 stars 46/mo

  • Multimodal understanding · Dataset · ACL 2019

    MELD

    Emotion and sentiment labels for 13,708 utterances from multi-party TV dialogue, with text, audio and video.

    1,096 stars 4,429/mo

  • Multimodal understanding · Code · 2019

    conv-emotion

    Reference implementations of emotion-recognition-in-conversation models, including DialogueRNN.

    1,532 stars

  • Multimodal understanding · Code · 2020

    multimodal-deep-learning

    Reference implementations of multimodal fusion models for sentiment and emotion.

    919 stars

  • Multimodal understanding · Code · ACM MM 2020

    MISA

    Splits each modality into a shared and a private representation before fusion.

    297 stars

  • Multimodal understanding · Dataset · 2021

    RECCON

    Finds the utterance that caused an emotion in a conversation.

    192 stars

  • Multimodal understanding · Dataset · 2022

    CICERO

    Commonsense inference over dialogue: causes, motivations, reactions and consequences.

    63 stars 241/mo

  • Multimodal understanding · Benchmark · 2024

    PuzzleVQA

    Visual puzzles and algorithmic tasks that separate perception errors from reasoning errors.

    122 stars 2,648/mo

  • Reading lists · Reading list · 2018

    Awesome Sentiment Analysis

    538 stars

  • Reading lists · Reading list · 2019

    Awesome ERC

    284 stars

Updated 2 November 2026 · All 84 public GitHub repositories · 51 models and 23 datasets on Hugging Face