tencent-ailab

IP-Adapter. The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

V-Express. V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.

SongGeneration. The official code repository for LeVo: High-Quality Song Generation with Multi-Preference Alignment

persona-hub. Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"

hok_env. Honor of Kings AI Open Environment of Tencent

SongBloom. The official code repository for SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement

grover. This is a Pytorch implementation of the paper: Self-Supervised Graph Transformer on Large-Scale Molecular Data

pika. a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi

MuQ. Official repository of the paper "MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization".

bddm. BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

FRA-RIR. Python

PCDMs. Implementation code：Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models

DrugOOD. OOD Dataset Curator and Benchmark for AI-aided Drug Discovery

MuCodec. Python

SongPrep. The official code repository for SongPrep: A Preprocessing Framework and End-to-end Model for Full-song Structure Parsing and Lyrics Transcription.

Frequency_Aug_VAE_MoESR. Latent-based SR using MoE and frequency augmented VAE decoder

Leopard. The repository for the paper titled "Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks"

BridgeVocoder. The official repo of BridgeVoC, which explores using the Schrödinger Bridge framework for neural vocoding.

tleague_projpage. Jinja

Interformer. Jupyter Notebook

3m-asr. 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition

RLogist. RLogist = RL (reinforcement learning) + Pathologist

UltraDualPathCompression. A Pytorch-based implementation of the compression and decompression module in "Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression".

hokoff. Python

MDM. MDM

marl-mini. Python

TriNet. TriNet: stabilizing self-supervised learning from complete or slow collapse on ASR.

Lodoss. Python

ICML21_OAXE. Python

season. [EMNLP 2022] Salience Allocation as Guidance for Abstractive Summarization

hifi3dface_projpage. Project page for our paper "High-Fidelity 3D Digital Human Creation from RGB-D Selfies".

GrndPodcastSum. (ACL 2022) The source code for the paper "Towards Abstractive Grounded Summarization of Podcast Transcripts"

OASum.

learning_singing_from_speech. Project page for our paper "DurIAN : DurIAN-SC: Duration Informed Attention Network based Singing Voice Conversion System".

Arena. Python

ZED. This is the repository for EMNLP 2022 paper "Efficient Zero-shot Event Extraction with Context-Definition Alignment"

valuationgame. Jupyter Notebook

AnLLM. Python

MetaLogic. Python

DrugAssist. DrugAssist: A Large Language Model for Molecule Optimization

TLeague. Python

machine-translation. Open source on machine translation

TPolicies. Python

siam.

inferflow. Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).

zebra-inference. Python

NegSampling-NER. Negative sampling for solving the unlabeled entity problem in NER. ICLR-2021 paper: Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition.

FOLNet. This repository includes the code for First-Order Logic Network (FOLNet).

Awesome-LLM-MT.

TImitate. Python

Macaw-LLM. Python

GuoFeng-Webnovel. Multilingual Corpus of Web Fiction

Is-ChatGPT-A-Good-Translator. A preliminary evaluation of ChatGPT/GPT-4 for machine translation.

Multi-Agents-Debate. The first work to explore Multi-Agents Debate with Large Language Models :D

Document-MT-LLM. Datasets on Document-Level Machine Translation via ChatGPt and GPT-4.

durian. Project page for our paper "DurIAN : Duration Informed Attention Network For Multimodal Synthesis".

pitch-net. Project page for our paper "PitchNet: Unsupervised Singing Voice Conversion with Pitch Adversarial Network".