Sea AI Lab

sdft

[ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".

sailor-llm

Sailor: Open Language Models for South-East Asia

sailcraft

Data Toolkit for Sailor Language Models

d4ft

A JAX library for Density Functional Theory.

zero-bubble-pipeline-parallelism

Zero Bubble Pipeline Parallelism

finetune-fair-diffusion

Code of the paper: Finetuning Text-to-Image Diffusion Models for Fairness

MDT

Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)

CLoT

CVPR'24, Official Codebase of our Paper: "Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation".

AnyDoor

AnyDoor: Test-Time Backdoor Attacks on Multimodal Large Language Models

Adan

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

InfNeRF

InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity

envpool

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

Agent-Smith

[ICML2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast

GDPO

Graph Diffusion Policy Optimization

lm-random-memory-access

Consistent3D

The official PyTorch implementation of Consistent3D (CVPR 2024)

EditAnything

Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

zero-bubble-megatron-deepspeed

Zero Bubble Pipeline Parallelism implemented on Megatron-Deepspeed

autofd

Automatic Functional Differentiation in JAX

mugs

A PyTorch implementation of Mugs proposed by our paper "Mugs: A Multi-Granular Self-Supervised Learning Framework".

MMCBench

D-TRAK

Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)

Megatron-LLM

distributed trainer for LLMs

metaformer

MetaFormer Baselines for Vision (TPAMI 2024)

sewformer

jax_xc

Exchange correlation functionals translated from libxc to jax

lorahub

The official repository of paper "LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition".

inceptionnext

InceptionNeXt: When Inception Meets ConvNeXt (CVPR 2024)

edp

[NeurIPS 2023] Efficient Diffusion Policy

ScaleLong

The official repository of paper "ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection" (NeurIPS 2023)