Sea AI Lab

EditAnything

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

poolformer

PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)

envpool

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

Adan

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

lorahub

[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

MDT

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

metaformer

MetaFormer Baselines for Vision (TPAMI 2024)

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".

zero-bubble-pipeline-parallelism

Zero Bubble Pipeline Parallelism

sailor-llm

⚓️ Sailor: Open Language Models for South-East Asia

mugs

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

sdft

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

regmix

🧬 RegMix: Data Mixture as Regression for Language Model Pre-training

Agent-Smith

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

sailcraft

🚢 Data Toolkit for Sailor Language Models

Consistent3D

The official PyTorch implementation of Consistent3D (CVPR 2024)

scaling-with-vocab

📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623

autofd

Automatic Functional Differentiation in JAX

AnyDoor

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

d4ft

A JAX library for Density Functional Theory.

finetune-fair-diffusion

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

I-FSJ

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NextGenAISafety @ ICML 2024)

dice

Official implementation of Bootstrapping Language Models via DPO Implicit Rewards

CPO

GDPO

Graph Diffusion Policy Optimization

optim4rl

Optim4RL is a Jax framework of learning to optimize for reinforcement learning.

lm-random-memory-access

sailcompass

zero-bubble-megatron-deepspeed

Zero Bubble Pipeline Parallelism implemented on Megatron-Deepspeed

InfNeRF

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