Pinned Repositories
Adan
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
EditAnything
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
envpool
C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.
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)
poolformer
PoolFormer: MetaFormer Is Actually What You Need for Vision (CVPR 2022 Oral)
understand-r1-zero
Understanding R1-Zero-Like Training: A Critical Perspective
volo
VOLO: Vision Outlooker for Visual Recognition
zero-bubble-pipeline-parallelism
Zero Bubble Pipeline Parallelism
Sea AI Lab's Repositories
sail-sg/EditAnything
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
sail-sg/understand-r1-zero
Understanding R1-Zero-Like Training: A Critical Perspective
sail-sg/oat
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
sail-sg/zero-bubble-pipeline-parallelism
Zero Bubble Pipeline Parallelism
sail-sg/inceptionnext
InceptionNeXt: When Inception Meets ConvNeXt (CVPR 2024)
sail-sg/oat-zero
A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.
sail-sg/sailor-llm
[EMNLP-2024] ⚓️ Sailor: Open Language Models for South-East Asia
sail-sg/TreeMeshGPT
[CVPR 2025] TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing
sail-sg/regmix
[ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)
sail-sg/CPO
[NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.
sail-sg/sailcraft
🚢 Data Toolkit for Sailor Language Models
sail-sg/autofd
Automatic Functional Differentiation in JAX
sail-sg/I-FSJ
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
sail-sg/sailor2
🔱 Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs
sail-sg/d4ft
A JAX library for Density Functional Theory.
sail-sg/jax_xc
Exchange correlation functionals translated from libxc to jax
sail-sg/LongSpec
LongSpec: Long-Context Speculative Decoding with Efficient Drafting and Verification
sail-sg/jrystal
A JAX-based Differentiable Density Functional Theory Framework for Materials
sail-sg/SkyLadder
The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling
sail-sg/Meta-Unlearning
sail-sg/closer-look-LLM-unlearning
The official code of the paper "A Closer Look at Machine Unlearning for Large Language Models".
sail-sg/Rigging-ChatbotArena
Improving Your Model Ranking on Chatbot Arena by Vote Rigging
sail-sg/VocabularyParallelism
Vocabulary Parallelism
sail-sg/LightTrans
The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"
sail-sg/sailcompass
🧭 SailCompass: Towards Reproducible and Robust Evaluation for Southeast Asian Languages
sail-sg/InfNeRF
InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity
sail-sg/Meta-ARVDM
Official Implementation of "Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework"
sail-sg/Megatron-Sailor2
Megatron for Sailor2/Qwen2.5
sail-sg/SEA-WildBench
Multilingual WildBench for south-east Asian languages.
sail-sg/AR-Video-Diffusion