GitHunt

Sea AI Lab

sail-sg

Languages

Python83%Jupyter Notebook7%C++3%C3%Shell3%

Repos

101

Stars

12.3k

Forks

865

Top Language

Python

Loading contributions...

Top Repositories

Repositories

101
SA
sail-sg/understand-r1-zero

Understanding R1-Zero-Like Training: A Critical Perspective

Python1.2k57Updated 6 months ago
llmr1-zeroreasoningrl
SA
sail-sg/envpool

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

C++1.3k128Updated 1 hour ago
atari-gamesbox2dcpp17dm-controldm-envgymhigh-performance-computinglock-free-queuemujocoparallel-processingpybind11reinforcement-learningreinforcement-learning-environmentsroboticsthreadpoolvizdoom
SA
sail-sg/Attention-Sink

[ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)

Python1605Updated 8 months ago
attention-mechanismattention-sinklanguage-modellarge-language-models
SA
sail-sg/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".

Python32217Updated 1 year ago
associationhumor-generationlarge-language-modelsleap-of-thoughtmultimodal-deep-learning
SA
sail-sg/imperceptible-jailbreaks

[ArXiv 2025] Imperceptible Jailbreaking against Large Language Models

Python255Updated 5 months ago
SA
sail-sg/MDT

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

Python59443Updated 1 year ago
SA
sail-sg/TeamHOI

[CVPR 2026] TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size

Python280Updated 1 week ago
character-animationcooperative-aiembodied-aihuman-motion-generationhuman-object-interactionhumanoidhumanoid-robotmulti-agent-reinforcement-learningmulti-agent-systemsphysics-based-animationphysics-based-simulationphysics-simulationreinforcement-learning
SA
sail-sg/zero-bubble-pipeline-parallelismFork

Zero Bubble Pipeline Parallelism

Python45233Updated 10 months ago
SA
sail-sg/Cheating-LLM-Benchmarks

[ICLR 2025] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates (Oral)

Jupyter Notebook831Updated 1 year ago
SA
sail-sg/DiffMemorize

[TMLR 2025] On Memorization in Diffusion Models

Python303Updated 2 years ago
diffusion-modelsgenerative-modelmemorization
SA
sail-sg/edp

[NeurIPS 2023] Efficient Diffusion Policy

Python1128Updated 2 years ago
SA
sail-sg/Stable-RL

Rethinking the Trust Region in LLM Reinforcement Learning

Python505Updated 2 weeks ago
SA
sail-sg/D-TRAK

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

Jupyter Notebook383Updated 2 years ago
attributiondata-attributiondata-centric-aidata-valuationddpmdiffusion-modelsinfluence-functionsinterpretabilitystable-diffusion
SA
sail-sg/tty-use

No description provided.

C150Updated 5 months ago
SA
sail-sg/Adan

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

Python80971Updated 9 months ago
adanartificial-intelligencebert-modelconvnextcuda-programmingdeep-learningdiffusiondreamfusionfairseqgpt2llm-trainingllmsmaemoeoptimizerpytorchresnettimmtransformer-xlvit
SA
sail-sg/LongSpec

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification

Python763Updated 8 months ago
SA
sail-sg/sdft

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

Shell1626Updated 1 year ago
language-modelself-distillationsupervised-finetuning
SA
sail-sg/CPO

[NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.

Python1359Updated 1 year ago
SA
sail-sg/EditAnything

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

Python3.4k200Updated 1 year ago
SA
sail-sg/metaformer

MetaFormer Baselines for Vision (TPAMI 2024)

Python49531Updated 1 year ago
metaformerstarrelutransformer
SA
sail-sg/poolformer

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

Python1.4k118Updated 1 year ago
image-classificationmlppoolingpytorchtransformer
SA
sail-sg/TreeMeshGPT

[CVPR 2025] TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

Python18515Updated 10 months ago
SA
sail-sg/Video-Next-Event-Prediction

No description provided.

Python221Updated 7 months ago
SA
sail-sg/oat

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

Python63961Updated 1 month ago
alignmentdistributed-rldistributed-trainingdpodueling-banditsgrpollmllm-aligmentllm-explorationonline-alignmentonline-rlppor1-zeroreasoningrlhfthompson-sampling
SA
sail-sg/variational-reasoning

Code for "Variational Reasoning for Language Models"

Python571Updated 5 months ago
SA
sail-sg/AnytimeReasoner

Optimizing Anytime Reasoning via Budget Relative Policy Optimization

Python533Updated 8 months ago
SA
sail-sg/SimLayerKV

The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.

Python500Updated 1 year ago
SA
sail-sg/VeriFree

Reinforcing General Reasoning without Verifiers

Python976Updated 9 months ago
SA
sail-sg/sewformer

No description provided.

Python20026Updated 2 years ago
SA
sail-sg/FDM

The official PyTorch implementation of Fast Diffusion Model

Python956Updated 2 years ago

Gists

Recent Activity

Sea AI Lab (sail-sg) | GitHunt