AI Agent Skills

[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced.

UFM: A Unified Dense Image Correspondence Estimator for both Optical Flow & Wide Baseline Matching Tasks. Matches any pair of images. (NeurIPS 2025)

[CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

End-to-end Lane Detection for Self-Driving Cars (ICCV 2019 Workshop)

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"

Monitor smart contracts deployed on blockchain and test against vulnerabilities with Mythril. It was presented at DEFCON 2019.

[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning

🔥[NeurIPS'25] DeepFund: Pilot for Your Next Fund Investment

[NeurIPS 2024] PointMamba: A Simple State Space Model for Point Cloud Analysis

[NeurIPS 2021] [T-PAMI] Global Filter Networks for Image Classification

Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st place on KITTI) [MVA 2019]

Official PyTorch implementation of "BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation" (NeurIPS 2021)

The First Place Solution of Kaggle iMaterialist (Fashion) 2019 at FGVC6

🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".

Official Chainer implementation of GP-GAN: Towards Realistic High-Resolution Image Blending (ACMMM 2019, oral)