yxchng

manim

Animation engine for explanatory math videos

pykan

Kolmogorov Arnold Networks

FoundationPose

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

iTransformer

Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight), https://openreview.net/forum?id=JePfAI8fah

fairchem

FAIR Chemistry's library of machine learning methods for chemistry

recurrentgemma

Open weights language model from Google DeepMind, based on Griffin.

Context-Cluster

[ICLR 2023 Oral] Image as Set of Points

RADIO

Official repository for "AM-RADIO: Reduce All Domains Into One"

pointMLP-pytorch

[ICLR 2022 poster] Official PyTorch implementation of "Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework"

PointLLM

[ECCV 2024] PointLLM: Empowering Large Language Models to Understand Point Clouds

piecewise-rectified-flow

PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator

T-GATE

T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!

ChebyKAN

Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.

fast-kan

FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)

LLaVA-UHD

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images

LaneSegNet

[ICLR 2024] Map Learning with Lane Segment for Autonomous Driving

LEGENT

Open Platform for Embodied Agents

imp

a family of highly capabale yet efficient large multimodal models

S-D-Mamba

Code for "Is Mamba Effective for Time Series Forecasting?"

OmniDrive

DiG

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

KAN-GPT-2

Training small GPT-2 style models using Kolmogorov-Arnold networks.

PSG4D

4D Panoptic Scene Graph Generation (NeurIPS'23 Spotlight)

VL-Mamba

Implementation of "VL-Mamba: Exploring State Space Models for Multimodal Learning"

opennerf

[ICLR 2024] OpenSet 3D Neural Scene Segmentation with Pixel-wise Features and Rendered Novel Views

PID

[NeurIPS 2023, ICMI 2023] Quantifying & Modeling Multimodal Interactions

CompactNet

Mamba-Reg

M3Net

Multi-Space Alignments Towards Universal LiDAR Segmentation

mask-grounding