yxchng

RWKV-CLIP

The official code of "RWKV-CLIP: A Robust Vision-Language Representation Learner"

EmbodiedScan

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

Lamini-Memory-Tuning

Banishing LLM Hallucinations Requires Rethinking Generalization

Depth-Anything-V2

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

mask-grounding

xlstm

Official repository of the xLSTM.

GaussianFormer

[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

Grounded_3D-LLM

Code&Data for Grounded 3D-LLM with Referent Tokens

Context-Cluster

[ICLR 2023 Oral] Image as Set of Points

recurrentgemma

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

DiG

DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

LaneSegNet

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

Mamba-Reg

imp

a family of highly capabale yet efficient large multimodal models

pointMLP-pytorch

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

T-GATE

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

PSG4D

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

fast-kan

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

piecewise-rectified-flow

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

KAN-GPT-2

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

ChebyKAN

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

PID

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

opennerf

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

M3Net

Multi-Space Alignments Towards Universal LiDAR Segmentation

OmniDrive

CompactNet

PointLLM

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

fairchem

FAIR Chemistry's library of machine learning methods for chemistry

RADIO

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

pykan

Kolmogorov Arnold Networks