Sharp Monocular View Synthesis in Less Than a Second

Context-measure: Contextualizing Metric for Camouflage

谷歌新书Agent设计模式(agentic design patterns)中文版，持续更新。附：在线阅读、pdf和epub电子书下载。

A curated list of awesome prompt/adapter learning methods for vision-language models like CLIP.

This package contains the original 2012 AlexNet code.

The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"

[NeurIPS '25 Spotlight] Official Pytorch implementation of "Vision Transformers Don't Need Trained Registers"

Lets make video diffusion practical!

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

Depth Anything 3

Official implementation for paper "Relational Surrogate Loss Learning", ICLR 2022

Differentiable Sorting Networks

Open source implementation of "Vision Transformers Need Registers"

Prefix-Tuning: Optimizing Continuous Prompts for Generation

PyTorch Implementation of Attention Prompt Tuning: Parameter-Efficient Adaptation of Pre-Trained Models for Action Recognition

Code for visualizing the loss landscape of neural nets

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models

VICRegL official code base

LSNet: See Large, Focus Small [CVPR 2025]

ICCV25 highlight

Collection of resources that combine dynamic systems, control with deep learning.

Build resilient language agents as graphs.

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Official implementation of CVPR 2024 paper "Prompt Learning via Meta-Regularization".

Reference PyTorch implementation and models for DINOv3