Stars
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
An interactive app based on Sethares' dissonance measures
[NeurIPS '25 Spotlight] Official Pytorch implementation of "Vision Transformers Don't Need Trained Registers"
official implementation of "Interpreting CLIP's Image Representation via Text-Based Decomposition"
Achieve state of the art inference performance with modern accelerators on Kubernetes
Top papers related to LLM-based agent evaluation
Code for CVPR 2022 paper "Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation"
ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).
Machine-learning-based performance prediction for AI workloads
Official pytorch implementation of the paper: "Classification Diffusion Models: Revitalizing Density Ratio Estimation"
[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration
A high-throughput and memory-efficient inference and serving engine for LLMs
OpenTelemetry Python API and SDK
Localizing Regions on 3D Shapes via Text Descriptions
Provides network connectivity to WSL 2 when blocked by VPN
Open-source observability for your GenAI or LLM application, based on OpenTelemetry
Robustifying Point Cloud Networks by Refocusing
This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 paper "Analyzing Sou…
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
A Gateway for connecting application services in different domains, networks, and cloud infrastructures
compare the theory attention gradient with PyTorch attention gradient
Pytorch code for ICRA 2022 Paper StructFormer