Sign in

Repository Index

47,133 repositories indexed

Filters (1)

Filters

Clear all filters

1–24 of 31 · Most stars

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like agent, llm and tools tracing, debugging multi-agentic system, self-hosted dashboard and advanced analytics with timeline and execution graph view

  • agentneo
  • agents
  • ai-performance-optimization
  • llm-testing

Official repository for the Boltz biomolecular interaction models

  • binding-prediction
  • drug-discovery
  • protein-structure

Computer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Networks, Skin Detection through Backprojection, Motion Detection and Tracking, Saliency Map.

  • convolutional-neural-networks
  • motion-tracking
  • color-detection
  • face-detection

🔥 The first-ever interactive streaming video generation benchmark.

  • avatar-performance
  • interaction-streaming-video
  • real-time-video-editing
  • streaming-video-generation

Source code for "DeepDTA: deep drug-target binding affinity prediction"

  • protein-ligand-interactions
  • convolutional-neural-networks

Automation of some MAPT activities and interaction with the mobile Android device.

  • android-analysis
  • frida
  • mobile-hacking
  • mobile-penetration-testing

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System

  • adversarial-attacks
  • ai-safety
  • autonomous-driving
  • backdoor-attacks

TransformerCPI: Improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments(BIOINFORMATICS 2020) https://doi.org/10.1093/bioinformatics/btaa524

  • self-attention
  • compound-protein-interaction
  • transformercpi
  • structure-free-virtual-sreening

A Macau food recommendation Agent built on Thompson Sampling + StackedPareto weight fusion, with a full evaluation pipeline (5-fold CV, bootstrap CIs, stress tests) on 5,000 simulated users and 100k interactions. Competition entry for the QwenPaw AI Developer Challenge.