RePlay
A Comprehensive Framework for Building End-to-End Recommendation Systems with State-of-the-Art Models
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
A Comprehensive Framework for Building End-to-End Recommendation Systems with State-of-the-Art Models
Official PyTorch implementation of the paper "Dataset Distillation with Neural Characteristic Function: A Minmax Perspective" (NCFM) in CVPR 2025 (Full Score, Highlight).
RAG evaluation without the need for "golden answers"
An intelligence orchestra
Develop an EvoAML framework integrating graph networks and temporal evolution analysis, aimed at addressing cross-industry tracking gaps and translating these methods into BSA/AMLA 2020 compliant solutions.
🔍 The hardest search benchmark in the wild — vague, multi-turn, proactive. 200 long-horizon tasks with persona-driven progressive disclosure, scored by verifiable schema-free knowledge-graph evaluation. No vibes, just triplet F1.
Make drawing and labeling bounding boxes a piece of cake
A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.
Metadata, scripts and baselines for the MTG-Jamendo dataset
[ECCV 2026] Official repo of "Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens"
Ghost Security's collection of AppSec skills for AI coding agents
The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.
Five-Star Chef: a fully multi-agent customer-service chatbot built on LangGraph, with text-to-SQL, text-to-Cypher, LightRAG, and multimodal capabilities.
Cataclysm - Code generation library for the end game
10 Claude skills that generate studio-quality AI video prompts for Seedance 2.0 on Higgsfield. Viral hooks, SaaS demos, personal brand, faceless content, luxury aesthetic & more.
Sentence paraphrase generation at the sentence level
This is an official PyTorch implementation of our NeurIPS 2023 paper "GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization"
12306 MCP Server is a high-performance train-ticket query backend based on the Model Context Protocol (MCP). It exposes standardized access to official 12306 real-time data, including ticket availability, station information, train stops, and transfer/connection plans.
Implementation of Q-Transformer, Scalable Offline Reinforcement Learning via Autoregressive Q-Functions, out of Google Deepmind
An unappealing collection of Claude Skills and resources.