-
HPE
- Taipei
Stars
Run a documented subset of verl-style OPD on one consumer GPU—typed config, Parquet prompts, and PEFT scale-out artifacts.
🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model + stateful harness
Foundations of Medical Large Language Model Learning
A cross-platform vector database, which can be integrated into existing databases as a plugin.
This project is based on "user comments from e-commerce platforms" and uses the "BERT + P-Tuning (soft template)" method to accurately classify the comment texts
Real-data options intelligence for AI agents — 29 Skills for Claude Code, Cursor & beyond
AI agent skill for end-to-end hotel search and booking—compare live rates across leading OTAs and hotel suppliers, verify availability, book stays, and manage reservations, cancellations, and payme…
[ECCV 2026 Oral] Official repository for Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
The memory-first, self-improving agent harness built on EverOS, with MiroThinker-powered deep research and reasoning.
Multimodal RL training framework for diffusion & omni models
This project leverages the ChatGLM-6B Large Language Model (LLM), combined with LoRA and P-Tuning fine-tuning techniques, to implement text classification and Information Extraction (IE) specifical…
On-chain Ethereum whale tracking with NLP sentiment analysis for price impact modelling
SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles
A compiler that converts PyTorch models into deployable TensorFlow custom ops backed by Triton PTX kernels.
An open source AI-native agentic SOC platform
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.
OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.
Cross-Area Adaptation Framework for GPR Subsurface Diagnosis
OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
Predicting high-fitness mutations based on protein inverse folding models
xiaogang00 / MATPO-PR
Forked from mzf666/MATPOOfficial implementation of MATPO-PR: Multi-Agent Tool-Integrated Policy Optimization with Process Reward.
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, …
AST-based outline director for human-centered AI presentation workflows.
⭐️ A cross-platform web-based All-in-One assistant tool for Claude Code, Codex & Gemini CLI, based on CC Switch.
A privacy-first, local-first password manager with cross-platform synchronization.