8000 WangShao2000 (Shaohan Wang) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View WangShao2000's full-sized avatar

Block or report WangShao2000

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

MPIE-Bench: Benchmark for multi-person character-consistent image editing under contact, with a six-axis evaluation protocol.

Python 10 Updated Jul 29, 2026

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

Python 1,368 92 Updated Jul 14, 2026

A deep research framework

Python 39 1 Updated Apr 21, 2026

AI Agent prompts for deep paper reading — auto-routes to benchmark, methodology, or survey/opinion analysis frameworks. Works with Cursor, Claude Code, Codex, and OpenCode.

17 6 Updated Jul 2, 2026

A-RAG: Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces. State-of-the-art RAG framework with keyword, semantic, and chunk read tools for multi-hop QA.

Python 366 61 Updated Feb 6, 2026

[ACL 2026] WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora

Python 21 1 Updated May 11, 2026

Wiki Live Challenge: Challenging Deep Research Agents with Expert-Level Wikipedia Articles

Python 5 1 Updated Feb 6, 2026

DeepResearch Bench II (DRB2) is the follow-up to DeepResearch Bench, with a stronger focus on measuring the gap between deep research systems and human experts. It does so by decomposing expert-wri…

Python 98 8 Updated Oct 19, 2026

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Python 850 88 Updated Sep 29, 2026

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

TypeScript 12,414 1,123 Updated Nov 11, 2026

The open-source code of MetaStone-S1.

Python 106 8 Updated Aug 1, 2025
Python 226 18 Updated Jul 17, 2025
0