Stars
Data and sample evaluation codes for Multimodal Rewardbench 2
Adapt Diffusion Models to Multi-frame interpolation
JittorGeometric is a Jittor-based graph machine learning library.
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505
[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
Agentic RAG for any scenario. Customize sources, depth, and width
NEO Series: Native Vision-Language Models from First Principles
This is the code for the paper "RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction", IEEE TCCN.
High-quality and compute-verified reproductions of cutting-edge AI papers.
Joint Semantic Detection and Dissemination Control of Phishing Attacks on Social Media via LLama- Based Modeling
Implementation of the papar "Sparse-to-Local-Dense Matching for Geometry-Guided Correspondence Estimation"
[TKDE2025] Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on large language model-based …
DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving
[PVLDB 2024 Best Paper Nomination] TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods
🔥[ICML 2024, Official Code] First work to propose a solution to the long-tail problem in IAA. 首篇针对IAA中的长尾问题提出解决方案的工作
FreeTacMan: Robot-free Visuo-Tactile Data Collection System for Contact-rich Manipulation
An Intelligent System for Spine Imaging Analysis and Automated Diagnostic Report Generation.
A curated collection of my quantitative finance research projects. Explores sector rotation, multi-factor models, and AI-driven strategies (machine learning/deep learning) across high, mid, and low…
Official codebase for "Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens" (NeruIPS 2025).
A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
Agent-ready RPA suite with out-of-the-box automation tools. Built for individuals and enterprises.
Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414
"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"