Lists (4)
Stars
This is the official code of DeepSearch paper!
Official Repository of TimePerceiver (NeurIPS 2025)
Benchmarking RAG and agentic systems in Go vs Python
PyTorch Implementation of "TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting" (ICML 2025)
[AAAI 2026 Oral] Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline
Based on the mHC architecture proposed by deepseek, the residual links of the existing iTransformer are replaced and updated to obtain a new time series SOTA
A simple yet powerful agent framework that delivers with open-source models
[KDD 2025] DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting
Tongyi Deep Research, the Leading Open-source Deep Research Agent
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
[ICML 2025] Official repository of the TQNet paper: "Temporal Query Network for Efficient Multivariate Time Series Forecasting". This work is developed by the Lab of Professor Weiwei Lin (linww@scu…
Official implementation of Browse-Master, a tool-augmented web-search agent.
Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos
RevIN: Reversible Instance Normalization For Accurate Time-series Forecasting Against Distribution Shift
[NeurIPS 2024 Spotlight] Official repository of the CycleNet paper: "CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns". This work is developed by the Lab of Professor …
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
Repo for "Adaptation of Agentic AI"
🛠️ DeepAgent: A General Reasoning Agent with Scalable Toolsets
Build, evaluate and train General Multi-Agent Assistance with ease
[AAAI 2026] Official implementation of "TimeMosaic: Information-Density Guided Time Series Forecasting via Adaptive Granularity Patch and Segment-wise Decoding"
[IEEE Intelligent Systems] Awesome-Graph-augmented-LLM-Agent (GLA)
Open-source implementation of AlphaEvolve
A novel time series forecasting method, Times2D, transforms 1D data into 2D space using multi-period decomposition and derivative heatmaps to achieve state-of-the-art performance.