Long-Term Tracking and Learning for Claude Code — 从源码机制到实战落地的完整知识库

Turn anything into slides

花笺，轻量优雅的跨平台桌面便签工具，支持 Markdown 编辑与预览

写论文时【一定】能用到的【prompt】

Code for Quality-aware Spatio-temporal Transformer Network for RGBT Tracking

Skills for Real Engineers. Straight from my .claude directory.

Official implementation of HIPTrack: Visual Tracking with Historical Prompts. (CVPR 2024)

Code and models for RELO

TradingAgents: Multi-Agents LLM Financial Trading Framework

符合nature论文学术表达和科研绘图的Skill

[ACL2026 main] Official implementation of "Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance"

👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!

My Python scripts to make high-quality figures for publications in top AI conferences and journals.

A personal investigation for RGBT tracking.

[NeurIPS 2024] VastTrack: Vast Category Visual Object Tracking

[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers

Taming Cascaded Mixture-of-Experts for Modality-missing Multi-modal Salient Object Detection

Official repo for ECCV 2024 paper: Fast Encoding and Decoding for Implicit Video Representation

CVPR 2024-Improved Implicit Neural Representation with Fourier Reparameterized Training

ICML2025-Inductive Gradient Adjustment for Spectral Bias in Implicit Neural Representations

Official implementation of "Implicit Neural Representations with Periodic Activation Functions"

[CVPR2026] SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking

Official code for the paper "Attention as a Hypernetwork"

An AI prompt optimizer for writing better prompts and getting better AI results.

Test-Time Training on Video Streams

[AAAI2026] CADTrack: Learning Contextual Aggregation with Deformable Alignment for Robust RGBT Tracking

The official repository for "Spatiotemporal-Untrammelled Mixture of Experts for Multi-Person Motion Prediction" (accepted by AAAI-26 oral)

[CVPR2026] RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation