[Pattern Recognition'24] Pytorch implementation of Multiple-environment Self-adaptive Network for Aerial-view Geo-localization 🚁 https://arxiv.org/abs/2204.08381

📌 Official baseline implementation of 'Last-Meter Precision Navigation for UAVs: A Diffusion-Refined Aerial Visual Servoing Approach‘, serving as the baseline for the UAVM @ ACM MM 2026 Workshop Ch…

Official Repo for ICCV25-Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization

🚁 Can Vision-Language Models Think from the Sky? UAVReason for Aerial Reasoning and Generation

Road Maps as Free Geometric Priors: Weather-Invariant Drone Geo-Localization with GeoFuse

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向，无论你是初学者还是进阶开发者，都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势，并通过实践掌握从理论到落地的全过程。

Graph-Backed Generative Brick Assembly

The official code of "Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search" [SIGIR 2026]

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Text-Instructed Generation and Refinement for Template-Free Hand-Object Interaction

[CVPR 2026] Code for "The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts"

[ICLR'26] SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models

The official code of "Minimizing the Pretraining Gap: Domain-aligned Text-Based Person Retrieval"

Official Repo for Look, Compare and Draw: Differential Query Transformer for Automatic Oil Painting

A Collection of AIGC Research Groups

A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2026/ECCV2024 AIGC

Open-source unified multimodal model

[ICLR 2026 🔥 ] Official implementation of "UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing"

Counter-Strike: 2 Offset Dumper

UM CIS PhD Qualifying Examination Resources - A curated collection of study notes, past materials, and preparation guides for the Qualifying Examination (QE) of the PhD programme in Computer and In…

[CVPR 2025] LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding

Source 2 Viewer is an all-in-one tool to browse VPK archives, view, extract, and decompile Source 2 assets, including maps, models, materials, textures, sounds, and more.

Pytorch implementation of "Test-time Adaptation for Cross-modal Retrieval with Query Shift".

IEEE CoG & NeurIPS workshop paper 'Counter-Strike Deathmatch with Large-Scale Behavioural Cloning'