利用 GitHub 的 Issues 和 GitHub Pages 搭建个人博客站点/数据展示。多屏幕适配。

Official Repository of paper MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

A GitHub Actions workflow for automatically counting open issues and their labels, and saving the statistics to a tag message for further request.

je曲谱库·移动端

Flutter 或 Vue 全家桶（Vue + VueRouter + Vuex + Axios）抓取 GitHub 上的 Issues，结合 GitHub Pages 搭建个人博客站点，支持 GitHub 登录和评论

Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration

ASANet: Asymmetric Semantic Aligning Network for RGB and SAR image land cover classification

explore AMT from the perspective of timbre

Adapting VLMs to Bench2Drive.

[TGRS'25] AirSpatialBot: A Spatially-Aware Aerial Agent for Fine-Grained Vehicle Attribute Recognization and Retrieval

[IGARSS 2025 Oral] A Simple Aerial Detection Baseline of Multimodal Language Models.

【Numbered musical notation tools】je 简谱 处理工具，包括转调、播放、制谱、midi提取（转换）与制作等

Solve Visual Understanding with Reinforced VLMs

GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks

GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding

[ICLR2025] Text4Seg: Reimagining Image Segmentation as Text Generation

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

汽车之家车型品牌车系车型等的数据

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Summary of Geoguesser Models / Agents

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

[NeurIPS 2024 Spotlight ⭐️ & TPAMI 2025] Parameter-Inverted Image Pyramid Networks (PIIP)

[ICLR 2025 Spotlight] OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

[TPAMI] Oriented object detection on STAR dataset.

A Survey on Vision-Language Geo-Foundation Models (VLGFMs)

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"