multimodal

A complete pipeline for BraTS 2020

[ICLR 2026] Official code repository for "⚡️VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration"

Real-event-anchored benchmark for detecting AI-generated videos in real-world crisis settings.

[CVPR 2025] Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering

[ICLR 2025] MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs

Democratizing Augmented Reality research and development.

PhyX: Does Your Model Have the "Wits" for Physical Reasoning?

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.

GAKG is a multimodal Geoscience Academic Knowledge Graph (GAKG) framework by fusing papers' illustrations, text, and bibliometric data.

Efficient Multimodal Foundation Model Adaptation for Recommendation

Unified interface for interacting with various LLMs hundreds of models, caching, fallback mechanisms, and enhanced reliability.

An agent that edits your Word and Excel files — then looks at them, through real Microsoft Office, to check its own work

Official repository of the paper "MIRAGE: A multimodal foundation model and benchmark for comprehensive retinal OCT image analysis", published in npj Digital Medicine (2025).

Official Implementation of VisualClaw: A Real-Time, Personalized Agent for the Physical World

OpenCV Spatial AI Competition 3rd prize winner project "Automatic Lawn Mower Navigation"

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（codex，claude code 等） 调用。

[CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"

PyTorch implementation of LIMoE