Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT GPT-5.6, Codex GPT-5.6, GPT-5.5. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xA…

[ECCV 2026] LivingWorld: Interactive 4D World Generation with Environmental Dynamics

[ECCV 2026] 3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

Effortless data labeling with AI support from Segment Anything and other awesome models.

[ICCV 2025] Medical World Model

Data Generation Pipeline for Mobility

Code for 3D-LLM: Injecting the 3D World into Large Language Models

[ICLR 2026🔥] SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense

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

[CVPR 2026] VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Search infrastructure for AI

Question-Aware Gaussian Experts for Audio-Visual Question Answering -- Official Pytorch Implementation (CVPR'25, Highlight)

ChronoQA - A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented Generation

🏆 Winner of Cloth Competition: 🥇 ICRA 2023, 🥈 ICRA 2024 - Center Direction Network for Grasping Point Localization on Cloths - IEEE Robotics and Automation Letters 2024 paper

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

This is the first released survey paper on hallucinations of large vision-language models (LVLMs). To keep track of this field and continuously update our survey, we maintain this repository of rel…

✨✨Latest Advances on Multimodal Large Language Models

COLMAP - Structure-from-Motion and Multi-View Stereo

[CVPR 2026 Highlight, the CVPR Compute Gold Star] Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

CLIPScore EMNLP code

Segment Anything in Medical Images

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

Official Repository for "Changes in Real Time: Online Scene Change Detection with Multi-View Fusion" (CVPR26-Highlight).

[ICLR 2026] Mobile-GS: Real-time Gaussian Splatting for Mobile Devices

Code for Reducing Hallucinations in Vision-Language Models via Latent Space Steering