MaRiO: Multi-agent Collaborative Reasoning via Shared Observations in MLLMs
cs.CV
Submitted: 2026-11-07
Updated: 2026-11-07
Project page: https://omarftt.github.io/MaRiO-page
Terminology
Sources
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- LLaVA-Video: Video Instruction Tuning With Synthetic Data
- Building Cooperative Embodied Agents Modularly with Large Language Models
- COMBO: Compositional World Models for Embodied Multi-Agent Cooperation
- Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
- MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
- LLaVA-OneVision: Easy Visual Task Transfer
- Ovis2.5 Technical Report
- Gemini: A Family of Highly Capable Multimodal Models
- Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
- Visual Spatial Tuning
- CLEVRER: CoLlision Events for Video REpresentation and Reasoning
- SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
- BLINK: Multimodal Large Language Models Can See but Not Perceive
- SQA3D: Situated Question Answering in 3D Scenes
- Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
- VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments
- Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
- GPT-4 Technical Report
- OpenAI GPT-5 System Card
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs