Rob Barton

Unifying image clustering across different clustering scenarios remains challenging due to fundamental gaps among tasks. We introduce a Guideline-Driven Image Clustering Agent, the first universal framework that bridges these gaps through textual guidelines. To incorporate complex guidelines without task-specific training, we propose Generative Concept Proxy Modeling, which generates guideline-aware embeddings via concept proxy extraction.

The Model Context Protocol (MCP) and Agent-to-Agent (A2A) have gained a significant industry attention over the past year. MCP first grabbed the world’s attention in dramatic fashion when it was published by Anthropic in November 2024, garnering tens of thousands of stars on GitHub within the first month. Organizations quickly saw the value of MCP as a way to abstract APIs into natural language, allowing LLMs to easily interpret and use them as tools.

Multimodal Large Language Models (MllMs) have achieved SOTA performance in various visual language tasks by fusing the visual representations with LLMs lever-aging some visual adapters. In this paper, we first establish that adapters using query-based Transformers such as Q-former is a simplified Multi-instance Learning method with-out considering instance heterogeneity/correlation.