SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.18096 · 2025

LLMs can see and hear without any training

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present MILS: Multimodal Iterative LLM Solver, a surprisingly simple, training-free approach, to imbue multimodal capabilities into your favorite LLM. Leveraging their innate ability to perform multi-step reasoning, MILS prompts the LLM to generate candidate outputs, each of which are scored and fed back iteratively, eventually generating a solution to the task. This enables various applications that typically require training specialized models on task-specific data. In particular, we establish a new state-of-the-art on emergent zero-shot image, video and audio captioning. MILS seamlessly applies to media generation as well, discovering prompt rewrites to improve text-to-image generation, and even edit prompts for style transfer! Finally, being a gradient-free optimization approach, MILS can invert multimodal embeddings into text, enabling applications like cross-modal arithmetic.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2501.18096")
get_code_for_paper("2501.18096")
have("2501.18096")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2501.18096.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2501.18096.svg)](https://syntology.ai/paper/2501.18096)

Connect an agent — have() is free.