AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Spatially-aware Weights Tokenization for NeRF-Language Models

Andrea Amaduzzi, Pierluigi Zama Ramirez, Giuseppe Lisanti, Samuele Salti, Luigi Di Stefano

NeurIPS 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Benchmarks and analysis of MLLMs

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a spatially-aware tokenization of NeRF MLP weights for language models that operate directly on NeRF parameters.

Problem

Understanding NeRFs with natural language by having multimodal LLMs process NeRF MLP weights; prior approaches rely on a global representation of the weights, which the abstract indicates is limiting.

Approach

Tokenize NeRF MLP weights in a spatially-aware way rather than through a single global weight representation, so an MLLM can consume the NeRF's parameters as structured tokens.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy