Skip to content
Preprint

Projector Is All You Train

Aug 2026 · 0 citations · 49 references
Computer Science

TL;DR

It is found that training only the projector is sufficient to achieve strong multimodal performance relative to existing baseline models and the authors' jointly trained MLLMs with the same encoder and backbone, and that joint training leads to undesirable drift in existing capabilities of the language model.

Abstract

The typical training process of a multimodal large language model (MLLM) involves adapting both the language model backbone and the projector between the backbone and a modality-specific encoder. We ask whether fine-tuning the backbone of an MLLM is necessary to adapt it to a new modality. Through experiments on 3D MLLMs, we find that training only the projector is sufficient to achieve strong multimodal performance relative to existing baseline models and our jointly trained MLLMs with the same encoder and backbone. We also show that joint training leads to undesirable drift in existing capabilities of the language model, which projector-only training avoids by definition. Furthermore, projector-only training has approximately twice the training sample throughput of joint training. We validate our findings across different language model backbones via 3D classification and captioning benchmarks as well as standard benchmarks evaluating language, vision, and spatial reasoning capabilities.

View source

Similar papers

Preprint Jul 2026

Alignment Is All You Need: Instruction-Free Training for General Audio-Language Models

The results suggest that competitive MLLM can emerge from alignment alone, reducing multimodal extension to a lightweight projector-training problem that generalizes across modalities and adapts rapidly to each new LLM release.

Xuanru Zhou, Yiwen Shao, Jiahong Li et al. · 1 citation

Multimodal Concept Mapping

This work investigates how MLLMs learn novel concepts by introducing concepts in unimodal pre-training or multimodal fine-tuning, and evaluates the model’s ability to generalize between the two settings, and evaluates how deeply a model maps concepts across modalities.

S. Boppana, Tian Yun, Carina Curto et al. · 0 citations
Preprint Jul 2026

MEUSLI: a Multilingual Projector for LLM-based ASR and Beyond

MEUSLI is introduced, the first open-science multilingual projector family that links a Whisper encoder with open-source multilingual LLMs, enabling fully open-source end-to-end ASR in 28 European languages.

Lorenzo Concina, Seraphina Fong, M. Matassoni et al. · 0 citations
Preprint Aug 2026

Matryoshka Language Model Suites

Training a language model suite classically requires training each model separately and serving them independently. We improve both training and inference efficiency by stacking sub-models of increasing size into a single nested architecture trained end-to-end. This Matryoshka training framework reduces the total parameter count of the suite, enables low-cost distillation from the largest to all smaller sub-models at every training step, and is well-suited for speculative decoding as the draft model is contained within the verifier. We validate our approach by training a Matryoshka suite comprising 500M, 1.5B, and 3B sub-models. Our suite is on par with independently trained baselines on benchmark performance and validation and out-of-domain perplexities, while using 36% less training compute and improving the throughput of speculative decoding by 14-26%. We also ablate key architectural choices, offering guidance for building strong Matryoshka LM suites.

Nathan Godey, Yoav Artzi · 0 citations
Preprint Jul 2026

Scaling Native Multimodal Pre-Training From Scratch

This empirical research establishes the essential groundwork for predictably scaling multimodal foundation models by modeling the influence of data composition on compute laws and allocation exponents and derive an efficiency frontier specifying precise configurations of model size, token count, and data mixture.

Haoyuan Wu, Aoqi Wu, Hai Wang et al. · 1 citation
Preprint Aug 2026

Evaluation-Conditioned Training: Teaching Models to Generalize to Stronger Oversight Regimes

Evaluation-Conditioned Training (ECT), a post-training framework that uses natural language to condition each training sample on the fidelity of the feedback the authors provide and then elicits the desired behavior by conditioning the LLM on a high-fidelity monitor in deployment, is introduced.

Alec Harris, Kasey Corra, Archie Chaudhury et al. · 0 citations