Skip to content
Preprint

ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs

Aug 2026 · 0 citations · 32 references
Computer Science

Abstract

Existing scaling strategies for Multimodal Large Language Models (MLLMs) typically expand either model parameters or sequential inference computation, incurring substantial memory or latency overhead. More importantly, most existing methods fail to alter the rigid, fixed computation allocation between the Vision Transformer and the Large Language Model components, limiting task-specific optimization. To address this, we introduce the Parallel Vision-Language (ParVL) scaling framework for MLLMs, which scales parallel computation by reusing the existing ViT and LLM backbone parameters across multiple vision and language branches. This framework raises a central question: given a fixed backbone parameter budget, how should additional shared-backbone computation be allocated between the vision and language modalities? We instantiate each parallel computational stream with branch-specific prefix parameters over a shared backbone, and train the entire model end-to-end via full-parameter supervised fine-tuning on roughly 13B tokens. We systematically study the computation-allocation trade-off between the ViT encoder and LLM decoder. ParVL improves overall multimodal performance over same-recipe single-branch baselines, and the best evaluated vision--language allocation varies across tasks. Code is available at https://github.com/YangYangGirl/ParVL.

View source

Similar papers

Preprint Jul 2026

Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs

SmartVL is proposed, a unified adaptive inference framework that jointly controls vision token number and model compute capability in response to varying input contents and compute budgets and consistently outperforms prior adaptive methods and achieves superior accuracy-efficiency Pareto frontiers.

Pengcheng Wang, Zhiquan Wang, Jayoung Lee et al. · 0 citations
Preprint Jul 2026

Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models

Scaling Large Language Models (LLMs) has been driven mainly by enlarging the Transformer backbone, but for an already-strong model this requires another round of costly pretraining. We study whether an existing backbone can keep improving by allocating more computation to each token while leaving the Transformer backbone fixed. Depth-recurrent (looped) Transformers pursue this goal but are hard to scale, because looped computation does not fit naturally with the pipeline parallelism used to train the largest models. We add computation along the sequence-length dimension, where the extra computation is simply a longer input and stays compatible with standard large-model training. We propose Hidden Decoding, a sequence-length scaling method applied during continued pretraining (CPT). It expands each token into n streams with independent embedding tables and keeps the intermediate streams'key-value cache as context, so each token performs more internal computation without adding or widening Transformer layers. To keep this affordable at scale, we introduce Stream-Factorized Attention, in which most layers attend only within each stream and only a few layers mix across streams, reducing the attention cost from quadratic to roughly linear in n. Experiments support two scaling results. At frontier scale, we train WeLM-HD4-80B and WeLM-HD4-617B at n=4 and improve their matched non-HD baselines, making Hidden Decoding the first demonstrated sequence-length scaling method at the 100B+ MoE scale. Across expansion factors, the gains grow as n increases, showing that sequence-length expansion is a practical fixed-backbone scaling path for frontier-scale LLMs.

Aiwei Liu, Cheng Shi, Chuhan Wu et al. · 2 citations
Preprint Aug 2026

Rollplex: Cross-Phase GPU Spatial Sharing for Vision Language Model Post-Training

Rollplex is presented, a runtime that decomposes the reference and training phase and moves the prefix computation into the rollout decode window and achieves speedup over serial colocation and disaggregation under the same GPU budget, while preserving the synchronous RL update.

Hanfeng Lu, Tianyu Feng, Suyi Li et al. · 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 Jul 2026

AutoEncoder-Compressed Parallel Split Learning for Pre-trained Model Fine-Tuning

AE-PSL is proposed, a communication-efficient PSL framework that compresses intermediate activations and gradients using a lightweight AutoEncoder placed at the split layer and introduces a novel two-stage alignment mechanism, which adapts the AE to the pre-trained model's feature manifold and client-specific feature distributions before DFT.

Bas Meuwissen, Vasileios Tsouvalas, N. Meratnia · 0 citations

Representation-Aware Modularity: Efficient Cross-Task Generalization for LLMs

RaMod, a Representation-Aware Modularity framework, is proposed, a Representation-Aware Modularity framework to extend the ReFT paradigm to CTG through two novel components: Dual-Modular Representation & Parameter Fine-tuning, which manipulates only a strategically chosen subset of hidden representations with modular interventions to guide the model toward solving unseen tasks.

Zheng Gong, Ying Sun, Chao Wang et al. · 0 citations