Challenge: Recent advances in multimodal large language models focus on improving performance . however, language prior conflict leads to suboptimal vision-language alignment .
Approach: They propose a method to decouple the alignment process from language prior interference . they use a proxy LLM to detach from language interference during pretraining .
Outcome: The proposed method improves training performance and generalizes training data.

Similar Papers

SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) integrate visual and textual inputs, yet modality alignment remains one of the most challenging aspects.
Approach: They propose a token-level supervision alignment method that enables more precise visual-text alignment during pretraining.
Outcome: The proposed method improves performance across various model sizes, with smaller models benefiting the most.
VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation (2026.acl-long)

Copied to clipboard

Challenge: Multimodal large language models have advanced rapidly, yet most remain English-centric . scaling multilingual multimodal instruction tuning is limited by the scarcity and high cost of non-English image–text supervision.
Approach: They propose a framework that decouples multilingual language enhancement from visual alignment by composing complementary task vectors over a shared LLM backbone.
Outcome: The proposed framework achieves competitive performance with a fully multimodally trained model using less than 2% of the text data.
A Survey on Training-free Alignment of Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a survey of large language models (LLMs) aims to ensure outputs adhere to human values, ethical standards, and legal norms.
Approach: They present the first systematic review of TF alignment methods . they categorize them by stages of pre-decoding, in-decoder and post-decoration .
Outcome: The proposed methods are based on training-free (TF) alignment techniques . they are able to be used in open-source and closed-source environments without retraining .
MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance (2024.emnlp-main)

Copied to clipboard

Challenge: MLLMs are deployed on limited image-text pairs, which makes them more vulnerable to catastrophic forgetting of their original abilities during safety fine-tuning.
Approach: They propose a plug-and-play strategy that detects harmful visual inputs and transforms harmful ones into harmless ones.
Outcome: The proposed approach mitigates the risks posed by malicious visual inputs without compromising the original performance of MLLMs.
Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Existing research treats MLLMs as unified systems optimized through end-to-end training, but the impact of vision encoder’s prior knowledge is seldom investigated.
Approach: They propose a metric to quantify the effect of prior knowledge on MLLM performance by integrating prior knowledge at the vision encoder level into a training framework.
Outcome: The proposed training framework incorporates prior knowledge at the vision encoder level, and significantly boosts visual understanding capabilities of MLLMs.
PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal instruction fine-tuning degrades textual reasoning capability, undermining multimodal performance.
Approach: They propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs to mitigate this degradation.
Outcome: The proposed framework reduces multimodal instruction fine-tuning degradation by incorporating a plateau-guided model merging method into MLLMs.
Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models (2024.acl-long)

Copied to clipboard

Challenge: Multi-modal large language models (MLLMs) are expected to support multi-turn queries of interchanging image and text modalities in production.
Approach: They propose to use visual-question-answering (VQA) datasets to annotate a 5k-sample VQA preference dataset and to investigate the degradation of VQA datasets.
Outcome: The proposed model surpasses the instruction-following capabilities of the language model with DPO and SteerLM.
DeepInsert: Early Layer Bypass for Efficient and Performant Multimodal Understanding (2026.eacl-long)

Copied to clipboard

Challenge: Recent work shows that hyperscaling of data and parameter count in LLMs is yielding diminishing improvement when weighed against training costs.
Approach: They propose to insert multimodal tokens directly into the middle of the model to bypass the early layers.
Outcome: The proposed method reduces training and inference costs while preserving performance.
Take a Closer Look at Multilinguality! Improve Multilingual Pre-Training Using Monolingual Corpora Only (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have demonstrated remarkable cross-lingual capability of pre-trained language models . however, semantic alignments may be the reason behind such capability but remain under-explored.
Approach: They propose token-level and semantic-level code-switched masked language modeling to improve cross-lingual interactions over mono-mPLMs without parallel sentences.
Outcome: The proposed method outperforms mono-mPLMs on natural language understanding and unsupervised machine translation tasks.
Aligners: Decoupling LLMs and Alignment (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications.
Approach: They propose to decouple LLMs and alignment by training *aligner* models that can be used to align any LLM on an as-needed basis.
Outcome: The proposed model can be used to align any LLM for a given criteria on an as-needed basis.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations