ModRWKV: Transformer Multimodality in Linear Time (2025.emnlp-main)

Copied to clipboard

Challenge: Currently, multimodal studies are based on large language models with quadratic-complexity Transformer architectures.
Approach: They propose a decoupled multimodal framework built upon the RWKV7 architecture as its LLM backbone and a lightweight architecture to achieve multi-source information fusion.
Outcome: The proposed framework achieves multi-source information fusion through dynamically adaptable heterogeneous modality encoders.

Similar Papers

RWKV: Reinventing RNNs for the Transformer Era (2023.findings-emnlp)

Copied to clipboard

Challenge: recurrent neural networks struggle to match the performance of Transformers due to limitations in parallelization and scalability.
Approach: They propose a model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs.
Outcome: The proposed model performs on par with similarly sized RNNs, suggesting future work can leverage this architecture to create more efficient models.
Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are a cornerstone in artificial intelligence due to their exceptional performance.
Approach: They propose a training-free approach that integrates existing MLLMs for effective multimodal expansion while retaining their original performance.
Outcome: The proposed approach can expand LLMs' multimodal capabilities while retaining original performance.
Unveiling Multimodal Processing: Exploring Activation Patterns in Multimodal LLMs for Interpretability and Efficiency (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in multimodal large language models have remained opaque.
Approach: They propose a method to convert dense MLLMs into fine-grained Mixture-of-Experts architectures.
Outcome: The proposed method outperforms random expert pruning and sparse activation and model pruning.
MM-LLMs: Recent Advances in MultiModal Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: MultiModal Large Language Models (MM-LLMs) have undergone significant advances in the past year . traditional MM models incur substantial computational costs, especially when trained from scratch .
Approach: They propose a taxonomy encompassing 126 MM-LLMs and summarize key training recipes to enhance their potency.
Outcome: The proposed models preserve the reasoning and decision-making capabilities of LLMs and empower diverse range of MM tasks.
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture (2025.findings-emnlp)

Copied to clipboard

Challenge: Long-context Large Language Models (MLLMs) are critical for video understanding and image analysis.
Approach: They propose a hybrid architecture that integrates Mamba and Transformer blocks . they introduce data construction methods that capture both temporal and spatial dependencies .
Outcome: The proposed model achieves competitive results across various benchmarks while maintaining high throughput and low memory consumption.
Learning Flexible Large Multimodal Models with Arbitrary Modality Combinations (2026.findings-acl)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) have potential for cross-modal understanding . but extending MLLM to handle diverse modalities introduces two challenges .
Approach: They propose a dual-stage compression mechanism to reduce the number of modality tokens per modality and condense it into a single, compact token sequence.
Outcome: Experiments show that Flex-M3 outperforms its counterpart trained on only full-modality data.
From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning, Efficiency and beyond (2024.lrec-tutorials)

Copied to clipboard

Challenge: This tutorial aims to deliver a comprehensive review of cutting-edge research in MLLMs.
Approach: This tutorial will review cutting-edge research in MLLMs and examine the impact of ML in learning and reasoning.
Outcome: This course will review cutting-edge research in MLLMs and examine the impact of ML models on learning, learning, and multimodal reasoning.
VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens.
Approach: They propose a training-free pruning framework that prunes multimodal tokens without a trained pruning method.
Outcome: The proposed pruning framework outperforms existing token pruning methods and generalizes across diverse MLLMs.
Adaptive Fusion Techniques for Multimodal Data (2021.eacl-main)

Copied to clipboard

Challenge: Effective fusion of data from multiple modalities is challenging due to the heterogeneous nature of multimodal data.
Approach: They propose two adaptive fusion techniques that aim to combine multimodal data effectively.
Outcome: The proposed networks can model context from other modalities better than existing methods.
Towards Unified Multimodal Large Language Models: A survey (2026.findings-acl)

Copied to clipboard

Challenge: unified multimodal large language models (MLLMs) are emerging but lack a systematic framework to connect them and situate current trends within a broader landscape.
Approach: They present a systematic review of unified Multimodal Large Language Models . they outline the foundational concepts and prerequisites for understanding them .
Outcome: The present review provides a systematic and systematic overview of unified MLLMs . it discusses persistent challenges and identify promising directions for future research .

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