Papers with multimodal scenarios

15 papers
MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference (2025.naacl-long)

Copied to clipboard

Challenge: Long-context Multimodal Large Language Models (MLLMs) require substantial computational resources as their multimodal Key-Value (KV) cache grows with increasing input lengths, challenging memory and time efficiency.
Approach: They propose a dynamic multimodal KV cache allocation strategy that dynamically allocating KV size based on attention entropy to better adapt to multimodal interactions.
Outcome: The proposed model achieves up to 72% KV cache memory reduction and 2.82 faster decoding speeds while maintaining or enhancing performance on various multimodal tasks in a long context.
CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models (2025.coling-main)

Copied to clipboard

Challenge: Large language models excel in various language tasks, while large multimodal models effectively handle visual-language problems.
Approach: They propose to use a multimodal multimodal model evaluation benchmark to evaluate model performance in Chinese K12 classrooms.
Outcome: The proposed model evaluation tool is integrated with the CMMaTH dataset.
Multiple Knowledge-Enhanced Interactive Graph Network for Multimodal Conversational Emotion Recognition (2024.findings-emnlp)

Copied to clipboard

Challenge: Multimodal Emotion Recognition in Conversations models struggle due to lack of Common Sense Knowledge (CSK).
Approach: They propose a multimodal approach to integrate multiple knowledge into the edge representations by integrating textual and visual CSK.
Outcome: The proposed model outperforms state-of-the-art methods on two popular datasets.
ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances have extended DPO to multimodal scenarios, achieving strong performance.
Approach: They propose to use a sentence-level preference optimization technique to optimize individual sentences for more precise preference optimization without additional models or parameters.
Outcome: Experiments show that Adaptive Sentence-level Preference Optimization significantly improves the alignment of multimodal models.
MCiteBench: A Multimodal Benchmark for Generating Text with Citations (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing work focuses on generating citations for text-only content . experimental results reveal MLLMs struggle to ground outputs reliably when handling multimodal input .
Approach: They propose a benchmark to assess the ability of MLLMs to generate text with citations in multimodal contexts.
Outcome: The proposed benchmark assesses the ability of MLLMs to generate text with citations in multimodal contexts.
Cross-lingual Multimodal Sentiment Analysis for Low-Resource Languages via Language Family Disentanglement and Rethinking Transfer (2025.findings-acl)

Copied to clipboard

Challenge: Existing multimodal sentiment analysis methods are limited to textual data and cannot handle multimodal scenarios.
Approach: They propose a transfer learning framework that allows cross-lingual and cross-modal alignments and a language family disentanglement module that enhances the sharing of language universals within families.
Outcome: The proposed method is superior to existing methods and can handle low-resource languages.
Vision-Language Models Can Self-Improve Reasoning via Reflection (2025.naacl-long)

Copied to clipboard

Challenge: Chain-of-thought (CoT) has been shown to improve the reasoning capability of large language models (LLMs).
Approach: They propose a framework which iteratively enhances the model’s Vision-language Reasoning by Reflecting on CoT Rationales.
Outcome: The proposed framework improves multimodal reasoning on vision-language tasks by 23% to 60% over baselines.
mDPO: Conditional Preference Optimization for Multimodal Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Recent studies have attempted to apply DPO to multimodal scenarios but have found it challenging to achieve consistent improvement.
Approach: They propose a multimodal DPO objective that prevents the over-prioritization of language-only preferences by also optimizing image preference.
Outcome: The proposed method significantly improves performance on two multimodal LLMs of different sizes and three widely used benchmarks.
Uni-Dubbing: Zero-Shot Speech Synthesis from Visual Articulation (2024.acl-long)

Copied to clipboard

Challenge: Multimodal speech synthesis is a key challenge due to the scarcity of datasets that pair audio with corresponding video.
Approach: They propose a method that incorporates modality alignment during the pre-training phase on multimodal datasets and freezes the video modality extraction component and the encoder module within the pretrained weights.
Outcome: The proposed method achieves a reduced word error rate (WER) of 31.73%, surpassing the previous best of 33.9% with single-modality audio.
MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference (2025.acl-long)

Copied to clipboard

Challenge: Existing KV cache eviction methods fail to capture modality-specific information, resulting in suboptimal performance.
Approach: They propose a modality-adaptive key-value (KV) cache eviction strategy to enhance the efficiency of multimodal large language models in long-context inference.
Outcome: The proposed method reduces the KV cache memory footprint and model inference latency while maintaining high accuracy across multimodal long-context tasks.
Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to multimodal relation extraction ignore structural constraints and lack semantic expressiveness for fine-grained relation understanding.
Approach: They propose a framework that reformulates multimodal relation extraction as a retrieval task driven by relation semantics.
Outcome: The proposed framework achieves state-of-the-art performance on the benchmark datasets MNRE and MORE and exhibits stronger robustness and interpretability.
Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to compress context information ignore holistic contextual dependencies.
Approach: They propose a method that adjusts position encodings to minimize the distance between context tokens and special tokens.
Outcome: Enhanced Position Layout (EPL) improves compression of context information in large language models.
Agentic Oversight via Dialectic Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to align Large Language Models (LLMs) rely heavily on human annotations, but a Debate between expert models is a promising oversight mechanism.
Approach: They propose a Debate between expert models to enable scalable oversight . they use a reasoning function to extend the framework to multilingual and multimodal spaces .
Outcome: The proposed framework outperforms single-expert baselines in six multilingual and multimodal scenarios and shows that argument-mediated supervision instils unsupervised reasoning signals in expert models.
Exploring and Detecting Self-disclosure in Multi-modal posts on Chinese Social Media (2025.findings-emnlp)

Copied to clipboard

Challenge: Self-disclosure can provide psychological comfort but can also pose privacy concerns . a lack of high-quality corpora, analysis, and methods for detection is limiting research .
Approach: They construct a high-quality text-image corpus on Chinese multimodal social media platforms . they analyze the distribution of self-disclosure types, modality preferences, user intent .
Outcome: The proposed corpus analyzes self-disclosure behaviors on Chinese social media platforms . it fine-tunes five multimodal large language models to enhance self-discovery detection .
Multimodal Safety Evaluation in Generative Agent Social Simulations (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models have enabled generative agents that simulate be-like behavior through natural language interactions.
Approach: They propose a reproducible simulation framework to evaluate generative agents in multimodal scenarios . they use metrics that quantify plan revisions and unsafe-to-safe conversions to evaluate their effectiveness .
Outcome: The proposed framework evaluates generative agents in three aspects: safety improvement over time, detection of unsafe activities across social contexts, social dynamics and acceptance rates.

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