Papers with fusion
FAD-X: Fusing Adapters for Cross-lingual Transfer to Low-Resource Languages (2022.aacl-short)
Copied to clipboard
| Challenge: | Adapter-based tuning is a technique that selectively updates language-specific parameters to adapt to a new language, rather than fine-tuning all shared weights. |
| Approach: | They propose to add light-weight adapters to multilingual pretrained language models (mPLMs) and add language-specific parameters to adapt to a new language. |
| Outcome: | The proposed adapter can enhance cross-lingual transfer from pretrained adapters for well-known named entity recognition and classification benchmarks. |
Analyzing Sentence Fusion in Abstractive Summarization (D19-54)
Copied to clipboard
Logan Lebanoff, John Muchovej, Franck Dernoncourt, Doo Soon Kim, Seokhwan Kim, Walter Chang, Fei Liu
| Challenge: | Abstractive summarization systems struggle to combine information from multiple sources, resulting in poor grammar and incorrect facts. |
| Approach: | They analyze the outputs of five abstractive summarization systems and examine their grammatical accuracy and faithfulness. |
| Outcome: | The proposed summarization systems are able to combine information from multiple sources, but they often fail to remain faithful to the original document. |
Multimodal Language Analysis with Recurrent Multistage Fusion (D18-1)
Copied to clipboard
| Challenge: | Comprehending multimodal language requires modeling interactions between modalities and between them. |
| Approach: | They propose a multistage fusion network which decomposes the fusion problem into multiple stages, each focused on a subset of multimodal signals for specialized, effective fusion. |
| Outcome: | The proposed model performs state-of-the-art across three datasets relating to multimodal sentiment analysis, emotion recognition, and speaker traits recognition. |
SportsMetrics: Blending Text and Numerical Data to Understand Information Fusion in LLMs (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models can handle text and data, but blending text and numerical data presents significant challenges. |
| Approach: | They propose four tasks to evaluate the numerical reasoning and information fusion capabilities of large language models in sports data analytics. |
| Outcome: | The proposed tasks evaluate the numerical reasoning and information fusion capabilities of large language models in sports data analytics. |
On the Relation between Linguistic Typology and (Limitations of) Multilingual Language Modeling (D18-1)
Copied to clipboard
| Challenge: | a key challenge in cross-lingual NLP is developing general language-independent architectures that are equally applicable to any language. |
| Approach: | They propose to use a full-vocabulary setup to test the performance of language modeling (LM) on 50 typologically diverse languages. |
| Outcome: | The proposed language modeling task is based on a full vocabulary setup focused on word-level prediction on 50 typologically diverse languages. |
CMTD: Cognitive Modeling with Traits and Distortions for Multimodal Emotion Recognition in Conversations (2026.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that traits temper negativity bias from distortions, and cognitive modeling with psychological, visual, and acoustic information can improve the performance of MERC. |
| Approach: | They propose a framework for multimodal emotion recognition in conversations that takes advantage of stable personality traits, dynamic cognitive distortions, visual and acoustic features of interlocutors to enhance the emotional intelligence of LLMs. |
| Outcome: | Experimental results show that traits temper negativity bias from distortions, and cognitive modeling with psychological, visual, and acoustic information can improve the performance of MERC. |
Divide, Conquer and Combine: Hierarchical Feature Fusion Network with Local and Global Perspectives for Multimodal Affective Computing (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to multimodal fusion are based on fusing features at holistic level instead of focusing on local and global interactions. |
| Approach: | They propose a general strategy called ‘divide, conquer and combine’ for multimodal fusion that combines local and global interactions in a hierarchy. |
| Outcome: | The proposed strategy achieves state-of-the-art performance on multimodal affective computing with higher efficiency. |
Harmonizing Dense and Sparse Signals in Multi-turn RL: Dual-Horizon Credit Assignment for Industrial Sales Agents (2026.acl-industry)
Copied to clipboard
| Challenge: | Large language models for industrial sales require balancing long-term commercial objectives with immediate linguistic constraints such as fluency and compliance. |
| Approach: | They propose a framework that disentangles optimization across time scales by normalizing advantages from turn-level and session-level rewards before fusion. |
| Outcome: | The proposed framework outperforms the state-of-the-art GRPO model in conversion rate and identity detection rate. |
Quantifying Synthesis and Fusion and their Impact on Machine Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Literature in Natural Language Processing (NLP) typically labels whole language with strict type of morphology, e.g. fusional or agglutinative. |
| Approach: | They propose to quantify morphological typology at the word and segment level by using two indices: synthesis (e.g. analytic to polysynthetic) and fusion (agglutinative to fusional). |
| Outcome: | The proposed method reduces the rigidity of NLP classification claims by measuring morphological diversity at the word and segment level. |
RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal question answering often requires identifying which video, audio, or sensor tokens are relevant to the question. off-camera speech, background noise, or motion outside the field of view often mislead fusion models that weight all streams equally. |
| Approach: | They propose a unified architecture for multimodal question answering that assigns scalar relevance scores to each token across modalities. |
| Outcome: | The proposed model outperforms state-of-the-art multimodal large language models on seven multi-modal QA benchmarks and egocentric and exocentric tasks. |
Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction (2022.findings-naacl)
Copied to clipboard
Xiang Chen, Ningyu Zhang, Lei Li, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen
| Challenge: | Existing approaches for named entity recognition and relation extraction suffer from error sensitivity when irrelevant object images are incorporated in texts. |
| Approach: | They propose a hierarchical visual prefix fusion NeTwork for visual-enhanced entity and relation extraction using pluggable visual prefixed visual features. |
| Outcome: | The proposed method achieves state-of-the-art on three benchmark datasets. |
Modality-Aware Integration with Large Language Models for Knowledge-Based Visual Question Answering (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to integrate multimodal knowledge in a modality-agnostic manner can be sub-optimal. |
| Approach: | They propose a modality-aware integration with large language models (LLMs) that leverages multimodal knowledge for both image understanding and knowledge reasoning. |
| Outcome: | The proposed model is able to bridge a tight inter-modal exchange while preserving insightful intra-modal learning. |
LANS: A Layout-Aware Neural Solver for Plane Geometry Problem (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing neural solvers take GPS as vision-language task but lack layout awareness . Existing models are criticized for complex rules and poor adaptability . |
| Approach: | They propose a layout-aware neural solver called LANS that integrates two modules to solve GPS. |
| Outcome: | The proposed solver outperforms existing neural and symbolic solvers on two datasets. |
Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering (P18-1)
Copied to clipboard
| Challenge: | Existing approaches to read comprehension style question answering are limited by the volume of annotated datasets. |
| Approach: | They propose a hierarchical attention network for reading comprehension style question answering . they first encode the question and paragraph with fine-grained language embeddings . then propose fusion approach to fuse information from both global and attended representations based on the hierarchic attention network . |
| Outcome: | The proposed method achieves state-of-the-art on the SQuAD and TriviaQA Wiki leaderboards and two adversarial SQu AD datasets. |
Bridging Argument Quality and Deliberative Quality Annotations with Adapters (2023.findings-eacl)
Copied to clipboard
| Challenge: | Assessing the quality of an argument is a complex, highly subjective task . argument quality dimensions are complex and dependent on the context in which it is assessed . |
| Approach: | They propose a multi-task learning framework that incorporates knowledge about related dimensions into the learning process. |
| Outcome: | The proposed framework improves quality prediction in an extrinsic, out-of-domain task. |
Hybrid Attention based Multimodal Network for Spoken Language Classification (C18-1)
Copied to clipboard
| Challenge: | Using linguistic content and vocal characteristics for multimodal deep learning is difficult for computers to interpret human meaning . |
| Approach: | They propose a deep multimodal network with feature attention and modality attention to classify utterance-level speech data. |
| Outcome: | The proposed system achieves state-of-the-art or competitive results on three published multimodal datasets. |
Scoring Sentence Singletons and Pairs for Abstractive Summarization (P19-1)
Copied to clipboard
Logan Lebanoff, Kaiqiang Song, Franck Dernoncourt, Doo Soon Kim, Seokhwan Kim, Walter Chang, Fei Liu
| Challenge: | Existing methods for summarizing content from single sentences are inadequately understood. |
| Approach: | They propose to combine singletons and pairs to create a summarizing sentence . they use a dataset of human-written abstracts to examine human-writing methods . |
| Outcome: | The proposed framework is based on human-written abstracts from three large datasets. |
A Dual Contrastive Learning Framework for Enhanced Multimodal Conversational Emotion Recognition (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods struggle to capture emotion shifts due to label replication and fail to preserve positive independent modality contributions during fusion. |
| Approach: | They propose a Dual Contrastive Learning Framework that enhances existing MERC models without additional data. |
| Outcome: | The proposed framework outperforms existing models on two MERC benchmark datasets and shows that it reduces label dependence and enhances emotion-sensitive independent modality features. |
Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain (2025.coling-main)
Copied to clipboard
| Challenge: | Existing research focuses on a limited set of retrieval methods, evaluated in pairs on domain-general datasets exclusively in English. |
| Approach: | They evaluate the efficacy of hybrid search across a variety of retrieval models in the french language . they find that fusion of different domain-general models consistently enhances performance . |
| Outcome: | The proposed model improves in-domain performance compared to a single model in a zero-shot context . the proposed model also improves when the models are trained in- domain . |
Fusion meets Function: The Adaptive Selection-Generation Approach in Event Argument Extraction (2025.coling-main)
Copied to clipboard
| Challenge: | Event Argument Extraction is a critical subtask of Event Extraction, focused on identifying event arguments within text. |
| Approach: | They propose a Fusion Selection-Generation-Based Approach that merges selective and generative methods to enhance argument extraction accuracy. |
| Outcome: | The proposed method improves on the RAMS and WikiEvents, while preserving the unique characteristics of both methods. |
On Mitigating Performance Disparities in Multilingual Speech Recognition (2024.emnlp-main)
Copied to clipboard
| Challenge: | Automatic Speech Recognition systems are not always equally effective for all users, and gender disparity in their performance is a significant concern. |
| Approach: | They compare performance of different fine-tuning algorithms for multilingual speech recognition across languages and genders. |
| Outcome: | The proposed algorithms improve performance and parity across languages and languages. |
Making Information Seeking Easier: An Improved Pipeline for Conversational Search (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing tools for conversational information seeking (CIS) do not support conversational contexts. |
| Approach: | They propose a highly effective pipeline for passage retrieval in a conversational search setting using a BERT-based classifier and a multi-view reranking component. |
| Outcome: | The proposed pipeline achieves 14.8% performance improvement over the current state-of-the-art pipeline and surpasses the Oracle. |
LiGen: Active Lipid Generation via a Molecular Language Model (2026.acl-long)
Copied to clipboard
| Challenge: | Lipid nanoparticles (LNPs) can deliver cargos to tumor and immune cells . traditional approaches rely on experimental screening and expert judgment . |
| Approach: | They propose a method to generate lipid molecules efficiently and actively using deep learning. |
| Outcome: | The proposed method outperforms baseline methods on multiple cell lines and achieves a 30% improvement over the current methods. |
DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies focus on cross-modal attention at the fusion stage, but modality features generated by disparate uni-encoders reside in their own spaces, leading to a decline in the quality of cross-modulation and decision-making. |
| Approach: | They propose a framework to align navigation-related modalities before fusion by cross-modal contrastive learning. |
| Outcome: | The proposed framework integrates with the majority of existing models, resulting in improved navigation performance on various VLN benchmarks, including R2R, R4R, and CVDN. |
Multi-stage Training with Improved Negative Contrast for Neural Passage Retrieval (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing neural firststage retrieval models overcome lexical gap issue by projecting query and document to a shared dense space. |
| Approach: | They propose a multi-stage framework for neural passage retrieval using synthetic data, negative sampling, and fusion techniques. |
| Outcome: | The proposed framework improves retrieval accuracy and enhances the negative contrast in both stages. |
Fusion-in-T5: Unifying Variant Signals for Simple and Effective Document Ranking with Attention Fusion (2024.lrec-main)
Copied to clipboard
| Challenge: | Current document ranking pipelines involve multiple ranking layers to integrate different information step-by-step. |
| Approach: | They propose a novel re-ranker Fusion-in-T5 which integrates text matching information, ranking features, and global document information into one single unified model via templated-based input and global attention. |
| Outcome: | The proposed model significantly improves ranking performance over complex cascade pipelines. |
AIMMerging: Adaptive Iterative Model Merging Using Training Trajectories for Language Model Continual Learning (2025.emnlp-main)
Copied to clipboard
Yujie Feng, Jian Li, Xiaoyu Dong, Pengfei Xu, Xiaohui Zhou, Yujia Zhang, Zexin Lu, Yasha Wang, Alan Zhao, Xu Chu, Xiao-Ming Wu
| Challenge: | Recent model merging-based methods struggle to effectively manage the trade-off between learning new knowledge and preventing catastrophic forgetting. |
| Approach: | They propose a model merging framework that utilizes learning and forgetting signals from the training trajectory to dynamically monitor the model’s training status. |
| Outcome: | The proposed framework achieves significant performance improvements over existing state-of-the-art methods on three CL benchmarks with various model sizes (from 770M to 13B). |
CLASP: Cross-modal Alignment Using Pre-trained Unimodal Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in speech-text pretraining rely on parallel speech- text data . however, data accessibility is a challenge due to the limited data available. |
| Approach: | They propose a framework for jointly performing speech and text processing without parallel corpora during pre-training but only downstream. |
| Outcome: | The proposed framework extracts distinct representations for speech and text, aligning them effectively in a newly defined space using a multi-level contrastive learning mechanism. |
MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Experts (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MultiPL is a special case of multiple natural languages and requires limited computational resources to generate multilingual code. |
| Approach: | They propose to extend LLMs by combining two paired experts to optimize expert selection at token and segment levels. |
| Outcome: | The proposed extension improves the performance of the base LLMs while retaining the most popular ones using limited computational resources. |
Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on multimodal sentiment analysis relies on back-propagated task loss or geometric property of feature spaces to produce favorable fusion results. |
| Approach: | They propose a framework which hierarchically maximizes the Mutual Information (MI) in unimodal input pairs and between multimodal fusion result and unimod input to maintain task-related information through multimodal integration. |
| Outcome: | The proposed framework maximizes the Mutual Information (MI) in unimodal input pairs and between multimodal fusion result and unimodulated input to maintain task-related information through multimodal integration. |
PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy (2025.acl-long)
Copied to clipboard
| Challenge: | Existing pipelines that combine document image restoration with semantic-aware post-OCR correction can improve text extraction from degraded images. |
| Approach: | They propose a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency. |
| Outcome: | The proposed pipeline reduces character error rates by 63.9-70.3% on 13,831 pages of real historical documents in English, French, and Spanish compared to OCR on raw images. |
An Information-Theoretic Characterization of Morphological Fusion (2021.emnlp-main)
Copied to clipboard
| Challenge: | Linguistic typology generally divides synthetic languages into groups based on their morphological fusion. |
| Approach: | They propose to quantify the degree of fusion of morphological features in a surface form . they recapitulate the usual linguistic classifications for concatenative systems . |
| Outcome: | The proposed measure recapitulates the usual classifications for concatenative systems and provides new measures for nonconcatenating ones. |
Integrating Representation Subspace Mapping with Unimodal Auxiliary Loss for Attention-based Multimodal Emotion Recognition (2024.lrec-main)
Copied to clipboard
Xulong Du, Xingnan Zhang, Dandan Wang, Yingying Xu, Zhiyuan Wu, Shiqing Zhang, Xiaoming Zhao, Jun Yu, Liangliang Lou
| Challenge: | Existing methods to identify emotions rely on a large modality gap in their representations . |
| Approach: | They propose a representation subspace mapping module that maps each modality into two distinct subspaces and a cross-modality attention module that leverages auxiliary loss to remove the noise unrelated to emotion classification. |
| Outcome: | The proposed approach achieves superior performance to state-of-the-art MER methods on the IEMOCAP and MSP-Improv datasets. |
Extractive Medical Entity Disambiguation with Memory Mechanism and Memorized Entity Information (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods focus on local optimal while ignoring sole-mention disambiguation boosted by richer context from other mentions’ disambiguating processes. |
| Approach: | They propose an approach to extracting medical entity disambiguation using memory mechanism and memorized entity information (M3E) they use a memory mechanism module that performs memory caching, retrieval, fusion and cross-network residual to aid the disambiguations of remaining mentions. |
| Outcome: | The proposed method outperforms state-of-the-art methods on two benchmark datasets. |
Is the Attention Matrix Really the Key to Self-Attention in Multivariate Long-Term Time Series Forecasting? (2026.acl-long)
Copied to clipboard
| Challenge: | In multivariate long-term time series forecasting, it is widely believed that the effectiveness of self-attention arises from its attention matrix. |
| Approach: | They propose a multi-branch MLP that isolates the ‘multi-brain mapping with element-wise operation’ structure from the Transformer and shows that it achieves competitive performance. |
| Outcome: | The proposed model outperforms three classic and three latest Transformer models and shows that it achieves competitive performance. |
Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
Mohammad Mahdi Abootorabi, Amirhosein Zobeiri, Mahdi Dehghani, Mohammadali Mohammadkhani, Bardia Mohammadi, Omid Ghahroodi, Mahdieh Soleymani Baghshah, Ehsaneddin Asgari
| Challenge: | Large Language Models (LLMs) suffer from hallucinations and outdated knowledge due to their reliance on static training data. |
| Approach: | They review training strategies, robustness enhancements, loss functions, and agent-based approaches and outline open challenges and future directions to guide research in this evolving field. |
| Outcome: | The proposed model improves accuracy and accuracy while integrating external dynamic information for improved factual grounding. |
Not All Modalities at Once: Dynamic Dropout and Bidirectional Fusion for Robust Multi-modal Knowledge Graph Completion (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing MKGC methods train with all modalities available, implicitly assuming consistent complementarity . however, this often induces modality dependence and modality competition under heterogeneous noise, which can hinder robust multi-modal fusion and limit overall performance. |
| Approach: | They propose a framework to infer missing links in multimodal knowledge graphs by leveraging structured triples together with auxiliary modalities such as text and images. |
| Outcome: | The proposed framework outperforms baselines and achieves new state-of-the-art results. |
Multimodal Fusion and Coherence Modeling for Video Topic Segmentation (2025.findings-acl)
Copied to clipboard
| Challenge: | Traditional video topic segmentation methods struggle to discern topical transitions . supervised approaches have improved performance on video action or scene segmentation . |
| Approach: | They propose a new task for video topic segmentation that enhances multimodality alignment and fusion by exploring different architectures using Cross-Attention and Mixture of Experts. |
| Outcome: | The proposed model improves on educational videos, in the form of lectures . it combines cross-attention and mixture of experts to strengthen multimodality alignment and fusion . |
Controlled Transformation of Text-Attributed Graphs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Graph generation is the process of generating new graphs with similar attributes to real world graphs. |
| Approach: | They propose a controllable multi-objective translation model for text-attributed graphs that can translate a given source graph to a target graph while satisfying multiple desired graph attributes at granular level. |
| Outcome: | The proposed model can translate a given source graph to a target graph while satisfying multiple desired graph attributes at granular level. |
Dual-oriented Disentangled Network with Counterfactual Intervention for Multimodal Intent Detection (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for multimodal intent detection have two limitations: (i) close entanglement of multimodal semantics with modal structures; (ii) insufficient learning of causal effects of semantic and modality-specific information on the final predictions. |
| Approach: | They propose a Dual-oriented Disentangled Network with Counterfactual Intervention model that decouples semantics-oriented and modality-oriented representations and a Counterfective Intervention Module that applies causal inference to understand causal effects by injecting confounders. |
| Outcome: | The proposed model overcomes key limitations in existing systems by effectively disentangling and utilizing modality-specific and multimodal semantic information. |
Mixing Inference-time Experts for Enhancing LLM Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for improving reasoning quality in large language models are limited to using a single expert. |
| Approach: | They propose a framework that finetunes and merges expert logits from one LLM . they use commonsense and entailment reasoning experts to improve chain-of-thought reasoning . |
| Outcome: | The proposed framework outperforms baselines on three question-answering datasets. |
FusionFlow: Enabling Deep Structural Exploration for Automated Agentic Workflow Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing workflow generation methods rely on incremental refinement or tree-based search over a single evolving workflow. |
| Approach: | They propose a framework centered on workflow fusion that synthesizes multiple independently evolved workflows and allows exploration of deeper regions of the workflow space within a finite budget. |
| Outcome: | Experiments show that FusionFlow outperforms existing workflow generation methods on six reasoning benchmarks. |
Let’s Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCR (2025.findings-acl)
Copied to clipboard
| Challenge: | Various fusion strategies have been explored for integration of large language models into multi-modal systems. |
| Approach: | They propose a framework for deep fusion decoding that integrates large language models into cross-modal text recognition systems. |
| Outcome: | The proposed framework surpasses cascaded methods in English and Mandarin, and significantly reduces WERs by 17.7%. |
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning (2025.acl-long)
Copied to clipboard
Yujie Feng, Xujia Wang, Zexin Lu, Shenghong Fu, Guangyuan Shi, Yongxin Xu, Yasha Wang, Philip S. Yu, Xu Chu, Xiao-Ming Wu
| Challenge: | Continual learning (CL) is crucial for large language models without costly retraining. |
| Approach: | They propose a framework for recurrent knowledge identification and fusion that enables dynamic estimation of parameter importance distributions to enhance knowledge transfer. |
| Outcome: | The proposed framework mitigates catastrophic forgetting and enhances knowledge transfer. |
Beyond the Panorama: Training-Free Hierarchical Perception-Reasoning for Fine-Grained Vision in MLLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing multimodal large language models (MLLMs) face challenges in fine-grained visual tasks. |
| Approach: | They propose a training-free hierarchical perception-reasoning framework that enhances fine-grained visual understanding by simulating human perception mechanisms. |
| Outcome: | The proposed framework enhances fine-grained visual understanding by simulating human perception mechanisms. |
Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for detecting hate speech ignore misalignment and uncertainty between modalities . social media platforms have become conduits for the rapid dissemination of hate speech . |
| Approach: | They propose an uncertainty-aware cross-modal alignment framework for hate speech detection that minimizes the misalignment of image and text in memes. |
| Outcome: | The proposed framework produces a competitive performance compared with existing methods. |
NeuRAG: End-to-End Neural Knowledge Augmentation via Hyper-Neurons (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to grounding large language models in external knowledge are constrained by a decoupled architecture: retrieval and reasoning operate as separate stages, with retrieved text merely prepended as passive context. |
| Approach: | They propose an end-to-end Neuralized RAG framework that unifies knowledge retrieval and fusion through Hyper-Neurons. |
| Outcome: | Extensive experiments across multiple datasets and LLMs demonstrate NeuRAG’s strong and consistent performance as a promising novel RAG paradigm. |
GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies rely on item metadata to construct abbreviated item IDs, leading to a loss of valuable details. |
| Approach: | They propose a Generative Recommender via semantic-aware multi-granular late fusion to integrate rich semantics efficiently with minimal information loss. |
| Outcome: | The proposed model outperforms eight state-of-the-art recommendation models on four benchmark datasets and achieves significant improvements of 11.5-16.0% in Recall@5 and 5.3-13.6% in NDCG@5. |
Breaking the Noise Barrier: LLM-Guided Semantic Filtering and Enhancement for Multi-Modal Entity Alignment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multi-modal entity alignment (MMEA) aims to identify equivalent entities between two multimodal knowledge graphs. |
| Approach: | They propose a novel LLMguided MMEA framework that prioritizes noise reduction before fusion. |
| Outcome: | The proposed framework prioritizes noise reduction before fusion and improves semantics on the noisy FB YG dataset. |
Emotion-Wheel-Guided Audio-Referred Text Representation for Multimodal Emotion Recognition in Conversation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Emotion Recognition in Conversation ignore their distinct communicative roles and information capacities and apply uniform penalties regardless of affective proximity. |
| Approach: | They propose a modality-aware fusion strategy capturing linguistic features from text as the primary source and audio as a complementary component. |
| Outcome: | The proposed method captures linguistic features from text as the primary source and audio as a complementary component and supervised contrastive loss to encode emotional proximity based on Russell’s circumplex model. |
Agent for Numerical Data Retrieval and Understanding by Code Generation and Multimodal Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Numerical data from sensors and time series are widely used in scientific research fields such as nuclear fusion . efficient numerical data analysis tools are crucial to accelerate experimental research . |
| Approach: | They propose a model-agnostic and data-adic agent that processes numerical data by code generation and multimodal reasoning. |
| Outcome: | The proposed agent outperforms existing methods on benchmarks on sensor data classification and time series understanding. |