Copertina

DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Zijing, Wang, Mingyang, Nie, Ercong, Liu, Yongkang, Feng, Shi, Zhao, Mengjie, Wang, Daling, Yang, Xiaocui, Schütze, Hinrich
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs
di: Wang, Zijing, et al.
Pubblicazione: (2026)

ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning
di: Liu, Yongkang, et al.
Pubblicazione: (2026)

Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning
di: Liu, Yongkang, et al.
Pubblicazione: (2025)

Why Do More Experts Fail? A Theoretical Analysis of Model Merging
di: Wang, Zijing, et al.
Pubblicazione: (2025)

SAD: A Large-Scale Strategic Argumentative Dialogue Dataset
di: Liu, Yongkang, et al.
Pubblicazione: (2026)

A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation
di: Liu, Yongkang, et al.
Pubblicazione: (2024)

Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response
di: Liu, Yongkang, et al.
Pubblicazione: (2023)

ChatZero:Zero-shot Cross-Lingual Dialogue Generation via Pseudo-Target Language
di: Liu, Yongkang, et al.
Pubblicazione: (2024)

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
di: Wang, Mingyang, et al.
Pubblicazione: (2025)

SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning
di: Liu, Yongkang, et al.
Pubblicazione: (2026)

High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning
di: Liu, Yongkang, et al.
Pubblicazione: (2026)

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
di: Nie, Ercong, et al.
Pubblicazione: (2025)

Tracing Multilingual Factual Knowledge Acquisition in Pretraining
di: Liu, Yihong, et al.
Pubblicazione: (2025)

Muse: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles
di: Wang, Zihan, et al.
Pubblicazione: (2024)

BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning
di: Nie, Ercong, et al.
Pubblicazione: (2024)

MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis
di: Xu, Xingle, et al.
Pubblicazione: (2025)

LangSAMP: Language-Script Aware Multilingual Pretraining
di: Liu, Yihong, et al.
Pubblicazione: (2024)

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining
di: Liu, Yihong, et al.
Pubblicazione: (2023)

Decomposed Prompting: Probing Multilingual Linguistic Structure Knowledge in Large Language Models
di: Nie, Ercong, et al.
Pubblicazione: (2024)

MEKiT: Multi-source Heterogeneous Knowledge Injection Method via Instruction Tuning for Emotion-Cause Pair Extraction
di: Mu, Shiyi, et al.
Pubblicazione: (2025)

DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
di: Teng, Yao, et al.
Pubblicazione: (2024)

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
di: Zhao, Yinzhi, et al.
Pubblicazione: (2026)

HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy
di: Liu, Yongkang, et al.
Pubblicazione: (2024)

Generative Emotion Cause Explanation in Multimodal Conversations
di: Wang, Lin, et al.
Pubblicazione: (2024)

GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network
di: Yuan, Shuzhou, et al.
Pubblicazione: (2024)

DiM: $f$-Divergence Minimization Guided Sharpness-Aware Optimization for Semi-supervised Medical Image Segmentation
di: Wang, Bingli, et al.
Pubblicazione: (2024)

Enhancing LLM-based Recommendation through Semantic-Aligned Collaborative Knowledge
di: Wang, Zihan, et al.
Pubblicazione: (2025)

Refusal Direction is Universal Across Safety-Aligned Languages
di: Wang, Xinpeng, et al.
Pubblicazione: (2025)

The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing
di: Cao, Yuan, et al.
Pubblicazione: (2026)

Fast-DiM: Towards Fast Diffusion Morphs
di: Blasingame, Zander W., et al.
Pubblicazione: (2023)

NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis
di: Wang, Mingyang, et al.
Pubblicazione: (2023)

Pixel-Level Reasoning Segmentation via Multi-turn Conversations
di: Cai, Dexian, et al.
Pubblicazione: (2025)

GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
di: Wan, Faxian, et al.
Pubblicazione: (2026)

Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation
di: Shangguan, Haonan, et al.
Pubblicazione: (2025)

Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence
di: He, Linyang, et al.
Pubblicazione: (2024)

Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models
di: Yuan, Shuzhou, et al.
Pubblicazione: (2025)

NEAT: Neuron-Based Early Exit for Large Reasoning Models
di: Liu, Kang, et al.
Pubblicazione: (2026)

DiM-Gestor: Co-Speech Gesture Generation with Adaptive Layer Normalization Mamba-2
di: Zhang, Fan, et al.
Pubblicazione: (2024)

Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs
di: Blasingame, Zander W., et al.
Pubblicazione: (2024)

DiM-TS: Bridge the Gap between Selective State Space Models and Time Series for Generative Modeling
di: Yao, Zihao, et al.
Pubblicazione: (2025)