Image de couverture de livre

PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Zijing, Liu, Yongkang, Wang, Mingyang, Nie, Ercong, Chen, Deyuan, Zhao, Zhengjie, Feng, Shi, Wang, Daling, Yang, Xiaocui, Zhang, Yifei, Schütze, Hinrich
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
par: Wang, Zijing, et autres
Publié: (2026)

Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning
par: Liu, Yongkang, et autres
Publié: (2025)

Why Do More Experts Fail? A Theoretical Analysis of Model Merging
par: Wang, Zijing, et autres
Publié: (2025)

ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning
par: Liu, Yongkang, et autres
Publié: (2026)

A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation
par: Liu, Yongkang, et autres
Publié: (2024)

SAD: A Large-Scale Strategic Argumentative Dialogue Dataset
par: Liu, Yongkang, et autres
Publié: (2026)

Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response
par: Liu, Yongkang, et autres
Publié: (2023)

ChatZero:Zero-shot Cross-Lingual Dialogue Generation via Pseudo-Target Language
par: Liu, Yongkang, et autres
Publié: (2024)

Muse: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profiles
par: Wang, Zihan, et autres
Publié: (2024)

Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models
par: Nie, Ercong, et autres
Publié: (2025)

BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning
par: Nie, Ercong, et autres
Publié: (2024)

The Anatomy of an Edit: Mechanism-Guided Activation Steering for Knowledge Editing
par: Cao, Yuan, et autres
Publié: (2026)

MEKiT: Multi-source Heterogeneous Knowledge Injection Method via Instruction Tuning for Emotion-Cause Pair Extraction
par: Mu, Shiyi, et autres
Publié: (2025)

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models
par: Wang, Mingyang, et autres
Publié: (2025)

HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy
par: Liu, Yongkang, et autres
Publié: (2024)

Enhancing LLM-based Recommendation through Semantic-Aligned Collaborative Knowledge
par: Wang, Zihan, et autres
Publié: (2025)

GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
par: Wan, Faxian, et autres
Publié: (2026)

SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning
par: Liu, Yongkang, et autres
Publié: (2026)

High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning
par: Liu, Yongkang, et autres
Publié: (2026)

Pixel-Level Reasoning Segmentation via Multi-turn Conversations
par: Cai, Dexian, et autres
Publié: (2025)

MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis
par: Xu, Xingle, et autres
Publié: (2025)

GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network
par: Yuan, Shuzhou, et autres
Publié: (2024)

Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization
par: Wang, Mingyang, et autres
Publié: (2024)

NEAT: Neuron-Based Early Exit for Large Reasoning Models
par: Liu, Kang, et autres
Publié: (2026)

Tracing Multilingual Factual Knowledge Acquisition in Pretraining
par: Liu, Yihong, et autres
Publié: (2025)

How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A
par: Huang, YiJie, et autres
Publié: (2026)

Generative Emotion Cause Explanation in Multimodal Conversations
par: Wang, Lin, et autres
Publié: (2024)

Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering
par: Zhang, Xiaoming, et autres
Publié: (2024)

Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing
par: Zhao, Yinzhi, et autres
Publié: (2026)

Rehearsal-Free Modular and Compositional Continual Learning for Language Models
par: Wang, Mingyang, et autres
Publié: (2024)

Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence
par: He, Linyang, et autres
Publié: (2024)

Hateful Person or Hateful Model? Investigating the Role of Personas in Hate Speech Detection by Large Language Models
par: Yuan, Shuzhou, et autres
Publié: (2025)

Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation
par: Shangguan, Haonan, et autres
Publié: (2025)

Can LLMs Beat Humans in Debating? A Dynamic Multi-agent Framework for Competitive Debate
par: Zhang, Yiqun, et autres
Publié: (2024)

TOOL-ED: Enhancing Empathetic Response Generation with the Tool Calling Capability of LLM
par: Cao, Huiying, et autres
Publié: (2024)

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining
par: Liu, Yihong, et autres
Publié: (2023)

On the Entity-Level Alignment in Crosslingual Consistency
par: Liu, Yihong, et autres
Publié: (2025)

Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders
par: Veitsman, Yana, et autres
Publié: (2026)

ES4R: Speech Encoding Based on Prepositive Affective Modeling for Empathetic Response Generation
par: Gao, Zhuoyue, et autres
Publié: (2026)

From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
par: Wang, Xiao, et autres
Publié: (2026)