Imagen de Portada

Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Zeping, Ananiadou, Sophia
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing
por: Yu, Zeping, et al.
Publicado: (2025)

Neuron-Level Knowledge Attribution in Large Language Models
por: Yu, Zeping, et al.
Publicado: (2023)

Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering
por: Yu, Zeping, et al.
Publicado: (2024)

Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
por: Yu, Zeping, et al.
Publicado: (2024)

How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning
por: Yu, Zeping, et al.
Publicado: (2024)

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models
por: Yu, Zeping, et al.
Publicado: (2025)

Parameter Alignment Mitigates Catastrophic Forgetting in Multilingual Expert Language Models
por: Ahuja, Sanchit, et al.
Publicado: (2026)

Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
por: Watts, Ishaan, et al.
Publicado: (2026)

Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
por: Yamaguchi, Atsuki, et al.
Publicado: (2025)

Mitigating Catastrophic Forgetting in Continual Learning through Model Growth
por: Süalp, Ege, et al.
Publicado: (2025)

Emotion Detection for Misinformation: A Review
por: Liu, Zhiwei, et al.
Publicado: (2023)

Model-Dowser: Data-Free Importance Probing to Mitigate Catastrophic Forgetting in Multimodal Large Language Models
por: Hwang, Hyeontaek, et al.
Publicado: (2026)

Evolutionary Strategies lead to Catastrophic Forgetting in LLMs
por: Abdi, Immanuel, et al.
Publicado: (2026)

Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning
por: Ren, Weijieying, et al.
Publicado: (2024)

Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs
por: Kabir, Mohsinul, et al.
Publicado: (2025)

Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
por: Zhu, Didi, et al.
Publicado: (2024)

Catastrophic Forgetting in LLMs: A Comparative Analysis Across Language Tasks
por: Haque, Naimul
Publicado: (2025)

MMAFFBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMs
por: Liu, Zhiwei, et al.
Publicado: (2025)

Mitigating Catastrophic Forgetting in Mathematical Reasoning Finetuning through Mixed Training
por: Reynolds, John Graham
Publicado: (2025)

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal
por: Huang, Jianheng, et al.
Publicado: (2024)

More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs
por: Liu, Chengyuan, et al.
Publicado: (2024)

Conditions for Catastrophic Forgetting in Multilingual Translation
por: Liu, Danni, et al.
Publicado: (2025)

Improved Supervised Fine-Tuning for Large Language Models to Mitigate Catastrophic Forgetting
por: Ding, Fei, et al.
Publicado: (2025)

Activated Parameter Locating via Causal Intervention for Model Merging
por: Kong, Fanshuang, et al.
Publicado: (2024)

Dynamic Orthogonal Continual Fine-tuning for Mitigating Catastrophic Forgettings
por: Zhang, Zhixin, et al.
Publicado: (2025)

Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Framework
por: Xing, Peng, et al.
Publicado: (2024)

Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models
por: Zhang, Hengyuan, et al.
Publicado: (2024)

Countering Catastrophic Forgetting of Large Language Models for Better Instruction Following via Weight-Space Model Merging
por: Lyu, Mengxian, et al.
Publicado: (2026)

CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation
por: Fawi, Muhammad
Publicado: (2024)

How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization
por: Song, Shezheng, et al.
Publicado: (2025)

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
por: Ma, Qianli, et al.
Publicado: (2025)

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
por: Huang, Yuqing, et al.
Publicado: (2025)

Disentangled VAD Representations via a Variational Framework for Political Stance Detection
por: Xu, Beiyu, et al.
Publicado: (2025)

Factual consistency evaluation of summarization in the Era of large language models
por: Luo, Zheheng, et al.
Publicado: (2024)

The Lay Person's Guide to Biomedicine: Orchestrating Large Language Models
por: Luo, Zheheng, et al.
Publicado: (2024)

OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning
por: Xiong, Yifeng, et al.
Publicado: (2025)

EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis
por: Liu, Zhiwei, et al.
Publicado: (2024)

A Comparative Empirical Study of Catastrophic Forgetting Mitigation in Sequential Task Adaptation for Continual Natural Language Processing Systems
por: Abrahamyan, Aram, et al.
Publicado: (2026)

Revisiting Catastrophic Forgetting in Large Language Model Tuning
por: Li, Hongyu, et al.
Publicado: (2024)

Self-Distillation as a Performance Recovery Mechanism for LLMs: Counteracting Compression and Catastrophic Forgetting
por: Liu, Chi, et al.
Publicado: (2026)