Image de couverture de livre

Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Takmaz, Ece, Bylinina, Lisa, Dotlacil, Jakub
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Correlates of Image Memorability in Vision Encoders: Activations, Attention Entropy, Patch Uniformity and Autoencoder Losses
par: Takmaz, Ece, et autres
Publié: (2025)

Decoding Emotions in Abstract Art: Cognitive Plausibility of CLIP in Recognizing Color-Emotion Associations
par: Widhoelzl, Hanna-Sophia, et autres
Publié: (2024)

Common Objects Out of Context (COOCo): Investigating Multimodal Context and Semantic Scene Violations in Referential Communication
par: Merlo, Filippo, et autres
Publié: (2025)

Describing Images $\textit{Fast and Slow}$: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes
par: Takmaz, Ece, et autres
Publié: (2024)

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
par: Du, Yiyang, et autres
Publié: (2025)

How to Merge Your Multimodal Models Over Time?
par: Dziadzio, Sebastian, et autres
Publié: (2024)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
par: Liu, Xinxin, et autres
Publié: (2026)

Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations
par: Moll, Johannes, et autres
Publié: (2025)

Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging
par: Fu, Zihang, et autres
Publié: (2026)

VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information
par: Kamoi, Ryo, et autres
Publié: (2024)

ViCA: Efficient Multimodal LLMs with Vision-Only Cross-Attention
par: Liu, Wenjie, et autres
Publié: (2026)

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
par: Jiang, Lingjie, et autres
Publié: (2025)

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
par: Shang, Yuzhang, et autres
Publié: (2024)

Do Multimodal Large Language Models Understand Welding?
par: Khvatskii, Grigorii, et autres
Publié: (2025)

Exploring the Role of Explicit Temporal Modeling in Multimodal Large Language Models for Video Understanding
par: Li, Yun, et autres
Publié: (2025)

The Impact of Image Resolution on Biomedical Multimodal Large Language Models
par: Chen, Liangyu, et autres
Publié: (2025)

Optimizing Multimodal Language Models through Attention-based Interpretability
par: Sergeev, Alexander, et autres
Publié: (2025)

Can Large Vision-Language Models Understand Multimodal Sarcasm?
par: Wang, Xinyu, et autres
Publié: (2025)

Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models
par: Chen, Jiaxing, et autres
Publié: (2024)

Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models
par: Nazir, Maham, et autres
Publié: (2026)

LLAVADI: What Matters For Multimodal Large Language Models Distillation
par: Xu, Shilin, et autres
Publié: (2024)

Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization
par: Pi, Renjie, et autres
Publié: (2024)

You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet
par: Qin, Zhen, et autres
Publié: (2024)

EmotionHallucer: Evaluating Emotion Hallucinations in Multimodal Large Language Models
par: Xing, Bohao, et autres
Publié: (2025)

Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
par: Zhan, Xiaoyu, et autres
Publié: (2025)

Evaluating Multimodal Large Language Models on Vertically Written Japanese Text
par: Sasagawa, Keito, et autres
Publié: (2025)

UniChange: Unifying Change Detection with Multimodal Large Language Model
par: Zhang, Xu, et autres
Publié: (2025)

ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models
par: Tu, Yahan, et autres
Publié: (2024)

Exploring Multimodal Large Language Models for Radiology Report Error-checking
par: Wu, Jinge, et autres
Publié: (2023)

Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models
par: Zhu, Minjie, et autres
Publié: (2024)

Kosmos-G: Generating Images in Context with Multimodal Large Language Models
par: Pan, Xichen, et autres
Publié: (2023)

Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models
par: Kim, Mingyeong, et autres
Publié: (2026)

Model Composition for Multimodal Large Language Models
par: Chen, Chi, et autres
Publié: (2024)

SAP-Bench: Benchmarking Multimodal Large Language Models in Surgical Action Planning
par: Xu, Mengya, et autres
Publié: (2025)

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
par: HyperAI Team, et autres
Publié: (2025)

Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More
par: Wen, Zichen, et autres
Publié: (2025)

Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization
par: Zhang, Zefeng, et autres
Publié: (2025)

SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency
par: Yuan, Qianhao, et autres
Publié: (2025)

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models
par: Liu, Jianyu, et autres
Publié: (2025)

Zero-Shot Scene Understanding with Multimodal Large Language Models for Automated Vehicles
par: Elhenawy, Mohammed, et autres
Publié: (2025)