Copertina

Return of the Encoder: Maximizing Parameter Efficiency for SLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Elfeki, Mohamed, Liu, Rui, Voegele, Chad
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Exploring the Potential of Encoder-free Architectures in 3D LMMs
di: Tang, Yiwen, et al.
Pubblicazione: (2025)

Do Vision and Language Encoders Represent the World Similarly?
di: Maniparambil, Mayug, et al.
Pubblicazione: (2024)

UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
di: Lin, Bin, et al.
Pubblicazione: (2025)

MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension
di: Liu, Ting, et al.
Pubblicazione: (2024)

Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction
di: Rashad, Mohamed
Pubblicazione: (2024)

Shifting AI Efficiency From Model-Centric to Data-Centric Compression
di: Liu, Xuyang, et al.
Pubblicazione: (2025)

Improving Chain-of-Thought Efficiency for Autoregressive Image Generation
di: Gu, Zeqi, et al.
Pubblicazione: (2025)

Can Visual Encoder Learn to See Arrows?
di: Terashita, Naoyuki, et al.
Pubblicazione: (2025)

Renaissance: Investigating the Pretraining of Vision-Language Encoders
di: Fields, Clayton, et al.
Pubblicazione: (2024)

CSLRConformer: A Data-Centric Conformer Approach for Continuous Arabic Sign Language Recognition on the Isharah Datase
di: Elden, Fatimah Mohamed Emad
Pubblicazione: (2025)

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
di: Jiang, Dongzhi, et al.
Pubblicazione: (2025)

Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
di: Zhang, Juntian, et al.
Pubblicazione: (2025)

Frozen Transformers in Language Models Are Effective Visual Encoder Layers
di: Pang, Ziqi, et al.
Pubblicazione: (2023)

NAS-LoRA: Empowering Parameter-Efficient Fine-Tuning for Visual Foundation Models with Searchable Adaptation
di: Chen, Renqi, et al.
Pubblicazione: (2025)

EPEE: Towards Efficient and Effective Foundation Models in Biomedicine
di: Zhan, Zaifu, et al.
Pubblicazione: (2025)

Knowledge Generation for Zero-shot Knowledge-based VQA
di: Cao, Rui, et al.
Pubblicazione: (2024)

Maximizing Asynchronicity in Event-based Neural Networks
di: Hao, Haiqing, et al.
Pubblicazione: (2025)

Imperfect Vision Encoders: Efficient and Robust Tuning for Vision-Language Models
di: Panos, Aristeidis, et al.
Pubblicazione: (2024)

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
di: Hong, Jixiang, et al.
Pubblicazione: (2025)

LLMs Can Compensate for Deficiencies in Visual Representations
di: Takishita, Sho, et al.
Pubblicazione: (2025)

Parameter Competition Balancing for Model Merging
di: Du, Guodong, et al.
Pubblicazione: (2024)

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
di: Liu, Weiyang, et al.
Pubblicazione: (2023)

Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities
di: Zhou, Ziwei, et al.
Pubblicazione: (2025)

MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion
di: Jiang, Ruixiang, et al.
Pubblicazione: (2024)

Can Vision Language Models Judge Action Quality? An Empirical Evaluation
di: Freitas, Miguel Monte e, et al.
Pubblicazione: (2026)

DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models
di: Zou, Chengke, et al.
Pubblicazione: (2024)

VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
di: Jiang, Ziyan, et al.
Pubblicazione: (2024)

Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
di: Qu, Kevin, et al.
Pubblicazione: (2026)

ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model
di: Zhang, Juntian, et al.
Pubblicazione: (2025)

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
di: Zhou, Wenrui, et al.
Pubblicazione: (2025)

MiniGPT-Med: Large Language Model as a General Interface for Radiology Diagnosis
di: Alkhaldi, Asma, et al.
Pubblicazione: (2024)

Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comics
di: Ryan, Yuriel, et al.
Pubblicazione: (2025)

Cross-Modal Adapter for Vision-Language Retrieval
di: Jiang, Haojun, et al.
Pubblicazione: (2022)

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
di: Guo, Ziyu, et al.
Pubblicazione: (2025)

InfraGPT Smart Infrastructure: An End-to-End VLM-Based Framework for Detecting and Managing Urban Defects
di: Mohamed, Ibrahim Sheikh, et al.
Pubblicazione: (2025)

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
di: Yue, Yang, et al.
Pubblicazione: (2025)

Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View
di: Qi, Jianyu, et al.
Pubblicazione: (2025)

Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
di: Wang, Peng, et al.
Pubblicazione: (2024)

AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
di: Zhou, Ziwei, et al.
Pubblicazione: (2026)

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
di: Xu, Haolei, et al.
Pubblicazione: (2026)