Image de couverture de livre

Visual Instruction Bottleneck Tuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Oh, Changdae, Li, Jiatong, Im, Shawn, Li, Sharon
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Understanding Multimodal LLMs Under Distribution Shifts: An Information-Theoretic Approach
par: Oh, Changdae, et autres
Publié: (2025)

General Exploratory Bonus for Optimistic Exploration in RLHF
par: Li, Wendi, et autres
Publié: (2025)

Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
par: Long, Lin, et autres
Publié: (2025)

How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
par: Im, Shawn, et autres
Publié: (2026)

Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities
par: Oh, Changdae, et autres
Publié: (2026)

Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
par: Park, Seongheon, et autres
Publié: (2026)

Understanding the Learning Dynamics of Alignment with Human Feedback
par: Im, Shawn, et autres
Publié: (2024)

VAUQ: Vision-Aware Uncertainty Quantification for LVLM Self-Evaluation
par: Park, Seongheon, et autres
Publié: (2026)

Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism
par: Lee, Sangyoun, et autres
Publié: (2024)

Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
par: Oldfield, James, et autres
Publié: (2025)

Improved Baselines with Visual Instruction Tuning
par: Liu, Haotian, et autres
Publié: (2023)

Perturb-and-Compare Approach for Detecting Out-of-Distribution Samples in Constrained Access Environments
par: Lee, Heeyoung, et autres
Publié: (2024)

Towards Calibrated Robust Fine-Tuning of Vision-Language Models
par: Oh, Changdae, et autres
Publié: (2023)

Thinking Makes LLM Agents Introverted: How Mandatory Thinking Can Backfire in User-Engaged Agents
par: Li, Jiatong, et autres
Publié: (2026)

Learning to Instruct for Visual Instruction Tuning
par: Zhou, Zhihan, et autres
Publié: (2025)

Parrot: Multilingual Visual Instruction Tuning
par: Sun, Hai-Long, et autres
Publié: (2024)

UMIE: Unified Multimodal Information Extraction with Instruction Tuning
par: Sun, Lin, et autres
Publié: (2024)

Bridging Writing Manner Gap in Visual Instruction Tuning by Creating LLM-aligned Instructions
par: Jing, Dong, et autres
Publié: (2025)

VisNec: Measuring and Leveraging Visual Necessity for Multimodal Instruction Tuning
par: Dong, Mingkang, et autres
Publié: (2026)

How Real Is AI Tutoring? Comparing Simulated and Human Dialogues in One-on-One Instruction
par: Li, Ruijia, et autres
Publié: (2025)

Reconstructive Visual Instruction Tuning
par: Wang, Haochen, et autres
Publié: (2024)

Reasoning Is All You Need for Urban Planning AI
par: Yang, Sijie, et autres
Publié: (2025)

Mitigating the Linguistic Gap with Phonemic Representations for Robust Cross-lingual Transfer
par: Jung, Haeji, et autres
Publié: (2024)

Data Selection for Multi-turn Dialogue Instruction Tuning
par: Li, Bo, et autres
Publié: (2026)

Instruction Tuning With Loss Over Instructions
par: Shi, Zhengyan, et autres
Publié: (2024)

Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact
par: Lee, Hyunji, et autres
Publié: (2025)

EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning
par: Xie, Hongxia, et autres
Publié: (2024)

SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning
par: Wang, Ziqi, et autres
Publié: (2024)

Aligning Instruction Tuning with Pre-training
par: Liang, Yiming, et autres
Publié: (2025)

Adaptive Task Balancing for Visual Instruction Tuning via Inter-Task Contribution and Intra-Task Difficulty
par: Dai, Yanqi, et autres
Publié: (2024)

System-2 Mathematical Reasoning via Enriched Instruction Tuning
par: Cai, Huanqia, et autres
Publié: (2024)

Enhancing Multimodal Continual Instruction Tuning with BranchLoRA
par: Zhang, Duzhen, et autres
Publié: (2025)

Human Motion Instruction Tuning
par: Li, Lei, et autres
Publié: (2024)

Conveying Imagistic Thinking in Traditional Chinese Medicine Translation: A Prompt Engineering and LLM-Based Evaluation Framework
par: Han, Jiatong
Publié: (2025)

Robotic Visual Instruction
par: Li, Yanbang, et autres
Publié: (2025)

Optimizing Psychological Counseling with Instruction-Tuned Large Language Models
par: Li, Wenjie, et autres
Publié: (2024)

Joint Flashback Adaptation for Forgetting-Resistant Instruction Tuning
par: Zhao, Yukun, et autres
Publié: (2025)

An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations
par: Park, Seonghwan, et autres
Publié: (2025)

Discovering the Representation Bottleneck of Graph Neural Networks
par: Wu, Fang, et autres
Publié: (2022)

Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuning
par: Safaei, Bardia, et autres
Publié: (2025)