Image de couverture de livre

Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Samandarov, Samandar, Ismoiljonov, Nazirjon, Sattorov, Abdullah, Sabyrbayev, Temirlan
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Model
par: Mitra, Sinjini, et autres
Publié: (2026)

Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
par: Zhang, Zeyu, et autres
Publié: (2026)

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution
par: Vu, Kiana, et autres
Publié: (2024)

Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
par: Sharma, Kartik, et autres
Publié: (2025)

Bootstrapped Reward Shaping
par: Adamczyk, Jacob, et autres
Publié: (2025)

SplitFrozen: Split Learning with Device-side Model Frozen for Fine-Tuning LLM on Heterogeneous Resource-Constrained Devices
par: Ma, Jian, et autres
Publié: (2025)

PostMark: A Robust Blackbox Watermark for Large Language Models
par: Chang, Yapei, et autres
Publié: (2024)

Bootstrapping Expectiles in Reinforcement Learning
par: Clavier, Pierre, et autres
Publié: (2024)

Imitation Bootstrapped Reinforcement Learning
par: Hu, Hengyuan, et autres
Publié: (2023)

BLAZER: Bootstrapping LLM-based Manipulation Agents with Zero-Shot Data Generation
par: Das, Rocktim Jyoti, et autres
Publié: (2025)

Trained Persistent Memory for Frozen Decoder-Only LLMs
par: Jeong, Hong
Publié: (2026)

Bootstrap SGD: Algorithmic Stability and Robustness
par: Christmann, Andreas, et autres
Publié: (2024)

Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization
par: Carstensen, Timur, et autres
Publié: (2025)

From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales
par: Viakhirev, Ivan, et autres
Publié: (2026)

Learning to Rewrite Prompts for Bootstrapping LLMs on Downstream Tasks
par: Zhou, Qinhao, et autres
Publié: (2025)

WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper
par: Akinrintoyo, Emmanuel, et autres
Publié: (2025)

Value of Information-Enhanced Exploration in Bootstrapped DQN
par: Plataniotis, Stergios, et autres
Publié: (2025)

Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models
par: Armstrong, Marcus, et autres
Publié: (2026)

Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
par: Zhao, Guangyu, et autres
Publié: (2024)

Partially Frozen Random Networks Contain Compact Strong Lottery Tickets
par: Otsuka, Hikari, et autres
Publié: (2024)

Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
par: Hariri, Mohsen, et autres
Publié: (2025)

AgentOCR: Reimagining Agent History via Optical Self-Compression
par: Feng, Lang, et autres
Publié: (2026)

Bootstrapped Model Predictive Control
par: Wang, Yuhang, et autres
Publié: (2025)

Flattening Hierarchies with Policy Bootstrapping
par: Zhou, John L., et autres
Publié: (2025)

Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise
par: Meng, Li, et autres
Publié: (2022)

Bootstrapping LLMs via Preference-Based Policy Optimization
par: Jia, Chen
Publié: (2025)

Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods
par: Jeong, Hong
Publié: (2026)

Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations
par: Acharya, Pratyush, et autres
Publié: (2026)

TopoReformer: Mitigating Adversarial Attacks Using Topological Purification in OCR Models
par: Kumar, Bhagyesh, et autres
Publié: (2025)

Bootstrap Off-policy with World Model
par: Zhan, Guojian, et autres
Publié: (2025)

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
par: Li, Xuancheng, et autres
Publié: (2026)

LANPO: Bootstrapping Language and Numerical Feedback for Reinforcement Learning in LLMs
par: Li, Ang, et autres
Publié: (2025)

When Denoising Hinders: Revisiting Zero-Shot ASR with SAM-Audio and Whisper
par: Islam, Akif, et autres
Publié: (2026)

Bootstrapping your behavior: a new pretraining strategy for user behavior sequence data
par: Wu, Weichang, et autres
Publié: (2025)

Affordance-Guided Reinforcement Learning via Visual Prompting
par: Lee, Olivia Y., et autres
Publié: (2024)

Smart Sampling: Self-Attention and Bootstrapping for Improved Ensembled Q-Learning
par: Khan, Muhammad Junaid, et autres
Publié: (2024)

Frozen Transformers in Language Models Are Effective Visual Encoder Layers
par: Pang, Ziqi, et autres
Publié: (2023)

Bootstrapped Mixed Rewards for RL Post-Training: Injecting Canonical Action Order
par: Gupta, Prakhar, et autres
Publié: (2025)

Learning for Interval Prediction of Electricity Demand: A Cluster-based Bootstrapping Approach
par: Dube, Rohit, et autres
Publié: (2023)

Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation
par: Che, Fengdi, et autres
Publié: (2024)