Boost Black-Box VLMs Without Training: Class-Aware Prompt Reweighting (CARPRT)

The article analyzes the prompt‑sensitivity problem of zero‑shot classification in vision‑language models, critiques class‑agnostic prompt weighting, and presents CARPRT—a training‑free, black‑box compatible method that reweights prompts per class using similarity scores and pseudo‑labels, achieving consistent gains across datasets and model architectures.

Black-Box OptimizationClass-Aware ModelingPrompt Reweighting

0 likes · 11 min read

Boost Black-Box VLMs Without Training: Class-Aware Prompt Reweighting (CARPRT)

Test Development Learning Exchange

Apr 4, 2024 · Artificial Intelligence

Scikit‑Optimize (skopt): Features, Use Cases, and Code Examples

Scikit‑Optimize is a Python library for black‑box optimization that offers adaptable, efficient algorithms, hyper‑parameter tuning, interactive monitoring, and seamless Scikit‑Learn integration, illustrated with five comprehensive code examples covering basic usage, constrained and interactive optimization, and visualization.

Bayesian OptimizationBlack-Box Optimizationhyperparameter tuning

0 likes · 7 min read

Scikit‑Optimize (skopt): Features, Use Cases, and Code Examples

Xiaohongshu Tech REDtech

Nov 11, 2022 · Artificial Intelligence

Language Model as a Service and Black‑Box Optimization: Insights from Prof. Qiu Xipeng’s Talk

Prof. Qiu Xipeng’s talk highlighted how large language models can be offered as a service and efficiently adapted via in‑context learning, lightweight label‑tuning, and gradient‑free black‑box optimization, showcasing a unified asymmetric Transformer (CPT) that handles understanding, generation, ABSA and NER tasks while reducing resource demands.

Black-Box OptimizationLLMLanguage Model

0 likes · 15 min read

Language Model as a Service and Black‑Box Optimization: Insights from Prof. Qiu Xipeng’s Talk

Dada Group Technology

Jun 9, 2017 · Artificial Intelligence

Deep Reinforcement Learning: Concepts, Black‑Box Optimization, and the Cross‑Entropy Method

This article introduces reinforcement learning and deep reinforcement learning, explains key algorithms such as DQN and policy gradients, discusses black‑box optimization and the cross‑entropy method, and provides resources and code examples for further study.

Black-Box OptimizationDQNartificial intelligence

0 likes · 7 min read

Deep Reinforcement Learning: Concepts, Black‑Box Optimization, and the Cross‑Entropy Method