EEVEE is a test‑time prompt‑learning framework that lets LLM agents continuously improve across diverse tasks by co‑evolving a router and specialized prompts, achieving a cumulative +42 gain over many tasks while keeping token usage low and preserving single‑task performance.
This article analyzes the current limitations of Graph Prompt Learning, reveals that representation‑level prompts are essentially equivalent to fine‑tuning a downstream classifier, and introduces UniPrompt—a method that leverages pre‑trained graph models while preserving input graph structure for superior in‑domain and cross‑domain performance.
The paper introduces ATPrompt, a method that inserts fixed attribute tokens into learnable prompts for CLIP‑style vision‑language models, enabling the soft prompts to capture generic attribute representations and significantly improve base‑to‑novel generalization without extra regularization losses.
This article reviews how large language models are transforming recommendation systems, covering their fundamentals, recent LLM‑enabled methods for representation, learning and generalization, challenges such as scalability, bias and privacy, and future research directions including personalized prompts and robust model integration.
This article reviews how the rapid rise of large language models, exemplified by ChatGPT, is transforming recommendation systems by addressing traditional ID‑centric limitations, introducing prompt‑based and ID‑free representations, discussing recent research advances, practical challenges, and future research directions.
With the rapid rise of ChatGPT and large language models, recommendation systems are undergoing a transformative shift, moving beyond traditional behavior‑based methods to leverage LLMs for improved generalization, representation, and prompt‑based learning, while addressing challenges such as scalability, interpretability, bias, and deployment costs.
This article details Baidu Fengchao's practical use of large language models to improve search advertising satisfaction, covering search ad relevance, the transition from DNN to ERNIE, prompt-based industry isolation, AIGC applications, and a Q&A on model architecture and optimization.
The article details how Baidu's Fengchao team leverages large language models, including a transition from DNN embeddings to ERNIE, introduces multi‑level tokenization and discrete core‑word inputs, and applies prompt learning and AIGC techniques to improve search advertising satisfaction and industry‑specific relevance modeling.
Recent advances in visual language models enable zero-shot multimodal tasks, and this article explores their application to open-set object detection, prompt learning, and promptable surgical instrument segmentation, highlighting methods like CLIP, CoOp, and the DetPro framework with experimental results across multiple benchmarks.
This article explains how Alibaba's enterprise search system tackles query intent recognition by combining knowledge‑enhanced techniques, short‑text classification, and pretrained language models such as StructBERT and prompt‑learning, and it shares two real‑world case studies, experimental results, and future research directions.
This article reviews the evolution of NLP training paradigms, explains why prompt learning is needed, defines its core concepts, and surveys major hard‑template and soft‑template methods such as PET, LM‑BFF, P‑tuning, and Prefix‑tuning, highlighting their advantages for few‑shot and zero‑shot scenarios.
This article provides a comprehensive overview of the GPT series, explains the differences between prompt learning and instruction learning, details the three‑stage training pipeline of InstructGPT/ChatGPT—including supervised fine‑tuning, reward‑model training, and PPO‑based reinforcement learning—examines their strengths, weaknesses, and future research directions, and discusses the broader impact of these models on AI development.
This report reviews the background, recent research progress, practical applications, and future directions of controllable text generation using transformer‑based pretrained language models, highlighting methods such as decoding strategies, prompt learning, memory networks, continual learning, contrastive training, and knowledge integration.
This article presents a comprehensive overview of lightweight adaptation methods—including language, domain, and optimization‑goal adapters and structured prompts—to overcome language mismatch, low domain fit, and objective differences when deploying open‑source multimodal large models in real‑world AI applications.
FSL++—a RoBERTa‑large‑based few‑shot model enhanced with domain‑adaptive pre‑training, prompt learning, diverse embedding‑level augmentations, and ensemble self‑training—topped the Chinese FewCLUE benchmark, beating human accuracy on news and scientific classification tasks and delivering measurable gains across multiple Meituan product scenarios.
