Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
Keming Lu, Bowen Yu, Chang Zhou +1 authors
Ditto, a self-alignment method, enhances the role-playing capabilities of open-source large language models by fine-tuning them on a large generated dataset, achieving performance comparable to proprietary chatbots.
Zihan Liu, Wei Ping, Rajarshi Roy +3 authors
ChatQA uses a two-stage instruction tuning method with a dense retriever to improve zero-shot conversational QA performance, outperforming GPT-4 on multiple datasets.
Ziheng Jiang, Haibin Lin, Yinmin Zhong +29 authors
MegaScale is a production system designed to train large language models at scale using more than 10,000 GPUs, focusing on efficiency, stability, and fault tolerance through advanced observability and diagnostic tools.
Jiongnan Liu, Yutao Zhu, Shuting Wang +6 authors
A novel model constructs user-specific embeddings using a lightweight plug-in module to personalize LLM outputs without fine-tuning, improving performance on various tasks.
Pei Zhou, Aman Madaan, Srividya Pranavi Potharaju +9 authors
LLMs perform well in inferring beliefs but struggle translating these into actions; Foresee and Reflect (FaR) improves their action guidance in social scenarios.
Han Lin, Abhay Zala, Jaemin Cho +1 authors
VideoDirectorGPT combines LLMs for video content planning with a layout-controlled video generator, enabling temporally consistent multi-scene video generation from text prompts.
Yixiao Li, Yifan Yu, Chen Liang +4 authors
LoftQ, a novel quantization framework, improves performance of LLMs by simultaneously quantizing and initializing LoRA fine-tuning, reducing the gap in downstream task performance.
William Berrios, Gautam Mittal, Tristan Thrush +2 authors
LENS uses language models to reason over outputs from vision modules, achieving competitive performance in vision and vision-language tasks without multimodal training.
Lionel Wong, Gabriel Grand, Alexander K. Lew +4 authors
A framework combining large language models and probabilistic programs translates language into a symbolic language of thought for rational, commonsense reasoning across multiple cognitive domains.
Xiao Liu, Hao Yu, Hanchen Zhang +19 authors
AgentBench is a multi-dimensional benchmark for evaluating LLMs as autonomous agents across various interactive environments, highlighting performance differences between commercial and open-source models.
Ning Miao, Yee Whye Teh, Tom Rainforth
A zero-shot verification scheme improves LLMs' question-answering performance by identifying and correcting errors in step-by-step reasoning.
Yuxian Gu, Li Dong, Furu Wei +1 authors
MiniLLM distills knowledge from large generative language models to smaller models using reverse KLD for better precision, quality, and performance.
Jifan Yu, Xiaozhi Wang, Shangqing Tu +32 authors
A benchmark for evaluating large language models emphasizes knowledge-related abilities, uses a mix of datasets, and incorporates self-contrast metrics to detect knowledge hallucination.
Hang Zhang, Xin Li, Lidong Bing
Video-LLaMA is a multi-modal framework that integrates visual and auditory understanding into LLMs by extending image encoders to video and aligning audio signals, achieving effective video-language correspondence.
Zhiwei Liu, Weiran Yao, Jianguo Zhang +12 authors
A comprehensive comparison and new orchestration strategy for LLM-augmented Autonomous Agents (LAAs) demonstrate their effectiveness in decision-making and multi-step reasoning tasks.
Lingjiao Chen, Matei Zaharia, James Zou
Strategies including prompt adaptation, LLM approximation, and LLM cascade are proposed to reduce costs and maintain or improve performance when using large language models.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号