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。
Shengnan An, Zexiong Ma, Zeqi Lin +3 authors
LeMa, a learning-from-mistakes approach, enhances LLMs' mathematical reasoning by learning from inaccurate reasoning paths corrected by GPT-4, surpassing SOTA performance on math problems.
Zhenwei Shao, Zhou Yu, Jun Yu +5 authors
A systematic study of lightweight large multimodal models (LMMs) led to the development of the Imp family, which achieves superior performance compared to larger models and is capable of high-speed inference on mobile devices.
Zhongfei Qing, Zhongang Cai, Zhitao Yang +1 authors
A new system combines language models and motion retrieval to generate long, stable, and semantically aligned human motions from text descriptions, outperforming previous methods in trajectory, action, and blending tasks.
Yumeng Wang, Yuchen Wu, Cheng Qian +6 authors
The study proposes PRISK, a framework that reveals how personalized context in LLMs increases irrelevant personalization, preference narrowing, and sycophantic bias.
Hanjia Lyu, Song Jiang, Hanqing Zeng +2 authors
Combining diverse prompts and input augmentation techniques improves personalized content recommendation performance using large language models.
Jianqiang Ren, Chao He, Lin Liu +10 authors
The Make-A-Character (Mach) framework uses large language and vision models to create realistic, 3D avatars from text descriptions efficiently, enabling customization and seamless integration with existing CG pipelines.
Dave Van Veen, Cara Van Uden, Louis Blankemeier +12 authors
Domain-adapted large language models outperform human experts in various clinical text summarization tasks, improving completeness, correctness, and aligning with physician preferences.
Alexander Borzunov, Max Ryabinin, Artem Chumachenko +5 authors
A decentralized system pools idle compute resources to enable efficient inference and fine-tuning of large language models over a consumer-grade network, showcasing significant performance improvements.
Chunting Zhou, Pengfei Liu, Puxin Xu +12 authors
A 65B parameter LLaMa language model trained with minimal instructional data matches or outperforms models with extensive human preference modeling in most cases, indicating that pretraining is predominantly responsible for knowledge acquisition.
Fuxiao Liu, Tianrui Guan, Zongxia Li +4 authors
HallusionBench is a benchmark that highlights language hallucination and visual illusion issues in vision-language models (VLMs), showcasing the limitations of current state-of-the-art models like GPT-4V and LLaVA-1.5.
Qiying Yu, Quan Sun, Xiaosong Zhang +4 authors
CapsFusion is an advanced framework that improves multimodal pretraining data by combining web-based image-text pairs and synthetic captions, leading to enhanced model performance, sample efficiency, and scalability.
Xiangpeng Wei, Haoran Wei, Huan Lin +15 authors
PolyLM, a multilingual LLM trained on 640 billion tokens, enhances multilingual capabilities through bilingual data and curriculum learning, outperforming other models on multilingual tasks while maintaining English performance.
Difei Gao, Lei Ji, Luowei Zhou +4 authors
A multi-modal AI assistant, AssistGPT, with a Plan, Execute, Inspect, and Learn (PEIL) approach integrates LLMs with various tools to handle complex visual-based tasks and achieves state-of-the-art results on benchmarks and beyond.
Benjamin Spector, Chris Re
A staged speculative decoding algorithm enhances LLM inference efficiency in small-batch, on-device settings by restructuring speculative batches and adding a second decoding stage.
Yecheng Jason Ma, William Liang, Guanzhi Wang +6 authors
Eureka, an LLM-powered reward design algorithm, generates human-level reward functions enhancing reinforcement learning for complex manipulation tasks and RLHF, including pen spinning with a simulated Shadow Hand.
Cheng Li, Mingyang Zhang, Qiaozhu Mei +4 authors
A multistage and multitask framework using large language models enhances personalized text generation by improving retrieval, ranking, summarization, synthesis, and generation skills.
Aojun Zhou, Ke Wang, Zimu Lu +8 authors
A novel code-based self-verification method significantly improves math reasoning in GPT-4 Code Interpreter, enhancing accuracy on the MATH dataset.
Ariel N. Lee, Cole J. Hunter, Nataniel Ruiz
A fine-tuned and merged family of large language models named Platypus, using LoRA modules and a curated dataset, achieves top performance on the Open LLM Leaderboard with reduced data and compute.
Lingjiao Chen, Matei Zaharia, James Zou
The performance and behavior of GPT-3.5 and GPT-4 fluctuated significantly between March and June 2023 across various tasks, emphasizing the necessity for ongoing LLM quality monitoring.
Ziqi Wang, Le Hou, Tianjian Lu +4 authors
A new framework, ImPlicit Self-ImprovemenT (PIT), uses human preference data to implicitly enhance the quality of Large Language Model responses, outperforming prompting-based methods.
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