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。
Frank F. Xu, Yufan Song, Boxuan Li +18 authors
A benchmark platform evaluates AI agents' autonomy in performing professional tasks in a simulated workplace environment, showing that a significant portion of simpler tasks can be automated but complex, long-term tasks remain challenging.
Shaolei Zhang, Qingkai Fang, Zhe Yang +1 authors
LLaVA-Mini, a unified large multimodal model, significantly reduces computational cost and latency by compressing vision tokens to a single token before feeding them to the LLM backbone, outperforming previous models.
Shanghaoran Quan, Jiaxi Yang, Bowen Yu +14 authors
CodeElo is a standardized code generation benchmark based on CodeForces contests, providing comprehensive evaluation of LLMs' coding abilities with reliable Elo ratings.
Xiaotian Han, Yiren Jian, Xuefeng Hu +8 authors
InfiMM-WebMath-40B, a large multimodal dataset, significantly improves mathematical reasoning capabilities in LLMs, achieving state-of-the-art performance on multimodal benchmarks.
Ting Jiang, Shaohan Huang, Shengyue Luo +8 authors
MoRA, a high-rank updating method using square matrices, enhances the ability of large language models to learn and memorize new knowledge, especially in memory-intensive tasks, compared to LoRA.
Liangyu Zha, Junlin Zhou, Liyao Li +22 authors
TableGPT, a fine-tuned language model with global tabular representations, enables seamless interaction and complex operations on tables via natural language and functional commands.
Yifan Xu, Xiao Liu, Xueqiao Sun +7 authors
AndroidLab provides a systematic framework for training and evaluating Android agents, supporting both large language models and multimodal models, and improves their task success rates.
Xun Liang, Shichao Song, Zifan Zheng +6 authors
A theoretical framework called Internal Consistency and a Self-Feedback framework with Self-Evaluation and Self-Update modules are presented to address reasoning and hallucination in large language models by assessing coherence across model layers.
Chenglei Si, Diyi Yang, Tatsunori Hashimoto
LLM-generated research ideas are perceived as more novel than those from human experts but are deemed slightly less feasible, based on blind evaluations by NLP researchers.
Ge Zhang, Scott Qu, Jiaheng Liu +42 authors
MAP-Neo, a fully open-sourced bilingual LLM with 7B parameters, achieves performance comparable to existing state-of-the-art LLMs, enhancing transparency and fostering innovation in the open research community.
Sarah Gao, Andrew Kean Gao
A tool called Constellation clusters and visualizes large language models uploaded to Hugging Face using hierarchical clustering and n-gram analysis.
Ahmet Üstün, Viraat Aryabumi, Zheng-Xin Yong +14 authors
Aya, a multilingual generative language model supporting over 50% lower-resourced languages, excels in both generative and discriminative tasks across 99 languages, and provides extensive evaluations and open-source resources.
Junyu Luo, Xiao Luo, Xiusi Chen +3 authors
A semi-supervised fine-tuning framework named SemiEvol enhances LLM adaptation using both labeled and unlabeled data, showing improved performance through bi-level knowledge propagation and collaborative learning.
David Grangier, Angelos Katharopoulos, Pierre Ablin +1 authors
The study evaluates various machine learning approaches under constrained inference and training budgets, demonstrating that hyper-networks and mixture of experts perform well with large pretraining budgets, while small models trained on importance sampled datasets are better with large specialization budgets.
Zhuoqun Li, Xuanang Chen, Haiyang Yu +7 authors
StructRAG enhances LLMs by identifying optimal structure types, reconstructing documents into these structures, and inferring answers for knowledge-intensive reasoning tasks, achieving state-of-the-art performance.
Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren +17 authors
Gecko is a compact and versatile text embedding model that distills knowledge from large language models to achieve strong retrieval performance on benchmarks.
Zihan Wang, Deli Chen, Damai Dai +3 authors
Research on parameter-efficient fine-tuning for Large Language Models with Mixture-of-Experts architecture reveals that task-specific expert tuning can enhance performance and efficiency.
Wenqi Zhang, Zhenglin Cheng, Yuanyu He +8 authors
A multi-modal self-instruct benchmark using large language models and code capabilities enhances understanding and reasoning for abstract images and visual tasks, improving performance metrics like chart understanding and map navigation.
Tiannan Wang, Jiamin Chen, Qingrui Jia +43 authors
Weaver, a family of specialized large language models, achieves superior writing capabilities through pre-training and fine-tuning methods, surpasses GPT-4 in various writing tasks, and supports retrieval-augmented generation and tool usage.
Xubo Liu, Zhongkai Zhu, Haohe Liu +8 authors
WavJourney leverages Large Language Models to generate structured audio scripts from text, which are then processed by task-specific audio models to create audio content, enabling explainable and human-controlled audio production.
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