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。
Shaolei Zhang, Ju Fan, Meihao Fan +2 authors
DeepAnalyze-8B, an agentic LLM, autonomously completes the data science pipeline from raw data to research reports using curriculum-based training and data-grounded trajectory synthesis.
M-A-P Team, Xinrun Du, Yifan Yao +92 authors
SuperGPQA, a benchmark evaluating LLMs across 285 disciplines, reveals performance gaps and offers insights into the collaborative filtering process with human experts.
Yu Sun, Xingyu Qian, Weiwen Xu +7 authors
ReasonMed, a large medical reasoning dataset, enhances the accuracy of medical question answering models by combining detailed reasoning paths with concise summaries, setting new benchmarks for model performance.
Thaddäus Wiedemer, Yuxuan Li, Paul Vicol +6 authors
Veo 3, a generative video model, exhibits zero-shot capabilities across various visual tasks, suggesting a trajectory towards becoming a unified, generalist vision foundation model.
Xun Liang, Jiawei Yang, Yezhaohui Wang +9 authors
SurveyX enhances automated survey generation through innovative preprocessing and post-processing methods, improving content and citation quality beyond existing systems.
Violet Xiang, Charlie Snell, Kanishk Gandhi +11 authors
The Meta Chain-of-Thought framework extends traditional CoT by explicitly modeling reasoning, enabling more powerful and human-like reasoning in LLMs through process supervision, synthetic data generation, and reinforcement learning.
Yuchen Fan, Kaiyan Zhang, Heng Zhou +15 authors
LLMs can serve as efficient simulators for RL tasks by leveraging internal knowledge, reducing reliance on external search engines and improving sim-to-real transfer.
Haoran Wei, Yaofeng Sun, Yukun Li
DeepSeek-OCR uses optical 2D mapping to compress long contexts, achieving high OCR precision with reduced vision tokens and demonstrating practical value in document processing.
Ding Chen, Simin Niu, Kehang Li +6 authors
HaluMem, a benchmark for evaluating memory hallucinations in AI systems, identifies and analyzes hallucinations across memory extraction, updating, and question answering stages using large-scale human-AI interaction datasets.
Xueqing Peng, Lingfei Qian, Yan Wang +41 authors
MultiFinBen is a multilingual and multimodal benchmark for financial domain tasks, evaluating LLMs across modalities and linguistic settings, revealing challenges in complex cross-lingual and multimodal financial reasoning.
Shibo Hao, Sainbayar Sukhbaatar, DiJia Su +4 authors
A new reasoning paradigm, Coconut, utilizes continuous representations in latent space to enhance LLM performance on complex reasoning tasks, particularly those requiring backtracking.
Zheyuan Yang, Lyuhao Chen, Arman Cohan +1 authors
Two post-training strategies, distillation and RLVR, enable inference-time scaling in table reasoning tasks, resulting in a model (Table-R1-Zero) that matches GPT-4.1's performance using fewer parameters and shows strong generalization.
Sergey Pletenev, Maria Marina, Daniil Moskovskiy +4 authors
Low-rank adaptation (LoRA) effectively updates LLMs with new knowledge but risks degrading performance on external benchmarks due to data bias and overconfidence.
Zifan Zheng, Yezhaohui Wang, Yuxin Huang +4 authors
This survey explores the interpretability and underlying mechanisms of attention heads within Large Language Models to understand their reasoning processes.
Philippe Laban, Alexander R. Fabbri, Caiming Xiong +1 authors
The SummHay task evaluates LLMs and RAG systems on summarizing long-context documents by identifying relevant insights and citing sources, revealing challenges even for systems with document relevance signals.
Daniil Moskovskiy, Nikita Sushko, Sergey Pletenev +2 authors
A pipeline generates multilingual synthetic detoxification data using LLMs, outperforming models trained on human-annotated datasets in few-shot settings.
Yue Liu, Hongcheng Gao, Shengfang Zhai +7 authors
GuardReasoner enhances LLM safety through enhanced reasoning capabilities using specialized training datasets and techniques, outperforming existing models on guardrail tasks.
Shuaijie She, Yu Bao, Yu Lu +7 authors
DuPO is a dual learning framework that generates annotation-free feedback using a generalized duality, enhancing performance across various tasks without relying on costly labels.
Eilam Shapira, Omer Madmon, Itamar Reinman +3 authors
A benchmark for evaluating Large Language Models in strategic, language-based games provides insights into their rationality, mimicry of human behavior, and impact of economic characteristics on performance and outcome.
Liang Wang, Nan Yang, Xiaolong Huang +3 authors
A method using synthetic data and contrastive loss achieves high-quality text embeddings without labeled data, and sets state-of-the-art results when combined with labeled data.
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