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。
Hao Liang, Zhengyang Zhao, Meiyi Qiang +22 authors
DataFlex is a unified framework for dynamic data-centric training of large language models that supports sample selection, domain mixture adjustment, and sample reweighting while maintaining compatibility with standard training workflows and enabling efficient large-scale deployment.
Marah Abdin, Sam Ade Jacobs, Ammar Ahmad Awan +81 authors
Phi-3-mini, a compact 3.8 billion parameter language model, achieves competitive performance with larger models through an enhanced training dataset and alignment.
Anton Razzhigaev, Matvey Mikhalchuk, Temurbek Rahmatullaev +4 authors
Analysis of Large Language Models reveals that even minor tokens are crucial for context, and introduces LLM-Microscope for assessing token-level nonlinearity and contextual memory.
An Yang, Baosong Yang, Binyuan Hui +55 authors
The Qwen2 series, comprising 0.5 to 72 billion parameter models, surpasses prior open models across language understanding, generation, multilingualism, coding, math, and reasoning, with exceptional performance in benchmarks like MMLU, GPQA, HumanEval, GSM8K, BBH, MT-Bench, Arena-Hard, and LiveCodeBench.
Jin Xu, Zhifang Guo, Jinzheng He +11 authors
Qwen2.5-Omni is a multimodal model that processes text, images, audio, and video in a streaming fashion and generates text and speech using a dual-track architecture, achieving state-of-the-art performance on multimodal benchmarks.
Jinjie Ni, Qian Liu, Longxu Dou +5 authors
Diffusion language models outperform autoregressive models in low-data settings due to any-order modeling, iterative bidirectional denoising, and Monte Carlo augmentation, and maintain advantages even at scale.
Guilherme Penedo, Hynek Kydlíček, Loubna Ben allal +5 authors
FineWeb, a 15-trillion token dataset from Common Crawl snapshots, outperforms other open datasets in LLM training, and its educational subset, FineWeb-Edu, significantly improves performance on knowledge and reasoning benchmarks.
Long Phan, Alice Gatti, Ziwen Han +661 authors
HLE is a challenging multi-modal benchmark that highlights the limitations of current LLMs in closed-ended academic questions.
01. AI, Alex Young, Bei Chen +28 authors
The Yi model family, based on transformer architecture, showcases strong performance across benchmarks and modalities through optimized data and scalable infrastructure.
Jeffrey Li, Alex Fang, Georgios Smyrnis +56 authors
DataComp for Language Models (DCLM) provides a benchmark with a standardized corpus and recipes to improve language models through controlled dataset experiments, showing the importance of data curation for performance and compute efficiency.
Shengnan An, Zexiong Ma, Zeqi Lin +2 authors
FILM-7B enhances long-context processing by using information-intensive training with synthesized datasets, improving retrieval and performance on real-world tasks without compromising short-context performance.
Jun Zhao, Zhihao Zhang, Qi Zhang +2 authors
A comprehensive study on transferring English-dominant LLMs to non-English languages using LLaMA demonstrates that comparable performance can be achieved with minimal pretraining data across various language capabilities and response quality metrics.
Arindam Mitra, Luciano Del Corro, Guoqing Zheng +11 authors
AgentInstruct, an agentic framework, generates high-quality synthetic data for post-training language models, leading to significant performance improvements across various benchmarks.
Gemini Team, Rohan Anil, Sebastian Borgeaud +939 authors
Gemini, a family of multimodal models, achieves state-of-the-art performance across various benchmarks, including human-expert performance on MMLU, through advanced cross-modal reasoning and language understanding.
Zecheng Tang, Zechen Sun, Juntao Li +2 authors
LOGO, a preference optimization strategy, enhances LCM generation performance and context window size by efficiently training with limited data.
Zayne Sprague, Fangcong Yin, Juan Diego Rodriguez +7 authors
Chain-of-thought prompting enhances large language model performance primarily in math or logic tasks by improving symbolic reasoning, but it is less beneficial in other domains and can be selectively applied to save inference costs.
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