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。
Shen Nie, Fengqi Zhu, Zebin You +7 authors
LLaDA, a diffusion model trained from scratch, outperforms autoregressive models in benchmarks and demonstrates strong instruction-following capabilities, challenging the dominance of ARMs in LLMs.
Ruiyan Gong, Yingnan Guo, Junjun Hu +37 authors
ABot-N1 improves visual language navigation by separating reasoning from control through a slow-fast architecture that uses explicit chain-of-thought reasoning and pixel goals to guide continuous waypoint generation, achieving strong results across diverse embodied tasks.
Keen You, Haotian Zhang, Eldon Schoop +5 authors
Ferret-UI, a multimodal large language model tailored for mobile UI screens, enhances understanding and interaction through region annotations and a comprehensive dataset of UI tasks, outperforming existing models including GPT-4V.
Tiwei Bie, Maosong Cao, Xiang Cao +47 authors
LLaDA2.1 introduces a novel token-to-token editing approach with speed and quality modes, enhanced through reinforcement learning for improved reasoning and instruction following in large language diffusion models.
Tingchen Fu, Jiawei Gu, Yafu Li +2 authors
An empirical analysis of MathIF identifies a tension between enhancing reasoning capacity and maintaining instruction adherence in large language models.
Gemma Team, Aishwarya Kamath, Johan Ferret +213 authors
Gemma 3 introduces vision capabilities, broader language coverage, and extended context length, featuring an optimized architecture and post-training enhancements to outperform previous versions.
Chengyue Wu, Yukang Gan, Yixiao Ge +5 authors
A new post-pretraining method using expanded Transformer blocks for Large Language Models improves knowledge without catastrophic forgetting, yielding LLaMA Pro-8.3B that excels in general tasks, programming, and mathematics.
Dawid Jan Kopiczko, Tijmen Blankevoort, Yuki Markus Asano
Vector-based Random Matrix Adaptation (VeRA) reduces the number of trainable parameters by 10x compared to LoRA while maintaining performance, and is demonstrated on benchmarks like GLUE and E2E, showing its utility in instruction-following.
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.
Hiroki Furuta, Ofir Nachum, Kuang-Huei Lee +3 authors
An instruction-following multimodal agent named WebGUM, trained offline using vision transformers and language models, significantly outperforms existing methods in web navigation and multi-step reasoning tasks.
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