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。
Tao Zhang, Xiangtai Li, Hao Fei +5 authors
OMG-LLaVA integrates pixel-level vision understanding and reasoning capabilities through a universal segmentation method combined with LLM, achieving high performance across multiple benchmarks.
Tianbao Xie, Danyang Zhang, Jixuan Chen +14 authors
OSWorld provides a scalable, real computer environment for evaluating multimodal agents across various operating systems and tasks, highlighting significant gaps in current LLM/VLM capabilities.
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.
Wei Chen, Zhiyuan Li, Zhen Guo +1 authors
An on-device Planner-Action framework, utilizing Phi-3 Mini for planning and Octopus for execution, employs model fine-tuning and multi-LoRA training to enhance efficiency and multi-domain handling on resource-constrained devices.
Xiao Yang, Kai Sun, Hao Xin +24 authors
The Comprehensive RAG Benchmark (CRAG) evaluates RAG solutions with diverse QA tasks, revealing gaps in LLM accuracy and future research directions.
Lianmin Zheng, Wei-Lin Chiang, Ying Sheng +10 authors
Using strong large language models as judges for evaluating other LLM-based chat assistants achieves high agreement with human preferences, offering a scalable and explainable solution compared to traditional benchmarks.
Dahyun Kim, Yungi Kim, Wonho Song +4 authors
A stepwise direct preference optimization approach improves the alignment of large language models with human preferences and enhances their performance.
Chengqian Ma, Wei Tao, Haoyu Zhang +1 authors
Motion-Omni is an end-to-end framework that jointly generates spoken dialogue and full-body co-speech motion from shared hidden states, using scalable pseudo-labeling and a unified evaluation protocol to achieve real-time, aligned responses.
Houwen Peng, Kan Wu, Yixuan Wei +17 authors
A new FP8 automatic mixed-precision framework for training large language models reduces memory usage and increases speed compared to BF16 and Nvidia Transformer Engine.
Hanlin Wang, Hao Ouyang, Qiuyu Wang +10 authors
WorldDirector enables controllable video generation with persistent object memory by decoupling semantic motion planning from visual rendering through LLM coordination of 3D trajectories and camera movements.
Tao Ge, Jing Hu, Xun Wang +2 authors
The In-context Autoencoder (ICAE) compresses long contexts into memory slots for efficient LLM inference using a combination of pretraining and fine-tuning.
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.
Yaqi Zhang, Di Huang, Bin Liu +7 authors
MotionGPT generates realistic human motion using multimodal control signals by adapting a small portion of LLM parameters to handle unified input instructions.
Tiange Luo, Chris Rockwell, Honglak Lee +1 authors
Cap3D generates high-quality descriptive text for 3D objects using pretrained models and datasets, surpassing human performance in quality, cost, and speed.
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