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。
Xixi Wu, Kuan Li, Yida Zhao +11 authors
ReSum, a novel paradigm with periodic context summarization, enhances web agents' performance on knowledge-intensive tasks by overcoming context window limitations, achieving significant improvements over ReAct.
Kai Mei, Zelong Li, Shuyuan Xu +3 authors
AIOS, an operating system embedding large language models, addresses resource allocation, context switching, and concurrency challenges for intelligent agents, demonstrating reliability and efficiency.
Leon Voukoutis, Dimitris Roussis, Georgios Paraskevopoulos +6 authors
Developers created Meltemi 7B, a 7 billion parameter open-source large language model for Greek, trained on a 40 billion token corpus, and enhanced with instruction-tuning for chat applications.
Junying Chen, Zhenyang Cai, Pengcheng Chen +5 authors
ShareGPT-4o-Image and Janus-4o enable open research in photorealistic, instruction-aligned image generation through a large dataset and multimodal model.
Dahyun Kim, Chanjun Park, Sanghoon Kim +15 authors
A novel technique, depth up-scaling (DUS), efficiently enhances large language models (LLMs) without complex changes, building SOLAR 10.7B that outperforms existing open-source models in various NLP tasks, including instruction-following.
Pratyush Maini, Vineeth Dorna, Parth Doshi +26 authors
BeyondWeb, a synthetic data generation framework, outperforms existing datasets and accelerates training for large language models by optimizing multiple factors.
Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster +6 authors
Llemma, a large language model pretrained on mathematical data, outperforms existing models and demonstrates tool use and formal theorem proving capabilities.
Shivalika Singh, Freddie Vargus, Daniel Dsouza +30 authors
The initiative builds a human-curated instruction-following dataset spanning 65 languages and creates the largest multilingual collection of instruction-following instances through templating and translating existing datasets across 114 languages, contributing datasets and platforms for participatory research.
Seungone Kim, Jamin Shin, Yejin Cho +8 authors
Prometheus, an open-source LLM, matches GPT-4's evaluation capabilities using customized score rubrics and outperforms ChatGPT across various benchmarks.
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.
Wei Huang, Xudong Ma, Haotong Qin +7 authors
LLaMA3 performance degrades significantly when quantized to low bit-width, highlighting challenges in low-bit quantization for large language models.
Renat Aksitov, Sobhan Miryoosefi, Zonglin Li +10 authors
A ReAct-style LLM agent with iterative training using reinforcement learning and self-distillation improves complex question-answering performance with fewer parameters.
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.
Xiaohan Wang, Yuhui Zhang, Orr Zohar +1 authors
VideoAgent, an agent-based system using a large language model, significantly enhances long-form video understanding through interactive reasoning and efficient zero-shot accuracy on EgoSchema and NExT-QA benchmarks.
Zhaoyan Sun, Shan Zhong, Daizhou Wen +10 authors
A comprehensive benchmark named AgenticDataBench is introduced to evaluate data agents across diverse domains with fine-grained task annotations and skill-based coverage metrics.
Navve Wasserman, Noam Rotstein, Roy Ganz +1 authors
A diffusion model is trained to add objects to images based on text descriptions using a large-scale dataset of images with removed objects, outperforming existing methods.
Rong Shan, Tianyi Xu, Congmin Zheng +9 authors
Image Bundle Composition reframes retrieval as dynamic assembly of relationally coherent image groups, with a benchmark and agentic framework addressing combinatorial joint relevance.
Shuangkang Fang, Yufeng Wang, Yi-Hsuan Tsai +4 authors
CE3D++ enables flexible dialogue-driven 3D and 4D scene editing by decoupling 2D editing from 3D reconstruction via a Hash-Atlas network and using a large language model to autonomously invoke visual tools.
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