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。
Pooyan Rahmanzadehgervi, Logan Bolton, Mohammad Reza Taesiri +1 authors
State-of-the-art large language models with vision capabilities perform poorly on simple visual tasks, indicating limitations in their visual understanding.
Zirui Guo, Xubin Ren, Lingrui Xu +2 authors
RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.
Junteng Liu, Yunji Li, Chi Zhang +12 authors
WebExplorer, a data-driven approach for developing advanced web agents, achieves state-of-the-art performance in information-seeking tasks through systematic data generation and reinforcement learning.
Yuxiang Wei, Zhe Wang, Jiawei Liu +2 authors
Magicoder, using OSS-Instruct to incorporate open-source code snippets, achieves superior performance on coding benchmarks while reducing bias in synthetic data generation.
Xingyao Wang, Boxuan Li, Yufan Song +21 authors
OpenDevin is a platform for developing AI agents that interact with the world by writing code, using command lines, and browsing the web, with support for multiple agents and evaluation benchmarks.
Wei Xiong, Hanning Zhang, Chenlu Ye +3 authors
Self-rewarding reasoning large language models independently generate and correct their outputs during inference using a two-stage algorithmic framework, enhancing performance without external feedback.
Daixuan Cheng, Shaohan Huang, Furu Wei
Transforming raw corpora into reading comprehension texts enhances large language models' question-answering abilities across various domains and improves performance on general benchmarks.
Minki Kang, Jongwon Jeong, Seanie Lee +2 authors
Agent Distillation transfers reasoning and task-solving capabilities from large language models to smaller models using enhanced prompts and self-consistent actions, matching performance of larger models on various reasoning tasks.
Mengzhao Chen, Meng Wu, Hui Jin +10 authors
A comprehensive comparison of low-precision floating-point and integer quantization in large language models reveals that fine-grained integer formats, especially MXINT8, offer superior accuracy and efficiency over floating-point formats in many cases.
Xingyu Tan, Xiaoyang Wang, Qing Liu +4 authors
SkillZip compresses reusable procedural skills into contract-preserving, executable graph units to enable efficient retrieval and expansion under limited context budgets.
Ramakrishna Bairi, Atharv Sonwane, Aditya Kanade +6 authors
CodePlan automates repository-level coding tasks, such as package migration and temporal code edits, using a planning framework that leverages LLMs with context derived from code repositories and change analysis.
Tong Wu, Yang Liu, Jun Bai +6 authors
NPR, a teacher-free framework, enhances Large Language Models with native parallel reasoning capabilities through self-distilled training, Parallel-Aware Policy Optimization, and a robust NPR Engine, achieving substantial performance and speed improvements.
Guilherme Penedo, Hynek Kydlíček, Vinko Sabolčec +7 authors
A new pre-training dataset curation pipeline based on FineWeb supports multilingual LLMs by automatically adapting to any language, improving model performance and balancing dataset quality.
Roberto L. Castro, Andrei Panferov, Soroush Tabesh +5 authors
Quartet, a hardware-supported FP4 training approach for large language models, demonstrates state-of-the-art accuracy while significantly reducing computational costs compared to standard or FP8 precision.
Zhengyi Wang, Jonathan Lorraine, Yikai Wang +4 authors
The work demonstrates the capability of LLMs to generate 3D meshes from text by introducing a novel approach to tokenize 3D mesh data, allowing the unification of 3D and text modalities without expanding the model's vocabulary.
Itay Nakash, Nitay Calderon, Eyal Ben David +2 authors
AdaptiVocab, a novel vocabulary adaptation method, enhances the efficiency of Large Language Models in domain-specific applications without sacrificing performance by reducing token usage.
Yuxiang Wei, Olivier Duchenne, Jade Copet +6 authors
SWE-RL leverages reinforcement learning to enhance large language models' software engineering reasoning, achieving state-of-the-art performance and generalized reasoning skills by learning from extensive open-source software evolution data.
Tianyi Jiang, Arctanx An, Hengyi Feng +12 authors
A novel training-free framework called Chain of Mindset enables step-level adaptive mindset orchestration for large language models by integrating spatial, convergent, divergent, and algorithmic reasoning approaches.
Yana Wei, Liang Zhao, Jianjian Sun +15 authors
A two-stage paradigm using Qwen2.5-VL-7B and multimodal reinforcement learning achieves state-of-the-art performance in visual reasoning benchmarks.
Wei Shen, Jiangbo Pei, Yi Peng +7 authors
Skywork-R1V3, an open-source vision-language model, enhances visual reasoning through a post-training reinforcement learning framework, achieving state-of-the-art performance on multimodal 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