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。
Jeffrey Amico, Gabriel Passamani Andrade, John Donaghy +12 authors
Swarm sAmpling Policy Optimization (SAPO) is a decentralized and asynchronous RL algorithm that enhances post-training language models without supervised fine-tuning, achieving significant reward gains and scalability across diverse hardware.
DeepReinforce Team, Xiaoya Li, Xiaofei Sun +4 authors
GrandCode is a multi-agent reinforcement learning system that outperforms human competitors in competitive programming challenges by orchestrating specialized agent modules and employing novel reward policy optimization techniques.
Qwen, An Yang, Baosong Yang +39 authors
Qwen2.5, an enhanced series of large language models, demonstrates superior performance across various benchmarks and use cases through extensive pre-training and advanced post-training techniques.
Jiyan He, Guang Liang, Hao Liu +19 authors
ZGCM-1 is a 7B open foundation model that combines internal reasoning with external tool use, trained via efficient architecture-system co-design, progressive long-context scaling, and autonomous agent workflows to achieve strong reasoning and efficiency.
Ziyang Zhang, Yubin Jing, Yuanhao Zeng +3 authors
Active Taskless Distillation enables language models to acquire task capabilities from a teacher using only single unrelated words, without direct task examples or model access.
Mind Lab, Song Cao, Vic Cao +59 authors
MinT is a managed infrastructure system that enables efficient low-rank adaptation training and serving by keeping base models resident and moving lightweight adapter revisions, scaling across multiple dimensions including large model architectures, reduced storage requirements, and distributed policy management.
Zongjie Li, Alan Z. W, John Nicolas J +4 authors
A data-centric framework with specialized systems for reasoning analysis, cost reduction, and execution verification enables small teams to train open-weight cyber agents that achieve top-tier performance on benchmark suites.
Xiaomi LLM-Core Team, Bingquan Xia, Bowen Shen +61 authors
MiMo-7B, a large language model optimized for reasoning tasks, enhances pre-training with data mixing and Multi-Token Prediction, and post-training with reinforcement learning on math and programming problems, achieving superior performance over larger models.
NVIDIA, Niket Agarwal, Arslan Ali +75 authors
The Cosmos World Foundation Model Platform provides a framework for developing customized world models for Physical AI by leveraging video curation, pre-trained models, and tokenizers.
Mouxiang Chen, Binyuan Hui, Zeyu Cui +5 authors
Parallel scaling (ParScale) improves inference efficiency by reusing existing parameters and executing multiple transformations in parallel, offering superior performance with reduced memory and latency compared to parameter scaling.
Saleh Ashkboos, Maximilian L. Croci, Marcelo Gennari do Nascimento +2 authors
SliceGPT, a novel post-training sparsification method, reduces model parameters by up to 25% without significant performance decrease, optimizing inference speed and GPU usage on large language models.
Ming Li, Yanhong Li, Tianyi Zhou
Investigating gradient patterns in LLMs during fast vs. slow training reveals that slow thinking (chain-of-thoughts) enhances learning stability and distinguishes correct reasoning paths.
Corby Rosset, Ching-An Cheng, Arindam Mitra +3 authors
A Direct Nash Optimization (DNO) algorithm is introduced for post-training large language models using preference feedback, achieving state-of-the-art performance with polynomial parameters.
Wenyi Hong, Weihan Wang, Ming Ding +22 authors
The CogVLM2 family of visual language models, including CogVLM2, CogVLM2-Video, and GLM-4V, advances image and video understanding with enhanced architectures and training methods.
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.
Jonghyun Song, Sangjun Song, Minjae Oh +3 authors
SHAPE analyzes chain-of-thought reasoning via semantic spaces and heuristics to diagnose LLM mathematical reasoning and improve post-training.
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