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。
Chengshuai Zhao, Zhen Tan, Pingchuan Ma +5 authors
CoT reasoning in LLMs is found to be limited by the distribution discrepancy between training and test data, suggesting it is not a robust form of reasoning.
Rui-Jie Zhu, Zixuan Wang, Kai Hua +30 authors
LoopLM, a family of pre-trained Looped Language Models, enhances reasoning by integrating iterative computation and entropy regularization during pre-training, achieving superior performance with better knowledge manipulation.
Shenzhi Wang, Le Yu, Chang Gao +15 authors
Token entropy patterns are crucial in RLVR, with high-entropy tokens significantly impacting reasoning performance and model optimization.
Jonas Geiping, Sean McLeish, Neel Jain +6 authors
A novel language model scales test-time computation by reasoning in latent space, outperforming token-based models on reasoning benchmarks.
Zixuan Huang, Yang Zhou, Kaixuan Wang +6 authors
Proposed multiple-choice planning and deferred trajectory verification reduce reasoning bias and improve verifiable autonomous driving decisions.
Alexander Panfilov, David Schmotz, Ilia Shumailov +5 authors
Encrypted reasoning traces shared across sessions and models can be intercepted and injected into weaker models to extract proprietary reasoning, private data, hidden hazards, and hidden prompts.
Yifan Jiang, Yueying Wang, Rui Zhao +4 authors
VideoP2R, a process-aware reinforcement fine-tuning framework, improves video reasoning and understanding by modeling perception and reasoning separately, achieving state-of-the-art results on multiple benchmarks.
Chengpeng Li, Mingfeng Xue, Zhenru Zhang +7 authors
START integrates external tools into large reasoning models to enhance capabilities, using techniques like Hint-infer and Hint Rejection Sampling Fine-Tuning, achieving high performance across various benchmarks.
Yunheng Li, Guohong Mu, Hao Li +4 authors
OraRL improves reinforcement learning post-training for video multimodal language models by integrating oracle rollouts with decoupled advantage estimation and sign-balanced pruning, achieving higher sample efficiency and scalability without chain-of-thought generation.
Yu Sun, Xingyu Qian, Weiwen Xu +7 authors
ReasonMed, a large medical reasoning dataset, enhances the accuracy of medical question answering models by combining detailed reasoning paths with concise summaries, setting new benchmarks for model performance.
Yizhou Wang, Chen Tang, Han Deng +29 authors
A scientific reasoning foundation model pre-trained on diverse scientific data supports multiple tasks and enhances cross-domain generalization and fidelity through specialized training techniques.
Violet Xiang, Charlie Snell, Kanishk Gandhi +11 authors
The Meta Chain-of-Thought framework extends traditional CoT by explicitly modeling reasoning, enabling more powerful and human-like reasoning in LLMs through process supervision, synthetic data generation, and reinforcement learning.
Jinghui Lu, Jiayi Guan, Zhijian Huang +47 authors
OneVL presents a unified vision-language-action framework that improves latent chain-of-thought reasoning for autonomous driving by integrating language and visual world model supervision for faster, more accurate trajectory prediction.
Weiyun Wang, Zhe Chen, Wenhai Wang +8 authors
A preference optimization process enhances multimodal reasoning, particularly Chain-of-Thought performance, in large language models through automated data construction and mixed preference optimization, demonstrating significant improvements on 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.
Xiaomi LLM-Core Team, Zihao Yue, Zhenru Lin +71 authors
MiMo-VL-7B-SFT and MiMo-VL-7B-RL provide state-of-the-art general visual understanding and multimodal reasoning through four-stage pre-training and Mixed On-policy Reinforcement Learning, outperforming models with up to 78B parameters.
Liyan Xu, Mo Yu, Fandong Meng +1 authors
Research investigates latent planning dynamics in large language models through a probing method called Tele-Lens, revealing limited global planning and enabling improved uncertainty estimation and CoT bypass recognition.
Namgyu Ho, Huzama Ahmad, Woosung Koh +3 authors
Declarative Attention lets language models declare relevant context regions during reasoning to skip most KV cache reads, reducing attended tokens with small accuracy trade-offs.
Yu Zhao, Huifeng Yin, Bo Zeng +6 authors
Marco-o1 extends reasoning models to open-ended domains without clear standards using Chain-of-Thought fine-tuning, Monte Carlo Tree Search, reflection mechanisms, and innovative reasoning strategies.
NVIDIA, Alisson Azzolini, Hannah Brandon +42 authors
Cosmos-Reason1 models, using hierarchical and two-dimensional ontologies for physical common sense and embodied reasoning, generate embodied decisions through multimodal large language models trained in vision and Physical AI stages.
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