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。
Björn Engdahl, Adrian Kosowski, Jan Chorowski +6 authors
A 150M-parameter reasoning model using recurrent latent reasoning and in-context learning achieves a new cost-accuracy frontier on ARC-AGI-1.
SenseNova, Joint Research Team, Zhongang Cai +59 authors
GPT-6-Astra achieves high performance across diverse robotic tasks via in-context learning, yet real-world deployment reveals gaps in demonstration cost, execution time, and practical embodied intelligence.
Xingxuan Zhang, Gang Ren, Hao Yuan +57 authors
LimiX-2 is a scaled tabular foundation model using contextual mechanism networks and context-conditional masked modeling to learn joint data structures, improving predictions and causal skeleton recovery.
Jingqi Tong, Yurong Mou, Hangcheng Li +11 authors
The "Thinking with Video" paradigm enhances multimodal reasoning by integrating video generation models, demonstrated through the Video Thinking Benchmark and improved performance on both vision and text tasks.
Mo Yu, Lemao Liu, Junjie Wu +5 authors
A study investigates whether large language models understand physical concepts through a grid-based task, showing that they significantly underperform compared to humans and highlighting the stochastic parrot phenomenon.
Tianzhu Ye, Li Dong, Yuqing Xia +4 authors
Diff Transformer improves large language models by selectively focusing attention on relevant context and reducing noise, leading to better performance in scaling, long-context modeling, key information retrieval, and in-context learning.
Jiajun Shi, Siyuan Tao, Yuhao Wu +18 authors
S³Gym evaluates whether large language model agents can self-test, self-judge, and self-improve through interaction experience across text-based games, revealing that effective self-improvement depends on task structure and experience representation.
Haojian Huang, Zexi Li, Junhao Guo +36 authors
In-context learning for robots connects contextual evidence to physical execution through four interface families, enabling task inference and transfer across changing conditions.
Yuzhang Tian, Jianbo Zhao, Haoyu Dong +8 authors
SpreadsheetLLM introduces SheetCompressor and Chain of Spreadsheet to enhance LLMs' performance on spreadsheet tasks through efficient encoding and understanding.
Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier +28 authors
A study of Multimodal Large Language Models finds a mix of pre-training data and image encoder design crucial for SOTA performance on multimodal benchmarks.
Shen Nie, Fengqi Zhu, Zebin You +7 authors
LLaDA, a diffusion model trained from scratch, outperforms autoregressive models in benchmarks and demonstrates strong instruction-following capabilities, challenging the dominance of ARMs in LLMs.
Le Xue, Manli Shu, Anas Awadalla +24 authors
xGen-MM, an extension of Salesforce's xGen initiative, provides a framework for developing Large Multimodal Models with pre-trained, instruction-tuned, and safety-tuned variants.
Yuanzhi Li, Sébastien Bubeck, Ronen Eldan +3 authors
A new 1.3 billion parameter Transformer-based language model, phi-1.5, demonstrates comparable performance to much larger models on common sense reasoning and complex tasks despite the absence of web data.
Alexander Nikulin, Ilya Zisman, Alexey Zemtsov +3 authors
XLand-100B is a large-scale dataset for in-context reinforcement learning, containing extensive learning histories in the XLand-MiniGrid environment.
Yaroslav Aksenov, Nikita Balagansky, Sofia Maria Lo Cicero Vaina +3 authors
A modification to the Based model kernel enhances its in-context learning capabilities, outperforming existing subquadratic architectures in language modeling tasks on the Pile dataset.
Ruibin Yuan, Hanfeng Lin, Shuyue Guo +54 authors
YuE, a family of open foundation models based on LLaMA2, can generate long-form music with aligned lyrics, coherent structure, and appropriate accompaniment using innovative techniques in next-token prediction, conditioning, and pre-training.
Mo Yu, Tsz Ting Chung, Chulun Zhou +8 authors
A benchmark called PRELUDE evaluates long-context understanding by assessing the consistency of prequel stories with original books, revealing significant challenges for models compared to humans.
Hongcheng Gao, Zihao Huang, Lin Xu +11 authors
The Turing Eye Test evaluates MLLMs' perceptual capabilities on synthetic images, revealing that vision tower generalization is a key gap compared to human perception.
Zeyi Sun, Ziyang Chu, Pan Zhang +6 authors
X-Prompt, an auto-regressive large-vision language model, uses in-context learning to achieve competitive performance in seen and unseen image generation tasks.
Zhongyang Li, Ziyue Li, Tianyi Zhou
A novel test-time optimization method, C3PO, improves the accuracy and efficiency of Mixture-of-Experts Large Language Models by re-weighting experts based on surrogate objectives from neighboring samples.
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