Explore · 每周精选
发现最受关注的研究论文,追踪研究趋势,订阅感兴趣的期刊与关键词。
598 篇论文 · 按点赞排序
OpenAI, Aaron Hurst, Adam Lerer +416 authors
GPT-4o is an omnimodal autoregressive model trained to handle text, audio, image, and video inputs, offering high-performance outputs across these modalities, with particular strengths in vision and audio.
Yixin Liu, Kai Zhang, Yuan Li +9 authors
A comprehensive review of Sora, a text-to-video generative AI model, including its underlying technologies, applications, challenges, and future directions in video generation and human-AI interaction.
Yuchao Gu, Yipin Zhou, Yunfan Ye +5 authors
ROICtrl, an adapter for diffusion models using ROI-Align and ROI-Unpool, improves regional instance control in text-based visual generation with lower computational costs.
Qiushi Sun, Kanzhi Cheng, Zichen Ding +12 authors
OS-Genesis is a novel GUI data synthesis pipeline that enhances the training of GUI agents by reversing the trajectory collection process to improve data quality and diversity.
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.
Junyu Luo, Xiao Luo, Kaize Ding +3 authors
A noise-robust supervised fine-tuning framework enhances large language models' performance in downstream tasks by detecting and relabeling noisy data.
Chujie Zheng, Zhenru Zhang, Beichen Zhang +6 authors
ProcessBench evaluates models' ability to identify errors in mathematical reasoning steps, showing that existing process reward models struggle with difficult problems and underperform compared to critic models and a fine-tuned PRM.
Omer Bar-Tal, Hila Chefer, Omer Tov +11 authors
A text-to-video diffusion model using Space-Time U-Net architecture generates realistic, diverse, and coherent videos through a single pass, achieving state-of-the-art results and supporting various content creation and editing tasks.
Dirk Groeneveld, Iz Beltagy, Pete Walsh +40 authors
OLMo, an open-sourced language model, provides comprehensive access to training data, code, and architecture, facilitating research and innovation in language modeling.
Eilam Shapira, Omer Madmon, Itamar Reinman +3 authors
A benchmark for evaluating Large Language Models in strategic, language-based games provides insights into their rationality, mimicry of human behavior, and impact of economic characteristics on performance and outcome.
Pengcheng Chen, Jin Ye, Guoan Wang +15 authors
GMAI-MMBench is a comprehensive general medical AI benchmark that evaluates large vision-language models across multiple medical domains and perceptual granularities, identifying key insufficiencies and highlighting areas for improvement.
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.
Chin-Yang Lin, Chung-Ho Wu, Chang-Han Yeh +3 authors
FrugalNeRF addresses few-shot NeRF challenges by using weight-sharing voxels and a cross-scale adaptation scheme, improving quality and reducing training time.
Tianyu Zheng, Ge Zhang, Tianhao Shen +5 authors
OpenCodeInterpreter, an open-source system for generating, executing, and refining code, achieves high performance on benchmarks through execution and human feedback, reducing the gap with proprietary systems like GPT-4 Code Interpreter.
Viacheslav Surkov, Chris Wendler, Mikhail Terekhov +3 authors
Sparse autoencoders are applied to learn interpretable features from intermediate updates in text-to-image diffusion models, such as SDXL Turbo, enhancing understanding of these models' internal mechanisms.
Keen You, Haotian Zhang, Eldon Schoop +5 authors
Ferret-UI, a multimodal large language model tailored for mobile UI screens, enhances understanding and interaction through region annotations and a comprehensive dataset of UI tasks, outperforming existing models including GPT-4V.
Gagan Bhatia, El Moatez Billah Nagoudi, Hasan Cavusoglu +1 authors
FinTral, a multimodal LLM enhanced through domain-specific pretraining, instruction fine-tuning, and RLAIF, outperforms ChatGPT-3.5 and GPT-4 in financial analysis tasks with exceptional zero-shot performance.
Andrey Gromov, Kushal Tirumala, Hassan Shapourian +2 authors
Layer pruning of pre-trained LLMs with parameter-efficient finetuning methods shows minimal performance degradation and significant resource savings in both finetuning and inference.
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.
Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich +10 authors
LayerSkip, an end-to-end method, accelerates large language model inference through layer dropout and self-speculative decoding without auxiliary layers.
Fabian Gloeckle, Badr Youbi Idrissi, Baptiste Rozière +2 authors
Training large language models to predict multiple future tokens simultaneously enhances their sample efficiency and performance, particularly on generative benchmarks and small algorithmic tasks, with decreased inference time.
Haoran Wei, Chenglong Liu, Jinyue Chen +9 authors
GOT, a unified OCR model with 580M parameters, handles various types of characters and OCR tasks and offers advanced features like region-level recognition and dynamic resolution.
Runqi Qiao, Qiuna Tan, Guanting Dong +15 authors
WE-MATH benchmark evaluates Large Multimodal Models in visual mathematical reasoning, focusing on knowledge acquisition and generalization principles beyond end-to-end performance.
Niklas Muennighoff, Luca Soldaini, Dirk Groeneveld +21 authors
A sparse Mixture-of-Experts language model with 7 billion parameters achieves superior performance by using only 1 billion parameters per input token and outperforms larger models in various experiments.
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.
Peng Wang, Shuai Bai, Sinan Tan +16 authors
The Qwen2-VL Series uses Naive Dynamic Resolution and Multimodal Rotary Position Embedding to enhance visual processing and achieves competitive performance on multimodal benchmarks.
Zichen Liu, Yue Yu, Hao Ouyang +6 authors
MagicQuill integrates an interface with a multimodal large language model and diffusion prior to enable efficient and precise real-time image editing through minimal user input.
Eric Zelikman, Georges Harik, Yijia Shao +3 authors
Quiet-STaR is an extension of the Self-Taught Reasoner that teaches language models to infer and generate rationales for each token, improving their ability to predict difficult tokens and answer questions without task-specific fine-tuning.
Byung-Kwan Lee, Beomchan Park, Chae Won Kim +1 authors
MoAI, a new LLVM, integrates outputs from external CV models to enhance VL tasks without expanding model size or curating extra datasets.
Ayush Kaushal, Tejas Pandey, Tejas Vaidhya +2 authors
The Spectra LLM suite provides insights into the performance and characteristics of low-bitwidth models through comprehensive training and evaluation of FloatLMs, QuantLMs, and TriLMs across various benchmarks and datasets.
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