AI研究论文每日精选

每日精选AI研究论文及翻译

学习您的参考模型，以实现良好的对齐。
Learn Your Reference Model for Real Good Alignment

Alexey Gorbatovski, Boris Shaposhnikov, Alexey Malakhov, Nikita Surnachev, Yaroslav Aksenov, Ian Maksimov, Nikita Balagansky, Daniil Gavrilov•Apr 15, 2024•870

Megalodon：具有无限上下文长度的高效LLM预训练和推理
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Xuezhe Ma, Xiaomeng Yang, Wenhan Xiong, Beidi Chen, Lili Yu, Hao Zhang, Jonathan May, Luke Zettlemoyer, Omer Levy, Chunting Zhou•Apr 12, 2024•682

TransformerFAM：反馈注意力即工作记忆
TransformerFAM: Feedback attention is working memory

Dongseong Hwang, Weiran Wang, Zhuoyuan Huo, Khe Chai Sim, Pedro Moreno Mengibar•Apr 14, 2024•440

Video2Game：从单个视频中实时、交互式、逼真且兼容浏览器的环境
Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video

Hongchi Xia, Zhi-Hao Lin, Wei-Chiu Ma, Shenlong Wang•Apr 15, 2024•312

压缩线性地代表智能。
Compression Represents Intelligence Linearly

Yuzhen Huang, Jinghan Zhang, Zifei Shan, Junxian He•Apr 15, 2024•281

Ctrl-Adapter：一种高效且多功能的框架，用于将各种控制器适应到任何扩散模型中。
Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

Han Lin, Jaemin Cho, Abhay Zala, Mohit Bansal•Apr 15, 2024•220

HQ-Edit：一种用于基于指令的图像编辑的高质量数据集
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

Mude Hui, Siwei Yang, Bingchen Zhao, Yichun Shi, Heng Wang, Peng Wang, Yuyin Zhou, Cihang Xie•Apr 15, 2024•130

关于多模态大型语言模型的推理解码
On Speculative Decoding for Multimodal Large Language Models

Mukul Gagrani, Raghavv Goel, Wonseok Jeon, Junyoung Park, Mingu Lee, Christopher Lott•Apr 13, 2024•132

Tango 2：通过直接偏好优化实现基于扩散的文本转音频生成的对齐
Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization

Navonil Majumder, Chia-Yu Hung, Deepanway Ghosal, Wei-Ning Hsu, Rada Mihalcea, Soujanya Poria•Apr 15, 2024•120

AI研究论文每日精选

学习您的参考模型，以实现良好的对齐。
Learn Your Reference Model for Real Good Alignment

Megalodon：具有无限上下文长度的高效LLM预训练和推理
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

TransformerFAM：反馈注意力即工作记忆
TransformerFAM: Feedback attention is working memory

Video2Game：从单个视频中实时、交互式、逼真且兼容浏览器的环境
Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video

压缩线性地代表智能。
Compression Represents Intelligence Linearly

Ctrl-Adapter：一种高效且多功能的框架，用于将各种控制器适应到任何扩散模型中。
Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

HQ-Edit：一种用于基于指令的图像编辑的高质量数据集
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

关于多模态大型语言模型的推理解码
On Speculative Decoding for Multimodal Large Language Models

Tango 2：通过直接偏好优化实现基于扩散的文本转音频生成的对齐
Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization

TextHawk：探索多模态大型语言模型的高效细粒度感知
TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models

驯化潜在扩散模型用于神经辐射场修复
Taming Latent Diffusion Model for Neural Radiance Field Inpainting

CompGS：通过压缩高斯飘粒实现高效的3D场景表示
CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting

Support

AI研究论文每日精选

学习您的参考模型，以实现良好的对齐。
Learn Your Reference Model for Real Good Alignment

Megalodon：具有无限上下文长度的高效LLM预训练和推理
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

TransformerFAM：反馈注意力即工作记忆
TransformerFAM: Feedback attention is working memory

Video2Game：从单个视频中实时、交互式、逼真且兼容浏览器的环境
Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video

压缩线性地代表智能。
Compression Represents Intelligence Linearly

Ctrl-Adapter：一种高效且多功能的框架，用于将各种控制器适应到任何扩散模型中。
Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

HQ-Edit：一种用于基于指令的图像编辑的高质量数据集
HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

关于多模态大型语言模型的推理解码
On Speculative Decoding for Multimodal Large Language Models

Tango 2：通过直接偏好优化实现基于扩散的文本转音频生成的对齐
Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization

TextHawk：探索多模态大型语言模型的高效细粒度感知
TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models

驯化潜在扩散模型用于神经辐射场修复
Taming Latent Diffusion Model for Neural Radiance Field Inpainting

CompGS：通过压缩高斯飘粒实现高效的3D场景表示
CompGS: Efficient 3D Scene Representation via Compressed Gaussian Splatting