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
Dani Valevski, Yaniv Leviathan, Moab Arar +1 authors
GameNGen, a neural model-powered game engine, simulates high-quality gameplay in real-time using a diffusion model conditioned on past frames and actions.
Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao +8 authors
OpenELM, an open language model, uses layer-wise scaling to enhance accuracy and is released with comprehensive training and evaluation frameworks, enabling transparent and reproducible research.
Marah Abdin, Jyoti Aneja, Harkirat Behl +24 authors
A 14-billion parameter language model surpasses its teacher model in STEM-focused QA through strategic use of synthetic data, improved data quality, and enhanced training techniques.
Seungone Kim, Juyoung Suk, Shayne Longpre +7 authors
Prometheus 2 is an advanced open-source evaluator LM that aligns closely with human and proprietary LM judgments, supporting both direct assessment and pairwise ranking with customizable criteria.
Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu +15 authors
Segment Anything Model 2 (SAM 2) uses a transformer architecture with streaming memory to achieve high performance in image and video segmentation, requiring fewer interactions and faster processing than previous models.
Justin Zhao, Timothy Wang, Wael Abid +7 authors
LoRA fine-tuning reduces computational resources while maintaining high performance across various tasks and models, and LoRAX allows for efficient deployment of multiple LLMs on a single GPU.
Matt Deitke, Christopher Clark, Sangho Lee +48 authors
Molmo, a new family of open-weight VLMs, excels through a high-quality human-annotated image caption dataset and a diverse fine-tuning dataset, outperforming both proprietary and open models in benchmark and human evaluations.
Senqiao Yang, Yukang Chen, Zhuotao Tian +4 authors
VisionZip reduces visual token redundancy and enhances efficiency in vision-language models, improving performance and inference speed across various tasks.
Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey +530 authors
Llama 3, a multilingual and multi-modal language model with 405B parameters, achieves competitive performance across tasks including image, video, and speech recognition when integrated through a compositional approach.
Pei Zhou, Jay Pujara, Xiang Ren +7 authors
SELF-DISCOVER is a framework enabling LLMs to generate task-specific reasoning structures, enhancing performance on complex reasoning tasks with reduced computational cost.
Wei Chen, Zhiyuan Li
The Octopus v4 model uses functional tokens to integrate and direct queries to task-specific open-source language models, achieving SOTA performance with models under 10B parameters.
Yiran Ding, Li Lyna Zhang, Chengruidong Zhang +5 authors
LongRoPE extends pre-trained LLMs' context window to 2048k tokens with minimal fine-tuning costs and maintains original performance.
Ziming Liu, Yixuan Wang, Sachin Vaidya +5 authors
Kolmogorov-Arnold Networks (KANs) outperform Multi-Layer Perceptrons (MLPs) in accuracy and interpretability by using learnable activation functions and spline-based weights.
Shitao Xiao, Yueze Wang, Junjie Zhou +6 authors
OmniGen is a unified diffusion model for image generation that supports diverse tasks without additional modules, emphasizing simplicity, knowledge transfer, and reasoning capabilities.
Viet Nguyen, Anh Aengus Nguyen, Trung Dao +4 authors
SNOOPI framework improves one-step text-to-image diffusion models with Proper Guidance-SwiftBrush and Negative-Away Steer Attention, enhancing both training stability and negative prompt support.
Opher Lieber, Barak Lenz, Hofit Bata +19 authors
Jamba, a hybrid Transformer-Mamba MoE model, achieves state-of-the-art performance with high throughput and minimal memory usage, supporting large context lengths.
Xuezhi Wang, Denny Zhou
LLMs can perform chain-of-thought reasoning through top-k decoding without manual prompt engineering, outperforming greedy decoding and showing higher confidence in answers.
Dongxu Li, Yudong Liu, Haoning Wu +7 authors
Aria is an open multimodal native AI model with best-in-class performance across various tasks, designed with a mixture-of-experts architecture and pre-trained through a four-stage pipeline.
Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth Gopal
A novel Infini-attention mechanism allows Transformer-based LLMs to handle infinitely long inputs with limited memory and compute, enabling efficient long-context modeling and fast inference.
Artidoro Pagnoni, Ram Pasunuru, Pedro Rodriguez +11 authors
A Byte Latent Transformer (BLT) matches tokenization-based LLM performance at scale with improved inference efficiency and robustness, using entropy-based byte patching.
David Raposo, Sam Ritter, Blake Richards +3 authors
Transformer-based models can dynamically allocate computational resources to specific positions in input sequences, leading to efficient performance with reduced FLOPs.
Junying Chen, Zhenyang Cai, Ke Ji +5 authors
The proposed approach enhances medical reasoning in large language models using verifiable problems, guided search, and reinforcement learning to achieve superior performance in medical problem-solving.
Xin Chan, Xiaoyang Wang, Dian Yu +2 authors
Persona-driven synthetic data creation using a large language model and 1 billion diverse personas for various applications demonstrates versatility, scalability, and flexibility.
Guilherme Penedo, Hynek Kydlíček, Loubna Ben allal +5 authors
FineWeb, a 15-trillion token dataset from Common Crawl snapshots, outperforms other open datasets in LLM training, and its educational subset, FineWeb-Edu, significantly improves performance on knowledge and reasoning benchmarks.
Lihe Yang, Bingyi Kang, Zilong Huang +4 authors
Depth Anything V2 improves monocular depth estimation through synthetic images, larger teacher models, and pseudo-labeled real images, achieving better efficiency and accuracy than Stable Diffusion models.
Hugo Laurençon, Léo Tronchon, Matthieu Cord +1 authors
Idefics2, a vision-language model with 8 billion parameters, achieves state-of-the-art performance on multimodal benchmarks through extensive experimental validation.
Kuzma Khrabrov, Anton Ber, Artem Tsypin +10 authors
A new dataset and benchmark, $\nabla^2$DFT, enhances neural network potentials for molecular property prediction, Hamiltonian prediction, and conformational optimization with extensive, diverse molecular data.
Zhengxuan Wu, Aryaman Arora, Zheng Wang +4 authors
Representation Finetuning (ReFT) methods, exemplified by Low-rank Linear Subspace ReFT (LoReFT), achieve high efficiency and performance by adapting representations in frozen base models, outperforming state-of-the-art Parameter-efficient Fine-tuning (PEFT) methods.
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.
Kai Wang, Zhaopan Xu, Yukun Zhou +4 authors
Diffusion models can generate high-performing neural network parameters using an autoencoder, producing new subsets of network parameters with comparable or improved performance.
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