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。
50 篇论文 · 按点赞排序
Mistral-AI, Abhinav Rastogi, Albert Q. Jiang +97 authors
Magistral, a scalable reinforcement learning pipeline, demonstrates that RL can enhance multimodal understanding and instruction following in large language models without requiring existing RL traces.
Junying Chen, Zhenyang Cai, Pengcheng Chen +5 authors
ShareGPT-4o-Image and Janus-4o enable open research in photorealistic, instruction-aligned image generation through a large dataset and multimodal model.
Zhen Li, Chuanhao Li, Xiaofeng Mao +17 authors
Sekai, a worldwide video dataset with comprehensive annotations, is introduced to support world exploration applications, enhancing video generation models.
Yunlong Lin, Zixu Lin, Kunjie Lin +8 authors
JarvisArt, an MLLM-driven agent, achieves superior photo retouching by understanding user intent and coordinating multiple retouching tools in Lightroom, outperforming GPT-4o on a novel benchmark.
Nikhil Kandpal, Brian Lester, Colin Raffel +24 authors
The Common Pile v0.1 dataset, an 8-terabyte collection of openly licensed text, is used to train competitive 7 billion parameter LLMs.
Jiacheng Chen, Ramin Mehran, Xuhui Jia +2 authors
A generative visual compositing framework using a diffusion model for scene editing and composition with source masking and simulated object jittering.
King Zhu, Hanhao Li, Siwei Wu +12 authors
Systematic exploration of test-time scaling methods in large language agents reveals that computational scaling improves performance, especially through parallel sampling, sequential revision, effective verification, and increased rollout diversity.
Jianyi Wang, Shanchuan Lin, Zhijie Lin +10 authors
SeedVR2 is a one-step diffusion-based video restoration model that uses adaptive window attention and feature matching loss to achieve high visual quality with reduced computational cost compared to existing methods.
Zehuan Huang, Haoran Feng, Yangtian Sun +3 authors
AnimaX creates multi-skeleton 3D animations by blending video diffusion model priors with skeleton-based control, using joint video-pose diffusion and shared positional encodings.
Tianchen Zhao, Ke Hong, Xinhao Yang +8 authors
PAROAttention reorganizes visual attention patterns to enable efficient sparsification and quantization, reducing memory and computational costs with minimal impact on performance.
Bin Lin, Zongjian Li, Xinhua Cheng +9 authors
A unified generative framework called UniWorld uses semantic features from visual-language models for image perception and manipulation, outperforming BAGEL with reduced data.
Zelai Xu, Zhexuan Xu, Xiangmin Yi +5 authors
VS-Bench is a multimodal benchmark designed to evaluate Vision Language Models' strategic reasoning and decision-making in complex multi-agent environments.
Yuhao Wu, Yushi Bai, Zhiqiang Hu +2 authors
An incentivization-based reinforcement learning approach is used to develop a large language model capable of generating ultra-long, high-quality text without the need for synthetic data or supervised fine-tuning.
Etash Guha, Ryan Marten, Sedrick Keh +47 authors
The OpenThoughts project created open-source datasets leading to reasoning models that match or exceed state-of-the-art benchmarks in math, code, and science.
Tong Wu, Shuai Yang, Ryan Po +4 authors
A new framework enhances video world models' long-term consistency by integrating a geometry-grounded long-term spatial memory mechanism.
Jiaqi Li, Junshu Tang, Zhiyong Xu +6 authors
Hunyuan-GameCraft is a novel framework for high-dynamic interactive video generation in game environments that addresses limitations in dynamics, generality, and efficiency through unified input representation, hybrid history-conditioned training, and model distillation.
Xinyu Yang, Yuwei An, Hongyi Liu +2 authors
Multiverse, a generative model enabling native parallel text generation, achieves performance comparable to autoregressive models through a three-stage MapReduce paradigm and efficient attention mechanisms.
Lianghong Guo, Yanlin Wang, Caihua Li +6 authors
A pipeline named SWE-Factory automates the creation and validation of GitHub issue resolution datasets for training and evaluating Large Language Models, using SWE-Builder for environment setup, exit-code-based grading, and automated fail2pass validation.
Chenlong Wang, Yuanning Feng, Dongping Chen +3 authors
NoWait suppresses explicit self-reflection tokens during inference to enhance efficiency in multimodal reasoning without reducing model utility.
Dongwei Jiang, Alvin Zhang, Andrew Wang +2 authors
LLMs show resistance to feedback, termed feedback friction, even under ideal conditions, and sampling-based strategies only partially mitigate this issue.
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