中文
相关论文

相关论文: MinerU2.5-Pro: Pushing the Limits of Data-Centric …

200 篇论文

Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension,…

机器学习 · 计算机科学 2026-04-17 Bingbing Wen , Sirajul Salekin , Feiyang Kang , Bill Howe , Lucy Lu Wang , Javier Movellan , Manjot Bilkhu

Recent advancements in open-source multi-modal large language models (MLLMs) have primarily focused on enhancing foundational capabilities, leaving a significant gap in human preference alignment. This paper introduces OmniAlign-V, a…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Xiangyu Zhao , Shengyuan Ding , Zicheng Zhang , Haian Huang , Maosong Cao , Weiyun Wang , Jiaqi Wang , Xinyu Fang , Wenhai Wang , Guangtao Zhai , Haodong Duan , Hua Yang , Kai Chen

Deep generative models provide state-of-the-art performance across a wide array of applications, with recent studies showing increasing applicability for science and engineering. Despite a growing corpus of literature focused on the…

机器学习 · 计算机科学 2026-05-14 Jacob K. Christopher , James E. Warner , Ferdinando Fioretto

The widespread adoption of large language models such as ChatGPT and Bard has led to unprecedented demand for these technologies. The burgeoning cost of inference for ever-increasing model sizes coupled with hardware shortages has limited…

Production deployments in complex systems require ML architectures to be highly efficient and usable against multiple tasks. Particularly demanding are classification problems in which data arrives in a streaming fashion and each class is…

机器学习 · 计算机科学 2023-07-12 Mateusz Wójcik , Witold Kościukiewicz , Mateusz Baran , Tomasz Kajdanowicz , Adam Gonczarek

World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols…

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

机器学习 · 计算机科学 2025-09-16 Pedro Savarese

Despite the rapid progress of Vision-Language Models (VLMs), their capabilities are inadequately assessed by existing benchmarks, which are predominantly English-centric, feature simplistic layouts, and support limited tasks. Consequently,…

计算机视觉与模式识别 · 计算机科学 2025-11-14 Ketong Chen , Yuhao Chen , Yang Xue

Generating step-by-step "how-to" procedures is a key LLM capability: how-to advice is commonly requested in chatbots, and step-by-step planning is critical for reasoning over complex tasks. Yet, measuring and improving procedural validity…

机器学习 · 计算机科学 2026-02-10 Yapei Chang , Kyle Lo , Mohit Iyyer , Luca Soldaini

Pipeline parallelism is a crucial paradigm for large-scale model training. However, imbalances in memory footprint across stages can lead to significant GPU memory wastage, limiting the model sizes that pipeline parallelism can effectively…

分布式、并行与集群计算 · 计算机科学 2025-05-12 Xuan Peng , Xuanhua Shi , Haolin Zhang , Yunfei Zhao , Xuehai Qian

Analyzing textual data is a very challenging task because of the huge volume of data generated daily. Fundamental issues in text analysis include the lack of structure in document datasets, the need for various preprocessing steps %(e.g.,…

数据库 · 计算机科学 2016-12-20 Ciprian-Octavian Truică , Jérôme Darmont , Julien Velcin

Increasing reliance on mobile broadband (MBB) networks for communication, vehicle navigation, healthcare, and other critical purposes calls for improved monitoring and troubleshooting of such networks. While recent advances in monitoring…

网络与互联网体系结构 · 计算机科学 2019-01-23 Veljko Pejovic , Ivan Majhen , Miha Janez , Blaz Zupan

The success of Deep Artificial Neural Networks (DNNs) in many domains created a rich body of research concerned with hardware accelerators for compute-intensive DNN operators. However, implementing such operators efficiently with complex…

分布式、并行与集群计算 · 计算机科学 2021-08-27 Dennis Rieber , Axel Acosta , Holger Fröning

Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…

人工智能 · 计算机科学 2025-08-13 Shuo Cai , Su Lu , Qi Zhou , Kejing Yang , Zhijie Sang , Congkai Xie , Hongxia Yang

Recent advances in deep learning have driven rapid progress in time series forecasting, yet many state-of-the-art models continue to struggle with robust performance in real-world applications, even when they achieve strong results on…

机器学习 · 计算机科学 2025-10-24 Qitai Tan , Yiyun Chen , Mo Li , Ruiwen Gu , Yilin Su , Xiao-Ping Zhang

Hyper-parameters optimization (HPO) is vital for machine learning models. Besides model accuracy, other tuning intentions such as model training time and energy consumption are also worthy of attention from data analytic service providers.…

机器学习 · 计算机科学 2023-04-21 Hui Dou , Shanshan Zhu , Yiwen Zhang , Pengfei Chen , Zibin Zheng

The performance of large language models (LLMs) across diverse downstream applications is fundamentally governed by the quality and composition of their pretraining corpora. Existing domain reweighting algorithms primarily optimize data…

机器学习 · 计算机科学 2025-05-28 Simin Fan , Maria Ios Glarou , Martin Jaggi

While traditional tree-based ensemble methods have long dominated tabular tasks, deep neural networks and emerging foundation models have challenged this primacy, yet no consensus exists on a universally superior paradigm. Existing…

To solve deep metric learning problems and producing feature embeddings, current methodologies will commonly use a triplet model to minimise the relative distance between samples from the same class and maximise the relative distance…

计算机视觉与模式识别 · 计算机科学 2017-07-28 Ben Harwood , Vijay Kumar B G , Gustavo Carneiro , Ian Reid , Tom Drummond

Recent progress in deep research systems has been impressive, but evaluation still lags behind real user needs. Existing benchmarks predominantly assess final reports using fixed rubrics, failing to evaluate the underlying research process.…

‹ 上一页 1 8 9 10 下一页 ›