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

Universal domain adaptation aims to align the classes and reduce the feature gap between the same category of the source and target domains. The target private category is set as the unknown class during the adaptation process, as it is not…

Recent advancements in Machine Unlearning (MU) have introduced solutions to selectively remove certain training samples, such as those with outdated or sensitive information, from trained models. Despite these advancements, evaluation of MU…

Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements,…

The evaluation of code-generating Large Language Models (LLMs) is fundamentally constrained by two intertwined challenges: a reliance on static, easily contaminated problem sources and the use of superficial, low-rigor testing. This paper…

This paper introduces MiniCPM4, a highly efficient large language model (LLM) designed explicitly for end-side devices. We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data,…

Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute. However, as frameworks specialize performance optimization to patterns in popular networks, they…

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…

Evaluating models on datasets often fails to capture their behavior when faced with unexpected and diverse types of inputs. It would be beneficial if we could evaluate the difference between human annotation and model prediction for an…

Document understanding is a key business process in the data-driven economy since documents are central to knowledge discovery and business insights. Converting documents into a machine-processable format is a particular challenge here due…

Language models (LMs) exhibit impressive performance and generalization capabilities. However, LMs struggle with the persistent challenge of catastrophic forgetting, which undermines their long-term sustainability in continual learning…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

Many analysis and prediction tasks require the extraction of structured data from unstructured texts. However, an annotation scheme and a training dataset have not been available for training machine learning models to mine structured data…

Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce BeyondBench, an evaluation framework using algorithmic…

Modern frameworks for training large foundation models (LFMs) employ dataloaders in a data-parallel manner, with each loader processing a disjoint subset of training data. When preparing data for LFM training that originates from multiple,…

Multi-task indoor scene understanding is widely considered as an intriguing formulation, as the affinity of different tasks may lead to improved performance. In this paper, we tackle the new problem of joint semantic, affordance and…

Existing ML benchmarks lack the depth and diversity of annotations needed for evaluating models on business process management (BPM) tasks. BPM is the practice of documenting, measuring, improving, and automating enterprise workflows.…

Most enterprise document AI today is a pipeline. Parse, index, retrieve, generate. Each of those stages has been studied to death on its own -- what's still hard is evaluating the system as a whole. We built EnterpriseDocBench to take a…

Reading order detection is the foundation of document understanding. Most existing methods rely on uniform supervision, implicitly assuming a constant difficulty distribution across layout regions. In this work, we challenge this assumption…

Data efficiency, despite being an attractive characteristic, is often challenging to measure and optimize for in task-oriented semantic parsing; unlike exact match, it can require both model- and domain-specific setups, which have,…

Geometric data pruning methods, while practical for leveraging pretrained models, are fundamentally unstable. Their reliance on extrinsic geometry renders them highly sensitive to latent space perturbations, causing performance to degrade…