Tag: Multimodal Data

All the articles with the tag "Multimodal Data".

• Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders

  Published: 10 May, 2025 |  at  10:58 AM

  

  61.78 🤔

  This paper uses Sparse Autoencoders to identify and manipulate language-specific features in Large Language Models, introducing a monolinguality metric, demonstrating context dependency via code-switching, and enhancing steering vectors for better control over multilingual generation while revealing significant language-specific impacts through ablation studies.

• Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision

  Published: 4 May, 2025 |  at  04:27 PM

  

  59.70 🤔

  本文提出Instruct-LF方法，通过结合LLMs的指令遵循能力和梯度-based统计模型，实现无需任务监督的目标导向潜在因素发现，提高了下游任务性能并在人工评估中被偏好。

• PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning

  Published: 4 May, 2025 |  at  04:28 PM

  

  53.32 🤔

  本文提出PointLoRA方法，通过低秩适配和多尺度令牌选择，实现点云模型的参数高效微调，显著减少可训练参数同时在多个数据集上达到竞争性性能。

• Survey of Abstract Meaning Representation: Then, Now, Future

  Published: 8 May, 2025 |  at  12:18 AM

  

  95.51 😐

  本文综述了抽象意义表示（AMR）作为一种图结构语义表示框架的发展、解析与生成方法、多语言扩展及下游应用，揭示其在提升机器语言理解中的潜力与局限。

• Style Feature Extraction Using Contrastive Conditioned Variational Autoencoders with Mutual Information Constraints

  Published: 8 May, 2025 |  at  10:25 AM

  

  93.98 😐

  This paper proposes a novel method combining contrastive learning with conditional variational autoencoders and mutual information constraints to extract style features from unlabeled data, demonstrating effectiveness on simple datasets like MNIST while facing challenges with natural image datasets due to augmentation limitations and qualitative evaluation.