Tag: Multimodal Data

All the articles with the tag "Multimodal Data".

• PICD: Versatile Perceptual Image Compression with Diffusion Rendering

  Published: 15 May, 2025 |  at  11:10 AM

  

  95.81 🤔

  PICD introduces a versatile perceptual image compression codec using diffusion rendering with three-tiered conditioning to achieve high text accuracy and visual quality for both screen and natural images, outperforming existing methods in key metrics like FID and text accuracy.

• VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation

  Published: 16 May, 2025 |  at  11:10 AM

  

  94.40 🤔

  This paper introduces VideoUFO, a million-scale dataset of 1.09 million video clips across 1,291 user-focused topics for text-to-video generation, curated from YouTube with minimal overlap with existing datasets, demonstrating improved performance on worst-performing topics when training a simple model like MVDiT.

• Gameplay Highlights Generation

  Published: 14 May, 2025 |  at  11:06 AM

  

  92.19 🤔

  This paper presents a method to generate gameplay highlight reels by finetuning the X-CLIP multimodal model on an in-house FPS game dataset, achieving over 90% event detection accuracy and demonstrating transfer learning, while optimizing deployment through quantization.

• The Effect of Language Diversity When Fine-Tuning Large Language Models for Translation

  Published: 26 May, 2025 |  at  11:23 AM

  

  88.75 🤔

  本文通过系统性实验证明，在大型语言模型微调中增加语言多样性可显著提升所有类别翻译对的性能，并通过中层表征分析揭示跨语言迁移机制，但多样性收益存在阈值。

• Scaling Reasoning can Improve Factuality in Large Language Models

  Published: 20 May, 2025 |  at  11:09 AM

  

  87.44 🤔

  本文通过从先进模型中提取并用知识图谱增强推理轨迹，微调Qwen2.5系列模型，并在复杂开放域问答任务中验证了测试时计算扩展（并行采样和预算强制）可提升事实准确性2-8%，尤其对小型模型效果显著。