Papers

Filtered to multimodal learning · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs

57 upvotes · 23 JUL 2026 · Hao Liang, Qihan Lin, Zhaoyang Han et al.

This paper introduces a new framework for training educational language models, specifically designed to evaluate their ability to understand curriculum knowledge and its visual presentation. Practitioners might care about this work because it aims to improve language models' performance in educational settings.

educational language modelscurriculum cognitionknowledge graphsgraph-guided supervised learningmultimodal learningbenchmarking

FlowMimic: Mask-free Visual Editing and Generation with Pixel-pair Warped Flow Field for Online Video Editing Data Generation and Modality Mimicry

31 upvotes · 20 JUL 2026 · Dingyun Zhang, Lixue Gong, Wei Liu

This paper creates a new AI model that can edit and generate videos without needing masks, and can also learn to mimic image editing capabilities. Practitioners might care about this because it could lead to more diverse and realistic video editing data, and enable AI models to understand and generate human-like video editing instructions.

video editinggenerative modelsmultimodal learningimage editingtemporal flow fieldsmodality mimicry

Scaling Native Multimodal Pre-Training From Scratch

21 upvotes · 24 JUL 2026 · Haoyuan Wu, Aoqi Wu, Hai Wang et al.

This paper investigates how to scale large language models to also understand and interact with the physical world by training them on multiple types of data from scratch, allowing them to reason about both text and images. Practitioners might care because this could lead to more robust and versatile AI systems that can handle a wider range of tasks.

transformer-based modelsmultimodal learningscalabilityvision-language modelsmodel sizecomputational budget