Papers

Filtered to multimodal learning · clear filter

Browse by term

continual learning 83reinforcement learning 50large language models 12benchmarking 11benchmarks 11language models 11vision-language models 11robotics 7natural language processing 6world models 6generative models 5recursive self-improvement 5attention mechanisms 4diffusion Transformers 4multi-agent systems 4multimodal learning 4multimodal models 4on-policy distillation 4self-distillation 4self-supervised learning 4transformers 4video generation 4vision-language-action models 4agent-based systems 3agentic models 3agentic search 3autonomous systems 3coding agents 3diffusion models 3image generation 3

Matching papers

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

172 upvotes · 14 SEP 2026 · DeepCybo Team, Yu Bin, Haipeng Cao et al.

This paper develops a unified model that can understand physical environments, generate actions, and predict future states, using a combination of vision, language, and embodied interactions. Practitioners may care about this model because it could be used to create robots or other agents that can interact with and adapt to their physical surroundings.

vision-language modelsphysical foundation modelsembodied AImultimodal learningrobotics

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

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

55 upvotes · 27 AUG 2026 · Senqiao Yang, Chengyao Wang, Yuxin Chen et al.

This paper proposes a new approach to training Vision-Language-Action models by using a pre-trained backbone that captures generalizable visual-action knowledge from a large, diverse dataset of robot trajectories. This allows the model to perform well on new, unseen tasks without requiring a large amount of task-specific data.

vision-language-action modelscontinual learningrepresentation learningrobot learningmultimodal learning

Intern-S2-Preview: Scientific Agentic Foundation Model

50 upvotes · 13 AUG 2026 · Lei Bai, Jiaqi Cao, Chiyu Chen et al.

This paper introduces Intern-S2-Preview, a type of AI model designed to support scientific discovery by reasoning over different types of evidence, interacting with scientific tools, and sustaining progress over long periods. Practitioners might care because it could lead to more accurate scientific understanding and forecasting.

scientific agentic foundation modelsmultimodal learningscientific reasoningreinforcement learningnumerical forecasting