Papers

Filtered to automated data construction · clear filter

Browse by term

continual learning 89reinforcement learning 42vision-language models 20benchmarks 13benchmarking 12robotics 12large language models 10language models 9world models 9video generation 7multimodal models 5recursive self-improvement 5video world models 5agentic models 4agents 4diffusion models 4foundation models 4generative models 4human-computer interaction 4multimodal large language models 4natural language processing 4policy optimization 4reasoning 4self-supervised learning 4spatial reasoning 4conversational AI 3dialogue systems 3embodied AI 3evaluation benchmarks 3LLMs 3

Matching papers

Holi-World: Building Holistic World Intelligence from Human-Ego Experience

104 upvotes · 19 OCT 2026 · Hao Li, Xiyuan Zheng, Yuanyuan Gao et al.

This paper develops a system to turn human experience into a learning resource for AI, enabling machines to better understand the world and its changes, which could improve self-driving cars, robots, and other applications that rely on human-like perception.