Papers

Filtered to scene exploration · clear filter

Browse by term

continual learning 91reinforcement learning 43vision-language models 18benchmarking 12benchmarks 11robotics 11large language models 10language models 9world models 9video generation 6generative models 5multimodal models 5natural language processing 5recursive self-improvement 5video world models 5agents 4dialogue systems 4diffusion models 4foundation models 4multimodal large language models 4on-policy distillation 4reasoning 4self-distillation 4self-supervised learning 4conversational AI 3evaluation benchmarks 3human-computer interaction 3LLMs 3multi-agent systems 3policy optimization 3

Matching papers

SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

128 upvotes · 19 OCT 2026 · Zhaoxi Zhang, Hao Liang, Linxuan Wu et al.

This paper introduces a benchmark, SpatialScout, to evaluate vision-language model (VLM) agents on active 3D mapping, where agents must explore and map 3D scenes to construct accurate metric maps. Practitioners in AI and robotics might care about this research because it aims to develop agents that can build reliable 3D spatial representations through active perception.

vision-language models3D mappingactive perceptionscene explorationobject localization

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

111 upvotes · 21 SEP 2026 · Wangbo Yu, Kunhao Liu, Wenbo Hu et al.

This paper introduces WorldCrafter, a video world model that learns to remember past observations and use them to generate consistent and accurate video representations, even when exploring dynamic environments from different viewpoints. Practitioners might care about this work because it can improve the reliability and effectiveness of interactive exploration applications, such as virtual reality or autonomous robots.

implicit 3D-aware memoryvideo world modelsfew-shot learningcamera-controlscene exploration