5 papers · 1 filter
DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous Driving
Shuzheng Wang, Haoxuan Li, Shengzhen Li +5
Vision-Language Models (VLMs) and world models have demonstrated strong capabilities in semantic understanding and future scene evolution for autonomous driving. However, effective…
MemAct: Streaming Spatial Understanding with Memory and Active Exploration
Yuxi Wei, Wei Huang, Qirui Chen +2
Spatial understanding is essential for embodied agents navigating and interacting with the physical world. As observations arrive incrementally, agents must reason in a streaming m…
See, Remember, Explore: A Benchmark and Baselines for Streaming Spatial Reasoning
Yuxi Wei, Wei Huang, Qirui Chen +2
Spatial understanding is fundamental for embodied agents, yet most spatial VLMs and benchmarks remain offline-evaluating post-hoc QA over pre-recorded inputs and overlooking two cr…
DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving
Shuyao Shang, Bing Zhan, Yunfei Yan +9
We propose DynVLA, a driving VLA model that introduces a new CoT paradigm termed Dynamics CoT. DynVLA forecasts compact world dynamics before action generation, enabling more infor…
InSight-o3: Empowering Multimodal Foundation Models with Generalized Visual Search
Kaican Li, Lewei Yao, Jiannan Wu +7
The ability for AI agents to "think with images" requires a sophisticated blend of reasoning and perception. However, current open multimodal agents still largely fall short on the…