7 papers
SenseSwarm: Swarm Exploration via Neural Structure Estimation with Shared World-Anticipation for Rapid Mapping
Haohua Que, Haojia Gao, Mingkai Liu +7
A robot swarm covers a building faster with more robots, but the map is only as complete as the space the robots have physically visited. We target the amount of an unknown buildin…
EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action
Hao Wang, Jiajun Wen, Jingzhi Liu +21
Vision-language-action (VLA) policies emphasize semantic understanding, whereas world-action models (WAMs) learn predictive representations of environment dynamics. Systems that ex…
Retrieve in Time, Correct in Frequency
Yuze Fan, Yue Cao, Pengjie Gao +7
Frozen vision-language-action (VLA) policies generate temporally extended action chunks, but long-horizon manipulation remains vulnerable to accumulated execution error and visual…
HERA: Historical Evidence Routing Adapter for Physical Prediction in Latent World Models
Yuanruyi, Yue Cao, Haojia Gao +7
Predictive video models have emerged as promising world models by learning latent visual dynamics from large-scale video. Yet these models remain challenged by physical events unde…
RADAR: Revealing Asymmetric Development of Abilities in MLLM Pre-training
Yunshuang Nie, Bingqian Lin, Minzhe Niu +7
Pre-trained Multi-modal Large Language Models (MLLMs) provide a knowledge-rich foundation for post-training by leveraging their inherent perception and reasoning capabilities to so…
PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly
Liang Ma, Jiajun Wen, Min Lin +12
While vision-language models (VLMs) have demonstrated promising capabilities in reasoning and planning for embodied agents, their ability to comprehend physical phenomena, particul…
EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning
Bingqian Lin, Yunshuang Nie, Khun Loun Zai +10
Recent studies have revealed the potential of training open-source Large Language Models (LLMs) to unleash LLMs' reasoning ability for enhancing vision-language navigation (VLN) pe…