4 papers
TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction
Lei Jin, Yiding Ma, Xin Zhang +3
World Action Models (WAMs) combine future-state prediction with robot action generation, but existing approaches largely rely on visual futures. Visual prediction captures scene st…
OracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking
Yiding Ma, Chengyun Ruan, Kaibo Huang +3
Forecasting is a composite capability encompassing information gathering, evidence integration, situational assessment, and decision-making. Large language models (LLMs) combine re…
WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
Yu Shang, Zhuohang Li, Yiding Ma +18
While world models have emerged as a cornerstone of embodied intelligence by enabling agents to reason about environmental dynamics through action-conditioned prediction, their eva…
LongScape: Advancing Long-Horizon Embodied World Models with Context-Aware MoE
Yu Shang, Lei Jin, Yiding Ma +4
Video-based world models hold significant potential for generating high-quality embodied manipulation data. However, current video generation methods struggle to achieve stable lon…