This work converts observed trajectories and interaction cues into parsable textual prompts, so that interaction semantics are expressed more explicitly in the model input and remains competitive with recent LM-based prediction methods and strong trajectory prediction base-lines on ADE/FDE.
JEPA-WAM, a latent WAM built in a pretrained V-JEPA space, which couples latent transition prediction with continuous action generation through a shared predictor, predicts a spatially structured joint current-future target that captures task-shared visual temporal structure between current and future observations, while preserving dense patch-level correspondence.
Yihan Lin, Jiawei He, Shifeng Bao et al.· 2 citations
SimWAM, a simple yet effective WAM that leverages future-video prediction as a training-time supervision signal, co-trains a pretrained video expert and a lightweight action expert with joint flow matching and applies reinforcement learning to optimize a compositional driving reward beyond trajectory imitation.
Trajectory prediction is essential for many robotic applications, yet most existing models rely on fixed-length observations and struggle with temporally irregular inputs. In real-world settings, prediction difficulty further increases when agents exhibit strong maneuverability, as their future motions depend on distinct short-term and long-term temporal cues. A Maneuver-aware Temporal Fusion framework is proposed to separate short-term dynamics from long-term intentions and fuse them through a motion-complexity-guided attention mechanism. The framework first extracts temporal features at different scales, and then adaptively balances them according to the maneuver patterns of each agent. To support incomplete or short observations, a self-distillation strategy is introduced to reconstruct missing motion segments, enabling consistent prediction without relying on explicit teacher-student models. Furthermore, a Mamba-Transformer hybrid backbone is employed to enhance computational efficiency and improve generalization under arbitrary observation lengths. Experiments on the ETH/UCY and SDD datasets show that MaTF consistently outperforms existing methods, particularly in scenarios with irregular or shortened observations.
Shuobo Wang, Wenyuan Qin, Yong-Zhao Hua et al.· IEEE Robotics and Automation...· 0 citations
Latent-OPD is proposed, which augments OPD with trajectory-level latent distillation and introduces a progressive teacher-lookahead strategy, which aligns middle-to-late student layers with increasingly deeper teacher layers, establishing Latent-OPD as a highly effective approach to frame-efficient video reasoning.
Aoni Shen, Yongheng Zhang, Yinghui Li et al.· 1 citation
This work proposes a novel test-time alignment approach that leverages trajectory-guided structured sampling for dynamic inference-time refinement, achieving better alignment with visual grounding and ensuring logical consistency, and demonstrates that this approach significantly improves accuracy without incurring prohibitive inference overhead.
Tianbao Jiang, Weicong Ni, Gerard de Melo et al.· 0 citations
