The paper introduces a declarative framework for anticipatory reasoning about interactive motion in dynamic environments. It combines an ASP model of trajectory dynamics, semantically-guided prediction of branching futures, and an energy-based optimization to evaluate and rank anticipations. The approach is evaluated on the Argoverse 2 benchmark, providing explicit, inspectable event-level hypotheses for each anticipated trajectory.
arXiv:2606. 28758v1 Announce Type: cross Abstract: Predicting future states is essential for autonomous agents, yet current Vision-Language-Action (VLA) models fundamentally lack this capability, relying instead on reactive perception-action mapping.
Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only one side of this requirement: Vision-Language-Action (VLA) models exploit VLM priors for semantic reasoning, while World Action Models (WAMs) provide future-aware prediction through generative world modeling.
Conventional visual navigation policies often struggle with myopic decision-making and mode collapse in complex environments. While world models offer a promising alternative, existing paradigms typically isolate perception, generation, and control, failing to capture their shared spatio-temporal dynamics.
arXiv:2607. 08375v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving.
The paper introduces IG‑VLA, a vision‑language‑action framework that learns to imagine task‑relevant future scene evolution in a latent spatiotemporal space, guiding action prediction without generating full pixel‑level videos. It further compresses this future reasoning into a compact Scene Gist Token via Scene Gist Memory, enabling efficient inference. Experiments on LIBERO, LIBERO‑Plus, and VLABench show that IG‑VLA improves success rates by nearly 6% and speeds up inference up to 6.38× compared to strong baselines.
arXiv:2606. 01810v1 Announce Type: new Abstract: Current benchmarks for embodied vision-language planning often favor linguistic next-token prediction over physically grounded next-state reasoning.
The paper proposes an event‑aligned visual action reasoning framework for World‑Action Models (WAMs), aligning visual prediction with task‑relevant interaction events rather than fixed temporal intervals. By supervising visual‑action prediction around these events, the model focuses on critical state changes and reduces redundant actions through an execution validity head. Experiments show a 10.26‑point improvement in DOMINO success rate and strong transfer to higher DOMINO levels without adaptation.
arXiv:2607. 03182v1 Announce Type: cross Abstract: Autonomous driving planning requires translating navigation intent, traffic rules, dynamic interactions, and language instructions into executable continuous trajectories.
arXiv:2608. 12854v1 Announce Type: cross Abstract: Autonomous driving requires planning under both semantic constraints and predictive dynamics.
arXiv:2605.10426v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing reasoning mecha...
arXiv:2601. 18537v4 Announce Type: replace-cross Abstract: Accurate long-horizon vessel trajectory prediction remains challenging due to compounded uncertainty from complex navigation behaviors and environmental factors.
The paper argues that current embodied vision‑language planning benchmarks favor linguistic next‑token prediction over physically grounded next‑state reasoning, leading models to rely on language priors rather than true causal dependencies. To address this, the authors introduce Causal‑Plan‑Bench, a diagnostic suite covering four causal dimensions, and Causal‑Plan‑1M, a million‑scale corpus of explicit causal reasoning traces extracted from egocentric videos. Extensive experiments show that existing models perform poorly on these tasks, while a new model trained with a tailored recipe—Causal Planner based on Qwen3‑VL‑8B—achieves significant gains, demonstrating the feasibility of physically grounded causal reasoning.