Samuel Barbeau, Simon Roy, Giovanni Beltrame, Christian Desrosiers, Nicolas Thome
Joint-Embedding Predictive Architectures (JEPAs) enable agents to plan in latent space by imagining the outcomes of candidate actions, yet task specification remains a bottleneck. Visual targets provide precise local gradients but poor distant guidance, while language is flexible yet limited by noisy cross-modal alignment or dependence on distinct large generative models. We introduce LAGO (Latent Goal Prediction from Language), a hierarchical world model in which a single predictor both forecasts action-conditioned dynamics and grounds language instructions as sequences of intermediate latent subgoals, training both modes with a single regression objective over a shared latent space. At each planning step, LAGO predicts a sequence of latent subgoals from a language instruction and optimizes an action sequence using a soft-minimum alignment cost that rewards subgoal proximity without enforcing a rigid path. Subgoals are repredicted as the agent's state evolves, turning a single long-horizon instruction into a sequence of locally tractable objectives. Across environments spanning navigation and manipulation, LAGO outperforms flat and hierarchical image-goal planners, with the largest gains on long-horizon navigation with curved, hazard-constrained paths, where it more than doubles the success rate of a goal-conditioned behavior cloning policy trained on the same demonstrations. Grounding language in the world model's own latent space also outperforms vision-language reward models, including one that plans with ground-truth dynamics.
Operational Earth observation increasingly calls for answering queries such as ``find the image pairs where a new building appeared.'' This means searching an archive of before-and-after (bi-temporal) satellite image pairs and ranking each pair by how well it matches a natural-language description of the change. The component that performs this match, the fusion module that combines the ``before'' and ``after'' views, must be run at query time across many candidate pairs, so its speed largely sets the cost of every search. We present a controlled comparison of how to build that module. Using one fixed image encoder (a frozen CLIP model) and one training recipe for all variants, we evaluate eight designs drawn from three families: attention, state-space models (Mamba), and learned compression (our Temporal Bottleneck Fusion, TBF). Each design is tested on two benchmarks (LEVIR-CC and Dubai-CC) with ten random seeds, so the reported differences are statistically grounded. We outline three findings: first, a training-free two-stage search (a cheap difference model that shortlists candidates, followed by attention fusion that re-ranks them) matches or exceeds full-fusion recall on LEVIR-CC while cutting query cost $10$-$15\times$, with comparable R@1/R@5 on Dubai-CC; second, the linear-time scan of Mamba, attractive on paper, gives no speed benefit at the patch counts typical of vision transformers ($L{=}196$): the scan is limited by memory bandwidth, whereas attention maps cleanly onto parallel hardware; and third, compressing the fused representation (TBF) reduces parameters by $2.3\times$ and latency by $1.6\times$ for a change-only BLEU-1 cost of $0.007$, although more aggressive compression quietly discards change-relevant detail that aggregate metrics fail to reveal.