Rollout-Decoded Reconstruction (RDR) closes this gap with a single loss term that free-runs the model during training exactly as evaluation will, decodes every rollout latent, and penalizes reconstruction error against ground truth.
Abstract
A latent world model trains its decoder on latents anchored to observations, then deploys it on the model's own free-running rollout, hundreds of steps past the last observation. Rollout-Decoded Reconstruction (RDR) closes this gap with a single loss term that free-runs the model during training exactly as evaluation will, decodes every rollout latent, and penalizes reconstruction error against ground truth. The term adds no parameters, costs training-time compute only, and reduces to the standard objective at weight zero, so every comparison in this paper is a one-flag A/B. On the chaotic Kuramoto-Sivashinsky equation, RDR raises valid prediction time (the time to first crossing of normalized error 0.5) from $3.87 \pm 0.23$ to $6.97 \pm 0.42$ time units at an identical 193,568 parameters, a $1.80\times$ improvement confirmed on seeds never used in selection and holding in 10 of 10 preregistered configurations at ratios of 1.71-2.50$\times$. The results come from a single system; a sweep in which the advantage grows with latent width is descriptive, and control experiments on two classic tasks are preliminary.
We introduce TinyCast, an attention-free zero-shot forecaster that emits a predictive distribution from 146,505 parameters, on the premise that at this size the periodic structure of a context is worth computing rather than learning. A zero-parameter spectral detector supplies the dominant periods, the context is folded on their phase, and a dilated convolutional encoder and a block-autoregressive quantile decoder model the rest. It is smaller than every zero-shot entry on the GIFT-Eval board whose parameter count can be established. On probabilistic accuracy it defines the size-accuracy frontier. Among zero-shot entries declaring no test-data leakage it is the only one below 1.4M parameters that emits a predictive distribution, and every entry scoring better carries at least that budget. On Chronos-ZS and fev-bench every neural model ahead of it carries at least 28 times its parameters. Because the mixing path is convolutions and matrix multiplications only, it exports to static INT8 and forecasts end to end on an embedded device without per-signal fitting.
Noise-Contrastive GRPO is introduced, which injects scale-calibrated Gaussian noise into the last hidden layer of the prompt-encoding pass for half of each rollout group, branching those rollouts from a displaced departure state and integrates into a standard RLVR pipeline as a ~50-line change to the inference engine.
Michael M. Jerge, Joseph Pelczar, J. Downes· 0 citations
The Direct Prediction World Model is introduced, a non-recursive architecture that compresses an action sequence of arbitrary length into a single embedding and predicts the endpoint observation in a single forward pass, making long-horizon end-to-end training practical at horizons where unrolled autoregressive training becomes unstable.
Xinyi Li, Zaishuo Xia, Chenjie Hao et al.· 0 citations
Results suggest that geometric regularization of a recurrent bottleneck can act as a useful training-time prior without adding any inference overhead to the inference-time architecture.
Arpan Ghosh, Jin-Ho Kim, Ye-Chan An et al.· Electronics· 0 citations
Adaptive compute for world models -- early-exit or mixture-of-depths predictors that spend variable depth per rollout step -- presumes that extra depth buys better predictions. In autoregressive rollouts, where planning actually happens, that premise requires depth's per-step precision to survive composition. We test it directly with one pre-registered instrument, the shallow penalty rho = err(shallowest-exit rollout)/err(full-depth rollout), on nine DeepMind Control tasks under matched single-step (K=1) and multi-step (K=4) training, eight seeds each. Three regimes emerge: depth helps (intrinsic, 6/9 tasks, rho up to 8x), depth actively hurts (inversion, 2/9, rho down to 0.87x), or depth barely matters (flat). The inversion is created by training, not the dynamics: supervising early exits only at the first rollout step erases it (Delta=+0.28, n=8, non-overlapping distributions) -- a routability catch-22: the per-step deep supervision that makes exits routable also trains them to out-roll the full stack. The regime is predictable: a frozen dimensionality-only classifier, committed before training, labels held-out tasks correctly out-of-sample, including an extreme extrapolation. The inversion reproduces under a transformer predictor, yet its manifestation is configuration-dependent, shifting with metric space, horizon, encoder, backbone, and -- most strongly -- training data: on the two tasks we retrained, competent-policy data removes both the inversion and the intrinsic tradeoff, loss unchanged. In a CEM planner, rho predicts whether planning benefits from depth. Every threshold and gate was committed before the corresponding compute, including a pre-registered negative for the motivating hypothesis. Whether more compute helps a world model is not a task property; it is a property of the operating configuration, with a stable, predictable, mechanism-backed core.
Recurrent-depth reasoners aim to solve harder problems by iterating their update longer at test time, but additional iterations can improve, preserve, or degrade an answer. We show that a measurable property of the trained operator, its finite-time dynamical regime (estimated as settling, marginal, or drifting), indicates which of these occurs. We give a sufficient condition for depth-safety: once an operator's per-step displacement is small relative to the decoder margin, the decoded answer cannot change under further iterations. Empirically, on algorithmic tasks trained from $800$ unaugmented examples per difficulty tier, settling operators do not degrade with added depth, and on some tasks convert it into higher accuracy on harder unseen instances (Sudoku, $0.19$ to $0.34$ past the training horizon). A single terminal fixed-point objective moves the regime and the depth behavior together: removing it induces drift and removes the gains, and adding it to a generic recurrence yields depth-safe extrapolation on carry propagation. We give four operational criteria for useful test-time depth, use them to catalogue failure modes, and, as a consistency check, apply the same measurements to Huginn-3.5B, which falls in the non-settling family.
Ivan Viakhirev, Kirill Borodin, Amirah Almutairi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
