arXiv Machine Learning
Jun 25
Conformal Orbit-Valid Trust Horizons for Equivariant World Models
arXiv:2606. 24946v1 Announce Type: new Abstract: Learned world models are useful only over horizons on which their rollout error remains controlled.
Certified World Models: Predictability Across Configuration, Horizon, and Resolution
arXiv:2606. 13092v3 Announce Type: replace Abstract: Scale buys interpolation; structure buys certifiable transfer.
Related stories
arXiv Machine Learning
Jun 25
When Do Conservation Laws Survive Learned Representations? Certified Horizons for Latent World Models
arXiv:2606. 24945v1 Announce Type: new Abstract: We ask a representation-learning question about physical world models: when does a conservation law remain certifiable after a model learns a latent representation?
arXiv AI
Jun 3
Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group
arXiv:2606. 03003v1 Announce Type: cross Abstract: A latent world model built from an equivariant encoder $E$ and an equivariant predictor $f$ inherits a provable symmetry of its training loss: when the world's dynamics genuinely carries a group $G$ acting on latents by an orthogonal representation $\rho(g)$, the one-step prediction relMSE is exactly invariant across the whole group, so fitting the dynamics on a restricted slice of orientations mathematically determines it on the entire orbit (j\v{u} y\=i f\v{a}n s\=an).
arXiv Machine Learning
Aug 12
Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability
arXiv:2608. 10172v1 Announce Type: new Abstract: Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or an artifact of the method that found it.
arXiv Machine Learning
Jul 14
A Control Theory of Predictability in Latent World Models
arXiv:2607. 10362v1 Announce Type: new Abstract: Latent world models are trained to predict future states in a learned representation and are then deployed inside a planner that selects actions by simulating them forward.
arXiv Machine Learning
Jul 7
Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal Consistency
arXiv:2606. 12471v2 Announce Type: replace-cross Abstract: Klindt, LeCun, and Balestriero (arXiv:2605.
arXiv Machine Learning
Jul 3
Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perception
arXiv:2607. 01537v1 Announce Type: new Abstract: Certified world models estimate how long their predictions remain valid.
arXiv Machine Learning
Jul 7
Asymptotic-Preserving A Posteriori Analysis of Diffusion and Flow-Matching Samplers
arXiv:2607. 04113v1 Announce Type: new Abstract: Diffusion and flow-matching samplers integrate a learned probability-flow ODE from a large noise scale down to a small terminal floor $\sigma_{\min}$, at which the score is stiff and the flow develops a boundary layer.
arXiv Machine Learning
Jul 27
Multi-Horizon Consistency as Geometry: When Latent Dynamics Contract, and When They Do Not
arXiv:2607. 21645v1 Announce Type: new Abstract: Multi-horizon latent consistency is a common training knob in video predictors and world models, but practitioners rarely know what it does to transition geometry.
Hugging Face Trending Papers
Jul 5
Asymptotic-Preserving A Posteriori Analysis of Diffusion and Flow-Matching Samplers
Diffusion and flow-matching samplers integrate a learned probability-flow ODE from a large noise scale down to a small terminal floor $σ_{\min}$, at which the score is stiff and the flow develops a boundary layer. We treat $σ_{\min}$ as a singular-perturbation parameter and determine which fixed-step samplers are asymptotic-preserving (AP), that is, stable and uniformly accurate as $σ_{\min}\to0$, casting the criteria as an a posteriori audit: residual functionals with $σ_{\min}$-uniform coefficients, computable on a pretrained checkpoint without ground-truth scores or exact trajectories.
arXiv Machine Learning
Jul 7
Reduced-Order Models: The Mother of World Models
arXiv:2607. 03198v1 Announce Type: new Abstract: World models -- compressed latent representations of an environment that support action-conditioned prediction and planning -- are typically presented as a product of modern self-supervised learning.
arXiv AI
Jul 17
When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models
arXiv:2607. 14169v1 Announce Type: new Abstract: Large language models can synthesize a game's rules as executable code - a Code World Model (CWM) - which a classical planner then searches over.