✗ Failed on benchmark
2026
Train a neural state-space model using all replayed transitions, but assign larger weights to samples near the current operating context rather than discarding distant samples. Add a strictly positive weight floor so local adaptation cannot eliminate global coverage or make the regression problem rank-deficient. This should improve prediction across nonlinear regimes while retaining the numerical robustness of full-data training.
Useful7/10
Difficulty4/10
Novelty5/10
△ Mechanism confirmed, baseline not beaten
2026
Equip a neural policy or learned world model with an MPPI-style rollout planner whose perturbation covariance is conditioned on a discretized latent-state cell and updated from observed transition residuals. Apply spatial diffusion to neighboring covariance estimates using a kernel matched to the empirical visitation distribution, so covariance adaptation is smoothing rather than an unstable independent estimate at every state.
Useful7/10
Difficulty6/10
Novelty7/10
✗ Failed on benchmark
2026
Construct a finite-range, translation-equivariant recurrent convolutional module with an absorbing inactive state, then train its local dynamics so that seeded activity crosses coarse-grained space-time blocks with probability above an oriented-percolation threshold. This should produce reliable long-range propagation without dense global attention while remaining robust to non-monotone local updates and perturbations. Block statistics also provide a diagnostic for vanishing propagation or…
Useful7/10
Difficulty5/10
Novelty8/10
✗ Mechanism failed
2026
Replace the unconstrained transition of a recurrent or state-space neural network with a DMDc-initialized linear latent transition plus a learned nonlinear residual. Estimate the transition from a short warm-up dataset using Hankel delay coordinates, retain eigenmodes with decay rates near the unit circle for long-term memory, and let the neural residual model dynamics not explained by the linear backbone. This should make long-horizon prediction and slowly varying signals easier to learn while…
Useful7/10
Difficulty5/10
Novelty6/10
△ Mechanism confirmed, baseline not beaten
2026
Make a diffusion policy or MPPI-style action-sequence sampler less committed to model-predicted cost rankings when the learned world model is inaccurate. Estimate a normalized prediction residual or ensemble disagreement, increase the sampling temperature with that residual, and retain ordinary low-temperature exploitation when the model is accurate.
Useful7/10
Difficulty4/10
Novelty6/10
△ Mechanism confirmed, baseline not beaten
2026
Separate a pretrained sequence model's passive prediction from the causal effect of an action, and learn only the latter with a compact monotone adapter. The adapter receives the current latent state and an action deviation, but its action-to-output Jacobian is constrained to have the physically correct sign, preventing intervention predictions that move opposite to the applied control.
Useful7/10
Difficulty4/10
Novelty7/10
△ Mechanism confirmed, baseline not beaten
2026
Attach a finite-state monitor to a neural policy and allow only actions whose successor remains in the simultaneous backward-reachable winning set for all active modes. Modes may encode safety, hardware configuration, and independent task goals. This gives a hard runtime constraint rather than relying on a reward penalty to teach the policy not to enter irreversible dead ends.
Useful7/10
Difficulty4/10
Novelty7/10
△ Mechanism confirmed, baseline not beaten
2026
Replace an unconstrained recurrent or neural-ODE vector field with a Lie-algebra-valued connection depending on time, input position, and an auxiliary spectral parameter. Train the model both for prediction and for approximate zero curvature, so evolution along different discretized paths is compatible rather than accumulating arbitrary noncommutative drift.
Useful7/10
Difficulty6/10
Novelty7/10
△ Mechanism confirmed, baseline not beaten
2026
Train an encoder and decoder whose latent observables evolve through one shared linear Koopman matrix, while directly penalizing the empirical invariance residual of the learned observable subspace. This discourages latent coordinates that fit one-step transitions but continually leave the representational subspace, improving long-horizon rollout stability.
Useful7/10
Difficulty5/10
Novelty6/10
△ Mechanism confirmed, baseline not beaten
2026
Add a safety projection step to every or selected Euler updates of a flow-matching action sampler. Instead of correcting only the first action, differentiate a collision-risk function through the predicted full action chunk, construct local linear inequality constraints, and apply the smallest correction that makes the future trajectory safe.
Useful7/10
Difficulty5/10
Novelty5/10
✗ Failed on benchmark
2026
Attach a sampling-based rollout correction head to a neural policy or learned world model, and adapt its temperature and number of rollouts so that approximation error stays within the contraction margin of a nominal policy. The controller should spend samples only when the local state-dependent error gain is close to violating the small-gain condition, instead of using a fixed MPPI sample count everywhere.
Useful7/10
Difficulty6/10
Novelty7/10
✗ Failed on benchmark
2026
Replace dense coarse-to-fine cross-attention at multiresolution interfaces with a sparse, nonnegative overlap operator whose weighted feature average is exactly conserved between the two resolutions. Use this operator as a low-order path and blend it with an unrestricted neural cross-attention path through a convex limiter that keeps features inside a box or simplex domain. The construction is especially suitable for adaptive token grids, hierarchical graph neural networks, neural operators…
Useful7/10
Difficulty5/10
Novelty8/10
△ Mechanism confirmed, baseline not beaten
2026
Replace a dense multiresolution voxel or hash-grid encoder with an omnitree-like anisotropic feature partition. Each cell stores a vector-valued scaling feature and its children are introduced only when local Haar detail energy is large; coarsening replaces children by their mean, so compression does not introduce an arbitrary offset. Splitting can be restricted to the coordinate whose one-dimensional detail coefficient is largest, allowing thin structures to receive resolution only in the…
Useful7/10
Difficulty5/10
Novelty7/10
✗ Failed on benchmark
2026
Use the paper's parameterized invariant-torus residual and pseudo-arclength Newton correction to train a neural ODE across a continuous family of latent dynamical regimes. The continuation constraint allows the solver to pass through saddle-node folds, where stepping a physical control parameter alone would fail or jump to a different branch.
Useful7/10
Difficulty7/10
Novelty8/10
✓✓ Beats tuned baseline
2026
Replace an unconstrained one-step transition network with a symmetric damping–symplectic-core–damping composition. The damping strength is one learned scalar rate and is applied through positive exponential diagonal factors, so every step has a known contraction law while the neural core models nonlinear conservative transport.
Useful7/10
Difficulty5/10
Novelty7/10
△ Mechanism confirmed, baseline not beaten
2026
Add conformal prediction sets for every action of a contextual policy, then select the action maximizing its worst-case utility over the corresponding set. Calibrate the sets using the outcome generated by this same max-min policy, rather than calibrating each action independently; this directly targets reliable utility under deployment decisions.
Useful7/10
Difficulty5/10
Novelty7/10
△ Mechanism confirmed, baseline not beaten
2026
Use a maximal-volume cross approximation of the parameter-by-space transport-signature matrix to select informative training conditions and compact spatial features. This provides an active-learning alternative to random snapshot selection or ordinary PCA, targeting parameters that are difficult to interpolate from the current reduced representation.
Useful7/10
Difficulty5/10
Novelty7/10
✗ Mechanism failed
2026
Add a deterministic complex-valued state-space bank whose mode detunings become progressively smaller with mode index, Delta_n=c n^{-p}, while input couplings decay as B_n=b n^{-kappa}. For slowly varying or constant forcing, the summed state follows the paper's subresonant response and grows like t^{1-alpha}, providing controllable power-law memory with only O(N) recurrent state updates. This should improve long-context retention compared with a same-size unconstrained RNN or uniformly spaced…
Useful7/10
Difficulty5/10
Novelty7/10
✓ Mechanism works
2026
Replace orthogonal Procrustes alignment between two latent dynamical systems with a learned bijection h that makes their transitions commute: h(f(z)) approximately equals g(h(z)). Parameterize h as an invertible affine map or coupling flow, allowing the correspondence to be non-orthogonal while retaining an exact inverse. The same constraint can be applied over multiple rollout steps, encouraging two models to represent the same computation even when their latent coordinates differ…
Useful7/10
Difficulty5/10
Novelty6/10
✓✓ Beats tuned baseline
2026
Train a neural controller as a uniformly accurate surrogate of a trusted but expensive controller, and use a measured small-gain condition to decide whether the surrogate is safe for closed-loop deployment. The approximation tolerance becomes an interpretable residual-state budget instead of an opaque validation metric.
Useful7/10
Difficulty5/10
Novelty7/10
✗ Failed on benchmark
2026
Add a latent mode bank whose coordinates are learned by neural power iteration on observed state transitions rather than by jointly fitting an unconstrained latent dynamics model. Each mode is repeatedly regressed toward its one-step pushforward, normalized under the data distribution, and deflated against previously learned modes. The resulting latent coordinates are constrained to have approximately linear, diagonal dynamics, which should improve long-horizon prediction and make the…
Useful7/10
Difficulty5/10
Novelty7/10
△ Mechanism confirmed, baseline not beaten
2026
Represent a predicted convex object by one point per prescribed unit direction and decode it as the convex hull of those points. Enforce direction-wise maximizer inequalities so every point is a genuine vertex, then use the covering-radius bound to choose the number and placement of directions according to the desired geometric accuracy.
Useful7/10
Difficulty5/10
Novelty7/10
✗ Mechanism failed
2026
Train a network to predict the context-dependent observation matrix rather than the latent inverse parameters themselves, then compute the latent parameters with a differentiable ridge-regression solve. This gives one model that can assimilate arbitrary observation vectors, exposes the conditioning of the inverse problem, and avoids forcing an MLP to learn the entire map from observations to parameters.
Useful7/10
Difficulty5/10
Novelty7/10
Audited (legacy)
2026
Replace independent per-action distributional value heads with a critic whose shared latent particle produces a vector of return samples for all actions simultaneously. Train the predicted joint return vector against a Bellman target vector formed from coupled counterfactual reward-transition samples, using a sliced Wasserstein loss. The greedy action is selected by the mean of the corresponding marginal particles, while shared particles retain cross-action dependence for learning and…
Useful7/10
Difficulty6/10
Novelty7/10