arXiv Machine Learning
Jul 21
When Can Safe Controllers Adapt? Information before Commitment
arXiv:2607. 16895v1 Announce Type: new Abstract: Safe adaptive control is online adaptation under a safety guarantee on the learning trajectory itself.
Revocable Learned State via Process Sidecars
arXiv:2606. 30788v1 Announce Type: new Abstract: Language models are often adapted in stages: a public skill phase, a private memory phase, and a later safety phase that learns to refuse outputs tied to the remembered entities.
Related stories
arXiv Machine Learning
5d ago
Thermodynamics of Learning: A Typed Four-Component Accounting of Memory, Fit, and Value
arXiv:2608. 12791v1 Announce Type: cross Abstract: What a finite learning device has recorded and what will hold value for it on future tasks are not the same quantity.
arXiv Machine Learning
5d ago
Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation
arXiv:2606. 21253v2 Announce Type: replace Abstract: Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment, but its value is usually argued informally.
arXiv Machine Learning
Aug 5
ForgettingOT: Certified Speculative Batching from Sinkhorn's Projective Forgetting
arXiv:2607. 24741v2 Announce Type: replace-cross Abstract: Positive two-marginal entropic optimal transport is solved by a nonlinear, positive, order-preserving, homogeneous Sinkhorn map.
arXiv AI
Jul 17
Gate-Zero Growth: A Geometric Framework for Function-Preserving Continual Learning
arXiv:2607. 14571v1 Announce Type: cross Abstract: We introduce \emph{gate-zero growth}, a function-preserving (FP) operator for continual learning that adds new residual blocks through a zero-initialised gate.
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 AI
Jun 16
Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning
arXiv:2606. 16515v1 Announce Type: cross Abstract: Hamilton-Jacobi-Bellman theory implies that the optimal goal-conditioned action depends on the goal only through the gradient of the goal-reaching distance at the current state, yet standard online GCRL still conditions the actor on the raw goal -- a signal that is geometrically uninformative when the goal is far from the data distribution.
arXiv AI
Jul 9
Grounding Spatial Relations in a Compact World Model: Instruction Leakage and a Goal-Free Dynamics Fix
arXiv:2607. 06925v1 Announce Type: new Abstract: Compact world models that condition on a language goal promise to ground relations such as ``put the red block left of the blue block'' using a sparse set of explicit \emph{reference anchors}.
arXiv AI
Jul 15
Adaptive Compute in Latent World Models: When Depth Helps, Hurts, or Doesn't Matter
arXiv:2607. 10203v2 Announce Type: replace-cross Abstract: Adaptive-compute world models -- early-exit or mixture-of-depths predictors that spend variable depth per step -- assume depth buys better predictions and can be routed adaptively.
arXiv Machine Learning
5d ago
A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the Gated-Linear-Recurrence Family
arXiv:2608. 12700v1 Announce Type: new Abstract: Systems that generate GPU kernels with language models report high correctness rates.
arXiv AI
Jul 15
Sensitivity to Subjective Expected Utility Maximization: A Methodological Study, with an Illustrative Application to LLM Decision-Making
arXiv:2607. 11920v1 Announce Type: cross Abstract: Evaluating decisions made under uncertainty is hard when labeled outcomes are scarce, costly, or confounded with luck.
arXiv AI
Jul 14
When Does Depth Survive Composition? Compute--Quality Regimes in Latent World Models
arXiv:2607. 10203v1 Announce Type: cross Abstract: Adaptive-compute world models -- early-exit or mixture-of-depths predictors that spend variable depth per step -- assume depth buys better predictions and can be routed adaptively.