arXiv:2610.26179v2 Announce Type: replace Abstract: Hierarchical world models plan over long horizons by passing predicted states from a coarse model to a lower-level controller. Choosing these state...
arXiv:2609.39934v1 Announce Type: cross Abstract: Checkpoint selection in domain generalization often relies on source-validation accuracy, yet the selected checkpoint need not provide reliable proba...
arXiv:2609.36569v1 Announce Type: cross Abstract: Checkpoint selection is a routine decision in supervised fine-tuning (SFT): training produces multiple checkpoints, but only one is retained. Yet fix...
Decision‑FLIP is a budget‑free pruning framework for Gaussian occupancy models that scores each persistent Gaussian row by how many voxel decisions change when the row is removed. It uses a guarded Otsu split on the log‑score distribution to select survivors without a target, then compiles the survivors into a smaller checkpoint, reducing bank size and latency. Across multiple model‑dataset settings, the method removes 12–79% of rows, cuts latency by 7–45%, and saves up to 8.0% of whole‑model compute while keeping semantic mIoU within 0.18 points of the original.
arXiv:2606. 30852v1 Announce Type: new Abstract: Reasoning models spend different amounts of useful computation across instances, but it remains unclear when a learned stopping rule improves over simple confidence or convergence thresholds.
arXiv:2607. 07665v1 Announce Type: new Abstract: Classifier-free guidance (CFG) is the standard way to strengthen class-conditioning in diffusion and flow-matching samplers, yet at large guidance it oversaturates and destabilizes, symptoms practitioners suppress with more steps or limited-interval schedules.
The paper introduces a sparse, residual world model that focuses on predicting only the changes in a scene by using a per-object change gate and a residual delta head. On a MuJoCo tabletop pushing benchmark, this approach outperforms a dense multilayer perceptron, achieving 2.5 to 4.6 times better next‑state pose accuracy with 8.6 to 11.1 times fewer parameters, maintaining high change‑detection F1 scores, and showing strong transfer across object counts. In autoregressive rollout and sampling‑based planning, the sparse model accumulates less error and enables successful planning where dense models fail.
arXiv:2608. 14650v1 Announce Type: new Abstract: Existing adaptive-inference and world-action-model systems use cheap-stage outputs or predicted futures to allocate additional computation.
arXiv:2607. 21372v1 Announce Type: cross Abstract: Score Entropy Discrete Diffusion (SEDD) parameterizes discrete reverse processes with unconstrained positive score ratios.
arXiv:2609.36433v1 Announce Type: new Abstract: Diffusion models enable high-quality visual generation, but iterative denoising remains computationally expensive, especially under classifier-free gui...
arXiv:2610.09272v1 Announce Type: new Abstract: Attention routing requires a signal that predicts the value of attention on the current prefix. We evaluate whether hidden-state extrapolation error, c...
Classifier-free guidance (CFG) is the standard way to strengthen class-conditioning in diffusion and flow-matching samplers, yet at large guidance it oversaturates and destabilizes, symptoms practitioners suppress with more steps or limited-interval schedules. We analyze CFG through an asymptotic-preserving, numerical-analysis lens.