This paper tackles the tendency of graph diffusion models to lose global topology—such as cycles and higher-order motifs—during local denoising. It introduces MG-Diff, a framework that extracts a discrete Morse skeleton from a graph and conditions generation on this sparse topological backbone. By framing diffusion as traversing a discrete cobordism, the authors aim to anchor the generative trajectory to structurally critical events rather than treating topology as an afterthought. The promise is better preservation of connectivity and improved uncertainty quantification in spatio-temporal forecasting.

Federated learning suffers from client drift when local data is heterogeneous, slowing convergence and degrading the global model. This paper proposes Activation Sharing Federated Learning (ASFL), a method in which clients exchange hidden-layer activations and labels with a randomly paired peer each round, then perform a partial tail round updating only the deeper layers using the pooled activations before standard local training. The premise is that aligning latent representations directly across clients mitigates heterogeneity more effectively than parameter-space regularization, while partial backpropagation cuts per-round computation.

This paper develops a physics-informed Kolmogorov-Arnold network (KAN) solver for free-boundary PDEs, including elliptic obstacle problems and the time-dependent Stefan problem. The core idea is to replace fixed MLP node activations with learnable univariate B-splines on network edges, aiming for localized resolution of contact sets and moving interfaces. Accurate, parameter-efficient approximation of these coupled unknowns matters because classical mesh-based methods require explicit interface tracking or costly refinement, while standard PINNs may blur sharp free boundaries.

Test-time scaling is often proposed as a cheaper substitute for larger models, but its practical returns remain murky because prior evaluations usually focus on one domain and rarely charge selection costs to the budget. This paper introduces SELF-POT, a cross-domain benchmark and evaluation framework that charges every model call—including selection, critique, and voting—in actual dollars under fixed output-token caps. Across 350 sealed tasks in mathematics, programming, and agentic workflows, the authors show that extra inference yields wildly different returns depending on the domain and selection rule, and that the real bottleneck is often converting generated coverage into a valid submission rather than generating a correct candidate in the first place. By reframing test-time potential as a measured conversion profile tied to price and failure handling, the work connects empirical scaling behavior to concrete deployment trade-offs.

Adapting LLMs at test time usually requires gradients, task labels, or auxiliary demonstrations. This paper studies whether the input query alone contains enough signal to predict a useful parameter update. The authors propose a query-conditioned distributional hypernetwork that learns to output a distribution over LoRA adapters, trained with a differentiable Monte Carlo approximation of the marginal likelihood. They show that the mean update already outperforms deterministic hypernetworks, and that sampling diverse adapted models at test time provides a novel compute-scaling axis competitive with standard token sampling. Results are demonstrated on models from 1B to 4B parameters.

Many recent sampling algorithms built on Wasserstein gradient flows (WGF) and forward-only diffusion processes (FODP) come with exponential-convergence guarantees that are often read as proof of fast practical mixing. This paper argues that guarantee is misleading: the canonical KL-induced WGF and overdamped forward diffusion produce the same marginal Fokker--Planck evolution, so they inherit the same metastability and exponentially slow inter-mode transport known in statistical physics. Using spectral-gap and mean-first-passage-time analysis on multimodal targets, the authors show that well-separated modes induce mixing times that scale exponentially with barrier height, and that standard log-linear annealing does not remove this scaling. The conclusion is that purely local, gradient-driven sampling is structurally limited for multimodal distributions, motivating nonlocal transport mechanisms.

Intrinsically disordered protein regions (IDRs) are essential to cellular function but cannot be designed with structure-based methods because they lack stable folds. This work introduces IDiom, a protein language model pretrained on 54 million predicted IDRs, and RL-SAE, a reinforcement learning method that rewards the activation of interpretable sparse-autoencoder features to control sequence patterns. Together they enable composable, function-targeted generation of disordered sequences, though the results remain purely computational.

Equivariant machine learning interatomic potentials are held back by costly tensor product operations that dominate inference at scale. BranchIP addresses this by introducing lightweight, learned routers inside a single model that adaptively terminate tensor product refinement for individual features, trained with a novel distillation loss. On two realistic reactive systems—CO/Pt catalysis and CsH2PO4 proton conductors—it delivers up to 2.4× inference speedup and 2.6× memory reduction while preserving exact energy conservation and offering chemically interpretable routing patterns.

Rare weather regime transitions such as sudden stratospheric warmings are challenging to emulate because training data is overwhelmingly dominated by stable regimes. This paper develops a probabilistic ResNet-inspired Conditional Variational Autoencoder (CVAE) for the stochastic Holton-Mass model, a 75-dimensional idealized system with two metastable vortex states and rare noise-driven transitions. By training only on one-day-ahead predictions, the authors show that the emulator reproduces both short-term dynamics and demanding long-term statistics, and that unsupervised clustering of its 32-dimensional latent space yields four physically interpretable regime clusters. The results suggest a proof-of-concept pathway toward interpretable early warning systems for extreme events, although the study remains confined to a simplified testbed.

TRACE targets dynamic resource assignment in industrial systems where processing times, energy profiles, and queue capacities are unknown a priori. While existing LLM-based Automatic Heuristic Design learns only from scalar fitness scores, TRACE couples an evolutionary loop with an agentic workflow that distills noisy system logs into insights and executable surrogate models. This feedback turns blind trial-and-error into data-driven design, yielding heuristics that cut cost by over an order of magnitude relative to prior AHD methods and reduce energy by 65% against industry standards without sacrificing reliability.

SILSA tackles the cost and topological fragility of high-resolution 3D generation by replacing dense or sparse voxel tokens with compact sliding-window slice latents along the three canonical axes. Each of the 384 fixed tokens summarizes a local depth window, preserving cross-sectional continuity while enabling a single-stage rectified-flow generator. Topology-aware slice supervision and a Volumetric Anchor Lattice then maintain geometric and structural coherence. The paper reports large efficiency gains—over 98% fewer tokens than sparse voxelizers—and solid improvements in PSNR, coverage, and Betti error.

Unsupervised reinforcement learning aims to eliminate hand-crafted rewards, yet existing intrinsic motivation objectives either require selecting information variables or serve only as exploration bonuses. This paper introduces Forward CIP (F-CIP), an exact forward-in-time decomposition of the Controllable Information Production (CIP) objective—defined by the sum of positive open-loop Lyapunov exponents—into a per-step Markovian reward and a propagated information matrix memory. By doing so, it enables standard RL algorithms to unsupervisedly discover upright balancing and to simplify reward engineering for dynamic locomotion tasks.

Sound classification with transformers usually demands stacking many layers, which inflates parameters and compute. LAST asks whether the same blocks can be reused to refine only a single class token while keeping audio features fixed, trading depth for recurrence. Their looped Audio Spectrogram Transformer matches or exceeds deeper sequential baselines on AudioSet at roughly half the parameter count, suggesting that how tokens are updated matters as much as how many layers exist.

This work tackles street-view weather recognition under severe domain shift, where labeled training images come from generic outdoor datasets and real driving scenes are unlabeled at training time. The proposed Weather-Aware ADDA conditions the adversarial domain discriminator on predicted weather probabilities, encouraging alignment that remains sensitive to weather semantics. The idea is to enable reliable onboard camera-based perception for autonomous vehicles without requiring expensive labeled street-view data for every adverse condition.

This paper introduces Higher-order Grammar Representation (HGR), a method that lifts molecular graphs into combinatorial complexes and parses them into compact sequences of context-free production rules, making higher-order topology such as ring systems tractable for standard sequence models. To reduce benchmark bias toward simple rings, the authors also construct RingDiv, a ring-enriched benchmark of 1.18 million molecules. HGR is instantiated in generative models (HGR-VAE and HGR-LDF) and a foundation model (HGR-FM), with claims of 100% validity by construction and state-of-the-art distributional alignment and transfer performance.

Speech-based Alzheimer's assessment increasingly relies on self-supervised learning models, but their vulnerability to nuisance acoustic factors remains unclear. This paper asks whether noise and reverberation are merely encoded in SSL representations or actively drive diagnostic predictions. Using controlled input- and representation-space interventions on the ADReSSo dataset, the authors show that acoustic manipulations systematically shift classifier outputs even when no baseline group difference exists, challenging the assumption that predictive accuracy implies robustness.

Deep neural networks in long-lived systems often face task obsolescence, where previously valid outputs become invalid after deployment. Deep Repurposing (DR) addresses this by analytically redirecting obsolete latent structure toward retained regions instead of simply erasing it. This enables lightweight post-hoc adaptation without gradient updates, achieving retained performance comparable to or better than unlearning and editing baselines while operating up to 60× faster than retraining.

Operational geostationary fire products like the GOES Fire Detection and Characterization (FDC) suffer from high false-alarm rates and poor nighttime recall. This study replaces the FDC's rule-based algorithm with a CatBoost gradient-boosting model trained on over 60,000 GOES ABI fire pixels labeled by VIIRS active-fire detections. By evaluating on large 2024 regions outside the training domain, the authors show that a comparatively simple ML model can substantially outperform the operational product in precision, recall, and early detection latency, especially after dark.

How complex can a quantum device's responses become when it runs longer with a fixed internal memory? This paper quantifies this through sequential response capacity—the depth of an adaptively shattered binary tree of experiments—and proves a tight law: for fixed visible and memory dimensions, capacity grows as $\Theta(K\log((K+1)/\gamma))$ in run length $K$ and probability gap $\gamma$. The core construction shows that memory-one qubit phase channels already attain this scaling with exact zero-or-one responses, while fully measured classical processes under the same tester permissions are limited to linear capacity. The result establishes a fundamental information-theoretic separation between coherent quantum control and classical stochastic transitions under a finite memory budget.

Looped Transformers reuse the same parameter block across recurrent iterations, producing intermediate states that are usually discarded at decode time. This paper proposes LoopCD, a training-free contrastive decoding framework that treats an early recurrent state as a weak predictor to guide the final prediction, either in logit space (one extra output pass) or hidden-state space (zero extra overhead). The core insight is that recurrence naturally provides aligned weak-and-strong pairs without auxiliary models, and the authors show this can both boost accuracy at full depth and—more interestingly—allow halving the iterations while matching baseline performance, cutting forward FLOPs by roughly 23–48%.