Explore documented scientific discoveries, original research and new scientific developments. Search the library by topic, category or date.
arXiv:2610.36110v1 Announce Type: new Abstract: Semiparametric Bayesian networks (SPBNs) are flexible probabilistic graphical models for representing joint distributions of continuous variables through lower-dimensional conditional probability distributions (CPDs).
arXiv MLRead article →arXiv:2610.36109v1 Announce Type: new Abstract: Test-time updating lets a language model change persistent state after training---such as model weights, adapter parameters, or a memory module---before or while answering queries. Existing evaluations often compare systems using update count or frequency and performance measured immediately afterward.
arXiv MLRead article →arXiv:2610.36097v1 Announce Type: new Abstract: We study full-information online linear optimisation on the unit $\ell_p$ ball in $\mathbb{R}^d$, for fixed $2\le p<\infty$ and losses of dual norm at most one. Let $\Delta_T$ denote the cumulative loss of the best fixed action above each round's minimum.
arXiv MLRead article →arXiv:2610.36095v1 Announce Type: new Abstract: The quality with which language models follow instructions falls as the load grows, yet there is still no quantity that expresses the limit of a model in units of load with an uncertainty.
arXiv MLRead article →arXiv:2610.36082v1 Announce Type: new Abstract: Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quantitative reasoning.
arXiv MLRead article →arXiv:2610.36075v1 Announce Type: new Abstract: Hardware-accelerated reinforcement learning in JAX has gained rapid popularity in recent years and has proven to be a successful method of scaling online reinforcement learning. The resulting ecosystem, however, is fragmented: environment suites define their own interfaces, and algorithm implementations are typically written for a single suite, a single type of space…
arXiv MLRead article →arXiv:2610.36020v1 Announce Type: new Abstract: Dynamic creative optimization decides which creative of an ad to render for each request. Recent work places that choice before ad ranking, but relies on deterministic point predictors with no calibrated uncertainty. AI-generated content has made creatives nearly free, while feedback per creative remains sparse and selection faces a tight latency budget.
arXiv MLRead article →arXiv:2610.36009v1 Announce Type: new Abstract: Sparse expert execution does not remove the stored states needed to adapt a mixture-of-experts language model. We present DuplexTune, a framework for replaying coupled hidden states through pretrained attention and expert modules. Trainable width bridges connect two residual streams to the backbone.
arXiv MLRead article →arXiv:2610.35989v1 Announce Type: new Abstract: Variable-length training creates conflicting parallelism requirements across the layers of a hybrid-attention model. The longest samples require wide sequence-parallel (SP) groups of 16 or 32 ranks for full attention, whose cost grows quadratically with sequence length.
arXiv MLRead article →arXiv:2610.35985v1 Announce Type: new Abstract: Conditional memory layers, such as DeepSeek's Engram, attach large hashed n-gram tables to a language model, and removing them from DeepSeek-V4.1-Flash costs 36.8 PopQA points. Low-bit quantization loses long-tail facts first, and the standard remedy, giving more bits to frequently accessed rows, backfires: refining lookups by access frequency is worse than refining…
arXiv MLRead article →arXiv:2610.35975v1 Announce Type: new Abstract: Wind farm layout optimization becomes increasingly difficult as turbine count grows, especially when high-fidelity aerodynamic models are used. Conventional Kriging-based Bayesian optimization often suffers from low sample efficiency in high-dimensional layout spaces because sparse training data provide limited domain coverage.
arXiv MLRead article →arXiv:2610.35972v1 Announce Type: new Abstract: Leak localization in water distribution networks is challenging when multiple leaks occur simultaneously, particularly under sparse monitoring. Existing data-driven methods often assume a single or predefined number of leaks or require extensive enumeration of leak combinations.
arXiv MLRead article →arXiv:2610.35967v1 Announce Type: new Abstract: We present LatentLieODE, a novel neural ODE method to discover linear Lie symmetries and first integrals of the learned dynamics from timeseries observations such as video inputs. It starts with an autoencoder, which learns a low dimensional representation of the observed system and then maps trajectories to decorrelated latent coordinates $z \in \mathbb{R}^d$.
arXiv MLRead article →arXiv:2610.35965v1 Announce Type: new Abstract: In this work, generalization in machine learning is investigated using a predator-prey model. We overview biological and chemical interpretation of the stochastic gradient Langevin dynamics and generative adversarial network.
arXiv MLRead article →arXiv:2610.35963v1 Announce Type: new Abstract: Generative machine learning provides an end-to-end framework for aerodynamic design optimization by generating diverse aerodynamic configurations conditioned on target performance. However, the generated designs may violate geometric constraints or deviate from the prescribed aerodynamic performance.
arXiv MLRead article →arXiv:2610.35962v1 Announce Type: new Abstract: While progress in informal mathematics has come largely from scaling the chain-of-thought and agentic reasoning of frontier language models, formal theorem proving has increasingly relied on human-designed workflows around these models, such as planning, decomposition, and orchestrating specialized provers.
arXiv MLRead article →arXiv:2610.35961v1 Announce Type: new Abstract: Diabetic retinopathy grading from retinal fundus photographs is important but difficult to deploy on resource-constrained hardware. We conducted a controlled study of offline response-based knowledge distillation for five-class diabetic retinopathy grading on APTOS 2019, comparing ResNet-50, MobileNetV3-Large, and Swin Transformer-Tiny (Swin-T) teachers distilled into…
arXiv MLRead article →arXiv:2610.35960v1 Announce Type: new Abstract: Purpose: To compare 2D, 2.5D, and 3D residual networks for pulmonary nodule malignancy-risk classification and evaluate momentum-contrast pretraining, mild augmentation, and exclusion of indeterminate ratings. Methods: A retrospectively prepared LIDC-IDRI cohort contained 2,654 nodules labeled benign, indeterminate, or malignant using median radiologist ratings.
arXiv MLRead article →arXiv:2610.35958v1 Announce Type: new Abstract: When events resume after a long silence, explicit Gaussian point-process filters amplify the first update exponentially in the silence duration. We give the exact distribution of this update and a computable index that predicts when it overshoots.
arXiv MLRead article →arXiv:2610.35957v1 Announce Type: new Abstract: Distributed speculative decoding has emerged as a promising approach for device--server collaborative large language model (LLM) inference, but its decoding speedup is often limited by the vocabulary-scale communication overhead.
arXiv MLRead article →arXiv:2610.35955v1 Announce Type: new Abstract: Low-bit weight--activation quantization reduces the memory and computation needed to deploy large language models, but activation rounding can still degrade accuracy after calibration. Reconstruction from rounded inputs cannot distinguish activations within the same quantization bin.
arXiv MLRead article →arXiv:2610.35954v1 Announce Type: new Abstract: Autonomous vertical landing of reusable launch vehicles is a critical yet formidable challenge in aerospace engineering, primarily due to highly nonlinear dynamics, stringent precision require- ments, and inherent environmental uncertainties.
arXiv MLRead article →arXiv:2610.35877v1 Announce Type: new Abstract: Changing a deployment policy can invalidate a world model's uncertainty while leaving the physical transition mechanism and predictor unchanged. For one-step prediction, if source and target laws share the conditional mechanism $P(Y|X)=Q(Y|X)$, then the intervention is identified by the pre-outcome change of measure $w(X)=dQ_X/dP_X$.
arXiv MLRead article →arXiv:2610.35869v1 Announce Type: new Abstract: AI applications often invoke a model before they determine whether inference is necessary. That default is useful for ambiguous generative tasks, but it is poorly matched to work that is structured, deterministic, policy-bound, lookup-oriented, or directly verifiable.
arXiv MLRead article →