Category
2,173 papers
Optizing Your Sampling (OYS), which instead treats timestep selection as a black-box optimization problem, optimizing the target metric directly with Bayesian optimization, improves both simple and sophisticated samplers such as Euler and DPM-Solver++.
TabNSM provides an effective and scalable approach to deep tabular regression, and demonstrates that selective interaction modeling, structured regression supervision, and difficulty-aware sampling provide an effective and scalable approach to deep tabular regression.
The results reveal why GPT-style models do not transfer directly across modalities: architectures transfer, but tokenization interfaces do not and must discover effective representations while preserving the relational freedom from which contextual structure can emerge.
This work reproduces WEASEL 2.0 on 114 UCR datasets and tests the sensitivity of four design choices: the downstream classifier, the absence of feature weighting, the maximum window-size rule, the maximum ensemble-size rule, and the maximum ensemble-size rule.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work formalizes the hybrid LLM-planner and RL-controller architecture as a Goal-Augmented Markov Decision Process and shows that when the LLM per-state progress score is used as a bounded potential function, the resulting shaping term preserves the optimal policy set even when the LLM scores are inaccurate.
It is shown in this work that flow matching models with a potential-induced velocity yield an explicit scalar energy at all transport times, whose gradient is exactly the converted learned score and which recovers the marginal negative log-density at the population optimum.
This work describes an inference-time architectural enhancement for off-the-shelf foundation models that markedly reduces perplexity and boosts accuracy across generation and reasoning tasks, and proposes and evaluates an adaptive variant of recirculation which requires only light tuning of hyperparameters while freezing the original model weights.
Light is shed on the effect of dissimilarity between train and test feature distributions on forecasting models, compares deep learning versus non-deep learning models, and introduces modifications that are effective for non-deep learning models.
Log Reconstruction and Distance (LoRD), a lightweight post-hoc calibration framework for reliable log anomaly detection, is proposed and demonstrates that LoRD consistently improves confidence reliability and substantially reduces overconfident anomaly-related errors without sacrificing anomaly detection performance.
A task-centric, retrieval-based perspective is offered for how TFMs generalize: it is believed that tabular in-context generalization is largely retrieval-based, and good models are those that learn to identify relevant examples in the provided context and aggregate them well.
An LLM synthesizes an executable world model that a classical planner searches, and the model is accepted when it reproduces sampled transitions, and it is asked what that acceptance certifies in continuous control.
This work proposes a SHAP-enhanced Implicit-trajectory Generation for Metadata-free AutoFE (SIGMA), a scalable constant-context optimization framework that leverages SHAP values to provide task-aware signals for guiding group feature generation instead of semantic information.
General Science
Climate & Sustainability
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
A new algorithm learns to anticipate the unprecedented scenarios that critical infrastructure and global supply chains are least prepared for.
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
