Comparison of Euclidean and hyperbolic graph neural networks for analyzing Bitcoin transaction networks and fraud detection.
Analysis showing noisy data significantly degrades reinforcement learning with verifiable rewards despite claims of robustness.
Constrained reinforcement learning approach for hierarchical instruction following in LLMs with priority-ordered system prompts.
Experience replay mechanism preserving diversity in on-policy reinforcement learning for LLM reasoning using Jensen-Shannon divergence.
Credit assignment method using execution traces to improve GRPO performance in code generation tasks with verifiable rewards.
Study of specialized pretraining strategy using domain data during pretraining to improve finetuning performance and reduce forgetting.
Transfer learning method for adapting drug-response prediction models from cell lines to patient tumors.
Fine-tuning approach for improving mathematical reasoning in LLMs by optimizing exploration-aware trajectories with verifiable rewards.
Dual consensus mechanism for improving reinforcement learning from verifiable rewards in LLMs, avoiding convergence to spurious answers.
Physics-informed neural network surrogate model for fluid dynamics simulation near solid boundaries.
Foundation model approach for EEG analysis using latent prediction training for brain-computer interfaces and clinical applications.
Study of how large reasoning models use backtracking and self-verification to detect and correct errors in complex logical reasoning tasks.
Research on steering behavior in 35B MoE language models using sparse autoencoders and probe vectors to identify and control agentic traits.
MLP architecture with learned structural dropout and input-dependent gating for conditional computation and regularization.
Federated learning framework for non-IID distributed scenarios using generative one-shot learning without foundation model dependencies.
Spectral initialization method for neural networks designed for function parameterization using prior information.
Study on bias mitigation and generalization in age prediction models using causal analysis and invariant representations.
Methods for adding persistent memory to frozen encoder-decoder LLMs using continuous latent space adapters for multi-session learning.
Solver for distributional counterfactual explanations using optimal transport with statistical certification for model interpretability.
LLM compression method using capability-guided budget allocation that interprets what model components encode before pruning.
Optimal uncertainty bounds for multivariate kernel regression using Gaussian processes with applications to safe learning-based control.
High-frequency time series dataset at millisecond resolution for training and evaluating time series foundation models.
Test-time scaling and confidence calibration strategy using internal model information for improved reinforcement learning.
Foundation model for structured data with linear complexity for handling extremely large datasets in healthcare, finance, and e-commerce.
Unsupervised autoencoder regularization by aligning pairwise distances between latent and input spaces on learned manifolds.
Deep learning methods for tabular data using representation correction to improve on in-learning and pre-learning paradigms.
Analysis of when unsupervised reinforcement learning succeeds in LLM mathematical reasoning, addressing scalability of outcome-based RL.
Time reparameterization technique for improving machine learning reduced-order models of stiff dynamical systems.
Gaussian process classifier for multi-class problems using simplex geometry and Aitchison geometry for probability calibration.
Method for discrete reasoning using self-aware Markov models that correct errors in masked diffusion models through adaptive denoising.
Study on how Transformers develop internal geometric representations of grid-world environments through next-token prediction.
Research on matrix inversion updates for streaming outlier detection using Christoffel function and online learning.
Finsler geometry method for trajectory inference incorporating discrete, directed lineage priors in dynamical systems.
Deep-kernel-learning BEACON framework for automated microscopy discovery using novelty-driven target-space search.
Federated learning models predicting postoperative complications using multi-center healthcare data while preserving privacy.
Study showing chain-of-thought prompting degrades uncertainty quantification in vision-language models despite improving reasoning.
GeMA latent manifold benchmarking method for complex systems like rail networks using machine learning frontier estimation.
Analysis of quantized optimizer states in LLM pre-training, studying state staleness and effectiveness of reset strategies.
SpecMoE mixture-of-experts foundation model for cross-species EEG decoding with spectral and temporal signal analysis.
Bayesian hierarchical model inferring psychometric variables from neural and behavioral data in implicit association tests.
Contextual bandit algorithm combining dense arm features, non-linear rewards, and time-varying correlation for recommendations.
pADAM generative framework learning shared probabilistic priors across heterogeneous PDE families for multi-physics simulation.
SOMP algorithm for scaling gradient inversion attacks on LLMs, revealing privacy risks from shared gradients in large batch settings.
Conservative stochastic control framework for treatment optimization from irregularly sampled medical patient trajectories.
Method using adaptive moment estimation to stabilize guided diffusion sampling for image restoration and generation tasks.
Research on Gaussian mean estimation under realizable contamination with missing data patterns.
RaDAR: relation-aware diffusion contrastive learning for sparse collaborative filtering recommendations.
Stochastic resetting mechanism accelerates policy convergence in reinforcement learning on tabular environments.
Dynamic meta-layer aggregation defends federated learning against Byzantine adversaries and untargeted attacks.
Gauge-invariant spectral transformers for scalable graph neural operators maintaining symmetry in inductive learning.