Diffusion models for rare-event sampling in molecular dynamics. Scientific computing application with limited general AI interest.
Research on multilingual safety alignment for LLMs using resource-efficient methods. Addresses cross-lingual safety consistency.
Research on AI agent reliability evaluation beyond accuracy metrics. Analyzes consistency, perturbation robustness, and operational failures in deployed agents.
Theoretical analysis of approximation hardness for fair k-center clustering problem. Pure algorithmic theory with limited AI relevance.
Research on object-centric representations for compositional generalization in VQA tasks. Evaluates visual reasoning capabilities.
Research on FDR-controlled hypothesis testing using synthetic data from generative models. Statistical inference with auxiliary data.
Research comparing parameter-free representations to foundation models on single-cell RNA-seq downstream tasks. Biology-focused ML research.
Research on Spiking Neural Networks for efficient temporal information extraction with neuromorphic deployment. Addresses temporal resolution domain adaptation.
Analysis of Transformer optimization through gradient heterogeneity lens to explain Adam's superiority over SGD.
Research on continual learning with abundant memory, challenging traditional memory minimization constraints.
Research on lookback window bias in long-term time series forecasting benchmarks and model evaluation validity.
Research on emergent capabilities in language models via scaling. Analyzes breakthrough performance vs metric thresholding.
FedEFC method for federated learning with noisy labels using enhanced forward correction. Privacy-preserving distributed ML.
FedMerge: Federated learning approach creating personalized models per client by merging multiple global models.
ReaCritic: DRL method with transformer-based critic for heterogeneous network management and wireless optimization.
PLAICraft: Large-scale time-aligned Minecraft dataset with vision, speech, and action for embodied AI agents.
WINA: Training-free sparse activation method for LLM inference efficiency via weight-informed neuron selection.
XENON: LLM-based agent for Minecraft that algorithmically corrects knowledge from experience for robust long-horizon planning.
Theoretical study of expressive power of mixture-of-experts networks for tasks with low-dimensionality and sparsity.
DiffusionBlocks: Framework for block-wise transformer training via diffusion interpretation to reduce memory overhead.
Security research on neural network model extraction attacks via black-box queries on deep networks.
Research on step ordering in chain-of-thought reasoning for transformer arithmetic tasks. Studies impact on reasoning difficulty.
Benchmark study of stochastic approximation algorithms for fairness-constrained DNN training using Census data.
Causal discovery algorithm for time series robust to noise using power-law frequency spectra analysis.
Model-agnostic dynamic feature selection method with uncertainty quantification for resource-constrained decision-making.
Neural network output layer using orthogonal projection for satisfying convex constraints in feasible-by-design optimization.
Systematization of knowledge on data minimization principles in ML with focus on GDPR/CPRA regulatory compliance.
LLM-based framework for generating synthetic healthcare tabular data with fairness constraints from limited samples.
Method for single-pass uncertainty estimation in edge ML using next-activation prediction for microcontroller deployment.
Research characterizing universal activation sparsity properties in modern LLMs with implications for efficiency and interpretability.
Study on LLM self-improvement through reinforcement learning without external labels, addressing convergence toward majority-favored solutions.
Analysis of classifier-free guidance dynamics in diffusion models showing three-stage sampling process under multimodal conditions.
Research on training re-evaluation curves to optimize data curriculum ordering during LLM training for improved model retention.
Comparison of RNN architectures vs modern models for irregular time series prediction in healthcare/sensor domains.
Safety mechanism for RL agents balancing exploration and constraint satisfaction using uncertainty-aware modulation. Relevant to agent training.
Theoretical and empirical analysis of Transformers learning graph algorithms with proper training data. Explains generalization failures.
Transformer-based model for Bayesian clustering on datasets with missing values. Unsupervised learning extension of prior-data fitting.
Framework for synthesizing medical VQA datasets from biomedical literature using generator-verifier multimodal models. LLM application.
Variance reduction techniques for RL with verifiable rewards in large reasoning models. Applies to LLM post-training with policy gradients.
Q3R regularizer for low-rank training and fine-tuning of large deep learning models. Parameter-efficient training method.
Quantum kernel methods framework for classification on real-world datasets. Quantum ML research tangential to core interests.
Self-supervised learning for birdsong analysis using Residual-MLP-RNN. Domain-specific ML application outside core interests.
Security analysis of backdoor attacks in federated learning with LoRA fine-tuning. Covers distributed ML safety.
Theoretical analysis of entropy regularization in Dec-POMDPs proving policy convergence to equivariant solutions. Machine learning theory.
Adaptive aggregation method for quantum federated learning handling client quality variation, teleportation fidelity, and device instability.
Out-of-distribution detection for 3D molecular graphs using diffusion models. Addresses OOD challenges for irregular graph structures in molecular complexes.
Communication compression techniques for federated learning using biased compression with error feedback to handle asymmetric bandwidth constraints.
Imitation learning framework for combinatorial optimization under uncertainty. Studies how expert quality affects policy approximation in sequential decision problems.
Research analyzing Mixture-of-Experts architectures through geometric lens using Dual Jacobian-PCA spectral probe to understand routing and representation geometry.
Quantization-aware training framework for ultra-low bitwidth deployment of large models, improving stability over straight-through estimators.