Pipeline combining LSTM, synthetic data, and fine-tuning for EEG classification on implicit visual stimuli tasks.
Analysis of distributional reinforcement learning for complex domains like healthcare, addressing heterogeneous groups under uncertainty.
Tutorial on using flow- and score-based generative models for decision-making under distributional shift in operations research.
Neural architectures for learning to approximate Wasserstein-2 distances using Kuratowski embedding theorem.
System for generating editable design variations using decoder-only language model with Creative Markup Language representation.
Theoretical analysis of Q-value iteration convergence in multi-agent Stackelberg games using control-theoretic perspective.
Research on aligning LLMs with human preferences using relative density ratio optimization without assuming specific preference models, improving statistical consistency.
Study questioning necessity of prompt selection in task-free online continual learning for non-stationary data streams.
Ablation framework to estimate contributions of central, peripheral, and temporal visual information to human decision-making in Atari games.
TinyNina: edge-AI framework for satellite super-resolution applied to NO2 air quality monitoring with resource constraints.
DP-OPD: differentially private on-policy distillation method for compressing LLMs on sensitive data while maintaining privacy guarantees.
MAVEN: mesh-aware volumetric encoding network for simulating 3D flexible deformation using graph neural networks on mesh structures.
Discrete Prototypical Memories approach for federated time series foundation models using LLMs while preserving data privacy.
External validation study on ECG biometrics using Inception-v1 with ArcFace on MIMIC and HEEDB datasets.
Isokinetic Flow Matching introduces pathwise acceleration regularization to improve few-step sampling in flow-based generative models.
SLaB: sparse-lowrank-binary decomposition framework for efficient LLM compression maintaining performance at high compression ratios.
Multi-objective controllable language models framework enabling personalized alignment with varying human preferences beyond fixed reward optimization.
GAIN: multiplicative modulation technique for domain adaptation in LLMs, preventing catastrophic forgetting through feature re-emphasis.
Reproducibility study on spurious correlations and shortcut learning in DNNs, comparing frameworks for ensuring models use causally relevant features.
Revisits learning from equivalence queries model for modern ML systems like generative models and recommendation systems with periodic updates.
FlashSAC: off-policy reinforcement learning algorithm for stable, fast robot control in high-dimensional action spaces.
Detection method for free-riders in federated learning via simulated attack patterns, improving the WEF-based approach.
Deep learning approach for clinical mortality prediction from incomplete multimodal Electronic Health Records using point cloud paradigm.
Method to mitigate reward hacking in Best-of-N sampling for language models using pessimism, addressing inference-time compute scaling challenges.
Novel Anticipatory Reinforcement Learning framework for non-Markovian decision processes with jump-diffusions and structural breaks, designed for single trajectory learning.
Batch Loss Score metric for dynamic data pruning using exponential moving averages, accelerating deep learning training.
Explainable ML models for sepsis prediction using Romanian EHR dataset with 12,286 hospitalizations and 600 lab test types.
Quantization method for LLMs combining mixed-precision and low-rank decomposition for efficient INT computation on NPU devices.
Sampling parallelism approach for efficient Bayesian neural networks and uncertainty quantification in risk-sensitive applications.
Mechanistic analysis decomposing GPT-2 Small's final MLP into legible exception handler with 27 named neurons routing decisions.
Method using task reformulation to enable LLMs to learn from difficult problems via reinforcement learning from verifiable rewards.
Complete pipeline for federated unlearning with evaluation framework, enabling models to forget deleted data in distributed learning.
Algorithms for automatic concept selection in interpretable reinforcement learning policies without manual domain expertise.
Research on how generator access constraints affect autoregressive post-training and learning from rollouts vs prefix queries.
Python toolkit for intersectional fairness analysis in clinical ML models, addressing compounded disparities beyond single-axis comparisons.
Empirical robustness analysis of TabPFN's attention mechanisms for in-context learning on tabular data, examining noise immunity without retraining.
DSPy framework for optimizing LLM prompt engineering through declarative learning instead of manual trial-and-error, improving scalability and reproducibility.
Formalizes data attribution methods for adaptive learning settings where training data is generated by models themselves, addressing feedback loop in online/RL systems.
Investigation into interpretability challenges of latent reasoning models that operate without explicit natural language reasoning, examining two approaches.
Hierarchical Instance-Conditioned Mixture-of-Experts architecture for object detection using sparse routing at instance level rather than image/patch level.
Hierarchical instance-conditioned mixture-of-experts architecture for object detection with sparse parameter activation.
Graph neural networks with contrastive learning for predicting power outages from extreme weather events.
Novel stratification-based semantics for Signal Temporal Logic with applications to reinforcement learning.
CNN-attention hybrid model for decoding hand kinematics from EEG in brain-computer interfaces.
Training method enabling Code LLMs to simulate program execution step-by-step, improving competitive programming performance.
Multi-agent research showing emergence of compositional communication protocols for representing latent physical properties without explicit supervision.
IPSL-AID: generative diffusion model for climate downscaling from global to regional resolutions.
SpikeVPR: neuromorphic approach using event-based cameras and spiking neural networks for energy-efficient visual place recognition.
Cross-Stage Attention Residuals mechanism for medical image segmentation using selective aggregation of encoder-decoder outputs.
Lossless compression method for LLMs enabling fast inference on Ascend NPUs, addressing weight data transfer bottleneck.