Federated learning framework for multimodal sentiment analysis using uncertainty-aware fusion to handle missing modalities and heterogeneous data.
Pragma-VL approach balancing safety and helpfulness in multimodal LLMs through pragmatic alignment methods.
ICPRL framework enabling vision language models to learn physical reasoning from pixel-based interactive control.
DreamReader: unified interpretability toolkit for analyzing text-to-image diffusion models with causal and representation analysis.
Two-stage ML framework for identifying high-performance nested antiresonance fiber designs in telecommunications.
Approach for stable distributional alignment in LLMs to predict population response distributions across options.
Framework for training single models to answer conditional queries across heterogeneous datasets via task expansion.
Method addressing curriculum collapse in self-improving LLM reasoning systems through diverse problem generation.
Neural basis functions using untrained networks for multivariate function approximation in machine learning.
Research on linear structure in LLM attention head activations for KV cache optimization in Transformer inference.
Evaluates LLMs for gait classification from text-encoded kinematic waveforms, comparing performance to ML methods for clinical interpretability.
Analyzes overfitting and false refusals in fine-tuned LLMs through residual stream analysis, identifying safety data entropy as key factor.
LightningRL uses reinforcement learning to improve block-wise diffusion LLMs, breaking the accuracy-parallelism trade-off in parallel token generation.
Modular Neural Computer is a memory-augmented architecture combining external associative memory with functional MLP modules for exact algorithmic computation.
Studies out-of-distribution detection in motor imagery brain-computer interfaces to prevent misclassification on unseen data distributions.
Proposes feature-level interaction explanations for multimodal transformers, identifying cross-modal synergy and redundancy in predictions.
RBF-Solver proposes radial basis function-based multistep sampling for diffusion models to accelerate inference without predefined schemes.
AdaBox introduces adaptive density-based clustering with parameter generalization to reduce hyperparameter sensitivity across datasets.
Framework integrating vehicle sensor streams with contextual signals for V2X-augmented predictive maintenance using multi-dataset evaluation.
PolyGLU enables transformers' feed-forward neurons to dynamically route among multiple activation functions, improving architectural flexibility.
Real-time conversational AI system combining speaker segmentation with hierarchical end-of-turn detection for natural two-speaker voice interactions.
Proposes GPrune-LLM, a structured pruning method for LLMs that estimates neuron importance using distribution-robust techniques for better cross-task generalization.
Analyzes how diffusion models generalize despite optimal models memorizing training data, showing denoising trajectory properties affect generalization.
Investigates memorization behaviors in Rectified Flow generative models for image synthesis through theoretical and empirical analysis.
Proposes Kalman World Models, a method for training state-space models using recursive Bayesian filtering instead of backpropagation for online learning.
Flow matching-based approach for full-waveform inversion with generative priors to improve seismic imaging robustness.
Outcome-Aware Tool Selection method for semantic routers in LLM inference, reducing latency by offline interpolation without GPU cost.
Standardized benchmark dataset and evaluation framework for computational antibody design methods with unified metrics.
Framework for in-context learning on graphs without modality-specific encoders, enabling cross-domain adaptation for graph foundation models.
Multimodal diffusion model using flow matching for channel estimation, fusing LiDAR, camera, and location data.
Theoretical work on implementing higher-order mental-state dynamics in Transformers via triadic modulation for information pre-selection.
Framework reconciling in-context and in-weight learning in Transformers through dual representation space encoding to reduce conflict.
Probabilistic Gaussian Homotopy framework for nonconvex optimization using Boltzmann-weighted gradient aggregation.
Analysis of complex singularities in softmax cross-entropy loss that limit safe step sizes during optimization training.
End-to-end LLM method for auditing course information sheets at scale to identify GenAI vulnerabilities in academic assessments.
Survey of privacy-preserving machine learning for IoT devices, covering federated learning, differential privacy, and resource constraints.
Physics-informed CNN for precipitation nowcasting using volumetric radar data to estimate multi-altitude motion fields.
Federated learning approach for fraud detection in payment systems using NVIDIA FLARE, preserving privacy across institutions with non-IID data.
Systematic study of chemical language models for molecular property prediction, analyzing performance inconsistencies across benchmarks through controlled experiments.
SemRep: generative code representation learning using code transformations for semantic reasoning in software development.
PLUME: 140M-parameter foundation model for wireless packet traces using protocol-aware tokenization.
PDE-SSM: state-space block replacing attention in diffusion transformers using learnable convection-diffusion-reaction equations.
Dynamic curriculum learning approach using gradient-based difficulty estimation for adaptive example ordering.
GIP framework for selecting training examples for LLM fine-tuning by maximizing mutual information with task-specific signals.
IGU-LoRA: adaptive rank allocation for parameter-efficient fine-tuning of LLMs using integrated gradients and uncertainty scoring.
LLM-guided approach for interpretable dynamic graph clustering with semantic explanations of cluster formation and evolution.
Theoretical analysis extending Domingos interpolation formula to stochastic gradient descent, characterizing neural network generalization as kernel machines.
Deep metric learning approach (Siamese, Triplet, Vision Transformer) for identifying scribes in Chinese manuscript calligraphy datasets.
UVLM: unified framework for loading and benchmarking multiple vision-language models with standardized interface in Colab environment.
Self-training framework with label correction for handling noisy data in neural network training using bilevel optimization techniques.