OCP: Orthogonal Constrained Projection for Sparse Scaling in Industrial Commodity Recommendation
Proposes OCP method for improving item embeddings in large-scale commodity recommendation systems.
Proposes OCP method for improving item embeddings in large-scale commodity recommendation systems.
Studies off-policy learning in contextual bandits with supply constraints for recommendation and advertising systems.
Causal-theoretic approach for reward modeling using observational user feedback instead of expensive annotated data for RLHF alignment.
Ablation study examining necessity of components in Group Relative Policy Optimization for teaching LLMs reasoning and mathematical ability.
Deep VAE-GAN approach improving reservoir parameterization for data assimilation in petroleum reservoir simulation.
AutoPipe framework for automatically configuring LLM post-training pipelines combining supervised fine-tuning and reinforcement learning under budget constraints.
Study on using discriminators to enhance generative model training across GANs, weak learner frameworks, and diffusion models.
Method mitigating asynchronous data drift in federated learning where different devices experience different distribution shifts.
Neuroscience framework introducing authority-level priors to hierarchical predictive processing for understanding autonomic regulation.
Theoretical error analysis of Adam optimizer for training deep neural networks and beyond, addressing open research gaps.
Framework using normalizing flows to approximate diffusion process transition probability densities by solving Fokker-Planck equations.
Ensemble framework for loan default prediction handling nonlinear relationships and class imbalance in financial datasets.
Method augmenting reinforcement learning from verifiable rewards with context bootstrapping to improve exploration and reasoning pattern acquisition.
ML framework for anomaly detection in power plant monitoring systems balancing performance and fairness across regions.
Bayesian model for drug discovery incorporating variable selection and side information through inductive matrix completion.
Intrinsic reward method for reinforcement learning agents maximizing entropy of future state-action visitation distributions.
Novel symmetric Turing Test variant where groups of LLMs and humans interact, judge, and respond in time-bounded discussions.
Benchmarking study comparing AI agents' performance to human experts on domain-specific data science tasks, evaluating LLM-based automation of data science workflows.
Analysis of differential privacy guarantees and convergence in wireless federated learning without restrictive convexity assumptions.
CoMFed framework for communication-efficient federated learning with heterogeneous multimodal clients and privacy preservation.
Theoretical analysis questioning foundations of Spectral Graph Neural Networks for node classification tasks.
Study of multimodal jailbreak attacks on Spoken Language Models using gradient-based optimization across text and audio modalities.
Research on efficiency metrics for Vision-Language-Action embodied agents, showing that parameter/FLOP counts don't reflect real robotic platform performance.
Stock prediction framework using autoencoders and transformers with reinforcement learning for adaptive market regime detection.
Hierarchical Bayesian model for online latent-cause inference balancing generalization and discrimination in learning.
SHAPCA: interpretability framework combining SHAP and PCA for explainable ML on high-dimensional spectroscopy data.
Continual learning method using random projection layers with pretrained models for improved representation learning.
DyMoE: dynamic expert selection with mixed-precision quantization for efficient MoE model inference on edge devices.
SOL-ExecBench: 235-problem benchmark for CUDA kernel optimization against hardware efficiency limits for agentic AI systems.
MIDST challenge evaluating membership inference attacks on synthetic tabular data generated by diffusion models.
Statistical method for improving treatment effect estimation by aligning RCTs and observational studies under covariate mismatch.
Security analysis of phishing detectors examining evasion costs and robustness under adversarial feature manipulation.
Online learning algorithms for sequential decision-making with ranking feedback instead of numeric utility feedback.
CONSTRUCT method for real-time trustworthiness scoring of LLM structured outputs and field-level error detection.
MineDraft framework for batch parallel speculative decoding to accelerate LLM inference by hiding draft and verify stages.
Differentiable rendering technique for RF digital twins enabling gradient-based optimization of radio frequency systems.
Sensor fusion method combining UWB and inertial measurement for indoor localization under non-line-of-sight conditions.
Corpus poisoning attacks and defenses for RAG systems, demonstrating vulnerabilities in LLM-extended retrieval pipelines.
Training technique applying sharpness-aware minimization to spiking neural networks using surrogate gradient methods.
Medical imaging method combining intuitionistic fuzzy logic with U-Net architectures for MRI brain image segmentation.
FPGA-based SoC architecture for spiking neural networks using RISC-V controller and event-driven computation for edge AI.
Digital RTL architecture implementing predictive coding networks as alternative to backpropagation for distributed hardware learning.
Framework integrating deep generative models and normalizing flows to accelerate replica exchange molecular simulations.
Foundation diffusion model for computational pathology and histopathology image analysis with self-supervised learning.
Quantization-aware drift correction method for diffusion model sampling to reduce degradation from post-training quantization noise.
Few-shot learning adapter for CLIP using patch-level and text supervision without increasing inference costs.
Defense mechanism against backdoor attacks in audio/speech models using stability-based trigger detection at inference time.
Alternative training architecture for AI models using non-standard arithmetic and memory management for geometric and neuromorphic AI.
Transfer learning for pricing and assortment optimization across markets using multinomial logit choice models with bandit feedback.
Insight-V++ framework enables multi-agent visual reasoning for MLLMs with long-chain reasoning, addressing data scarcity and training optimization.