DepthCharge framework measures knowledge depth in LLMs through adaptive probing across domains, addressing inability to sustain accurate responses in domain-specific details.
Study of prospective memory failures in LLMs when formatting constraints conflict with complex tasks.
MDKeyChunker: Structure-aware document chunking and single-call LLM enrichment for improved RAG pipelines.
Transformer-based approach for polarization detection in social media using threshold tuning and class weighting.
Analysis of LLM reasoning behavior at self-organized criticality using phase transition characteristics.
Deep learning framework for OFDM waveform modulation to reduce peak-to-average power ratio.
Variational autoencoder with per-dimension Gaussian mixture priors for nonlinear independent component analysis.
Theoretical resolution of sample compression conjecture for finite function concept classes.
Time-LLM applied to wafer-level spatial profiling for plasma etching process monitoring.
ZeroFold: Pre-trained embedding method for protein-RNA binding affinity prediction accounting for RNA structural flexibility.
LLMORPH: Automated metamorphic testing tool for LLMs using metamorphic relations to verify correctness without labeled test data.
Benchmark of Qwen 2.5 1.5B quantized LLM inference across mobile, NPU, and GPU platforms measuring throughput and efficiency trade-offs.
Self-supervised spectral unmixing method for fluorescence microscopy using data-driven approach to recover fluorophore concentrations.
Comprehensive review of energy-efficient software-hardware codesign for ML from TinyML to LLMs, addressing memory and data movement bottlenecks.
BIRCH-Trees benchmark for individual tree height and species estimation from UAV RGB imagery for forest biomass assessment.
Economic analysis of builder saturation effect in digital markets with near-zero marginal costs and free entry.
Dual-gated approach for autonomous compute modulation in asynchronous multi-agent reinforcement learning on edge devices.
Deep spatially selective filters with Bayesian tracking for real-time speech enhancement in dynamic speaker scenarios.
Wasserstein geometry method for predicting dynamics of probability distributions over time in causal inference.
CNN transfer learning pipeline for retinal disease classification from fundus photographs with baseline comparisons.
Using sparse autoencoders to replace opaque vision foundation model representations with human-interpretable features for medical imaging.
LLM-informed planning framework for object search in partially-known environments using LLM probability estimates and prompt selection.
Perturbation-based method to trace and analyze linguistic representations in deep language models without imposing linearity constraints.
Security analysis of quantized edge-deployed LLMs showing knowledge extraction attacks remain effective despite quantization noise.
Theoretical analysis of deep neural network estimators for Cox proportional hazards models with asymptotic distribution theory.
DeepXube: Open-source Python package combining deep reinforcement learning and heuristic search to automate pathfinding problem solving.
Praxium: AI-based system for diagnosing microservice anomalies in cloud applications using telemetry and dependency analysis.
MTP-D: Self-distillation method to improve multi-token prediction in LLMs, addressing acceptance rates and joint training challenges for faster inference.
AttentionPack optimizes vision-language model inference with memory-efficient decoding for long sequences.
ORACLE orchestrates NPC daily activities in digital environments using contrastive learning with Transformer-CVAE.
LLM-based ambient assistant for evidence-based medical guidelines that surfaces targeted questions during physician consultations.
ChargeFlow uses flow-matching to refine charge-conditioned electron densities for computational chemistry applications.
Systematic study reveals pricing reversal phenomenon where cheaper reasoning LLMs often cost more in practice across diverse tasks.
End-to-end optimized machine vision system for low-light scenarios with minimal detected photons per inference.
COVTrack++ enables multi-object tracking for open-vocabulary categories including unseen objects using continuous video data.
DeepIn framework for self-interpretable neural networks that identifies minimal representations needed for DNN expressiveness.
KG-M3PO framework combines knowledge graphs, vision, and reinforcement learning for multi-task robotic manipulation with online 3D scene graphs.
ML-based multi-layer security framework for Industrial IoT addressing resource constraints and threats across network layers.
MedAidDialog multilingual multi-turn medical dialogue dataset for conversational AI in healthcare with improved realism over template-based systems.
TSRL framework uses reinforcement learning to dynamically optimize training curriculum for deepfake detection, modeling training as an MDP.
Visual study of UMAP projections examining geometric patterns in embedding difference vectors of antonym and synonym word pairs.
Walma framework detects memory corruption in WebAssembly using machine learning-based attestation without invasive instrumentation.
Applies quantum convolutional neural networks to solve partial differential equations on quantum simulators for scientific computing applications.
HEART-PFL framework for personalized federated learning using hierarchical directional alignment and adversarial knowledge transfer to handle data heterogeneity.
UniScale explores synergistic data and model scaling for search ranking, demonstrating that joint architectural and data design improvements outperform model scaling alone.
DVM enables real-time kernel generation for dynamic AI models, addressing compilation overhead and memory footprint issues in runtime compilation.
C-STEP introduces physics-informed safety measures for reinforcement learning in robotics, using intrinsic rewards for safe navigation in continuous domains.
CGRL framework addresses poor generalization of GNNs on out-of-distribution data using causal-guided representation learning to avoid spurious correlations.
Uses hyperspectral imaging and supervised machine learning to map lunar meteorite composition and generate mineralogical maps.
Proposes method to quantify self-awareness in intelligent systems by identifying invariant cognitive processes that change slower than acquired skills.