Quantitative model predicting when independently fine-tuned specialist LLMs can be fused post-hoc for improved performance using divergence metric.
Method addressing over-fragmentation in video object-centric learning through reconstruction-guided slot curriculum training approach.
Retrospective study using continuous AI monitoring to measure bed and chair fall rates in healthcare settings over exposure time.
Research on whether LLMs' step-by-step reasoning is genuinely used or post-hoc narrative generation through step-level evaluation of frontier models.
arXiv paper on brain-inspired object detection co-design. Algorithm-architecture optimization for CLIP-based task-oriented detection on edge devices.
arXiv paper analyzing hierarchical reasoning models for LLMs. Mathematical theory of recursive networks for algorithmic reasoning.
arXiv paper on off-policy evaluation for survival outcomes with censored data. Applied ML research for decision-making systems.
arXiv paper on black-box domain adaptation using dual-teacher distillation. Technical ML research on knowledge transfer without source access.
Computer vision method integrating expert eye gaze trajectories into transformer models for improved chest X-ray classification in radiology.
Human-AI co-design approach for privacy-preserving transformation of electronic health records using geometric operators to enable secure data sharing.
Novel stepwise variational inference method using vine copulas for estimating complex latent dependencies in probabilistic models.
Dataset and harm-aware model for Dari-language misinformation detection on YouTube with information type and harm level annotations.
Critical review framework evaluating membership inference attacks and conditions under which they pose genuine privacy threats to ML models.
Investigation of LLMs' reasoning and optimization capabilities under physical and operational constraints using Optimal Power Flow problems.
Object detection framework combining YOLOv10 with Kolmogorov-Arnold networks and vision-language models for interpretability.
Generative AI approach for lung CT synthesis across full Hounsfield Unit range to address medical imaging data scarcity.
Framework for model evaluation analyzing performance and reliability trade-offs when target KPI levels are unknown.
Zero-shot late fusion method combining audio-language models with specialist models for speech emotion recognition.
Systematic literature review of machine learning approaches for early detection of burnout in software engineers.
Scalable foundation model for automated knowledge graph generation from scientific literature using domain-specific optimization.
Active learning method leveraging vision-language foundation models for data-efficient visual recognition.
Safety monitoring approach for LLMs using activation watermarking to detect adaptive adversarial attacks during inference.
Method for weighted conformal anomaly detection under distribution shifts in low-data regimes.
Evaluation of LLMs' ability to mimic authorial styles of literary and political figures using zero-shot prompting.
Framework for sharing memory systems across heterogeneous LLM-based agents via contrastive trajectory distillation to improve knowledge reuse.
Study evaluating whether six LLMs can emulate emotional expression and personality traits across English and Arabic languages.
Research on query-efficient jailbreak fuzzing for LLMs that identifies token importance during prompt mutation to reduce redundant searching under query constraints.
Perceptual optimization strategies for 3D Gaussian Splatting using distortion losses validated via large-scale human evaluation.
Information-theoretic analysis of contextual graph matching with correlated Gaussian features deriving recovery thresholds.
ARGENT: vision-language model using hyperbolic geometry to capture hierarchical structure of visual and linguistic concepts.
Supervised contrastive metric learning for point cloud segmentation in particle detectors using density-based clustering.
VTAM: video-tactile-action model for embodied AI combining visual and tactile signals for contact-rich physical interaction.
VISOR: efficiency method for vision-language models using sparse dynamically selected interactions instead of visual token reduction.
Data-driven and empirical formula models to quantify momentum in competitive tennis matches.
ML model for virtual screening in drug discovery handling out-of-distribution regions with extrapolatory pseudo-label matching.
Minimal Frame Averaging: framework for constructing provably minimal frames achieving exact equivariance in ML systems efficiently.
Continuous action representation for 3D floorplanning addressing scalability bottlenecks from discrete canvas coordinates.
Convergence analysis of linear temporal difference learning in reinforcement learning without requiring linearly independent features.
HFLDD: hybrid federated learning framework using dataset distillation to address non-IID data heterogeneity and label distribution skew.
DART-Eval: benchmark for evaluating DNA language models on regulatory DNA prediction, interpretation and design tasks.
MSA-CNN: lightweight multi-scale CNN with attention mechanism for automatic sleep stage classification from signal data.
BalanceKV: streaming algorithm for approximating attention computations in LLMs using geometric process to reduce memory requirements for long-context generation.
Federated learning approach for designing data-driven feedforward control in vehicle lateral dynamics using distributed data across multiple systems.
Expectation Reflection: multiplicative parameter update paradigm for ML optimization using observation-prediction ratios instead of additive gradient descent.
Analysis of geometric properties and flatness in neural architecture search spaces.
Information-theoretic framework for characterizing and measuring information leakage in concept-based models.
Federated LoRA fine-tuning method for large language models with communication-efficient sparsified updates.
Meta-optimization approach for generating generalizable heuristics using LLMs for combinatorial optimization.
Multi-experiment equation learning method for deriving analytical models from agent-based simulation data.
State representation learning from trajectories using minimum action distance metric for MDPs.