STAMP: Multi-pattern Attention-aware Multiple Instance Learning for STAS Diagnosis in Multi-center Histopathology Images
arxiv.org·5d
🔍Retrieval-augmented generation
Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval
arxiv.org·2d
🔍Retrieval-augmented generation
PPL: Point Cloud Supervised Proprioceptive Locomotion Reinforcement Learning for Legged Robots in Crawl Spaces
arxiv.org·6d
⚙️AI Infrastructure Automation
HyperKD: Distilling Cross-Spectral Knowledge in Masked Autoencoders via Inverse Domain Shift with Spatial-Aware Masking and Specialized Loss
arxiv.org·6d
🔢Quantization of LLMs
Structured Kernel Regression VAE: A Computationally Efficient Surrogate for GP-VAEs in ICA
arxiv.org·6d
🧠Large Language Models (LLMs)
Towards Spatially Consistent Image Generation: On Incorporating Intrinsic Scene Properties into Diffusion Models
arxiv.org·5d
🔍Retrieval-augmented generation
Unifying Scale-Aware Depth Prediction and Perceptual Priors for Monocular Endoscope Pose Estimation and Tissue Reconstruction
arxiv.org·2d
🔢Quantization of LLMs
VeriPHY: Physical Layer Signal Authentication for Wireless Communication in 5G Environments
arxiv.org·6d
🔧Systems-level optimizations for LLM serving
Improving the Speaker Anonymization Evaluation's Robustness to Target Speakers with Adversarial Learning
arxiv.org·6d
🧠Large Language Models (LLMs)
A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Reality
arxiv.org·6d
🔍Retrieval-augmented generation
Emergence of Hierarchies in Multi-Agent Self-Organizing Systems Pursuing a Joint Objective
arxiv.org·6d
🤖Agents using LLMs
Over-Squashing in GNNs and Causal Inference of Rewiring Strategies
arxiv.org·6d
🧠Large Language Models (LLMs)
DualPhys-GS: Dual Physically-Guided 3D Gaussian Splatting for Underwater Scene Reconstruction
arxiv.org·6d
🔢Quantization of LLMs
ViMoNet: A Multimodal Vision-Language Framework for Human Behavior Understanding from Motion and Video
arxiv.org·6d
🧠Large Language Models (LLMs)
Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interaction
arxiv.org·2d
⚡Real-time AI Systems
Feature Impact Analysis on Top Long-Jump Performances with Quantile Random Forest and Explainable AI Techniques
arxiv.org·6d
📊AI Performance Profiling
MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography
arxiv.org·6d
🔍Retrieval-augmented generation
Accelerating exoplanet climate modelling: A machine learning approach to complement 3D GCM grid simulations
arxiv.org·5d
⚙️AI Infrastructure Automation
Realtime Multimodal Emotion Estimation using Behavioral and Neurophysiological Data
arxiv.org·6d
⚡Real-time AI Systems
impuTMAE: Multi-modal Transformer with Masked Pre-training for Missing Modalities Imputation in Cancer Survival Prediction
arxiv.org·6d
📊AI Performance Profiling