JMA: a General Algorithm to Craft Nearly Optimal Targeted Adversarial Example
arxiv.org·2d
🔢Quantization of LLMs
Time, Fences and the Ordering of Events in TSO
arxiv.org·2d
🔧Systems-level optimizations for LLM serving
Managing the unexpected: Operator behavioural data and its value in predicting correct alarm responses
arxiv.org·2d
📊AI Performance Profiling
Stochastic Modeling of Filtration with Sieving in Graded Pore Networks
arxiv.org·1d
⚙️AI Infrastructure Automation
Dataset Creation for Visual Entailment using Generative AI
arxiv.org·2d
🔍Retrieval-augmented generation
Quantization through Piecewise-Affine Regularization: Optimization and Statistical Guarantees
arxiv.org·2d
🔢Quantization of LLMs
Exploring the Tradeoff Between Diversity and Discrimination for Continuous Category Discovery
arxiv.org·2d
🔍Retrieval-augmented generation
ViPE: Video Pose Engine for 3D Geometric Perception
arxiv.org·2d
📊AI Performance Profiling
Tapas are free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments
arxiv.org·2d
🤖Agents using LLMs
Model Interpretability and Rationale Extraction by Input Mask Optimization
arxiv.org·2d
🧠Large Language Models (LLMs)
AgentMental: An Interactive Multi-Agent Framework for Explainable and Adaptive Mental Health Assessment
arxiv.org·2d
🤖Agents using LLMs
Inter-APU Communication on AMD MI300A Systems via Infinity Fabric: a Deep Dive
arxiv.org·2d
📊AI Performance Profiling
Visuomotor Grasping with World Models for Surgical Robots
arxiv.org·2d
⚙️AI Infrastructure Automation
Compositional Zero-shot Learning via Progressive Language-based Observations
arxiv.org·2d
🧠Large Language Models (LLMs)
A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous Driving
arxiv.org·2d
🔍Retrieval-augmented generation
Energy-Efficient Stochastic Computing (SC) Neural Networks for Internet of Things Devices With Layer-Wise Adjustable Sequence Length (ASL)
arxiv.org·6d
🔧Systems-level optimizations for LLM serving
Data-Efficient Learning for Generalizable Surgical Video Understanding
arxiv.org·5d
🧠Large Language Models (LLMs)
An Efficient Deep Learning Approach for Approximating Parameter-to-Solution Maps of PDEs
arxiv.org·2d
🔢Quantization of LLMs
Lightweight Attribute Localizing Models for Pedestrian Attribute Recognition
arxiv.org·2d
🔍Retrieval-augmented generation
A Real-time Concrete Crack Detection and Segmentation Model Based on YOLOv11
arxiv.org·2d
⚙️AI Infrastructure Automation