The 2R-Conjecture for the Hegselmann--Krause Model: A Proof in Expectation and New Directions
arxiv.org·2d
✨Model optimizations in LLMs
BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation
arxiv.org·4d
🧠Large Language Models (LLMs)
Improving the Speaker Anonymization Evaluation's Robustness to Target Speakers with Adversarial Learning
arxiv.org·2d
🧠Large Language Models (LLMs)
DualPhys-GS: Dual Physically-Guided 3D Gaussian Splatting for Underwater Scene Reconstruction
arxiv.org·2d
🔢Quantization of LLMs
ViMoNet: A Multimodal Vision-Language Framework for Human Behavior Understanding from Motion and Video
arxiv.org·2d
🧠Large Language Models (LLMs)
Age of Information Minimization in Goal-Oriented Communication with Processing and Cost of Actuation Error Constraints
arxiv.org·4d
✨Model optimizations in LLMs
Accelerating exoplanet climate modelling: A machine learning approach to complement 3D GCM grid simulations
arxiv.org·1d
⚙️AI Infrastructure Automation
Inclusive Employment Pathways: Career Success Factors for Autistic Individuals in Software Engineering
arxiv.org·2d
⚙️AI Infrastructure Automation
Multimodal AI Systems for Enhanced Laying Hen Welfare Assessment and Productivity Optimization
arxiv.org·4d
📊AI Performance Profiling
From Explainable to Explanatory Artificial Intelligence: Toward a New Paradigm for Human-Centered Explanations through Generative AI
arxiv.org·5d
⚙️AI Infrastructure Automation
CROP: Integrating Topological and Spatial Structures via Cross-View Prefixes for Molecular LLMs
arxiv.org·4d
🧠Large Language Models (LLMs)
Deep Reinforcement Learning with Local Interpretability for Transparent Microgrid Resilience Energy Management
arxiv.org·4d
⚙️AI Infrastructure Automation
Ethics2vec: aligning automatic agents and human preferences
arxiv.org·4d
📊AI Performance Profiling
Med-GRIM: Enhanced Zero-Shot Medical VQA using prompt-embedded Multimodal Graph RAG
arxiv.org·4d
🧠Large Language Models (LLMs)
EchoAid: Enhancing Livestream Shopping Accessibility for the DHH Community
arxiv.org·4d
🔍Retrieval-augmented generation
How Does a Virtual Agent Decide Where to Look? - Symbolic Cognitive Reasoning for Embodied Head Rotation
arxiv.org·3d
🧠Large Language Models (LLMs)
MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography
arxiv.org·2d
🔍Retrieval-augmented generation
Realtime Multimodal Emotion Estimation using Behavioral and Neurophysiological Data
arxiv.org·2d
⚡Real-time AI Systems
Assessing Engineering Student Perceptions of Introductory CS Courses in an Indian Context
arxiv.org·4d
🧠Large Language Models (LLMs)
AI Security Map: Holistic Organization of AI Security Technologies and Impacts on Stakeholders
arxiv.org·3d
📊AI Performance Profiling