Memory Enhanced Fractional-Order Dung Beetle Optimization for Photovoltaic Parameter Identification
arxiv.org·1h
✨Model optimizations in LLMs
DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentation
arxiv.org·1h
🔢Quantization of LLMs
Pay What LLM Wants: Can LLM Simulate Economics Experiment with 522 Real-human Persona?
arxiv.org·6d
✨Model optimizations in LLMs
Why are LLMs' abilities emergent?
arxiv.org·5d
✨Model optimizations in LLMs
Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning
arxiv.org·5d
⚡Real-time AI Systems
Robust, fast, and adaptive splitting schemes for nonlinear doubly-degenerate diffusion equations
arxiv.org·1h
🔢Quantization of LLMs
Robust-Sub-Gaussian Model Predictive Control for Safe Ultrasound-Image-Guided Robotic Spinal Surgery
arxiv.org·1h
✨Model optimizations in LLMs
Multi-Hop Privacy Propagation for Differentially Private Federated Learning in Social Networks
arxiv.org·1h
🌐Distributed LLM Systems
RooseBERT: A New Deal For Political Language Modelling
arxiv.org·6d
✨Model optimizations in LLMs
LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
arxiv.org·6d
🔍Retrieval-augmented generation
VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning
arxiv.org·1d
🔢Quantization of LLMs
FoundBioNet: A Foundation-Based Model for IDH Genotyping of Glioma from Multi-Parametric MRI
arxiv.org·1h
🔍Retrieval-augmented generation
Unsupervised Real-World Super-Resolution via Rectified Flow Degradation Modelling
arxiv.org·1h
🔢Quantization of LLMs
Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success
arxiv.org·5d
⚡Real-time AI Systems
Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination
arxiv.org·4d
🔧Systems-level optimizations for LLM serving
Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
arxiv.org·1h
🤖Agents using LLMs
From Explainable to Explanatory Artificial Intelligence: Toward a New Paradigm for Human-Centered Explanations through Generative AI
arxiv.org·1d
⚙️AI Infrastructure Automation
Diagrams-to-Dynamics (D2D): Exploring Causal Loop Diagram Leverage Points under Uncertainty
arxiv.org·1d
✨Model optimizations in LLMs
DTPA: Dynamic Token-level Prefix Augmentation for Controllable Text Generation
arxiv.org·5d
🔍Retrieval-augmented generation
Learning to Reason for Factuality
arxiv.org·4d
💬Prompt optimizations for LLM serving