RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Governing Execution Risk in Agentic AI Systems: A Trajectory-Guided Framework for Red Tea…
A Trust-region Framework for Moment Estimation
Lindblad-Inspired Multi-Timescale Reservoir Computing with Separable Rotation and Dissipa…
Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign a…
NuclearDiffusion: Text-to-Image Foundation Models for Learning Nuclear Energy Concepts
CheckOne: Lightweight Fault Detection and Mitigation for Vision Transformers
AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection
Modality Agreement- and Conflict-Aware Prototype Hypergraph Learning for Multimodal Inten…
LaPrune: Controllable Differentiable Sparsity at Million Scale
An Inline Control Architecture for Language Models in Intelligent Transportation Systems
FBID: Adaptive Personalized Federated Learning for Robust Out-of-Distribution Attack Dete…
Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Tra…
Spatiotemporal Graph Transformer for Traffic Intelligence in Edge Computing
Interpretable Fuzzy Inference for UAV Target Tracking Using Bounding-Box Geometry
InvFlowFD: Reference-Free and Background-Set-Free Perceptual Music Quality Metric with Fl…
LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling
TRNet: Topography-Guided Frequency Rectification and Structure-Aware Decoding for Multimo…
Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills
Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction
Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary
Strategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical Systems
EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream Drift
MIDAS: Multi-LLM Iterative Data-Adaptive Summarization
Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
ATLAS: Adaptive Topological Learning with Abstract Successors for Continual Learning
Equitable System-Prompt Selection via Constrained Mixed-Strategy GroupDRO
HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework …
Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborativ…
FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation