AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A C…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Diagnosing Temporal Misalignment in Multichannel Time-Series Classification with Minimum …
Ensemble Complexity in Photovoltaic Forecasting
Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for …
Calibrating Interpretability Instruments Before Trusting Their Verdicts
A property-registry contract for retrieve-or-refuse thermal-mechanical lattice search
From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Imag…
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions…
TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root …
Loop-Back Authority in LLM Agent Teams: A Paired Experiment on Flat and Hierarchical Coor…
SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU Outs…
RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction
SeqMaestro: From nucleotide sequences to biological hypotheses through interpretable mach…
Semantic Fibers and Cross-Gram Interference: A Calculus of Safety Drift in Overcomplete R…
CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation…
Neural-Network Solutions to Real-Space Charge Density and Generalization
Steering Generative Robot Policies with Lexicographic Preferences
LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Fi…
Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Inte…
On the role of the tokenizer in ECG transformer models
Physics Informed Neural Network model for the dynamical study of Abdominal Aortic Aneurysm
One Spectrum, Two Resources: Data-Memory Scaling in Autoregressive Prediction
Trustworthy, Explainable, and Sustainable Decentralized Intelligence for 6G Networks
AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference
LePlanner: An Iterative Amortized Controller For World Models
Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Perso…
MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
Legislating World-Model-Based Planning with Legal Reasoning
EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse
Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering