Phasor Attention: Mean Root Square Normalization for Phase Manifold Preservation
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Vis2Reg: Visibility-Aware Landmark-Free Geometric 3D--2D Registration for Liver Laparosco…
Multi-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis…
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LL…
Lyapunov Stability-Aware Stackelberg Game for Low-Altitude Economy: A Control-Oriented Pr…
O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Bia…
Enhancing Rubric-based RL via Self-Distillation
SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs
Anticipate Before Acting: Future-State-Conditioned Vision-Language Navigation
Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query G…
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasonin…
HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
Harness Engineering for LLM-Driven GPU Kernel Generation
Topological Signatures of Context-Level Reliability in TabPFN
RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Control
A Geometric Perspective on Stabilizing Value Conflict Resolution
The Art of Not Forgetting
TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization
Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices
LLMs and Agentic AI Systems for Smart Grids: A Tutorial on Architectures and Applications
CommitLLM: A Fine-Tuned Pipeline for Git Commit Message Generation
Thinking in Video: Can Video Generators Really Reason About the Real World?
One-step lowest-variance selection in a Gaussian random-field model motivated by masked d…
ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video
Retrieval-Augmented Interpretable Learning: Towards Task-Specific Zero-Shot Models in Hea…
SALT: Salience-Aware Lexical Trie for Long-Context Compression
Multilingual Sentence Embeddings for Linguistic-Integrated Reliability Audit
HyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in …