Traffic-Aware Randomized Smoothing for LLM-Based Network Intrusion Detection
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Learning Engagement Assistant (LEA): Cross-Course Scalability and Classroom Evaluation of…
Price of Fairness in Bandits: A Tight Minimax Characterization
Improving Text-to-Audio Instruction Following via Fine-Grained Feedback from Audio-Aware …
Can We Steer the Black-Box? Towards Controllability-Centric Evaluation of Recommender Sys…
ScanFocus: A Coarse-to-Fine Framework for Spatio-Temporal Video Grounding
Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Rel…
Learning Physics-Guided Residual Dynamics for Deformable Object Simulation
Symbiosis-Inspired Knowledge Distillation for Incremental Object Detection
GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding
DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments
DeepLoop: Depth Scaling for Looped Transformers
UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-a…
Spectral-Informed Neural Networks Outperform Spectral Methods in High-dimensional PDEs
GHR-VLM: Making Zero-Shot Transit Video Analytics Realizable with Grounded Hybrid Reasoni…
IMMNet: Hybrid Fusion of Model-based and Data-driven Approaches for Maneuvering Target Tr…
Agile perceptive multi-skill locomotion for quadrupedal robots in the wild
From Prediction to Collaboration: Interactive Symbolic Music Analysis
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilit…
Semantic Anchoring for Robotic Action Representations
The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account o…
OvisOCR2 Technical Report
Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction
Beyond Color Geometry: Evaluating Human-Like Color Representations in Vision Models
Barnamala: Parameter-Efficient Handwritten Devanagari Recognition at Benchmark Saturation
Social Simulations: from Agent-Based Modeling to Digital Twins
How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforce…
Anatomically Faithful but Temporally Blind: Auditing Attribution for Left-Ventricular Eje…
MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model