SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearni…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Clinician-Friendly Foundation Models for Ophthalmic Image Diagnostics without Fine-Tuning…
Formation of structural attractors in neuromorphic systems
When Tools Hurt LLM Reasoning: State-Dependent Belief Revision under External Evidence
Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Mai…
We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consc…
Analysis of Respiratory Sinus Arrhythmia with Neural Networks
Input-to-State Stability Framework for Fully Distributed Primal-Dual Dynamics for Quadrat…
Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generat…
Positional Encoding via Token-Aware Phase Attention
An Agent Model Abstraction for Human-AI Teaming Cognitive Coupling
ViT3Flow: A Test-Time Training Transformer MeanFlow for Postoperative Radiograph Synthesi…
Adaptive Cost-Sensitive Machine Learning for Autonomous Robot Navigation Failure Predicti…
Towards Embodied Air-Ground Cooperative Object Search: Benchmark, Dataset and Agentic Met…
SSP-DMGTimeNet: Physics-Constrained Learning for Spatiotemporal Trajectory Prediction of …
RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context Serving
Dual-Latent Memory Routing for Vision-Language Reasoning
Closed-Loop Evaluation of Bird's-Eye-View Maps from Cross-View Transformers as Inputs to …
Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review Budgets
EEG-Driven Decoding Framework for Passenger Hazard Perception in Highly Automated Vehicles
Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging
Full-Page Optical Music Recognition of Handwritten Monophonic Scores
Fine-Grained Instruction-Guided Graph Reasoning for Vision-and-Language Navigation
ChatBEV: Empowering Traffic Scene Understanding and Simulation via Vision-Language Model
S$^3$F-Net: A Multi-Modal Approach to Medical Image Classification via Spatial-Spectral S…
ProToMEx: Rapid, Interpretable Explanations via Structured Representations
Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpretin…
CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Ge…
Diffusion models for eye-gaze trajectory generation using position and velocity represent…
Data-driven rational function neural networks: a new method for generating analytical mod…