Predicting LLM Safety Before Release by Simulating Deployment
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning
Stage-Aware Adaptation and Distribution Calibration for Subject-Driven Personalized Text-…
PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation
TACoS: Weakly Supervised Learning of Two-Dimensional Materials from Scribble Annotations …
ASFR-Net: Adversarial Alignment and Spatio-Frequency Refinement Network for Heterogeneous…
From Text to Parameters: Predicting Item Parameters from Embedding Regularization with Re…
A knowledge-augmented dataset of high-risk driving scenarios with LLM annotations for aut…
GeoProp: Grounding Robot State in Vision for Generalist Manipulation
AT-Attn: Temporal-Aware Cross-Attention for Longitudinal Multimodal Alzheimer's Disease D…
Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints
Navigating Hierarchy: Hyperbolic Learning on Brain Graphs for Disorder Diagnosis
An Hybrid Quantum-Classical Diffusion Model for Image Generation
Complexity-Budgeted, Interaction-Aware Interpretable Model for Tabular Data
Behavior Leverage Imbalance in Multi-Teacher On-Policy Distillation
TRACE-Seg3D: Counterfactual Context Auditing For Robust 3D Glioma Segmentation Under Inst…
Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Au…
Online Data Selection Is Implicit Alignment
SHTA: Semantic Hard Token Correction and Center Alignment for Semi-Supervised Medical Ima…
Multimodal Spatiotemporal-Frequency Fusion with Peak Enhancement for Cellular Traffic For…
Dissociating the Internal Representations of Sycophancy in LLMs
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
Whose fairness? Structural concentration in AI bias research
The yes-no bias of large language models reflects answer order and wording, not shifts in…
Most LLM Conformity Needs No Speaker: Measuring the Speaker-Free Floor in Peer-Pressure B…
Self-Review Reinforcement Learning (SRRL) with Cross-Episode Memory and Policy Distillati…
Rendering-Aware Bayesian 3D Gaussian Splatting with Native Uncertainty and Adaptive Compl…
aiAuthZ: Off-Host, Identity-Bound Authorization for AI Agents
Lean-Quantum: Toward AI-Assisted Formalization of Quantum Information