Low-Resource Safety Failures Are Action Failures, Not Representation Failures
Research
Research News
New papers, breakthroughs and academic AI research
Loss-Invariant Projections as Passive Probes of Learned Representations
Research
SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction
Research
ElasticMem: Latent Memory as a Learnable Resource for LLM Agents
Research
Bayesian Data Augmentation for DNN Retraining with Binomial Outcomes in Vision-Based UAV Landing
Research
Ultrasound Operator Guidance Using World Modeling and Retrieval Based Action Planning
Research
GO-Based Clustering for Learning Cluster-Level Causal Gene Regulatory Networks
Research
SoK: Semantic Decision Engines in Network Control Loops
Research
Flash-OPD: Fast On-Policy Distillation
Research
Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling
Research
ExpHarness: Model-Agnostic Experience Learning through a Trainable Harness
Research
Learning While Scheduling Jobs under Context-Dependent Service Rates: An Anytime Rate-Optimal Algorithm
Research