AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
Research
Research News
New papers, breakthroughs and academic AI research
SPARC: SuperPixel-Aware Region Contrastive Learning for Self-Supervised Dense Prediction
Research
Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
Research
Variational objectives for amortized Bayesian inference in inverse problems: The role of posterior conditioning
Research
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
Research
LLM-Anchored Paralinguistic Enrichment for Alzheimer's Disease Detection
Research
Text-only adaptation in LLM-based ASR through text denoising
Research
Distributed Legal Infrastructure for a Trustworthy Agentic Web
Research
Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMs
Research
Measuring the Creativity of Frontier LLMs in Automated Research
Research
Empirical Auditing of Edge-Private Graph Generators
Research
SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
Research