Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Five Production LLMs
Research
Research News
New papers, breakthroughs and academic AI research
ANI: Adaptive Numerical Injection for Unifying Semantic and Arithmetic Representations in Numerical Reasoning
Research
Autoresearch in Mixed-Integer Linear and Nonlinear Programming
Research
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
Research
PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents
Research
SPROUT: A Scalable Diffusion Foundation Model for Multi-Crop Plant Phenotyping
Research
MiniRep: Robust Reputation-Based Aggregation for Multi-Agent Debate
Research
EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical Reasoning
Research
Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings
Research
From Image Interpretation to Clinical Reasoning: Upstream Physician-Context-Aware Multimodal Learning with Causal Reinforcement Learning
Research
LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly Detection
Research
On the Relaxation of Conditional Independence Assumption for Image Segmentation
Research