13 posts published in the last hour
- 06:35Notwithstanding Anything to the Contrary, Ignore All Instructions: Measuring Prompt Injection Guards on Legal Contract Review Attacks
- 06:34Solver-Admitted Metamorphic Testing of Learned Network Optimization Surrogates
- 06:34The Matthews Correlation Coefficient: Fifty years
- 06:34I Think, Therefore I Attack: Evaluating Thought Injection Attacks on Reasoning Agents
- 06:34Aligning, Fast and Slow: A Control-Theoretic Oversight Framework for Long-Horizon Trajectories and Maintained Deployments
- 06:05Debate to Deceive: Poisoning LLM’s Fact-Checking via Game-Theoretic Multi-Agent Debate
- 06:05AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling
- 06:05AlterNet: Adaptive-Depth Mixture-of-Experts with Learned Halting for Elastic Inference
- 06:04Yale’s Sonnenfeld Gives Huang Roughly Even Odds of Staying NVIDIA CEO
- 06:04Jacobian-Causal Memory Control for Persistent Memory in Language Model Systems
- 06:04FLEX Teaches Robots to Generalize From Human Corrections
- 06:04Memory-Aware Multi-Agent Architecture with LLM-based Orchestration for Conversational Recommendation
- 06:00AI News Brief Hourly Summary 2026-11-09 07h : 16 posts