17 posts published in the last hour
- 22:32RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning
- 22:32MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection
- 22:32Advancing Coding in Low-Resource Programming Languages
- 22:32AWAM: Active Trajectory-Conditioned View Imagination for Robust Robot Manipulation
- 22:32Microsoft says AI agents are like insider threats as ‘frontier models can’t be trusted’
- 22:32Designing for Imperfect Prompts: A Simulation-Based Evaluation of an LLM-Based Enterprise Data Assistant Using Knowledge Graphs
- 22:32MiniMax launches M3.1 Flash model, says it cuts AI agent costs by 70%
- 22:32Language Models Learn to Improve Language Models
- 22:10AI News Brief Roundup: 2026-10-19 Evening
- 22:04FlashReFocus: Interactive Image Refocusing in Seconds
- 22:04Beyond Marginal Influence: Interaction-Aware Memory Selection for LLM Agents
- 22:04qGAMMA: A Framework for Optimal DNN Mapping on Multi-Precision Accelerators
- 22:04Microsoft could hold an advantage with Copilot for Legal
- 22:04MGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning
- 22:03The fossil fuel comeback is here
- 22:03Preventing Data Hallucinations in Agentic AI for Optical Network Troubleshooting
- 22:00AI News Brief Hourly Summary 2026-10-20 00h : 14 posts