16 posts published in the last hour
- 03:33MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs
- 03:33LegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery
- 03:33Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization
- 03:33SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation
- 03:32Google takes Dreambeans to India in bid to bring AI-generated personal stories to the masses
- 03:32Concordat: Typed Sessions for LLM Agents
- 03:05From Prediction to Action: Population Health World Model for Digital Medicine
- 03:05Preparing our next security sprint to harden OpenAI
- 03:05Self-Building Labs
- 03:05Zyphra AI Introduces Zyphra Hierarchical Attention (ZHA): A Path to True Subquadratic Attention
- 03:04AgentOrch: How Close Can Global Orchestration Come to Step-by-Step Interaction?
- 03:04Former Army Secretary Dan Driscoll Joins OpenAI as Senior Counselor
- 03:04Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors
- 03:03Rewarding defenders with bigger bug bounties
- 03:03Reject, Remember, Retry: Why Multi-Turn Attackers Should Remember Their Mistakes
- 03:00AI News Brief Hourly Summary 2026-11-03 04h : 15 posts