15 posts were published in the last hour
- 18:32 : Same physical state, different collective dynamics: state encodings select synchronization outcomes in language-model agents
- 18:32 : PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue
- 18:32 : Expanding Daybreak as the Cyber Defense Window Narrows
- 18:32 : HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses
- 18:32 : Old OCR text cripples language model training, and FineBooks wants to fix that at scale
- 18:32 : Density-aware Hierarchical Clustering Based on Element-Categorized Connection Subgraphs
- 18:32 : OpenAI Expands Daybreak With Two Tiers and a New Cybersecurity Model
- 18:32 : GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base
- 18:3 : Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning
- 18:3 : Ask-E: An Environment for Calibrated Question Generation
- 18:3 : MaskFlow: Precise, Consistent and Seamless Regional Image Editing
- 18:3 : Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression
- 18:3 : OpenAI launches GPT-5.6-Cyber to help defenders find vulnerabilities before attackers do
- 18:3 : Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests
- 18:0 : AI News Brief Hourly Summary 2026-08-10 20h : 17 posts