13 posts published in the last hour
- 02:32Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific Reasoning
- 02:32DynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents
- 02:32ProIQA: A Process-Based Framework for Fine-Grained Math Item Quality Assessment
- 02:32Orchestration and Execution: How JONI Approaches the Agent Layer
- 02:32The Troy Moment of AI: Why Some Will Cheat and Some Will Follow?
- 02:32Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking
- 02:31MANAS-2: Constrained Reconstruction for EEG Foundation Models
- 02:03Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model
- 02:03Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens
- 02:03API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces
- 02:03EdiTikZ: Scientific Figure Editing from Revision Trajectories
- 02:02BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents
- 02:00AI News Brief Hourly Summary 2026-09-17 04h : 17 posts