13 posts published in the last hour
- 07:33GUARD: Natural Forgetting in Large Reasoning Models via Guided Answer-Reasoning Distillation
- 07:33Listen Before You Speak: Response Planning from Listener Facial Reactions for Conversational Speech Generation
- 07:32World Modeling in Transformers
- 07:32LLM-Generated Feature Pools for Time Series Anomaly Detection
- 07:32Best Voice Cloning APIs in 2026: Speaker Similarity, Consent Checks, and Price per 1M Characters
- 07:32ECG Mirage: Revealing and Mitigating the Underutilisation of ECGs in Vision-Language Models for Clinical Prediction
- 07:03Accelerating Dense LLMs via L0-regularized Mixture-of-Experts
- 07:03Beyond Accuracy: Centroid-Guided Contrastive Loss for Structured Fraudulent Job Posting Detection
- 07:03Calibrating Teacher–Student Discrepancy for On-Policy Distillation
- 07:03One Prompt Does Not Fit All: Self-Meta-Evolve for Personalized Information Extraction
- 07:03StepFun Launches Step 5 Preview: A 600B-Total, 27B-Active MoE Model With 1M Context for Long-Horizon Agentic Work
- 07:03Reducing Barriers to Academic Support: Evaluating a Course-Specific RAG System for Addressing Help-Seeking Disparities in Higher Education
- 07:00AI News Brief Hourly Summary 2026-09-21 09h : 10 posts