15 posts published in the last hour
- 12:36AdaTutor: Adaptive Tutoring through Pedagogical Strategy Selection
- 12:36SlowLab: Benchmarking Autonomous AI Agents on a Year of Experiments They Cannot Undo
- 12:36InferPriv: Evaluating Inferential Privacy Leakage in LLM Assistants
- 12:36The Next Battle in SaaS Starts Above MCP
- 12:35Hierarchical Task Network planning in the Goal Lifecycle
- 12:35IBM and Kaggle Partner on Continuous ScarfBench Migration Leaderboard
- 12:35Curriculum-Guided Acquisition of Hierarchical Task Knowledge from LLM-Generated Experience
- 12:08Rethinking Verification in Agent Harnesses
- 12:08CSI-TextBench: A Dataset and Benchmark for Language-Grounded Ambient Sensing Perception
- 12:07Google Gemini Omni: What It Actually Does, What It Costs, and How It Compares
- 12:07A Battery for AI Propensity Measurement: Rubrics, Synthetic Item Banks, and Annotations
- 12:07OpenAI’s partner content arrives in ChatGPT pre-summarized while the rest of the web gets raw scraps
- 12:07One Mean Log-Mel Vector per Phoneme: Simple and Fast Text Injection for Speech Recognition
- 12:06Industrial Intelligence: The next growth opportunity for manufacturing
- 12:06HobbyLM: A Sparse Mixture-of-Experts Model Family on a Hobby Budget