SupportCal Introduces Label-Free Calibration to Fix Overconfidence in Post-Trained AI Models
A new research paper published on arXiv details SupportCal, a post-hoc calibration technique that reduces overconfidence in post-trained la…
5 min read
AI Models
Explainers and news about frontier AI models, architectures, and benchmarks.
Toollery Framework Promises Scalable Skill Selection for LLM Agents Without Heavy Prompt Costs
A research paper on arXiv introduces Toollery, a training-free candidate-compression framework designed to help large language model agents…
6 min read
Researchers Introduce BudgetMem, a Training-Free Selective Memory Architecture for Long Contexts
A new research paper introduces BudgetMem, a selective memory architecture that prunes long-context documents using interpretable chunk-lev…
6 min read
New Training-Free Framework RG-ICL Boosts Medical Image Analysis in Multimodal AI
Researchers have introduced representation-guided in-context learning, an inference framework that improves medical image interpretation in…
5 min read