Pretraining with Hierarchical Memories: Separating Long-Tail and Common Knowledge
The impressive performance gains of modern language models currently rely on scaling parameters: larger models…
Category: Machine Learning
Which Evaluation for Which Model? A Taxonomy for Speech Model Assessment
Speech foundation models have recently achieved remarkable capabilities across a wide range of tasks. However,…
AdaBoN: Adaptive Best-of-N Alignment
Recent advances in test-time alignment methods, such as Best-of-N sampling, offer a simple and effective…
AgentBuilder: Exploring Scaffolds for Prototyping User Experiences of Interface Agents
Interface agents powered by generative AI models (referred to as “agents”) can automate actions based…
Decoding the Arctic to predict winter weather
With the help of AI, MIT Research Scientist Judah Cohen is reshaping subseasonal forecasting, with…
Gmail is entering the Gemini era
Learn more about the next era of Gmail, now using Gemini 3 and Personal Intelligence.
The End of the Sync Script: Infrastructure as Intent
There’s an open secret in the world of DevOps: Nobody trusts the CMDB. The Configuration…
AI and the Next Economy
The narrative from the AI labs is dazzling: build AGI, unlock astonishing productivity, and watch…
NarrativeTrack: Evaluating Video Language Models Beyond the Frame
Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability…
Improving User Interface Generation Models from Designer Feedback
Despite being trained on vast amounts of data, most LLMs are unable to reliably generate…