Evaluating Evaluation Metrics — The Mirage of Hallucination Detection
Hallucinations pose a significant obstacle to the reliability and widespread adoption of language models, yet…
Category: Machine Learning
Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices
Fine-tuning large language models (LLMs) with backpropagation — even for a subset of parameters such…
Inductive Domain Transfer In Misspecified Simulation-Based Inference
Simulation-based inference (SBI) is a statistical inference approach for estimating latent parameters of a physical…
Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?
This paper was accepted at the Evaluating the Evolving LLM Lifecycle Workshop at NeurIPS 2025.…
ODKE+: Ontology-Guided Open-Domain Knowledge Extraction with LLMs
Knowledge graphs (KGs) are foundational to many AI applications, but maintaining their freshness and completeness…
PrimeX: A Dataset of Worldview, Opinion, and Explanation
As the adoption of language models advances, so does the need to better represent individual…
Introducing vibe coding in Google AI Studio
Introducing vibe coding in Google AI Studio
Bias after Prompting: Persistent Discrimination in Large Language Models
A dangerous assumption that can be made from prior work on the bias transfer hypothesis…
Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping
We revisit scene-level 3D object detection as the output of an object-centric framework capable of…
New updates and more access to Google Earth AI
Earth AI is helping enterprises and cities with everything from environmental monitoring to disaster response.