10 Ways to Use Embeddings for Tabular ML Tasks
Embeddings — vector-based numerical representations of typically unstructured data like text — have been primarily…
Category: Machine Learning
MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE
The generation quality of large language models (LLMs) is often improved by utilizing inference-time sequence-level…
Over-Searching in Search-Augmented Large Language Models
Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval. However, they…
Multivariate Conformal Prediction using Optimal Transport
Conformal prediction (CP) quantifies the uncertainty of machine learning models by constructing sets of plausible…
DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search
Multimodal Large Language Models (MLLMs) in real-world applications require access to external knowledge sources and…
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold…
Signals for 2026
We’re three years into a post-ChatGPT world, and AI remains the focal point of the…
3 Questions: How AI could optimize the power grid
While the growing energy demands of AI are worrying, some techniques can also help make…
Inferring Optical Tissue Properties from Photoplethysmography using Hybrid Amortized Inference
Smart wearables enable continuous tracking of established biomarkers such as heart rate, heart rate variability,…
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…