Ranking is a fundamental and popular problem in search. However, existing ranking algorithms usually restrict the granularity of ranking to…
Machine Learning
Entity disambiguation (ED), which links the mentions of ambiguous entities to their referent entities in a knowledge base, serves as…
Voice assistants increasingly use on-device Automatic Speech Recognition (ASR) to ensure speed and privacy. However, due to resource constraints on…
Large Language Models (LLMs) have demonstrated impressive capability in different tasks and are bringing transformative changes to many domains. However,…
*Equal Contributors Parameter-efficient fine-tuning (PEFT) for personalizing automatic speech recognition (ASR) has recently shown promise for adapting general population models…
Lamini AI has introduced a groundbreaking advancement in large language models (LLMs) with the release of Lamini Memory Tuning. This…
In large language model (LLM) training, effective orchestration and compute resource management poses a significant challenge. Automation of resource provisioning,…
This post is co-written with Shamik Ray, Srivyshnav K S, Jagmohan Dhiman and Soumya Kundu from Twilio. Today’s leading companies…
Temporal reasoning involves understanding and interpreting the relationships between events over time, a crucial capability for intelligent systems. This field…
In June 2024, Databricks made three significant announcements that have garnered considerable attention in the data science and engineering communities.…
Topological Deep Learning (TDL) advances beyond traditional GNNs by modeling complex multi-way relationships, unlike GNNs that only capture pairwise interactions.…
Game-Shaper-AI is an AI-based software tool that interacts with AI Game-engines to address the challenges faced in the game development…
One of the main challenges in current multimodal language models (LMs) is their inability to utilize visual aids for reasoning…
Modern software development often involves managing extensive codebases, ensuring code accuracy, maintaining comprehensive documentation, and optimizing performance. These tasks are…
In artificial intelligence, integrating large language models (LLMs) and speech-to-speech translation (S2ST) systems has led to significant breakthroughs. Two recent…
The deep learning revolution in computer vision has shifted from manually crafted features to data-driven approaches, highlighting the potential of…
Machine unlearning is a cutting-edge area in artificial intelligence that focuses on efficiently erasing the influence of specific training data…
The release of the Tulu 2.5 suite by the Allen Institute for AI marks a significant advancement in model training…
Graph neural networks (GNNs), referred to as neural algorithmic reasoners (NARs), have shown effectiveness in robustly solving algorithmic tasks of…
In machine learning, differential privacy (DP) and selective classification (SC) are essential for safeguarding sensitive data. DP adds noise to…