zetabyte

​[[{“value”:” Contrastive Language-Image Pre-training (CLIP) has become important for modern vision and multimodal models, enabling applications such as zero-shot image classification and serving as vision encoders in MLLMs. However, most CLIP variants, including Meta CLIP, are limited to English-only data curation, ignoring a significant amount… Read More »Meta CLIP 2: The First Contrastive Language-Image Pre-training (CLIP) Trained with Worldwide Image-Text Pairs from Scratch Sajjad Ansari Artificial Intelligence Category – MarkTechPost

​[[{“value”:” NVIDIA has unveiled a major milestone in scalable machine learning: XGBoost 3.0, now able to train gradient-boosted decision tree (GBDT) models from gigabytes up to 1 terabyte (TB) on a single GH200 Grace Hopper Superchip. The breakthrough enables companies to process immense datasets for… Read More »NVIDIA XGBoost 3.0: Training Terabyte-Scale Datasets with Grace Hopper Superchip Michal Sutter Artificial Intelligence Category – MarkTechPost

​While the last decade has witnessed significant advancements in Automatic Speech Recognition (ASR) systems, performance of these systems for individuals with speech disabilities remains inadequate, partly due to limited public training data. To bridge this gap, the 2025 Interspeech Speech Accessibility Project (SAP) Challenge was… Read More »The Interspeech 2025 Speech Accessibility Project Challenge Apple Machine Learning Research

​We introduce DiceHuBERT, a knowledge distillation framework for compressing HuBERT, a widely used self-supervised learning (SSL)-based speech foundation model. Unlike existing distillation methods that rely on layer-wise and feature-wise mapping between teacher and student models, DiceHuBERT leverages HuBERT’s iterative self-distillation mechanism by directly replacing the… Read More »DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective Apple Machine Learning Research

​Device-directed speech detection (DDSD) is a binary classification task that separates the user’s queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience. To this end, we propose knowledge distillation (KD) to enhance DDSD accuracy… Read More »Adaptive Knowledge Distillation for Device-Directed Speech Detection Apple Machine Learning Research

​Autoregressive language models are constrained by their inherently sequential nature, generating one token at a time. This paradigm limits inference speed and parallelism, especially during later stages of generation when the direction and semantics of text are relatively certain. In this work, we propose a… Read More »Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential Apple Machine Learning Research

​[[{“value”:” Reinforcement learning (RL) plays a crucial role in scaling language models, enabling them to solve complex tasks such as competition-level mathematics and programming through deeper reasoning. However, achieving stable and reliable training dynamics is a challenge when scaling RL with larger computational resources. Current… Read More »Alibaba Introduces Group Sequence Policy Optimization (GSPO): An Efficient Reinforcement Learning Algorithm that Powers the Qwen3 Models Sajjad Ansari Artificial Intelligence Category – MarkTechPost