zetabyte

​[[{“value”:”Tokenizer design significantly impacts language model performance, yet evaluating tokenizer quality remains challenging. While text compression has emerged as a common intrinsic metric, recent work questions its reliability as a quality indicator. We investigate whether evaluating tokenizers on smaller models (350M parameters) reliably predicts their… Read More »Beyond Text Compression: Evaluating Tokenizers Across Scales Apple Machine Learning Research

​Vision foundation models pre-trained on massive data encode rich representations of real-world concepts, which can be adapted to downstream tasks by fine-tuning. However, fine-tuning foundation models on one task often leads to the issue of concept forgetting on other tasks. Recent methods of robust fine-tuning… Read More »Proxy-FDA: Proxy-Based Feature Distribution Alignment for Fine-Tuning Vision Foundation Models Without Forgetting Apple Machine Learning Research

​[[{“value”:”Recent generations of frontier language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their fundamental capabilities, scal- ing properties, and limitations remain insufficiently understood. Current evaluations primarily fo- cus… Read More »The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity Apple Machine Learning Research

​[[{“value”:”Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. However, current training recipes often relying on datasets dominated by short annotations with minimal rationales. In this work, we show that training VLM on short answers leads to poor generalization… Read More »Improve Vision Language Model Chain-of-thought Reasoning Apple Machine Learning Research

​Perceptual voice quality dimensions describe key characteristics of atypical speech and other speech modulations. Here we develop and evaluate voice quality models for seven voice and speech dimensions (intelligibility, imprecise consonants, harsh voice, naturalness, monoloudness, monopitch, and breathiness). Probes were trained on the public Speech… Read More »Voice Quality Dimensions as Interpretable Primitives for Speaking Style for Atypical Speech and Affect Apple Machine Learning Research