News
From Where Things Are to What They're For: Benchmarking Spatial'Functional Intelligence for Multimodal LLMs - Apple Machine Learning Research
7+ hour, 3+ min ago (330+ words) From Where Things Are to What They're For: Benchmarking Spatial'Functional Intelligence for Multimodal LLMs'Apple Machine Learning Research From Where Things Are to What They're For: Benchmarking Spatial'Functional Intelligence for Multimodal LLMs True spatial intelligence for multimodal agents transcends low-level geometric…...
Normalizing Flows with Iterative Denoising
6+ hour, 57+ min ago (125+ words) Apple Machine Learning Research Normalizing Flows with Iterative Denoising Authors Tianrong Chen, Jiatao Gu, David Berthelot, Joshua Susskind, Shuangfei Zhai Related readings and updates. STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis June 30, 2025research area Computer Vision, research area Methods…...
La Di R: Latent Diffusion Enhances LLMs for Text Reasoning
1+ week, 1+ day ago (134+ words) Authors Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang, Nicklas Majamaki, Navdeep Jaitly, Yi-An Ma, Lianhui Qin Thinking into the Future: Latent Lookahead Training for Transformers March 25, 2026research area Methods and Algorithms Workshop at ICLR This paper was accepted at the Workshop…...
Para RNN: Large-Scale Nonlinear RNNs, Trainable in Parallel
1+ week, 6+ day ago (757+ words) To accelerate research in efficient sequence modeling and enable researchers and practitioners to explore new nonlinear RNN models at scale, the Para RNN codebase has been released as an open-source framework for automatic training-parallelization of nonlinear RNNs. The computational cost…...
Apple Machine Learning Research at ICLR 2026
2+ week, 16+ hour ago (461+ words) Apple researcher Stephan Richter presenting at ICLR 2025. During exhibition hours, attendees will be able to experience demonstrations of Apple's ML research in our booth #204, including local LLM inference on Apple silicon with MLX and Sharp Monocular View Synthesis in Less…...
Can Large Language Models Understand Context?
2+ week, 1+ day ago (309+ words) Apple Machine Learning Research Can Large Language Models Understand Context? Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of…...
La Cy: What Small Language Models Can and Should Learn is Not Just a Question of Loss
3+ week, 6+ day ago (149+ words) This paper was accepted at the Workshop on Memory for LLM-Based Agentic Systems at ICLR. Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential August 8, 2025research area Methods and Algorithms, research area Speech and Natural Language Processing October 29, 2024research area Methods…...
A Theoretical Framework for Acoustic Neighbor Embeddings
3+ week, 6+ day ago (250+ words) Apple Machine Learning Research A Theoretical Framework for Acoustic Neighbor Embeddings This paper provides a theoretical framework for interpreting acoustic neighbor embeddings, which are representations of the phonetic content of variable-width audio or text in a fixed-dimensional embedding space. A…...
Pro Text: A Benchmark Dataset for Measuring (Mis)gendering in Long-Form Texts
1+ mon, 6+ day ago (103+ words) August 7, 2024research area Speech and Natural Language Processingconference ACL This paper was accepted at the Workshop on Gender Bias in Natural Language Processing 2024. Machine translation (MT) systems often translate terms with ambiguous gender (e. g. , English term "the nurse) into the gendered form…...
Entropy-Preserving Reinforcement Learning
1+ mon, 1+ week ago (284+ words) machinelearning. apple. com Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative solutions. As we…...