News

Breaking News

Entertainment

Movies & Series

Music

Science & Technology

Sport

Business & Money

Education & Personal Development

Life

Culture & Art

Hobbies

News

Entertainment

Science & Technology

Sport

Business & Money

Education & Personal Development

Life

Culture & Art

Hobbies

home
›
Apple Machine Learning Research
›
Software

Apple Machine Learning Research - Software

8 | Follower

Apple Machine Learning Research

23.11.2024

Multimodal Autoregressive Pre-Training of Large Vision Encoders - Apple Machine Learning Research

*Equal Contributors A dominant paradigm in large multimodal models is to pair a large language de- coder with a vision encoder. While it is…

Apple Machine Learning Research

23.11.2024

Do Compressed LLMs Forget Knowledge? An Experimental Study with Practical Implications - Apple Machine Learning Research

This paper was accepted at the Machine Learning and Compression Workshop at NeurIPS 2024. Compressing Large Language Models (LLMs) often…

Apple Machine Learning Research

22.11.2024

Do LLMs Estimate Uncertainty Well in Instruction-Following? - Apple Machine Learning Research

This paper was accepted at the Safe Generative AI Workshop (SGAIW) at NeurIPS 2024. Large language models (LLMs) could be valuable personal…

Apple Machine Learning Research

22.11.2024

Do LLMs Internally "Know" When They Follow Instructions? - Apple Machine Learning Research

This paper was accepted at the Foundation Model Interventions (MINT) Workshop at NeurIPS 2024. Instruction-following is crucial for building…

Apple Machine Learning Research

22.11.2024

Faster Algorithms for User-Level Private Stochastic Convex Optimization - Apple Machine Learning Research

We study private stochastic convex optimization (SCO) under user-level differential privacy (DP) constraints. In this setting, there are nnn…

Apple Machine Learning Research

22.11.2024

Instance-Optimal Private Density Estimation in the Wasserstein Distance - Apple Machine Learning Research

Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein…

Apple Machine Learning Research

22.11.2024

Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization - Apple Machine Learning Research

Learning with identical train and test distributions has been extensively investigated both practically and theoretically. Much remains to…

Apple Machine Learning Research

22.11.2024

Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions - Apple Machine Learning Research

We study the problem of differentially private stochastic convex optimization (DP-SCO) with heavy-tailed gradients, where we assume a…

Apple Machine Learning Research

22.11.2024

Private Online Learning via Lazy Algorithms - Apple Machine Learning Research

We study the problem of private online learning, specifically, online prediction from experts (OPE) and online convex optimization (OCO). We…

Apple Machine Learning Research

21.11.2024

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum - Apple Machine Learning Research

Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by…

Apple Machine Learning Research

20.11.2024

Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning - Apple Machine Learning Research

This paper was accepted at the Self-Supervised Learning - Theory and Practice (SSLTP) Workshop at NeurIPS 2024. Image-based Joint-Embedding…

Apple Machine Learning Research

20.11.2024

Generalization on the Unseen, Logic Reasoning and Degree Curriculum - Apple Machine Learning Research

This paper considers the learning of logical (Boolean) functions with a focus on the generalization on the unseen (GOTU) setting, a strong…

Apple Machine Learning Research

20.11.2024

Towards Low-Bit Communication for Tensor Parallel LLM Inference - Apple Machine Learning Research

This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) Workshop at NeurIPS 2024. Tensor parallelism…

Apple Machine Learning Research

19.11.2024

Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models - Apple Machine Learning Research

This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) Workshop at NeurIPS 2024. Large Language Models…

Apple Machine Learning Research

19.11.2024

Recurrent Drafter for Fast Speculative Decoding in Large Language Models - Apple Machine Learning Research

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large…

Apple Machine Learning Research

13.11.2024

Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization - Apple Machine Learning Research

This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) Workshop at NeurIPS 2024. The pre-training phase of…

Apple Machine Learning Research

07.11.2024

Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval - Apple Machine Learning Research

Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription…

Apple Machine Learning Research

05.11.2024

Empirical Methods in Natural Language Processing (EMNLP) 2024 - Apple Machine Learning Research

Apple is presenting new research at the Empirical Methods in Natural Language Processing (EMNLP) conference, which takes place in person in…

Apple Machine Learning Research

05.11.2024

Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models - Apple Machine Learning Research

This paper was accepted at the Adaptive Foundation Models (AFM) workshop at NeurIPS Workshop 2024. Follow-up conversations with virtual…

Apple Machine Learning Research

05.11.2024

Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP - Apple Machine Learning Research

Large pretrained vision-language models like CLIP have shown promising generalization capability, but may struggle in specialized domains…

Apple Machine Learning Research

02.11.2024

On Device Llama 3.1 with Core ML - Apple Machine Learning Research

Many app developers are interested in building on device experiences that integrate increasingly capable large language models (LLMs)…

Apple Machine Learning Research

01.11.2024

Computational Bottlenecks of Training Small-Scale Large Language Models - Apple Machine Learning Research

This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) workshop at NeurIPS Workshop 2024. While large…

Apple Machine Learning Research

31.10.2024

Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs - Apple Machine Learning Research

Translating text that contains entity names is a challenging task, as cultural-related references can vary significantly across languages…

Apple Machine Learning Research

30.10.2024

ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA Datasets with Large Language Models - Apple Machine Learning Research

The rapid evolution of Large Language Models (LLMs) and conversational assistants necessitates dynamic, scalable, and configurable…

Apple Machine Learning Research

29.10.2024

Promoting Cross-Modal Representations to Improve Multimodal Foundation Models for Physiological Signals - Apple Machine Learning Research

Many healthcare applications are inherently multimodal, involving several physiological signals. As sensors for these signals become more…

Apple Machine Learning Research

27.10.2024

Smart Audit System Empowered by LLM - Apple Machine Learning Research

Manufacturing quality audits are pivotal for ensuring high product standards in mass production environments. Traditional auditing…

Apple Machine Learning Research

26.10.2024

Divide-or-Conquer? Which Part Should You Distill Your LLM? - Apple Machine Learning Research

Recent methods have demonstrated that Large Language Models (LLMs) can solve reasoning tasks better when they are encouraged to solve…

Apple Machine Learning Research

25.10.2024

Combining Machine Learning and Homomorphic Encryption in the Apple Ecosystem - Apple Machine Learning Research

At Apple, we believe privacy is a fundamental human right. Our work to protect user privacy is informed by a set of privacy principles, and…

Apple Machine Learning Research

24.10.2024

MUSCLE: A Model Update Strategy for Compatible LLM Evolution - Apple Machine Learning Research

Large Language Models (LLMs) are regularly updated to enhance performance, typically through changes in data or architecture. Within the…

Apple Machine Learning Research

24.10.2024

CtrlSynth: Controllable Image-Text Synthesis for Data-Efficient Multimodal Learning - Apple Machine Learning Research

Pretraining robust vision or multimodal foundation models (e.g., CLIP) relies on large-scale datasets that may be noisy, potentially…

Apple Machine Learning Research

24.10.2024

Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison - Apple Machine Learning Research

The goal of aligning language models to human preferences requires data that reveal these preferences. Ideally, time and money can be spent…

Apple Machine Learning Research

22.10.2024

Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement - Apple Machine Learning Research

The growing demand for personalized and private on-device applications highlights the importance of source-free unsupervised domain…

Apple Machine Learning Research

19.10.2024

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities - Apple Machine Learning Research

*Equal Contributors Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their…

Apple Machine Learning Research

17.10.2024

Scalable Private Search with Wally - Apple Machine Learning Research

This paper presents Wally, a private search system that supports efficient semantic and keyword search queries against large databases. When…

Apple Machine Learning Research

17.10.2024

Generalizable Autoregressive Modeling of Time Series Through Functional Narratives - Apple Machine Learning Research

Time series data are inherently functions of time, yet current transformers often learn time series by modeling them as mere concatenations…

Apple Machine Learning Research

17.10.2024

Progressive Entropic Optimal Transport Solvers - Apple Machine Learning Research

Optimal transport (OT) has profoundly impacted machine learning by providing theoretical and computational tools to realign datasets. In…

Apple Machine Learning Research

17.10.2024

CAMPHOR: Collaborative Agents for Multi-Input Planning and High-Order Reasoning On Device - Apple Machine Learning Research

While server-side Large Language Models (LLMs) demonstrate proficiency in tool integration and complex reasoning, deploying Small Language…

Apple Machine Learning Research

12.10.2024

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models - Apple Machine Learning Research

Recent advancements in Large Language Models (LLMs) have sparked interest in their formal reasoning capabilities, particularly in…

Apple Machine Learning Research

12.10.2024

Vision-Based Hand Gesture Customization from a Single Demonstration - Apple Machine Learning Research

Hand gesture recognition is becoming a more prevalent mode of human-computer interaction, especially as cameras proliferate across everyday…

Apple Machine Learning Research

10.10.2024

On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization - Apple Machine Learning Research

Reinforcement Learning from Human Feedback (RLHF) is an effective approach for aligning language models to human preferences. Central to…

home›Apple Machine Learning Research›Software

Apple Machine Learning Research - Software

Multimodal Autoregressive Pre-Training of Large Vision Encoders - Apple Machine Learning Research

Do Compressed LLMs Forget Knowledge? An Experimental Study with Practical Implications - Apple Machine Learning Research

Do LLMs Estimate Uncertainty Well in Instruction-Following? - Apple Machine Learning Research

Do LLMs Internally "Know" When They Follow Instructions? - Apple Machine Learning Research

Faster Algorithms for User-Level Private Stochastic Convex Optimization - Apple Machine Learning Research

Instance-Optimal Private Density Estimation in the Wasserstein Distance - Apple Machine Learning Research

Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization - Apple Machine Learning Research

Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions - Apple Machine Learning Research

Private Online Learning via Lazy Algorithms - Apple Machine Learning Research

Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum - Apple Machine Learning Research

Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning - Apple Machine Learning Research

Generalization on the Unseen, Logic Reasoning and Degree Curriculum - Apple Machine Learning Research

Towards Low-Bit Communication for Tensor Parallel LLM Inference - Apple Machine Learning Research

Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models - Apple Machine Learning Research

Recurrent Drafter for Fast Speculative Decoding in Large Language Models - Apple Machine Learning Research

Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization - Apple Machine Learning Research

Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval - Apple Machine Learning Research

Empirical Methods in Natural Language Processing (EMNLP) 2024 - Apple Machine Learning Research

Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models - Apple Machine Learning Research

Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP - Apple Machine Learning Research

On Device Llama 3.1 with Core ML - Apple Machine Learning Research

Computational Bottlenecks of Training Small-Scale Large Language Models - Apple Machine Learning Research

Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphs - Apple Machine Learning Research

ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA Datasets with Large Language Models - Apple Machine Learning Research

Promoting Cross-Modal Representations to Improve Multimodal Foundation Models for Physiological Signals - Apple Machine Learning Research

Smart Audit System Empowered by LLM - Apple Machine Learning Research

Divide-or-Conquer? Which Part Should You Distill Your LLM? - Apple Machine Learning Research

Combining Machine Learning and Homomorphic Encryption in the Apple Ecosystem - Apple Machine Learning Research

MUSCLE: A Model Update Strategy for Compatible LLM Evolution - Apple Machine Learning Research

CtrlSynth: Controllable Image-Text Synthesis for Data-Efficient Multimodal Learning - Apple Machine Learning Research

Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison - Apple Machine Learning Research

Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement - Apple Machine Learning Research

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities - Apple Machine Learning Research

Scalable Private Search with Wally - Apple Machine Learning Research

Generalizable Autoregressive Modeling of Time Series Through Functional Narratives - Apple Machine Learning Research

Progressive Entropic Optimal Transport Solvers - Apple Machine Learning Research

CAMPHOR: Collaborative Agents for Multi-Input Planning and High-Order Reasoning On Device - Apple Machine Learning Research

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models - Apple Machine Learning Research

Vision-Based Hand Gesture Customization from a Single Demonstration - Apple Machine Learning Research

On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization - Apple Machine Learning Research

home
›
Apple Machine Learning Research
›
Software