News
Entertainment
Science & Technology
Sport
Business & Money
Life
Culture & Art
Hobbies
8 | Follower
Apple Machine Learning Research
19.12.2024
Accelerating LLM inference is an important ML research problem, as auto-regressive token generation is computationally expensive and…
18.12.2024
Teleoperation for robot imitation learning is bottlenecked by hardware availability. Can high-quality robot data be collected without a…
13.12.2024
Information Retrieval (IR) systems used in search and recommendation platforms frequently employ Learning-to-Rank (LTR) models to rank items…
12.12.2024
*Equal Contributors Large language models (LLMs) are increasingly being adapted to achieve task-specificity for deployment in real-world…
10.12.2024
This paper was accepted for presentation at the International Workshop on Federated Foundation Models (FL@FM-NeurIPS'24), held in…
07.12.2024
Motivated by the problem of next word prediction on user devices we introduce and study the problem of personalized frequency histogram…
The remarkable advancements in Multimodal Large Language Models (MLLMs) have not rendered them immune to challenges, particularly in the…
Apple is presenting new research at the annual conference on Neural Information Processing Systems (NeurIPS), which takes place in person in…
Apple researchers are advancing the field of ML through fundamental research that improves the world’s understanding of this technology and…
06.12.2024
This paper was accepted at the Fine-Tuning in Modern Machine Learning: Principles and Scalability (FITML) Workshop at NeurIPS 2024. Large…
Multi-modal large language models (MLLMs) have enabled numerous advances in understanding and reasoning in domains like vision, but we have…
05.12.2024
Motivated by the phenomenon of strategic agents gaming a recommendation system to maximize the number of times they are recommended to…
*Equal Contributors Data from wearable sensors (e.g., heart rate, step count) can be used to model mood patterns. We characterize feature…
Diffusion models have emerged as a powerful tool for generating high-quality images from textual descriptions. Despite their successes…
04.12.2024
Given a source and a target probability measure supported on Rd\mathbb{R}^dRd, the Monge problem aims for the most efficient way to map one…
Single-cell genomics has significantly advanced our understanding of cellular behavior, catalyzing innovations in treatments and precision…
27.11.2024
This paper was accepted at the Ninth Conference on Machine Translation (WMT24) at EMNLP 2024. The prosody of a spoken utterance, including…
23.11.2024
This paper was accepted at the Machine Learning and Compression Workshop at NeurIPS 2024. Compressing Large Language Models (LLMs) often…
*Equal Contributors A dominant paradigm in large multimodal models is to pair a large language de- coder with a vision encoder. While it is…
22.11.2024
Learning with identical train and test distributions has been extensively investigated both practically and theoretically. Much remains to…
We study private stochastic convex optimization (SCO) under user-level differential privacy (DP) constraints. In this setting, there are nnn…
We study the problem of private online learning, specifically, online prediction from experts (OPE) and online convex optimization (OCO). We…
Estimating the density of a distribution from samples is a fundamental problem in statistics. In many practical settings, the Wasserstein…
This paper was accepted at the Foundation Model Interventions (MINT) Workshop at NeurIPS 2024. Instruction-following is crucial for building…
This paper was accepted at the Safe Generative AI Workshop (SGAIW) at NeurIPS 2024. Large language models (LLMs) could be valuable personal…
We study the problem of differentially private stochastic convex optimization (DP-SCO) with heavy-tailed gradients, where we assume a…
21.11.2024
Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by…
20.11.2024
This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) Workshop at NeurIPS 2024. Tensor parallelism…
This paper was accepted at the Self-Supervised Learning - Theory and Practice (SSLTP) Workshop at NeurIPS 2024. Image-based Joint-Embedding…
This paper considers the learning of logical (Boolean) functions with a focus on the generalization on the unseen (GOTU) setting, a strong…
19.11.2024
This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) Workshop at NeurIPS 2024. Large Language Models…
We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large…
13.11.2024
This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) Workshop at NeurIPS 2024. The pre-training phase of…
07.11.2024
Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription…
05.11.2024
Apple is presenting new research at the Empirical Methods in Natural Language Processing (EMNLP) conference, which takes place in person in…
Large pretrained vision-language models like CLIP have shown promising generalization capability, but may struggle in specialized domains…
This paper was accepted at the Adaptive Foundation Models (AFM) workshop at NeurIPS Workshop 2024. Follow-up conversations with virtual…
02.11.2024
Many app developers are interested in building on device experiences that integrate increasingly capable large language models (LLMs)…
01.11.2024
This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) workshop at NeurIPS Workshop 2024. While large…
31.10.2024
Translating text that contains entity names is a challenging task, as cultural-related references can vary significantly across languages…