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

11.07.2025

Point-3D LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language Models - Apple Machine Learning Research

Effectively representing 3D scenes for Multimodal Large Language Models (MLLMs) is crucial yet challenging. Existing approaches commonly…

Apple Machine Learning Research

11.07.2025

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache - Apple Machine Learning Research

Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings, creating a growing need for fast and…

Apple Machine Learning Research

10.07.2025

Self-reflective Uncertainties: Do LLMs Know Their Internal Answer Distribution? - Apple Machine Learning Research

This paper was accepted at the Workshop on Reliable and Responsible Foundation Models (RRFMs) Workshop at ICML 2025. Uncertainty…

Apple Machine Learning Research

10.07.2025

Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency - Apple Machine Learning Research

The adoption of text-to-image diffusion models raises concerns over reliability, drawing scrutiny under the lens of various metrics like…

Apple Machine Learning Research

10.07.2025

A Variational Framework for Improving Naturalness in Generative Spoken Language Models - Apple Machine Learning Research

The success of large language models in text processing has inspired their adaptation to speech modeling. However, since speech is…

Apple Machine Learning Research

10.07.2025

Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion - Apple Machine Learning Research

Discrete diffusion is a promising framework for modeling and generating discrete data. In this work, we present Target Concrete Score…

Apple Machine Learning Research

10.07.2025

CommVQ: Commutative Vector Quantization for KV Cache Compression - Apple Machine Learning Research

Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often…

Apple Machine Learning Research

09.07.2025

Addressing Misspecification in Simulation-based Inference through Data-driven Calibration - Apple Machine Learning Research

Driven by steady progress in deep generative modeling, simulation-based inference (SBI) has emerged as the workhorse for inferring the…

Apple Machine Learning Research

08.07.2025

Faster Rates for Private Adversarial Bandits - Apple Machine Learning Research

We design new differentially private algorithms for the problems of adversarial bandits and bandits with expert advice. For adversarial…

Apple Machine Learning Research

08.07.2025

Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions - Apple Machine Learning Research

Wearable devices record physiological and behavioral signals that can improve health predictions. While foundation models are increasingly…

Apple Machine Learning Research

08.07.2025

The Geometries of Truth Are Orthogonal Across Tasks - Apple Machine Learning Research

This paper was presented at the Workshop on Reliable and Responsible Foundation Models at ICML 2025. Large Language Models (LLMs) have…

Apple Machine Learning Research

08.07.2025

Tracking the Best Expert Privately - Apple Machine Learning Research

We design differentially private algorithms for the problem of prediction with expert advice under dynamic regret, also known as tracking…

Apple Machine Learning Research

08.07.2025

Learning to Route LLMs with Confidence Tokens - Apple Machine Learning Research

Large language models (LLMs) have demonstrated impressive performance on several tasks and are increasingly deployed in real-world…

Apple Machine Learning Research

05.07.2025

Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging - Apple Machine Learning Research

Large-scale models are routinely trained on a mixture of different data sources. Different data mixtures yield very different downstream…

Apple Machine Learning Research

04.07.2025

Understanding Input Selectivity in Mamba - Apple Machine Learning Research

State-Space Models (SSMs), and particularly Mamba, have recently emerged as a promising alternative to Transformers. Mamba introduces input…

Apple Machine Learning Research

04.07.2025

Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs - Apple Machine Learning Research

The recent rapid adoption of large language models (LLMs) highlights the critical need for benchmarking their fairness. Conventional…

Apple Machine Learning Research

04.07.2025

SceneScout: Towards AI Agent-driven Access to Street View Imagery for Blind Users - Apple Machine Learning Research

People who are blind or have low vision (BLV) may hesitate to travel independently in unfamiliar environments due to uncertainty about the…

Apple Machine Learning Research

03.07.2025

The Super Weight in Large Language Models - Apple Machine Learning Research

Recent works have shown a surprising result: a small fraction of Large Language Model (LLM) parameter outliers are disproportionately…

Apple Machine Learning Research

02.07.2025

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video - Apple Machine Learning Research

Imitation learning for manipulation has a well-known data scarcity problem. Unlike natural language and 2D computer vision, there is no…

Apple Machine Learning Research

01.07.2025

Instruction-Following Pruning for Large Language Models - Apple Machine Learning Research

With the rapid scaling of large language models (LLMs), structured pruning has become a widely used technique to learn efficient, smaller…

Apple Machine Learning Research

28.06.2025

Evaluating Long Range Dependency Handling in Code Generation LLMs - Apple Machine Learning Research

As language models support larger and larger context sizes, evaluating their ability to make effective use of that context becomes…

Apple Machine Learning Research

28.06.2025

ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering - Apple Machine Learning Research

Precisely evaluating semantic alignment between text prompts and generated videos remains a challenge in Text-to-Video (T2V) Generation…

Apple Machine Learning Research

28.06.2025

Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention - Apple Machine Learning Research

In recent years, there have been remarkable breakthroughs in image-to-video generation. However, the 3D consistency and camera…

Apple Machine Learning Research

27.06.2025

Advancing Egocentric Video Question Answering with Multimodal Large Language Models - Apple Machine Learning Research

Egocentric Video Question Answering (QA) requires models to handle long-horizon temporal reasoning, first-person perspectives, and…

Apple Machine Learning Research

27.06.2025

From Interaction to Impact: Towards Safer AI Agents Through Understanding and Evaluating Mobile UI Operation Impacts - Apple Machine Learning Research

With advances in generative AI, there is increasing work towards creating autonomous agents that can manage daily tasks by operating user…

Apple Machine Learning Research

22.06.2025

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis - Apple Machine Learning Research

We present STARFlow, a scalable generative model based on normalizing flows that achieves strong performance in high-resolution image…

Apple Machine Learning Research

22.06.2025

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment - Apple Machine Learning Research

Existing paradigms for ensuring AI safety, such as guardrail models and alignment training, often compromise either inference efficiency or…

Apple Machine Learning Research

21.06.2025

Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks - Apple Machine Learning Research

We introduce a set of training-free ABX-style discrimination tasks to evaluate how multilingual language models represent language identity…

Apple Machine Learning Research

21.06.2025

Normalizing Flows are Capable Generative Models - Apple Machine Learning Research

Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density…

Apple Machine Learning Research

21.06.2025

Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction - Apple Machine Learning Research

End-to-end (E2E) Automatic Speech Recognition (ASR) models are trained using paired audio-text samples that are expensive to obtain, since…

Apple Machine Learning Research

21.06.2025

Scaling Laws for Unsupervised Finetuning of LLMs - Apple Machine Learning Research

A widespread strategy for obtaining a language model that performs well in a target domain is to fine-tune it by training it to do…

Apple Machine Learning Research

21.06.2025

Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results - Apple Machine Learning Research

Uncertainty Quantification (UQ) in Language Models (LMs) is key to improving their safety and reliability. Evaluations often use metrics…

Apple Machine Learning Research

20.06.2025

Aligning LLMs by Predicting Preferences from User Writing Samples - Apple Machine Learning Research

Accommodating human preferences is essential for creating aligned LLM agents that deliver personalized and effective interactions. Recent…

Apple Machine Learning Research

20.06.2025

Trade-offs in Data Memorization via Strong Data Processing Inequalities - Apple Machine Learning Research

Recent research demonstrated that training large language models involves memorization of a significant fraction of training data. Such…

Apple Machine Learning Research

20.06.2025

Variational Rectified Flow Matching - Apple Machine Learning Research

We study Variational Rectified Flow Matching, a framework that enhances classic rectified flow matching by modeling multi-modal velocity…

Apple Machine Learning Research

20.06.2025

INRFlow: Flow Matching for INRs in Ambient Space - Apple Machine Learning Research

Flow matching models have emerged as a powerful method for generative modeling on domains like images or videos, and even on irregular or…

Apple Machine Learning Research

11.06.2025

Apple Machine Learning Research at CVPR 2025 - Apple Machine Learning Research

Apple researchers are advancing AI and ML through fundamental research, and to support the broader research community and help accelerate…

Apple Machine Learning Research

10.06.2025

Updates to Apple's On-Device and Server Foundation Language Models - Apple Machine Learning Research

With Apple Intelligence, we're integrating powerful generative AI right into the apps and experiences people use every day, all while…

Apple Machine Learning Research

06.06.2025

Improve Vision Language Model Chain-of-thought Reasoning - Apple Machine Learning Research

Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness…

Apple Machine Learning Research

06.06.2025

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity - Apple Machine Learning Research

Recent generations of frontier language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes…

home›Apple Machine Learning Research›Software

Apple Machine Learning Research - Software

Point-3D LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language Models - Apple Machine Learning Research

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache - Apple Machine Learning Research

Self-reflective Uncertainties: Do LLMs Know Their Internal Answer Distribution? - Apple Machine Learning Research

Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency - Apple Machine Learning Research

A Variational Framework for Improving Naturalness in Generative Spoken Language Models - Apple Machine Learning Research

Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion - Apple Machine Learning Research

CommVQ: Commutative Vector Quantization for KV Cache Compression - Apple Machine Learning Research

Addressing Misspecification in Simulation-based Inference through Data-driven Calibration - Apple Machine Learning Research

Faster Rates for Private Adversarial Bandits - Apple Machine Learning Research

Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions - Apple Machine Learning Research

The Geometries of Truth Are Orthogonal Across Tasks - Apple Machine Learning Research

Tracking the Best Expert Privately - Apple Machine Learning Research

Learning to Route LLMs with Confidence Tokens - Apple Machine Learning Research

Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging - Apple Machine Learning Research

Understanding Input Selectivity in Mamba - Apple Machine Learning Research

Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs - Apple Machine Learning Research

SceneScout: Towards AI Agent-driven Access to Street View Imagery for Blind Users - Apple Machine Learning Research

The Super Weight in Large Language Models - Apple Machine Learning Research

EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video - Apple Machine Learning Research

Instruction-Following Pruning for Large Language Models - Apple Machine Learning Research

Evaluating Long Range Dependency Handling in Code Generation LLMs - Apple Machine Learning Research

ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering - Apple Machine Learning Research

Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention - Apple Machine Learning Research

Advancing Egocentric Video Question Answering with Multimodal Large Language Models - Apple Machine Learning Research

From Interaction to Impact: Towards Safer AI Agents Through Understanding and Evaluating Mobile UI Operation Impacts - Apple Machine Learning Research

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis - Apple Machine Learning Research

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment - Apple Machine Learning Research

Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Tasks - Apple Machine Learning Research

Normalizing Flows are Capable Generative Models - Apple Machine Learning Research

Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction - Apple Machine Learning Research

Scaling Laws for Unsupervised Finetuning of LLMs - Apple Machine Learning Research

Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results - Apple Machine Learning Research

Aligning LLMs by Predicting Preferences from User Writing Samples - Apple Machine Learning Research

Trade-offs in Data Memorization via Strong Data Processing Inequalities - Apple Machine Learning Research

Variational Rectified Flow Matching - Apple Machine Learning Research

INRFlow: Flow Matching for INRs in Ambient Space - Apple Machine Learning Research

Apple Machine Learning Research at CVPR 2025 - Apple Machine Learning Research

Updates to Apple's On-Device and Server Foundation Language Models - Apple Machine Learning Research

Improve Vision Language Model Chain-of-thought Reasoning - Apple Machine Learning Research

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity - Apple Machine Learning Research

home
›
Apple Machine Learning Research
›
Software