ML news

Sign In

by Apple ML

Apple MLFollow

Faster Retrieval for Better, More Efficient RAG

Faster Retrieval for Better, More Efficient RAG
...
...
Apple MLFollow

How AI Learns to Navigate Live iOS Apps

Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live iOS Apps
...
...
Apple MLFollow

GHARP: Real-Time Gaussian Head Animation from Large-Scale Reconstruction Prior

GHARP: Real-Time Gaussian Head Animation from Large-Scale Reconstruction Prior
...
...
Apple MLFollow

How Structured Choices Make Multimodal Agents Faster

Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
...
...
Apple MLFollow

When Should LLM Agents Plan Before Retrieving Tools?

Plan or Retrieve First? A Scale Study of Tool Discovery Architectures
...
...
Apple MLFollow

How to Run Giant LLMs Locally with MLX and RDMA

Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio
...
...
Apple MLFollow

How Speech Models Detect Code-Switching Without Transcripts

Code-Switching Detection via Language-Selective Dimensions in Speech Foundation Models
...
...
Apple MLFollow

Tri-Modal Diffusion: Learning Text, Images, and Audio

The Design Space of Tri-Modal Masked Diffusion Models
...
...
Apple MLFollow

Why Mixing Languages Beats Hyperparameter Tuning

Mix, Don’t Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings
...
...
Apple MLFollow

How Idle Apple Silicon Devices Become a Shared GPU Cloud

Minions: A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices
...
...
Apple MLFollow

How Reliable Are LLMs at Judging Translation Quality?

Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged
...
...
Apple MLFollow

How Rubrics Help AI Agents Learn Across Environments

RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
...
...
Apple MLFollow

How People Shape What Personal Sensing Systems Know

Negotiating Ontological Boundaries in User-Authored Personal Sensing Systems
...
...
Apple MLFollow

Why Confidence-Based Diffusion Misses Token Dependencies

Limits of Confidence in Diffusion
...
...
Apple MLFollow

How Language Discrimination Improves Multilingual Speech

Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
...
...
Apple MLFollow

How AI Learns and Improves from Its Own Failures

RLTL;DR: Self-Improvement by Internalizing Self-Generated Feedback
...
...
Apple MLFollow

Do AI Agents Need Complex Tools for ML Engineering?

How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
...
...
Apple MLFollow

How to Train and Evaluate Continual-Learning Agents

SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation
...
...
Apple MLFollow

How LLM Steering Balances Effectiveness and Fluency

On the Effectiveness-Fluency Trade-Off in LLM Conditioning: A Systematic Study
...
...
Apple MLFollow

Stabilizing Pseudo-Labels for Federated Speech Recognition

A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization
...
...