Apple ML Research

The internal kNN graph of UMAP can reveal critical insights about high-dimensional data that traditional embedding approaches overlook.

SelfCompact reveals that language models can autonomously manage context decay, achieving up to 18.1 points improvement in performance while cutting token costs by 30-70%.

Efficient conditioning methods for LLMs often sacrifice fluency, revealing a critical trade-off that could reshape deployment strategies.

MT-EditFlow bridges the gap between local planning and global success in multi-turn image editing, achieving a significant performance boost over leading models.

Forget training: PinPoint, a training-free point selector, closes the performance gap between zero-shot VLMs and fine-tuned specialists in referring image segmentation by intelligently choosing interior points for prompting SAM.

Outlier tokens in Diffusion Transformers aren't just extreme values; they corrupt local patch semantics, and can be tamed with Dual-Stage Registers to boost image generation quality.

Watermarks meant to identify AI-generated images can be easily removed or forged, even allowing attackers to falsely flag real images as AI-generated.

Training a smaller LLM on a carefully pruned dataset lets it memorize as many facts as a model 10x larger trained on everything.

LLM agents automating productivity tasks achieve only moderate success (39-64%) while exhibiting surprisingly high rates of unsafe actions (7-33%) in realistic, multi-service workflows.

Forget full KV caches: randomly routing attention across layers during training lets you drastically cut memory without hurting performance, and sometimes even helps.

Realistic user simulation is now possible: Pare offers a framework that moves beyond flat tool-calling APIs to model stateful user interactions, enabling better evaluation of proactive agents.

Forget painstakingly collecting user data – PersonaTrace lets you bootstrap realistic digital footprints with LLMs, and models trained on this synthetic data actually generalize better to real-world tasks.

Finally, a single model that can generate both your face and voice, convincingly controlled by text prompts and reference clips.

Text-to-video generation gets a 1.58x speed boost with CalibAtt, a training-free method that exploits consistent sparsity patterns in attention layers.

See in the dark: Dark3R unlocks structure from motion at signal-to-noise ratios below -4dB, where existing methods completely break down.

LLM agents can learn to solve tasks previously beyond their reach by exploring high-level language strategies instead of low-level actions, leading to more efficient and effective reinforcement learning.

Ditch slow, external segmentation pipelines: TrajTok learns trajectory tokens end-to-end, boosting video understanding while staying lean and adaptable.

Fine-tuning a specialized LLM to generate textual relevance labels for search ranking not only beats larger pre-trained models, but also drives significant real-world gains in App Store conversion rates, especially for tail queries.

Sticking to a single HTML-to-text extractor in your LLM pretraining pipeline could be leaving 71% of the data on the table.

A low-cost, portable e-waste sorter achieves high precision (90%) using a YOLOx model, promising to boost material recovery rates in recycling.

Just 20% of a strong model's chain-of-thought can unlock a weaker model's reasoning abilities, revealing the surprising transferability of CoT mechanics.

Key contribution not extracted.

RL fine-tuning can make vision-language models *less* reliable reasoners, as gains in benchmark accuracy come at the cost of faithfulness to the underlying visual grounding and chain-of-thought.