activity
20212025
most citedFerret: Refer and Ground Anything Anywhere at Any Granularity

43 citations · 69 across the 7 of their papers we have counts for

collaborators

7 papers

cs.LG2025

Apple Intelligence Foundation Language Models: Tech Report 2025

Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang +395

We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model opti…

cs.LG20241 cited

Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training

Xianzhi Du, Tom Gunter, Xiang Kong +5

Mixture-of-Experts (MoE) enjoys performance gain by increasing model capacity while keeping computation cost constant. When comparing MoE to dense models, prior work typically adop…

cs.CV202411 cited

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Brandon McKinzie, Zhe Gan, Jean-Philippe Fauconnier +29

In this work, we discuss building performant Multimodal Large Language Models (MLLMs). In particular, we study the importance of various architecture components and data choices. T…

cs.CV202343 cited

Ferret: Refer and Ground Anything Anywhere at Any Granularity

Haoxuan You, Haotian Zhang, Zhe Gan +6

We introduce Ferret, a new Multimodal Large Language Model (MLLM) capable of understanding spatial referring of any shape or granularity within an image and accurately grounding op…

cs.CV20233 cited

Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts

Erik Daxberger, Floris Weers, Bowen Zhang +7

Sparse Mixture-of-Experts models (MoEs) have recently gained popularity due to their ability to decouple model size from inference efficiency by only activating a small subset of t…

cs.CV20232 cited

Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness

Liangliang Cao, Bowen Zhang, Chen Chen +5

The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of m…