Author

Maxwell Horton

Observed name: Horton, Maxwell

Observed institution: Apple (United States)

OpenAlex ID: A5012428670

The Illusion of Thinking

2025 · Parshin Shojaee, Iman Mirzadeh, et al. · SuperIntelligence - Robotics - Safety & Alignment · 159

PDF

Label Refinery: Improving ImageNet Classification through Label Progression

2018 · Bagherinezhad, Hessam, Horton, Maxwell, et al. · arXiv (Cornell University) · 132

PDF

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

2025 · Parshin Shojaee, Iman Mirzadeh, et al. · neural information processing systems · 45

PDF

Learning Neural Network Subspaces

2021 · Wortsman, Mitchell, Horton, Maxwell, et al. · arXiv (Cornell University) · 17

PDF

Layer-Wise Data-Free CNN Compression

2022 · Maxwell Horton, Yanzi Jin, et al. · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · 14

PDF

Bytes Are All You Need: Transformers Operating Directly On File Bytes

2023 · Horton, Maxwell, Mehta, Sachin, et al. · arXiv (Cornell University) · 4

PDF

OpenELM: An Efficient Language Model Family with Open Training and Inference Framework

2024 · Mehta, Sachin, Sekhavat, Mohammad Hossein, et al. · arXiv (Cornell University) · 2

PDF

RangeAugment: Efficient Online Augmentation with Range Learning

2022 · Mehta, Sachin, Naderiparizi, Saeid, et al. · arXiv (Cornell University) · 2

PDF

SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks

2022 · Chien-Yu Lin, Anish Prabhu, et al. · Lecture notes in computer science · 2

PDF

LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time

2021 · Nunez, Elvis, Horton, Maxwell, et al. · arXiv (Cornell University) · 2

PDF

Efficient Mixture-of-Experts with Speculative Decoding via Expert Coactivation

2026 · Nishu, Kumari, Kim, Han-Byul, et al. · arXiv (Cornell University)

PDF

R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables

2026 · Horton, Maxwell, Lu, Wei, et al. · arXiv (Cornell University)

PDF

An Efficient and Streaming Audio Visual Active Speaker Detection System

2025 · Arnav Kundu, Yanzi Jin, et al. · IEEE International Conference on Acoustics Speech and Signal Processing

PDF

From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs

2025 · Nishu, Kumari, Mehta, Sachin, et al. · arXiv (Cornell University)

PDF

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

2025 · Tiwari, Rishabh, Xi, Haocheng, et al. · arXiv (Cornell University)

PDF

SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF

2024 · Chegini, Atoosa, Kazemi, Hamid, et al. · arXiv (Cornell University)

PDF

SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators

2024 · Shafipour, Rasoul, Harrison, David, et al. · arXiv (Cornell University)

PDF

KV Prediction for Improved Time to First Token

2024 · Horton, Maxwell, Cao, Qingqing, et al. · arXiv (Cornell University)

PDF

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data

2024 · Mehta, Sachin, Horton, Maxwell, et al. · arXiv (Cornell University)

PDF

CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement

2023 · Salehi, Mohammadreza, Farajtabar, Mehrdad, et al. · arXiv (Cornell University)

PDF

Diffusion Models as Masked Audio-Video Learners

2023 · Nunez, Elvis, Jin, Yanzi, et al. · arXiv (Cornell University)

PDF

On the Efficacy of Multi-scale Data Samplers for Vision Applications

2023 · Nunez, Elvis, Merth, Thomas, et al. · arXiv (Cornell University)

PDF

Works count: 22

Citation count: 379

H-index: 5

I10-index: 5