Joshua M. Susskind

Apple (United Kingdom) — United Kingdom

Neuroscience · Life Sciences

19h-index3.0kcitations64works1.32yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Psychology of Moral and Emotional Judgment(9), Generative Adversarial Networks and Image Synthesis(8), Advanced Vision and Imaging(7), Face Recognition and Perception(7), Domain Adaptation and Few-Shot Learning(7)

Publications64 total

Multimodal Autoregressive Pre-training of Large Vision Encoders
2025· 4 cited
Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion
arXiv (Cornell University)·2025Open Access
Scaling Laws for Native Multimodal Models
arXiv (Cornell University)·2025Open Access
Mechanisms of Projective Composition of Diffusion Models
arXiv (Cornell University)·2025· 1 citedOpen Access
How Parts Assemble into Wholes:Learning the Relative Composition of Images
SSRN Electronic Journal·2025Open Access
World-consistent Video Diffusion with Explicit 3D Modeling
arXiv (Cornell University)·2024Open Access
Multimodal Autoregressive Pre-training of Large Vision Encoders
arXiv (Cornell University)·2024· 2 citedOpen Access
CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control and Altering of T2I Models
Lecture notes in computer science·2024· 3 cited
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
arXiv (Cornell University)·2024Open Access
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
arXiv (Cornell University)·2024Open Access
CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models
arXiv (Cornell University)·2024· 2 citedOpen Access
Construction of Paired Knowledge Graph - Text Datasets Informed by Cyclic Evaluation
2024
Many-to-many Image Generation with Auto-regressive Diffusion Models
arXiv (Cornell University)·2024· 1 citedOpen Access
Scalable Pre-training of Large Autoregressive Image Models
arXiv (Cornell University)·2024· 6 citedOpen Access
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
2024
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
arXiv (Cornell University)·2023· 1 citedOpen Access
Swallowing the Bitter Pill: Simplified Scalable Conformer Generation
arXiv (Cornell University)·2023· 6 citedOpen Access
Vanishing Gradients in Reinforcement Finetuning of Language Models
arXiv (Cornell University)·2023Open Access
When can transformers reason with abstract symbols?
arXiv (Cornell University)·2023· 2 citedOpen Access
Pseudo-Generalized Dynamic View Synthesis from a Video
arXiv (Cornell University)·2023Open Access
page 1 of 4Next →

Frequent Co-authors

Shuangfei Zhai(16), Miguel Ángel Bautista(11), Adam K. Anderson(8), Etai Littwin(7), Walter Talbott(6), Nitish Srivastava(5), Hanlin Goh(5), Omid Saremi(5), Geoffrey E. Hinton(4), Chen Huang(4), Alaaeldin El-Nouby(4), Navdeep Jaitly(4), Vimal Thilak(4), Preetum Nakkiran(4), Daniel H. Lee(3), Marian Stewart Bartlett(3), Carlos Guestrin(3), Michal Klein(3), Alexander Toshev(3), Jiatao Gu(3)