Joshua M. Susskind

31 papers · 2021–2025 · 6 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (13) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) 🤝 Dynamic Duo (12) ❓ The Questioner (2) ⚡ Prolific Year (13) 💎 Century Club (31) 🔥 Unstoppable (5)

Conferences

ICLR (14) ICML (11) ICCV (2) WACV (2) COLING (1) NAACL (1)

Top co-authors

Shuangfei Zhai (12) Miguel Angel Bautista (12) Jiatao Gu (10) Navdeep Jaitly (6) Yizhe Zhang (6) Etai Littwin (6) Preetum Nakkiran (5) Yuyang Wang (4) Omid Saremi (4) Chen Huang (4)

Keywords

novel view synthesis (2) sim-to-real transfer (1) knowledge distillation (1) natural language generation (1) text generation (1) neural rendering (1) neural network optimization (1) nearest neighbor (1) shape reconstruction (1) knowledge graph (1) diffusion model (1) inductive bia (1) language model (1) neural radiance field (1) training stability (1) scene generation (1) radiance field (1) indoor scene (1) layer normalization (1) synthetic dataset (1)

Papers

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting ICML 2025

Mechanisms of Projective Composition of Diffusion Models ICML 2025

Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models ICML 2025

Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion ICML 2025

Normalizing Flows are Capable Generative Models ICML 2025

INRFlow: Flow Matching for INRs in Ambient Space ICML 2025

Denoising Autoregressive Transformers for Scalable Text-to-Image Generation ICLR 2025

Pseudo-Generalized Dynamic View Synthesis from a Video ICLR 2024

Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization ICLR 2024

Manifold Diffusion Fields ICLR 2024

Construction of Paired Knowledge Graph - Text Datasets Informed by Cyclic Evaluation COLING 2024

LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures ICLR 2024

What Algorithms can Transformers Learn? A Study in Length Generalization ICLR 2024

Vanishing Gradients in Reinforcement Finetuning of Language Models ICLR 2024

When can transformers reason with abstract symbols? ICLR 2024

Generative Modeling with Phase Stochastic Bridge ICLR 2024

Matryoshka Diffusion Models ICLR 2024

Scalable Pre-training of Large Autoregressive Image Models ICML 2024

Data-free Distillation of Diffusion Models with Bootstrapping ICML 2024

Swallowing the Bitter Pill: Simplified Scalable Conformer Generation ICML 2024

Diffusion Probabilistic Fields ICLR 2023

Stabilizing Transformer Training by Preventing Attention Entropy Collapse ICML 2023

NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion ICML 2023

MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors ICLR 2023

f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation ICLR 2023

Regularized Training of Nearest Neighbor Language Models NAACL 2022

Fast and Explicit Neural View Synthesis WACV 2022

Learning Representation from Neural Fisher Kernel with Low-rank Approximation ICLR 2022

Unconstrained Scene Generation With Locally Conditioned Radiance Fields ICCV 2021

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding ICCV 2021

On the Generalization of Learning-Based 3D Reconstruction WACV 2021