Binxu Wang

According to our database, Binxu Wang authored at least 19 papers between 2018 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Differentiable Faithfulness Alignment for Cross-Model Circuit Transfer.

Shun Shao, Binxu Wang, Shay B. Cohen, Anna Korhonen, Yonatan Belinkov

CoRR, April, 2026

Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training.

William Hoy, Binxu Wang, Xu Pan

CoRR, April, 2026

A Random Matrix Theory Perspective on the Consistency of Diffusion Models.

Binxu Wang, Jacob A. Zavatone-Veth, Cengiz Pehlevan

CoRR, February, 2026

Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers.

Binxu Wang, Jingxuan Fan, Xu Pan

CoRR, January, 2026

2025

Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry.

Thomas Fel, Binxu Wang, Michael A. Lepori, Matthew Kowal, Andrew Lee, Randall Balestriero, Sonia Joseph, Ekdeep Singh Lubana, Talia Konkle, Demba E. Ba, Martin Wattenberg

CoRR, October, 2025

An Analytical Theory of Power Law Spectral Bias in the Learning Dynamics of Diffusion Models.

Binxu Wang

CoRR, March, 2025

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models.

Thomas Fel, Ekdeep Singh Lubana, Jacob S. Prince, Matthew Kowal, Victor Boutin, Isabel Papadimitriou, Binxu Wang, Martin Wattenberg, Demba E. Ba, Talia Konkle

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applications.

Binxu Wang, John J. Vastola

Trans. Mach. Learn. Res., 2024

Diverse capability and scaling of diffusion and auto-regressive models when learning abstract rules.

Binxu Wang, Jiaqi Shang, Haim Sompolinsky

CoRR, 2024

2023

The Hidden Linear Structure in Score-Based Models and its Application.

Binxu Wang, John J. Vastola

CoRR, 2023

Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later.

Binxu Wang, John J. Vastola

CoRR, 2023

2022

On the level sets and invariance of neural tuning landscapes.

Binxu Wang, Carlos R. Ponce

Proceedings of the NeurIPS Workshop on Symmetry and Geometry in Neural Representations, 2022

High-performance evolutionary algorithms for online neuron control.

Binxu Wang, Carlos R. Ponce

Proceedings of the GECCO '22: Genetic and Evolutionary Computation Conference, Boston, Massachusetts, USA, July 9, 2022

2021

On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation.

Binxu Wang, David Mayo, Arturo Deza, Andrei Barbu, Colin Conwell

CoRR, 2021

The Geometry of Deep Generative Image Models and its Applications.

Binxu Wang, Carlos R. Ponce

CoRR, 2021

A Geometric Analysis of Deep Generative Image Models and Its Applications.

Binxu Wang, Carlos R. Ponce

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Weakly Supervised Object Localization Using Self-Paced Pyramid Adversarial Learning.

Fucheng Pan, Beilei Bian, Binxu Wang, Yueping Yang, Xiaoming Ju

Proceedings of the 2020 International Joint Conference on Neural Networks, 2020

2019

A Mechanism for Synaptic Copy Between Neural Circuits.

Yuxiu Shao, Binxu Wang, Andrew T. Sornborger, Louis Tao

Neural Comput., 2019

2018

Mutual Information and Information Gating in Synfire Chains.

Zhuocheng Xiao, Binxu Wang, Andrew T. Sornborger, Louis Tao

Entropy, 2018