Can Yaras
Jahn YAH-rahs | cjyaras [at] umich [dot] edu
cv | scholar | github
Hi! I’m a final-year PhD candidate in Electrical and Computer Engineering at the University of Michigan, advised by Qing Qu and Laura Balzano. I received my undergraduate degree from Duke University in Electrical and Computer Engineering, along with a major in Mathematics and a minor in Computer Science.
I’m currently interested in hardware-aware design of efficient machine learning algorithms via low-dimensional structure in learning and computation.
Publications
Selected
- C.Yaras, A.S.Xu, P.Abillama, C.Lee, L.Balzano. MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention. NeurIPS'25, Spotlight.
- C.Yaras, P.Wang, L.Balzano, Q.Qu. Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation. ICML'24, Oral.
Other
- P.Wang*, X.Li*, C.Yaras, Z.Zhu, L.Balzano, W.Hu, Q.Qu. Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination. Accepted to JMLR.
- C.Yaras, A.S.Xu, P.Abillama, C.Lee, L.Balzano. Zero-Shot Conversion to Monarch-Structured Attention. ICML’25, ES-FoMo III Workshop.
- C.Yaras*, S.Chen*, P.Wang, Q.Qu. Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning. CPAL'25.
- C.Yaras, P.Wang, W.Hu, Z.Zhu, L.Balzano, Q.Qu. Invariant Low-Dimensional Subspaces in Gradient Descent for Learning Deep Matrix Factorizations. NeurIPS’23, M3L Workshop.
- C.Yaras*, P.Wang*, Z.Zhu, L.Balzano, Q.Qu. Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold. NeurIPS'22.
- P.Wang*, H.Liu*, C.Yaras*, L.Balzano, Q.Qu. Linear Convergence Analysis of Neural Collapse with Unconstrained Features. NeurIPS’22, OPT Workshop.
- T.Sarwar, C.Yaras, X.Li, Q.Qu, P.C.Ku. Miniaturizing a Chip-Scale Spectrometer Using Local Strain Engineering and Total-Variation Regularized Reconstruction. Nano Letters.
- C.Yaras, K.Kassaw, B.Huang, K.Bradbury, J.M.Malof. Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery. IEEE J-STARS.
Preprints
- S.M.Kwon*, A.S.Xu*, C.Yaras, L.Balzano, Q.Qu. Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective. In Submission.
- (α-β) L.Balzano, T.Ding, B.D.Haeffele, S.M.Kwon, Q.Qu, P.Wang, Z.Wang, C.Yaras. An Overview of Low-Rank Structures in the Training and Adaptation of Large Models. In Submission.
- A.S.Xu, C.Yaras, P.Wang, Q.Qu. Understanding How Nonlinear Layers Create Linearly Separable Features for Low-Dimensional Data. In Submission.