most citedOut-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective

1 citations · 2 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination

Peng Wang, Xiao Li, Can Yaras +4

Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks…

cs.LG2026

Stochastic Sparse Attention for Memory-Bound Inference

Kyle Lee, Corentin Delacour, Kevin Callahan-Coray +5

Autoregressive decoding becomes bandwidth-limited at long contexts, as generating each token requires reading all key and value vectors from KV cache. We present Stochastic A…

cs.LG2026

Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension

Alec S. Xu, Can Yaras, Peng Wang +1

Deep neural networks have attained remarkable success across diverse classification tasks. Recent empirical studies have shown that deep networks learn features that are linearly s…

cs.LG2026

Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning

Can Yaras, Siyi Chen, Peng Wang +1

Multimodal learning has recently gained significant popularity, demonstrating impressive performance across various zero-shot classification tasks and a range of perceptive and gen…

cs.LG20261 cited

Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

Can Yaras, Peng Wang, Laura Balzano +1

While overparameterization in machine learning models offers great benefits in terms of optimization and generalization, it also leads to increased computational requirements as mo…

cs.LG2026

Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations

Alec S. Xu, Can Yaras, Matthew Asato +2

Recent empirical evidence has demonstrated that the training dynamics of large-scale deep neural networks occur within low-dimensional subspaces. While this has inspired new resear…