activity
20232025
most citedIn-Context Occam's Razor: How Transformers Prefer Simpler Hypotheses on the Fly

1 citations · 3 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL2025

Facts in Stats: Impacts of Pretraining Diversity on Language Model Generalization

Tina Behnia, Puneesh Deora, Christos Thrampoulidis

Language models are pretrained on sequences that blend statistical regularities (making text fluent) with factual associations between specific tokens (knowledge of facts). While r…

cs.LG2025★ 1 cited

In-Context Occam's Razor: How Transformers Prefer Simpler Hypotheses on the Fly

Puneesh Deora, Bhavya Vasudeva, Tina Behnia +1

In-context learning (ICL) enables transformers to adapt to new tasks through contextual examples without parameter updates. While existing research has typically studied ICL in fix…

cs.CL2024

Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations

Yize Zhao, Tina Behnia, Vala Vakilian +1

Next-token prediction (NTP) over large text corpora has become the go-to paradigm to train large language models. Yet, it remains unclear how NTP influences the mapping of linguist…

cs.LG2024

Supervised Contrastive Representation Learning: Landscape Analysis with Unconstrained Features

Tina Behnia, Christos Thrampoulidis

Recent findings reveal that over-parameterized deep neural networks, trained beyond zero training-error, exhibit a distinctive structural pattern at the final layer, termed as Neur…

cs.LG2023★ 1 cited

Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching

Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia +2

Supervised contrastive loss (SCL) is a competitive and often superior alternative to the cross-entropy loss for classification. While prior studies have demonstrated that both loss…

cs.LG2023★ 1 cited

On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data

Tina Behnia, Ganesh Ramachandra Kini, Vala Vakilian +1

Various logit-adjusted parameterizations of the cross-entropy (CE) loss have been proposed as alternatives to weighted CE for training large models on label-imbalanced data far bey…