activity
20242026
collaborators

6 papers

cs.CL2026

Short Data, Long Context: Distilling Positional Knowledge in Transformers

Patrick Huber, Ernie Chang, Chinnadhurai Sankar +4

Extending the context window of language models typically requires expensive long-context pre-training, posing significant challenges for both training efficiency and data collecti…

cs.LG2025

Layer by Layer: Uncovering Hidden Representations in Language Models

Oscar Skean, Md Rifat Arefin, Dan Zhao +4

From extracting features to generating text, the outputs of large language models (LLMs) typically rely on the final layers, following the conventional wisdom that earlier layers c…

cs.LG2025

Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning

Md Rifat Arefin, Gopeshh Subbaraj, Nicolas Gontier +4

Decoder-only Transformers often struggle with complex reasoning tasks, particularly arithmetic reasoning requiring multiple sequential operations. In this work, we identify represe…

cs.LG2024

Does Representation Matter? Exploring Intermediate Layers in Large Language Models

Oscar Skean, Md Rifat Arefin, Yann LeCun +1

Understanding what defines a good representation in large language models (LLMs) is fundamental to both theoretical understanding and practical applications. In this paper, we inve…

cs.CV2024

VFA: Vision Frequency Analysis of Foundation Models and Human

Mohammad-Javad Darvishi-Bayazi, Md Rifat Arefin, Jocelyn Faubert +1

Machine learning models often struggle with distribution shifts in real-world scenarios, whereas humans exhibit robust adaptation. Models that better align with human perception ma…

cs.LG2024

Unsupervised Concept Discovery Mitigates Spurious Correlations

Md Rifat Arefin, Yan Zhang, Aristide Baratin +4

Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases. Addressing this challenge typically involves methods relyi…